|
|
1.IntroductionThe Computer-Aided Diagnosis (CAD) conference at the annual SPIE Medical Imaging symposium reaches its 16th anniversary in 2022. An outgrowth of the tremendous interest in computer-aided diagnosis in biomedical imaging in the 1990s and early 2000s led to the creation of this separate conference. Prior to that time, computer-aided diagnosis papers were included in the Image Processing, Biomedical Applications, Picture Archiving and Communication Systems, and Perception conferences, all held within the annual SPIE Medical Imaging symposium. There are many commonalities between the Image Processing and CAD conferences at the annual Medical Imaging meeting. However, the evolution of the CAD conference from the Imaging Processing conference was the recognition that additional aspects of the overall research task included a greater need for both clinical input (on both the clinical question and the clinical outcomes) and a systems approach to the detection (localization) and diagnosis (classification) problems. Interestingly, many of the very early “firsts” in CAD were presented in the Imaging Processing conference prior to the launch of the CAD conference. The inaugural CAD conference was held in San Diego, California, in 2007 and spanned 3 days (Fig. 1). The conference was chaired by Maryellen Giger and Nico Karssemeijer. There were 12 program committee members with international representation including the United States, United Kingdom, France, Japan, and the Netherlands, and hailing from academia, government agencies (such as NIH and FDA), industry, and clinical practice. Over the years, new program committee members have been added. By 2022, the committee had grown to 48 members, including the two conference chairs, with international representation including the United States, Brazil, China, France, Germany, Israel, Japan, Korea, the Netherlands, and the United Kingdom. The chairs and cochairs for each year's CAD conference are listed in Table 1. Fig. 1Extract from the 2007 SPIE Medical Imaging program showing the inaugural CAD conference program committee.  At the inaugural conference in 2007, the oral sessions were divided into 12 separate sessions. The section topics were mammogram analysis, CT colon, a keynote session, pathology imaging, thoracic CT, MRI applications, CT lung nodules, breast tomosynthesis, cardiac/new applications, breast imaging, and thoracic/skeletal imaging. The conference had 179 submissions and 136 accepted papers. These were divided into 1 keynote, 59 oral, and 77 poster exhibits. The conference proceedings included 132 published full papers. In 2021, the oral sessions were divided into 13 separate sessions. The topics included a keynote session, lung (three separate sessions), breast (two sessions), abdomen (two sessions), cardiovascular and ophthalmology, musculoskeletal, pediatric/fetal applications, methodology, and neuroradiology including head and neck. The conference had 162 submissions and 110 accepted papers. These were divided into 64 oral and 44 poster exhibits. The conference proceedings included 99 published full papers and 102 presentations. Figure 2 shows statistics of submissions, acceptances, oral and poster presentations, and publications. The acceptance rate averaged 79% (range 68% to 97%). Fig. 2Statistics for the SPIE Medical Imaging Computer-Aided Diagnosis conference. Numbers of submissions, accepted, oral, and poster presentations and published proceedings articles are shown. Data courtesy of SPIE.  The CAD conference included a number of special sessions, frequently co-organized with one of the other SPIE Medical Imaging conferences. Many of the special sessions included panel discussions. Special sessions included Critical Issues in Adapting CAD into Clinical Practice (2008), Digital Pathology (2012), Challenges in CAD Development and Commercialization (2013), CAD Successes and Failures (2014), CAD Grand Challenge—Present and Future (2015), SPIE/IFCARS Joint Workshop on Information Management, Systems Integration, Standards, and Approval Issues for the Digital Operating Room (2016 and 2017), and Simulated Tumor Board: Brain and Breast (2020). These panel discussions, such as the 2020 Simulated Tumor Board, often included clinicians, beyond the regular scientific and technical attendees of SPIE MI, to expand the clinical knowledge base of the CAD researchers, many of whom might not have access to clinicians. Many of the other CAD conference special sessions included Grand Challenges with their discussions and outcomes including the SPIE-AAPM-NCI Lung Nodule Classification Challenge (LUNGx) (2015), SPIE-AAPM-NCI CAD Grand Challenges: Paving the Way for Imaging in the Era of Precision Medicine (2016), PROSTATEx Challenge and Digital Mammography DREAM Challenge (2017), PROSTATEx Lessons Learned and 2019 Challenge (2018), and BreastPathQ: Cancer Cellularity Challenge (2019). Keynote speakers are highlights of the annual conference. The conference’s inaugural keynote speaker in 2007 was Robert F. Wagner from the FDA. His keynote topic was “Computer-aided diagnosis and the general bioinformatics problem.” The keynote speakers and topics presented are shown in Table 2. Table 1Conference cochairs.
Table 2Keynote speakers and topics.
Live demonstrations, initiated by the CAD conference at the SPIE Medical Imaging meeting, are a popular session at the CAD conference. Begun at the inaugural CAD conference in 2007 and led by Maryellen L. Giger, The Univ. of Chicago (United States); Nico Karssemeijer, Radboud, Univ. Nijmegen (The Netherlands); and Michael F. McNitt-Gray, Univ. of California/Los Angeles (United States), live hands-on demonstrations continued annually thereafter. Organizers of the live demonstrations in later years included Bram van Ginneken, Univ. Medisch Ctr. Utrecht (The Netherlands); Stephen R. Aylward, Kitware, Inc. (United States); Heang-Ping Chan, Univ. of Michigan (United States); Horst Hahn, Fraunhofer MEVIS, (Germany); Lubomir Hadjiiski, Univ. of Michigan Health System (United States); and Karen Drukker, Univ. of Chicago (United States). Attendees vote for their favorite demonstration each year and awards are given for the highest vote-getter. The top contributors to the CAD conference are shown in Tables 3 and 4. Over the years, the most prolific contributor to the CAD conference has been Heang-Ping Chan, PhD, from the University of Michigan. The top contributing institution has been the University of Chicago. Table 3Top contributors to proceeding papers from the SPIE Medical Imaging CAD conferences.
Note: Numbers of articles published in the conference proceedings and co-authored by the given author. Search terms (Date of search October 29, 2021; only includes published proceedings articles, not abstracts that did not lead to a published proceedings article): scholarly works (1974) = [SPIE AND (Medical AND Imaging)] AND Source Title: (computer-aided AND diagnosis).1 Table 4Top contributing institutions to proceeding papers from the SPIE Medical Imaging CAD conferences.
Note: Search terms (Date of search October 29, 2021; only includes published proceedings articles, not abstracts that did not lead to a published proceedings article): Scholarly Works (1974) = [SPIE AND (Medical AND Imaging)] AND source title: (Computer-aided AND Diagnosis).1 The most downloaded papers of all time and from 2021 are shown in Tables 5 and 6, respectively. The all-time most downloaded papers cover a variety of topics including breast, brain, cardiac, and prostate imaging. The most downloaded papers from 2021 emphasized deep learning and COVID-19. Table 5Top 10 CAD proceedings paper downloads, 2007 to 2021.
Note: Data as of January 10, 2022, courtesy of SPIE. Table 6Top 10 CAD proceedings paper downloads from 2021 (Vol. 11597).
Note: Data as of January 10, 2022, courtesy of SPIE. The sessions at the CAD conference are typically organized by body organ rather than by methodology. Lung and breast have been two consistently presented areas throughout the life of the CAD conference. Other frequent topics include the abdomen, colon, cardiac and vascular, musculoskeletal, radiomics, deep learning, brain, head and neck, eye, and pathology imaging (which later became the separate Digital Pathology conference). As COVID-19 arose, it also became a topic within the CAD conference. While artificial neural networks, including deep learning with early versions of convolutional neural networks, had been included in SPIE CAD presentations since the mid-1990s, deep learning became a major focus in about 2016 and became the preeminent method of machine learning in subsequent years. In the next section, we review some of the topics covered during the life of the CAD conference. Because of the large number of oral and poster presentations over the years, only a small number of representative examples can be listed. Lung nodule analysis has been a consistent theme throughout the history of the SPIE Medical Imaging symposium and was a major theme that transferred from the Image Processing conference to the CAD conference.22–24 The Lung Image Database Consortium had several early papers.25 Lung nodule phantoms were a popular theme.26 Temporal analysis of lung disease also attracted attention.27 Other thoracic disease topics of recurrent interest included chronic obstructive pulmonary disease (COPD) and emphysema, diffuse lung parenchymal disease, lung cancer, pneumothorax detection, pneumoconiosis, tuberculosis, pleural effusions, and pulmonary embolism detection.28–35 Pulmonary patterns including texture analysis were a popular topic in 2010.36 In 2016, texture analysis was combined with deep learning.37 Chest radiograph diagnosis was notably enhanced with deep learning thereafter.38–41 Other notable topics included H1N1 pneumonia and population screening using chest radiography.42,43 Anatomic topics included interlobar fissure detection, mediastinal lymph node station mapping, airway analysis, and guidance for interventions.44–48 Introduction of thoracic low-dose CT (LDCT) led to the development of AI for emphysema, coronary artery calcifications, and osteoporosis.49,50 As COVID-19 arose with its presentation on chest radiographs and thoracic CTs, AI methods for COVID became a part of the CAD conference presentations.15,51 With the continuing rise in mammographic screening and multimodality breast diagnosis computer vision and machine learning systems, it is not surprising that breast has been a mainstay in the CAD conference. Many of the presenters on breast CAD had previously submitted to the image processing conference. Beyond full-field digital mammograms and breast ultrasound, CAD on breast tomosynthesis was an early topic for emerging technology.52–54 Other breast imaging technologies and topics with CAD applications included dynamic breast MRI, utilization of multiple views, lesion segmentation and classification, breast segmentation and density assessment, predictive models for cancer risk assessment, dedicated breast CT, 3D ultrasound, and breast cancer diagnosis with deep learning.55–62 In addition, AI methods for assessing prognosis and response to therapy have been presented.63 Abdominal imaging with a focus on bowel and liver was a frequent topic. Automated colonic polyp detection, classification, and measurement of CTC with or without traditional cathartic colon cleansing were popular topics in the early years of the conference before CT colonography became a mainstream clinical technique.64–69 Colon and colonic polyp analysis further included dual-energy CT colonography, taeniae coli detection, supine-prone colonic polyp registration, colitis detection, and colonoscopy video analysis.70–74 Other abdominal topics have included bladder segmentation, small bowel analysis including segmentation and Crohn disease detection, endoscopic image analysis for polyps and cancers, liver organ and lesion segmentation, liver elastography, kidney segmentation, renal calculi detection, pancreas segmentation, pancreatic cyst classification, and uterine and placental segmentation.75–85 Prostate MRI analysis, including whole gland segmentation, cancerous and noncancerous lesion detection and classification, and multiparametric and dynamic contrast-enhanced prostate MRI analysis, was also presented as part of various topics.11,86–91 Occasional presentations have focused on CAD in other oncologic diseases including assessment of lymphadenopathy, cervical cancer, esophageal cancer, pancreatic tumors, and multiple myeloma.92–98 CAD of cardiac and vascular imaging included coronary artery calcium scoring with deep learning, coronary artery detection, and stenosis analysis on angiography and CT, intravascular OCT, cardiomegaly assessment, and cardiac wall and chamber assessment.99–104 Atherosclerotic disease outside the heart was also assessed.105,106 CAD of brain imaging included detection, segmentation, and classification of brain tumors, Alzheimer’s dementia, neonatal brain analysis, stroke outcome prediction, radiogenomics of glioblastoma, intracranial hemorrhage and aneurysms, hydrocephalus diagnosis, glioma mutation assessment, and traumatic brain injury.8,107–116 A notable topic was the detection of head malformations in craniosynostosis from 3D photographs.117 CAD approaches in musculoskeletal imaging have focused on the spine and appendicular skeleton and the muscles and joints. Topics included fracture and metastases detection, bone quality, vertebral segmentation, spinal and neural foraminal stenosis detection, scoliosis and intervertebral disk degeneration assessment, localization of the epiphyses, automated bone mineral densitometry, osteoporosis, osteolysis, and muscle segmentation including analysis of the psoas muscles in amyotrophic lateral sclerosis.118–127 Analysis of pathology images was initially in the CAD conference including cytologic and histologic automated diagnosis, and multispectral fluorescence microscopy.128,129 However, now with the digital pathology conference at the SPIE Medical Imaging meeting, most papers have moved there. CAD of ophthalmological imaging has included analysis of images for diabetic retinopathy, retinal vascular analysis including microaneurysm detection, macular degeneration, malaria retinopathy, retinal cone photoreceptor detection, and retinopathy of prematurity.130–136 Radiomics, a more recent term for the human-engineered features extracted in many CAD algorithms, was first included as a session topic in 2016. Radiomics topics have included associations between breast MRI features and gene expression, associations of radiomics features with acquisition-related parameters such as interscanner variations and MR magnet strengths, harmonization methods, and prediction of molecular subtypes of pediatric medulloblastoma, as well as assessment of the effect of variations in texture software packages on algorithm performance and robustness.137–141 Other topics have included multiorgan segmentation, CAD methodology, CAD software, dental applications including arthritis of the temporomandibular joint (TMJ), and analysis of chronic wound, skin lesion, and eardrum images.142–150 Endocrine analysis included thyroid and parotid gland segmentation.151,152 Surgical applications included detection of retained foreign bodies.153 With 2085 accepted papers and 1985 published proceedings articles through 2021, the SPIE Medical Imaging CAD conference continues to thrive. The deep learning revolution in medical image processing has greatly contributed to this growth. It is expected that deep learning will continue to be one of the main drivers of scientific advances in computer-aided diagnosis over the next 5 to 10 years. The authors thank the many program committee members, conference chairs, session chairs, and authors whose ongoing participation contributed to the success of the CAD conference. DisclosuresAuthor RMS receives royalties from iCAD, PingAn, ScanMed, Philips, and Translation Holdings. His lab received research support from PingAn. Author MLG is a stockholder in R2 Technology/Hologic and QView, receives royalties from Hologic, GE Medical Systems, MEDIAN Technologies, Riverain Medical, Mitsubishi, and Toshiba, and was a cofounder of Quantitative Insights (now a consultant to Qlarity Imaging). AcknowledgmentsThis work was supported in part by the Intramural Research Program of the National Institutes of Health Clinical Center as well as funding from the National Cancer Institute and National Institute of Biomedical Imaging and Bioengineering, and the Department of Radiology at the University of Chicago. ReferencesLens.org, https://www.lens.org/lens/search/scholar/list?q=(SPIE%20Medical%20Imaging)%20AND%20source.title:(Computer-aided%20Diagnosis)&p=0&n=10&s=_score&d=%2B&f=false&e=false&l=en&authorField=author&dateFilterField=publishedYear&orderBy=%2B_score&presentation=false&preview=true&stemmed=true&useAuthorId=false&publishedYear.from=2007&publishedYear.to=2021 Google Scholar
S. D. Wu et al.,
“Fully automated chest wall line segmentation in breast MRI by using context information,”
Proc. SPIE, 8315 831507
(2012). https://doi.org/10.1117/12.911612 PSISDG 0277-786X Google Scholar
M. A. Koenrades et al.,
“Validation of an image registration and segmentation method to measure stent graft motion on ECG-gated CT using a physical dynamic stent graft model,”
Proc. SPIE, 10134 1013418
(2017). https://doi.org/10.1117/12.2254262 PSISDG 0277-786X Google Scholar
V. Wegmayr, S. Aitharaju and J. Buhmann,
“Classification of Brain MRI with big data and deep 3D convolutional neural networks,”
Proc. SPIE, 10575 105751S
(2018). https://doi.org/10.1117/12.2293719 PSISDG 0277-786X Google Scholar
Y. Bar et al.,
“Deep learning with non-medical training used for chest pathology identification,”
Proc. SPIE, 9414 94140V
(2015). https://doi.org/10.1117/12.2083124 PSISDG 0277-786X Google Scholar
W. Q. Sun, B. Zheng and W. Qian,
“Computer aided lung cancer diagnosis with deep learning algorithms,”
Proc. SPIE, 9785 97850Z
(2016). https://doi.org/10.1117/12.2216307 PSISDG 0277-786X Google Scholar
S. S. Ramachandran et al.,
“Using YOLO based deep learning network for real time detection and localization of lung nodules from low dose CT scans,”
Proc. SPIE, 10575 105751I
(2018). https://doi.org/10.1117/12.2293699 PSISDG 0277-786X Google Scholar
K. Jnawali et al.,
“Deep 3D convolution neural network for CT brain hemorrhage classification,”
Proc. SPIE, 10575 105751C
(2018). https://doi.org/10.1117/12.2293725 PSISDG 0277-786X Google Scholar
Q. Wei et al.,
“Anomaly detection for medical images based on a one-class classification,”
Proc. SPIE, 10575 105751M
(2018). https://doi.org/10.1117/12.2293408 PSISDG 0277-786X Google Scholar
S. F. Liu et al.,
“Prostate cancer diagnosis using deep learning with 3D multiparametric MRI,”
Proc. SPIE, 10134 1013428
(2017). https://doi.org/10.1117/12.2277121 PSISDG 0277-786X Google Scholar
Y. K. Tsehay et al.,
“Convolutional neural network based deep-learning architecture for prostate cancer detection on multiparametric magnetic resonance images,”
Proc. SPIE, 10134 1013405
(2017). https://doi.org/10.1117/12.2254423 PSISDG 0277-786X Google Scholar
M. Heidari et al.,
“Detecting COVID-19 infected pneumonia from x-ray images using a deep learning model with image preprocessing algorithm,”
Proc. SPIE, 11597 115970V
(2021). https://doi.org/10.1117/12.2580948 PSISDG 0277-786X Google Scholar
R. Paul et al.,
“Deep radiomics: deep learning on radiomics texture images,”
Proc. SPIE, 11597 1159705
(2021). https://doi.org/10.1117/12.2582102 PSISDG 0277-786X Google Scholar
D. Sriker et al.,
“Improved segmentation by adversarial U-Net,”
Proc. SPIE, 11597 1159719
(2021). https://doi.org/10.1117/12.2582130 PSISDG 0277-786X Google Scholar
Q. Y. Hu, K. Drukker and M. L. Giger,
“Role of standard and soft tissue chest radiography images in COVID-19 diagnosis using deep learning,”
Proc. SPIE, 11597 1159704
(2021). https://doi.org/10.1117/12.2581977 PSISDG 0277-786X Google Scholar
M. Q. Pan et al.,
“Deep learning-based aggressive progression prediction from CT images of hepatocellular carcinoma,”
Proc. SPIE, 11597 115972Y
(2021). https://doi.org/10.1117/12.2581057 PSISDG 0277-786X Google Scholar
P. J. R. Prasad et al.,
“Modifying U-Net for small dataset: a simplified U-Net version for liver parenchyma segmentation,”
Proc. SPIE, 11597 115971O
(2021). https://doi.org/10.1117/12.2582179 PSISDG 0277-786X Google Scholar
N. Moreau et al.,
“Comparison between threshold-based and deep learning-based bone segmentation on whole-body CT images,”
Proc. SPIE, 11597 115972U
(2021). https://doi.org/10.1117/12.2580892 PSISDG 0277-786X Google Scholar
J. M. Luna et al.,
“Radiomic features predict local failure-free survival in stage III NSCLC adenocarcinoma treated with chemoradiation,”
Proc. SPIE, 11597 1159720
(2021). https://doi.org/10.1117/12.2581873 PSISDG 0277-786X Google Scholar
Y. N. T. Vu et al.,
“An improved mammography malignancy model with self-supervised learning,”
Proc. SPIE, 11597 115970W
(2021). https://doi.org/10.1117/12.2582318 PSISDG 0277-786X Google Scholar
C. Agarwal et al.,
“CoroNet: a deep network architecture for enhanced identification of COVID-19 from chest x-ray images,”
Proc. SPIE, 11597 1159722
(2021). https://doi.org/10.1117/12.2580738 PSISDG 0277-786X Google Scholar
B. van Ginneken et al.,
“Automated detection of nodules attached to the pleural and mediastinal surface in low-dose CT scans,”
Proc. SPIE, 6915 69150X
(2008). https://doi.org/10.1117/12.772298 PSISDG 0277-786X Google Scholar
M. Bergtholdt, R. Wiemker and T. Klinder,
“Pulmonary nodule detection using a cascaded SVM classifier,”
Proc. SPIE, 9785 978513
(2016). https://doi.org/10.1117/12.2216747 PSISDG 0277-786X Google Scholar
M. L. Giger, K. Doi and H. MacMahon,
“Computerized detection of lung nodules in digital chest radiographs,”
Proc. SPIE, 0767 384
–387
(1987). https://doi.org/10.1117/12.967022 PSISDG 0277-786X Google Scholar
A. P. Reeves et al.,
“The lung image database consortium (LIDC): pulmonary nodule measurements, the variation, and the difference between different size metrics,”
Proc. SPIE, 6514 65140J
(2007). https://doi.org/10.1117/12.713672 PSISDG 0277-786X Google Scholar
Q. Li et al.,
“Factors affecting uncertainty in lung nodule volume estimation with CT: comparisons of findings from two estimation methods in a phantom study,”
Proc. SPIE, 9414 94140C
(2015). https://doi.org/10.1117/12.2081489 PSISDG 0277-786X Google Scholar
C. Ho, K. Lee and S. G. Armato,
“A computer-aided diagnosis system to identify regions of pathologic change in temporal subtraction images of the chest,”
Proc. SPIE, 9414 94141L
(2015). https://doi.org/10.1117/12.2082820 PSISDG 0277-786X Google Scholar
R. Rudyanto et al.,
“Detecting airway remodeling in COPD and emphysema using low-dose CT imaging,”
Proc. SPIE, 8315 83150S
(2012). https://doi.org/10.1117/12.91090 PSISDG 0277-786X Google Scholar
E. M. van Rikxoort et al.,
“Classification of pulmonary emphysema from chest CT scans using integral geometry descriptors,”
Proc. SPIE, 7963 79631O
(2011). https://doi.org/10.1117/12.878180 PSISDG 0277-786X Google Scholar
C. Chen et al.,
“Towards exaggerated emphysema stereotypes,”
Proc. SPIE, 8315 83150Q
(2012). https://doi.org/10.1117/12.911398 PSISDG 0277-786X Google Scholar
R. Wiemker et al.,
“Automated assessment of imaging biomarkers for the PanCan lung cancer risk prediction model with validation on NLST data,”
Proc. SPIE, 10134 1013421
(2017). https://doi.org/10.1117/12.2253905 PSISDG 0277-786X Google Scholar
O. Geva et al.,
“Pneumothorax detection in chest radiographs using local and global texture signatures,”
Proc. SPIE, 9414 94141P
(2015). https://doi.org/10.1117/12.2083128 PSISDG 0277-786X Google Scholar
H. Suzuki et al.,
“Computer aided diagnosis for severity assessment of pneumoconiosis using CT images,”
Proc. SPIE, 9785 978531
(2016). https://doi.org/10.1117/12.2217480 PSISDG 0277-786X Google Scholar
P. Maduskar et al.,
“Improved texture analysis for automatic detection of tuberculosis (TB) on chest radiographs with bone suppression images,”
Proc. SPIE, 8670 86700H
(2013). https://doi.org/10.1117/12.2008083 PSISDG 0277-786X Google Scholar
A. Mansoor, R. Casas and M. G. Linguraru,
“Spatial context learning approach to automatic segmentation of pleural effusion in chest computed tomography images,”
Proc. SPIE, 9785 978514
(2016). https://doi.org/10.1117/12.2216958 PSISDG 0277-786X Google Scholar
T. T. Kockelkorn et al.,
“Interactive annotation of textures in thoracic CT scans,”
Proc. SPIE, 7624 76240X
(2010). https://doi.org/10.1117/12.844932 PSISDG 0277-786X Google Scholar
S. R. Tarando et al.,
“Increasing CAD system efficacy for lung texture analysis using a convolutional network,”
Proc. SPIE, 9785 97850Q
(2016). https://doi.org/10.1117/12.2217752 PSISDG 0277-786X Google Scholar
Y. Anavi et al.,
“Visualizing and enhancing a deep learning framework using patients age and gender for chest x-ray image retrieval,”
Proc. SPIE, 9785 978510
(2016). https://doi.org/10.1117/12.2217587 PSISDG 0277-786X Google Scholar
R. K. Samala et al.,
“Analysis of deep convolutional features for detection of lung nodules in computed tomography,”
Proc. SPIE, 10950 109500Q
(2019). https://doi.org/10.1117/12.2512208 PSISDG 0277-786X Google Scholar
J. Liang et al.,
“Bone suppression on chest radiographs with adversarial learning,”
Proc. SPIE, 11314 1131409
(2020). https://doi.org/10.1117/12.2550868 PSISDG 0277-786X Google Scholar
Y. X. Tang et al.,
“Deep adversarial one-class learning for normal and abnormal chest radiograph classification,”
Proc. SPIE, 10950 1095018
(2019). https://doi.org/10.1117/12.2511787 PSISDG 0277-786X Google Scholar
J. H. Yao et al.,
“Computer-aided assessment of pulmonary disease in novel swine-origin H1N1 influenza on CT,”
Proc. SPIE, 10575 105751E
(2018). https://doi.org/10.1117/12.2293140 PSISDG 0277-786X Google Scholar
R. Sivaramakrishnan et al.,
“Comparing deep learning models for population screening using chest radiography,”
Proc. SPIE, 10575 105751E
(2018). https://doi.org/10.1117/12.2293140 PSISDG 0277-786X Google Scholar
M. Matsuhiro et al.,
“Extraction method of interlobar fissure based on multi-slice CT images,”
Proc. SPIE, 8670 867031
(2013). https://doi.org/10.1117/12.2007822 PSISDG 0277-786X Google Scholar
M. M. S. Matsumoto et al.,
“Automatic localization of IASLC-defined mediastinal lymph node stations on CT images using fuzzy models,”
Proc. SPIE, 9035 90350J
(2014). https://doi.org/10.1117/12.2044333 PSISDG 0277-786X Google Scholar
J. M. Liu et al.,
“Mediastinal lymph node detection on thoracic CT scans using spatial prior from multi-atlas label fusion,”
Proc. SPIE, 9035 90350M
(2014). https://doi.org/10.1117/12.2043737 PSISDG 0277-786X Google Scholar
B. L. Odry et al.,
“Comparison of analysis methods for airway quantification,”
Proc. SPIE, 8315 83152R
(2012). https://doi.org/10.1117/12.912420 PSISDG 0277-786X Google Scholar
M. Oda et al.,
“Automated branching pattern report generation for laparoscopic surgery assistance,”
Proc. SPIE, 9414 94141T
(2015). https://doi.org/10.1117/12.2082488 PSISDG 0277-786X Google Scholar
M. King et al.,
“Computer-aided assessment of cardiac computed tomographic images,”
Proc. SPIE, 6514 65141B
(2007). https://doi.org/10.1117/12.713857 PSISDG 0277-786X Google Scholar
Z. B. Rodgers et al.,
“Computerized assessment of coronary calcified plaques in CT images of a dynamic cardiac phantom,”
Proc. SPIE, 6915 69150M
(2008). https://doi.org/10.1117/12.773016 PSISDG 0277-786X Google Scholar
R. K. Samala et al.,
“Severity assessment of COVID-19 using imaging descriptors: a deep-learning transfer learning approach from non-COVID-19 pneumonia,”
Proc. SPIE, 11597 115971T
(2021). https://doi.org/10.1117/12.2582115 PSISDG 0277-786X Google Scholar
D. Kontos, P. R. Bakic and A. D. A. Maidment,
“Analysis of parenchymal texture properties in breast tomosynthesis images,”
Proc. SPIE, 6514 651417
(2007). https://doi.org/10.1117/12.713851 PSISDG 0277-786X Google Scholar
H. P. Chan et al.,
“Digital breast tomosynthesis: computerized detection of microcalcifications in reconstructed breast volume using a 3D approach,”
Proc. SPIE, 7624 76241D
(2010). https://doi.org/10.1117/12.844511 PSISDG 0277-786X Google Scholar
H. P. Chan et al.,
“Computer-aided detection of masses in digital tomosynthesis mammography: combination of 3D and 2D detection information,”
Proc. SPIE, 6514 651416
(2007). https://doi.org/10.1117/12.713640 PSISDG 0277-786X Google Scholar
A. Wismuller et al.,
“Neural network vector quantization improves the diagnostic quality of computer-aided diagnosis in dynamic breast MRI,”
Proc. SPIE, 6514 65141F
(2007). https://doi.org/10.1117/12.708819 PSISDG 0277-786X Google Scholar
X. W. Wang et al.,
“Improving CAD performance by fusion of the bilateral mammographic tissue asymmetry information,”
Proc. SPIE, 8315 831508
(2012). https://doi.org/10.1117/12.910531 PSISDG 0277-786X Google Scholar
J. Loose et al.,
“Assessment of texture analysis on DCE-MRI data for the differentiation of breast tumor lesions,”
Proc. SPIE, 7260 72600K
(2009). https://doi.org/10.1117/12.812971 PSISDG 0277-786X Google Scholar
L. Jiang et al.,
“Fully automated segmentation of whole breast in MR images by use of dynamic programming,”
Proc. SPIE, 9035 90350W
(2014). https://doi.org/10.1117/12.2043343 PSISDG 0277-786X Google Scholar
M. Otsuka et al.,
“Local mammographic density as a predictor of breast cancer,”
Proc. SPIE, 9414 941417
(2015). https://doi.org/10.1117/12.2082691 PSISDG 0277-786X Google Scholar
K. R. Mendel, H. Li and M. L. Giger,
“Quantitative breast MRI radiomics for cancer risk assessment and the monitoring of high-risk populations,”
Proc. SPIE, 9785 97851W
(2016). https://doi.org/10.1117/12.2217775 PSISDG 0277-786X Google Scholar
J. Lee et al.,
“Neutrosophic segmentation of breast lesions for dedicated breast CT,”
Proc. SPIE, 10134 101340Q
(2017). https://doi.org/10.1117/12.2254128 PSISDG 0277-786X Google Scholar
K. Drukker et al.,
“Deep learning and three-compartment breast imaging in breast cancer diagnosis,”
Proc. SPIE, 10134 101341F
(2017). https://doi.org/10.1117/12.2254516 PSISDG 0277-786X Google Scholar
K. Drukker et al.,
“Breast MRI radiomics for the pre-treatment prediction of response to neoadjuvant chemotherapy in node-positive breast cancer patients,”
Proc. SPIE, 10950 109502N
(2019). https://doi.org/10.1117/12.2513561 PSISDG 0277-786X Google Scholar
W. L. Cai et al.,
“Delineation of tagged region by use of local iso-surface roughness in electronic cleansing for CT colonography,”
Proc. SPIE, 6514 651409
(2007). https://doi.org/10.1117/12.710088 PSISDG 0277-786X Google Scholar
H. F. Wang et al.,
“Automated polyp measurement based on colon structure decomposition for CT colonography,”
Proc. SPIE, 9035 90350B
(2014). https://doi.org/10.1117/12.2043648 PSISDG 0277-786X Google Scholar
J. Liu et al.,
“High-performance computer aided detection system for polyp detection in CT colonography with fluid and fecal tagging,”
Proc. SPIE, 7260 72601B
(2009). https://doi.org/10.1117/12.811654 PSISDG 0277-786X Google Scholar
K. Suzuki et al.,
“An MTANN CAD for detection of polyps in false-negative CT colonography cases in a large multicenter clinical trial: preliminary results,”
Proc. SPIE, 6915 69150F
(2008). https://doi.org/10.1117/12.769824 PSISDG 0277-786X Google Scholar
J. M. Aman, J. H. Yao and R. M. Summers,
“Automatic colonic polyp shape determination using content-based image retrieval,”
Proc. SPIE, 7963 79632G
(2011). https://doi.org/10.1117/12.878196 PSISDG 0277-786X Google Scholar
J. M. Aman, J. H. Yao and R. M. Summers,
“Prediction of polyp histology on CT colonography using content-based image retrieval,”
Proc. SPIE, 7624 76240D
(2010). https://doi.org/10.1117/12.844571 PSISDG 0277-786X Google Scholar
J. J. Nappi, S. H. Kim and H. Yoshida,
“Automated detection of colorectal lesions with dual-energy CT colonography,”
Proc. SPIE, 8315 83150Y
(2012). https://doi.org/10.1117/12.911708 PSISDG 0277-786X Google Scholar
J. Lamy and R. M. Summers,
“Intra-patient colon surface registration based on teniæ coli,”
Proc. SPIE, 6514 65140C
(2007). https://doi.org/10.1117/12.709780 PSISDG 0277-786X Google Scholar
S. J. Wang et al.,
“Matching colonic polyps using correlation optimized warping,”
Proc. SPIE, 7624 76240E
(2010). https://doi.org/10.1117/12.844352 PSISDG 0277-786X Google Scholar
J. M. Liu et al.,
“Colitis detection on abdominal CT scans by rich feature hierarchies,”
Proc. SPIE, 9785 97851N
(2016). https://doi.org/10.1117/12.2217681 PSISDG 0277-786X Google Scholar
S. Gross et al.,
“Automated classification of colon polyps in endoscopic image data,”
Proc. SPIE, 8315 83150W
(2012). https://doi.org/10.1117/12.911177 PSISDG 0277-786X Google Scholar
L. Hadjiiski et al.,
“Segmentation of urinary bladder in CT urography (CTU) using CLASS,”
Proc. SPIE, 8315 83150J
(2012). https://doi.org/10.1117/12.912847 PSISDG 0277-786X Google Scholar
M. Oda et al.,
“Connection method of separated luminal regions of intestine from CT volumes,”
Proc. SPIE, 9414 94140P
(2015). https://doi.org/10.1117/12.2081977 PSISDG 0277-786X Google Scholar
J. J. Cerrolaza et al.,
“Quantification, validation, and follow-up of small bowel motility in Crohn’s disease,”
Proc. SPIE, 9414 94141D
(2015). https://doi.org/10.1117/12.2081480 PSISDG 0277-786X Google Scholar
D. Boschetto and E. Grisan,
“Superpixel-based classification of gastric chromoendoscopy images,”
Proc. SPIE, 10134 101340W
(2017). https://doi.org/10.1117/12.2254187 PSISDG 0277-786X Google Scholar
A. S. Maklad et al.,
“Blood vessel-based liver segmentation through the portal phase of a CT dataset,”
Proc. SPIE, 8670 86700X
(2013). https://doi.org/10.1117/12.2007546 PSISDG 0277-786X Google Scholar
B. Dzyubak et al.,
“Automated liver elasticity calculation for 3D MRE,”
Proc. SPIE, 10134 101340Y
(2017). https://doi.org/10.1117/12.2254476 PSISDG 0277-786X Google Scholar
J. F. Liu et al.,
“Automatic segmentation of kidneys from non-contrast CT images using efficient belief propagation,”
Proc. SPIE, 8670 867005
(2013). https://doi.org/10.1117/12.2007738 PSISDG 0277-786X Google Scholar
J. F. Liu et al.,
“Robust detection of renal calculi from non-contract CT images using TV-flow and MSER features,”
Proc. SPIE, 8670 867006
(2013). https://doi.org/10.1117/12.2008034 PSISDG 0277-786X Google Scholar
S. A. Sriram et al.,
“Multilevel UNet for pancreas segmentation from non-contrast CT scans through domain adaptation,”
Proc. SPIE, 11314 113140K
(2020). https://doi.org/10.1117/12.2551093 PSISDG 0277-786X Google Scholar
L. Gazit et al.,
“Quantification of CT images for the classification of high- and low-risk pancreatic cysts,”
Proc. SPIE, 10134 101340X
(2017). https://doi.org/10.1117/12.2255626 PSISDG 0277-786X Google Scholar
M. Shahedi et al.,
“Segmentation of uterus and placenta in MR images using a fully convolutional neural network,”
Proc. SPIE, 11314 113141R
(2020). https://doi.org/10.1117/12.2549873 PSISDG 0277-786X Google Scholar
Y. Peng et al.,
“A study of T2-weighted MR image texture features and diffusion-weighted MR image features for computer-aided diagnosis of prostate cancer,”
Proc. SPIE, 8670 86701H
(2013). https://doi.org/10.1117/12.2007979 PSISDG 0277-786X Google Scholar
G. J. S. Litjens et al.,
“Distinguishing prostate cancer from benign confounders via a cascaded classifier on multi-parametric MRI,”
Proc. SPIE, 9035 903512
(2014). https://doi.org/10.1117/12.2043751 PSISDG 0277-786X Google Scholar
P. C. Vos et al.,
“Combining T2-weighted with dynamic MR images for computerized classification of prostate lesions,”
Proc. SPIE, 6915 69150W
(2008). https://doi.org/10.1117/12.771970 PSISDG 0277-786X Google Scholar
P. Liu et al.,
“A prostate cancer computer-aided diagnosis system using multimodal magnetic resonance imaging and targeted biopsy labels,”
Proc. SPIE, 8670 86701G
(2013). https://doi.org/10.1117/12.2007927 PSISDG 0277-786X Google Scholar
N. Lay et al.,
“Detection of benign prostatic hyperplasia nodules in T2W MR images using fuzzy decision forest,”
Proc. SPIE, 9785 978527
(2016). https://doi.org/10.1117/12.2217906 PSISDG 0277-786X Google Scholar
K. M. Boehm et al.,
“Efficient Hilbert transform-based alternative to Tofts physiological models for representing MRI dynamic contrast-enhanced images in computer-aided diagnosis of prostate cancer,”
Proc. SPIE, 9414 94140S
(2015). https://doi.org/10.1117/12.2082309 PSISDG 0277-786X Google Scholar
J. Liu et al.,
“Automatic detection of axillary lymphadenopathy on CT scans of untreated chronic lymphocytic leukemia patients,”
Proc. SPIE, 8315 83150B
(2012). https://doi.org/10.1117/12.911836 PSISDG 0277-786X Google Scholar
J. M. Liu, J. M. White and R. M. Summers,
“Computer-aided lymph node detection in abdominal CT images,”
Proc. SPIE, 7624 76240U
(2010). https://doi.org/10.1117/12.844406 PSISDG 0277-786X Google Scholar
Y. Nakamura et al.,
“Automatic abdominal lymph node detection method based on local intensity structure analysis from 3D x-ray CT images,”
Proc. SPIE, 8670 86701K
(2013). https://doi.org/10.1117/12.2008282 PSISDG 0277-786X Google Scholar
T. Xu et al.,
“Multi-test cervical cancer diagnosis with missing data estimation,”
Proc. SPIE, 9414 94140X
(2015). https://doi.org/10.1117/12.2080871 PSISDG 0277-786X Google Scholar
M. H. A. Janse et al.,
“Early esophageal cancer detection using RF classifiers,”
Proc. SPIE, 9785 97851D
(2016). https://doi.org/10.1117/12.2208583 PSISDG 0277-786X Google Scholar
M. Goetz et al.,
“Machine-learning based comparison of CT-perfusion maps and dual energy CT for pancreatic tumor detection,”
Proc. SPIE, 9785 97851R
(2016). https://doi.org/10.1117/12.2216645 PSISDG 0277-786X Google Scholar
C. A. Zhou et al.,
“Deep learning-based risk stratification for treatment management of multiple myeloma with sequential MRI scans,”
Proc. SPIE, 11597 1159716
(2021). https://doi.org/10.1117/12.2582203 PSISDG 0277-786X Google Scholar
N. Lessmann et al.,
“Deep convolutional neural networks for automatic coronary calcium scoring in a screening study with low-dose chest CT,”
Proc. SPIE, 9785 978511
(2016). https://doi.org/10.1117/12.2216978 PSISDG 0277-786X Google Scholar
M. Tessmann et al.,
“Multi-scale feature extraction for learning-based classification of coronary artery stenosis,”
Proc. SPIE, 7260 726002
(2009). https://doi.org/10.1117/12.811639 PSISDG 0277-786X Google Scholar
K. P. Tung et al.,
“"Automatic detection of coronary stent struts in intravascular OCT imaging,”
Proc. SPIE, 8315 83150K
(2012). https://doi.org/10.1117/12.911216 PSISDG 0277-786X Google Scholar
J. D. Fuhrman et al.,
“Detection and classification of coronary artery calcifications in low dose thoracic CT using deep learning,”
Proc. SPIE, 10950 1095039
(2019). https://doi.org/10.1117/12.2513134 PSISDG 0277-786X Google Scholar
A. H. Dallal et al.,
“Automatic estimation of heart boundaries and cardiothoracic ratio from chest x-ray images,”
Proc. SPIE, 10134 101340K
(2017). https://doi.org/10.1117/12.2254136 PSISDG 0277-786X Google Scholar
G. Yang et al.,
“Differentiation of pre-ablation and post-ablation late gadolinium-enhanced cardiac MRI scans of longstanding persistent atrial fibrillation patients,”
Proc. SPIE, 10134 101340O
(2017). https://doi.org/10.1117/12.2250910 PSISDG 0277-786X Google Scholar
J. M. Liu et al.,
“Pelvic artery calcification detection on CT scans using convolutional neural networks,”
Proc. SPIE, 10134 101341A
(2017). https://doi.org/10.1117/12.2255247 PSISDG 0277-786X Google Scholar
J. M. Liu et al.,
“A semi-supervised CNN learning method with pseudo-class labels for vascular calcification detection on low dose CT scans,”
Proc. SPIE, 10950 109501L
(2019). https://doi.org/10.1117/12.2513228 PSISDG 0277-786X Google Scholar
S. M. S. Reza, R. Mays and K. M. Iftekharuddin,
“Multi-fractal detrended texture feature for brain tumor classification,”
Proc. SPIE, 9414 941410
(2015). https://doi.org/10.1117/12.2083596 PSISDG 0277-786X Google Scholar
J. Rexilius et al.,
“Multispectral brain tumor segmentation based on histogram model adaptation,”
Proc. SPIE, 6514 65140V
(2007). https://doi.org/10.1117/12.709410 PSISDG 0277-786X Google Scholar
Y. Yamashita et al.,
“Computer-aided classification of patients with dementia of Alzheimer’s type based on cerebral blood flow determined with arterial spin labeling technique,”
Proc. SPIE, 7624 76241J
(2010). https://doi.org/10.1117/12.845530 PSISDG 0277-786X Google Scholar
P. Moeskops et al.,
“Assessment of quantitative cortical biomarkers in the developing brain of preterm infants,”
Proc. SPIE, 8670 867011
(2013). https://doi.org/10.1117/12.2007829 PSISDG 0277-786X Google Scholar
P. C. Vos et al.,
“Automated prediction of tissue outcome after acute ischemic stroke in computed tomography perfusion images,”
Proc. SPIE, 9414 941412
(2015). https://doi.org/10.1117/12.2081600 PSISDG 0277-786X Google Scholar
N. M. Czarnek et al.,
“Radiogenomics of glioblastoma: a pilot multi-institutional study to investigate a relationship between tumor shape features and tumor molecular subtype,”
Proc. SPIE, 9785 97850V
(2016). https://doi.org/10.1117/12.2217084 PSISDG 0277-786X Google Scholar
H. Rajabzadeh-Oghaz et al.,
“Computer-assisted adjuncts for aneurysmal morphologic assessment: toward more precise and accurate approaches,”
Proc. SPIE, 10134 101341C
(2017). https://doi.org/10.1117/12.2255553 PSISDG 0277-786X Google Scholar
N. Takahashi et al.,
“Automated method to compute Evans index for diagnosis of idiopathic normal pressure hydrocephalus on brain CT images,”
Proc. SPIE, 10134 101342C
(2017). https://doi.org/10.1117/12.2251322 PSISDG 0277-786X Google Scholar
X. Zhang et al.,
“IDH mutation assessment of glioma using texture features of multimodal MR images,”
Proc. SPIE, 10134 101341S
(2017). https://doi.org/10.1117/12.2254212 PSISDG 0277-786X Google Scholar
G. Murugesan et al.,
“Single season changes in resting state network power and the connectivity between regions distinguish head impact exposure level in high school and youth football players,”
Proc. SPIE, 10575 105750F
(2018). https://doi.org/10.1117/12.2293199 PSISDG 0277-786X Google Scholar
L. Y. Tu et al.,
“Radiation-free quantification of head malformations in craniosynostosis patients from 3D photography,”
Proc. SPIE, 10575 105751U
(2018). https://doi.org/10.1117/12.2295374 PSISDG 0277-786X Google Scholar
S. Ghosh et al.,
“Automatic lumbar vertebra segmentation from clinical CT for wedge compression fracture diagnosis,”
Proc. SPIE, 7963 796303
(2011). https://doi.org/10.1117/12.878055 PSISDG 0277-786X Google Scholar
J. H. Yao et al.,
“Quantitative vertebral compression fracture evaluation using a height compass,”
Proc. SPIE, 8315 83151X
(2012). https://doi.org/10.1117/12.911703 PSISDG 0277-786X Google Scholar
M. Wels et al.,
“Multi-stage osteolytic spinal bone lesion detection from CT data with internal sensitivity control,”
Proc. SPIE, 8315 831513
(2012). https://doi.org/10.1117/12.911169 PSISDG 0277-786X Google Scholar
T. Wiese et al.,
“Detection of sclerotic bone metastases in the spine using watershed algorithm and graph cut,”
Proc. SPIE, 8315 831512
(2012). https://doi.org/10.1117/12.911700 PSISDG 0277-786X Google Scholar
M. M. Adankon et al.,
“Scoliosis curve type classification using kernel machine from 3D trunk image,”
Proc. SPIE, 8315 831514
(2012). https://doi.org/10.1117/12.911335 PSISDG 0277-786X Google Scholar
I. Castro-Mateos et al.,
“2D segmentation of intervertebral discs and its degree of degeneration from T2-weighted magnetic resonance images,”
Proc. SPIE, 9035 903517
(2014). https://doi.org/10.1117/12.2043755 PSISDG 0277-786X Google Scholar
F. Hahmann et al.,
“Classification of voting patterns to improve the generalized Hough transform for epiphyses localization,”
Proc. SPIE, 9785 978509
(2016). https://doi.org/10.1117/12.2216173 PSISDG 0277-786X Google Scholar
J. R. Wilkie et al.,
“Imputation methods for temporal radiographic texture analysis in the detection of periprosthetic osteolysis,”
Proc. SPIE, 6514 65141L
(2007). https://doi.org/10.1117/12.713732 PSISDG 0277-786X Google Scholar
W. D. Zhang et al.,
“Segmenting the thoracic, abdominal and pelvic musculature on CT scans combining atlas-based model and active contour model,”
Proc. SPIE, 8670 867008
(2013). https://doi.org/10.1117/12.2007970 PSISDG 0277-786X Google Scholar
R. Lai et al.,
“Prognostic power of the human psoas muscles FDG metabolism in amyotrophic lateral sclerosis,”
Proc. SPIE, 11314 113141Z
(2020). https://doi.org/10.1117/12.2548857 PSISDG 0277-786X Google Scholar
H. Itoh et al.,
“Cascade classification of endocytoscopic images of colorectal lesions for automated pathological diagnosis,”
Proc. SPIE, 10575 1057516
(2018). https://doi.org/10.1117/12.2293495 PSISDG 0277-786X Google Scholar
A. Tabesh et al.,
“Robust tumor morphometry in multispectral fluorescence microscopy,”
Proc. SPIE, 7260 726015
(2009). https://doi.org/10.1117/12.812968 PSISDG 0277-786X Google Scholar
X. Xu and B. Li,
“Automatic classification and detection of clinically relevant images for diabetic retinopathy,”
Proc. SPIE, 6915 69150Q
(2008). https://doi.org/10.1117/12.769858 PSISDG 0277-786X Google Scholar
C. I. Sánchez et al.,
“Mixture model-based clustering and logistic regression for automatic detection of microaneurysms in retinal images,”
Proc. SPIE, 7260 72601M
(2009). https://doi.org/10.1117/12.812088 PSISDG 0277-786X Google Scholar
A. Mizutani et al.,
“Automated microaneurysm detection method based on double ring filter in retinal fundus images,”
Proc. SPIE, 7260 72601N
(2009). https://doi.org/10.1117/12.813468 PSISDG 0277-786X Google Scholar
F. G. Venhuizen et al.,
“Automated age-related macular degeneration classification in OCT using unsupervised feature learning,”
Proc. SPIE, 9414 94141I
(2015). https://doi.org/10.1117/12.2081521 PSISDG 0277-786X Google Scholar
C. Agurto et al.,
“Vessel discoloration detection in malarial retinopathy,”
Proc. SPIE, 9785 978519
(2016). https://doi.org/10.1117/12.2216917 PSISDG 0277-786X Google Scholar
J. F. Liu, A. Dubra and J. Tam,
“Computer-aided detection of human cone photoreceptor inner segments using multi-scale circular voting,”
Proc. SPIE, 9785 97851A
(2016). https://doi.org/10.1117/12.2216929 PSISDG 0277-786X Google Scholar
M. Graziani et al.,
“Improved interpretability for computer-aided severity assessment of retinopathy of prematurity,”
Proc. SPIE, 10950 109501R
(2019). https://doi.org/10.1117/12.2512584 PSISDG 0277-786X Google Scholar
A. Saha et al.,
“Association of high proliferation marker Ki-67 expression with DCE-MR imaging features of breast: a large scale evaluation,”
Proc. SPIE, 10575 1057507
(2018). https://doi.org/10.1117/12.2293207 PSISDG 0277-786X Google Scholar
S. Rathore et al.,
“Deriving stable multi-parametric MRI radiomic signatures in the presence of inter-scanner variations: survival prediction of glioblastoma via imaging pattern analysis and machine learning techniques,”
Proc. SPIE, 10575 1057509
(2018). https://doi.org/10.1117/12.2293661 PSISDG 0277-786X Google Scholar
H. M. Whitney et al.,
“Robustness of radiomic breast features of benign lesions and luminal A cancers across MR magnet strengths,”
Proc. SPIE, 10575 105750A
(2018). https://doi.org/10.1117/12.2293764 PSISDG 0277-786X Google Scholar
S. R. Iyer et al.,
“Deformation heterogeneity radiomics to predict molecular subtypes of pediatric Medulloblastoma on routine MRI,”
Proc. SPIE, 10950 109501E
(2019). https://doi.org/10.1117/12.2513567 PSISDG 0277-786X Google Scholar
J. J. Foy et al.,
“Variations in algorithm implementation among quantitative texture analysis software packages,”
Proc. SPIE, 10575 105751K
(2018). https://doi.org/10.1117/12.2292573 PSISDG 0277-786X Google Scholar
X. R. Zhou et al.,
“Performance evaluation of 2D and 3D deep learning approaches for automatic segmentation of multiple organs on CT images,”
Proc. SPIE, 10575 105752C
(2018). https://doi.org/10.1117/12.2295178 PSISDG 0277-786X Google Scholar
X. He et al.,
“Potential reasons for differences in CAD effectiveness evaluated using laboratory and clinical studies,”
Proc. SPIE, 9414 94141V
(2015). https://doi.org/10.1117/12.2082811 PSISDG 0277-786X Google Scholar
A. Wismüller,
“The exploration machine: a novel method for analyzing high-dimensional data in computer-aided diagnosis,”
Proc. SPIE, 7260 72600G
(2009). https://doi.org/10.1117/12.813892 PSISDG 0277-786X Google Scholar
T. Syeda-Mahmood et al.,
“Medical sieve: a cognitive assistant for radiologists and cardiologists,”
Proc. SPIE, 9785 97850A
(2016). https://doi.org/10.1117/12.2217382 PSISDG 0277-786X Google Scholar
Y. Wu et al.,
“Computer aided periapical lesion diagnosis using quantized texture analysis,”
Proc. SPIE, 8315 831518
(2012). https://doi.org/10.1117/12.911500 PSISDG 0277-786X Google Scholar
L. R. Gomes et al.,
“Diagnostic index of 3D osteoarthritic changes in TMJ condylar morphology,”
Proc. SPIE, 9414 941405
(2015). https://doi.org/10.1117/12.2082226 PSISDG 0277-786X Google Scholar
M. F. A. Fauzi et al.,
“Segmentation and automated measurement of chronic wound images: probability map approach,”
Proc. SPIE, 9035 903507
(2014). https://doi.org/10.1117/12.2043791 PSISDG 0277-786X Google Scholar
J. N. Wang et al.,
“Segmentation of skin lesions in chronic graft versus host disease photographs with fully convolutional networks,”
Proc. SPIE, 10575 105750N
(2018). https://doi.org/10.1117/12.2293334 PSISDG 0277-786X Google Scholar
C. Senaras et al.,
“Detection of eardrum abnormalities using ensemble deep learning approaches,”
Proc. SPIE, 10575 105751A
(2018). https://doi.org/10.1117/12.2293297 PSISDG 0277-786X Google Scholar
J. M. Liu et al.,
“Automated segmentation of thyroid gland on CT images with multi-atlas label fusion and random classification forest,”
Proc. SPIE, 9414 941413
(2015). https://doi.org/10.1117/12.2082204 PSISDG 0277-786X Google Scholar
A. Hansch et al.,
“Comparison of different deep learning approaches for parotid gland segmentation from CT images,”
Proc. SPIE, 10575 1057519
(2018). https://doi.org/10.1117/12.2292962 PSISDG 0277-786X Google Scholar
T. C. Marentis et al.,
“Surgical retained foreign object (RFO) prevention by computer aided detection (CAD),”
Proc. SPIE, 9035 903529
(2014). https://doi.org/10.1117/12.2042469 PSISDG 0277-786X Google Scholar
BiographyRonald M. Summers is a tenured senior investigator and staff radiologist in the Radiology and Imaging Sciences Department at the NIH Clinical Center in Bethesda, Maryland. He is a fellow of the Society of Abdominal Radiologists and of the American Institute for Medical and Biological Engineering. His awards include the Presidential Early Career Award for Scientists and Engineers, the NIH Director’s Award, the NIH Ruth L. Kirschstein Mentoring Award, and the NIH Clinical Center Director’s Award. He is a member of the editorial boards of the Journal of Medical Imaging, Radiology: Artificial Intelligence, and Academic Radiology and a past member of the editorial board of Radiology. He was cochair of the SPIE Medical Imaging symposium in 2018 and 2019 and of the SPIE Medical Imaging Computer-Aided Diagnosis conference in 2010 and 2011. He has coauthored over 500 journal, review, and conference proceedings articles and is a coinventor on 17 patents. His research interests include thoracic and abdominal imaging, large radiology image databases, and artificial intelligence. Maryellen Giger is the A.N. Pritzker Distinguished Service Professor of Radiology, Committee on Medical Physics, and the College at the University of Chicago. She has been working, for decades, on computer-aided diagnosis/machine learning/deep learning in medical imaging for cancer and other diseases diagnosis and management. Her AI research in breast cancer for risk assessment, diagnosis, prognosis, and therapeutic response has yielded various translated components, and she has used these “virtual biopsies” in imaging-genomics association studies. She extended her AI in medical imaging research to include the analysis of COVID-19 on CT and chest radiographs, and is a contact PI at the NIBIB-funded Medical Imaging and Data Resource Center (MIDRC; midrc.org). She is a former president of AAPM and of SPIE; is a member of the NIBIB Advisory Council of NIH; and is the editor-in-chief of the Journal of Medical Imaging. She is a member of the National Academy of Engineering (NAE), a recipient of the AAPM William D. Coolidge Gold Medal, a recipient of the SPIE Director’s Award and the SPIE Harrison H. Barrett Award in Medical Imaging, and is a Fellow of AAPM, AIMBE, SPIE, SBMR, IEEE, IAMBE, and COS. In 2013, she was named by the International Congress on Medical Physics (ICMP) as one of the 50 medical physicists with the most impact on the field in the last 50 years. She was Chair of the SPIE Medical Imaging symposium in 2010 and 2011 and of the SPIE Medical Imaging Computer-Aided Diagnosis conference in 2007 and 2008. She was cofounder of Quantitative Insights (now Qlarity Imaging), which produces QuantX, the first FDA-cleared, machine-learning driven CADx (AI-aided) system. |
