Accurate polyp segmentation from colonoscopy is essential for the early detection of colorectal cancer. However, the variety of polyps manifested in images and the blurry boundary between a polyp and its surrounding mucosa make segmentation challenging. Hence, it is crucial to accurately identify regional boundaries of polyps in colonoscopy. In this paper, we propose Gated Semantic Boundary Network (Gate-SBNet), which is a novel twostream CNN architecture based on an encoder-decoder framework to segment polyps in colonoscopy images. One stream of Gate-SBNet uses a pre-trained ConvNeXt-B model from the image classification task as the semantic encoder to obtain multi-level semantic features from colonoscopy images. Another branch uses the Semantic Boundary Learning Module (SBLM) to learn boundary features based on multi-level semantic features, which process information in parallel with the semantic encoder. By introducing the Gate Convolution Layer (GCLs) into the SBLM module, the semantic information is converted more accurately to boundary information. Therefore, only boundary-related information will be processed by the SBLM. Then, we merge semantic and boundary features as input to an Unet model to obtain the final segmentation result. Our proposed approach was evaluated on five benchmark datasets: Kvasir, CVC-ClinicDB, CVC-ColonDB, CVC-300, and ETIS-LaribPolypDB. Experiments have demonstrated that it is an efficient architecture and capable of making accurate predictions about object boundaries and significantly improving the performance of finding thin and small objects.
Deep neural networks (DNNs) have been widely used in the medical imaging field. The large and high quality dataset is crucial for the performance of the deep learning models, but the medical data and ground-truth is often insufficient and very expensive in terms of time and human effort on the data collection. However, we can improve the performance of the deep learning model by augmenting the data we already have. In this work, we introduce a novel differential geometry-based quasi conformal (QC) mapping augmentation technique to augment the brain tumor images. The QC method lets the user specify or randomly generate a complex-valued function on the image domain via Beltrami coefficient. By solving the Beltrami equation with given Beltrami coefficient, the QC map, which can further guide the deformation of the image, is able to generate all possible linear and non-linear image warpings and it is flexible to allow the user to fully control the global and local deformations. Our experimental results demonstrate the efficiency and efficacy of the proposed method.
Glioblastoma multiforme (GBM) is the largest and most genetically and phenotypically heterogeneous category of primary brain tumors. Numerous novel chemical, targeted molecular and immune-active therapies in trial produce promising responses in a small disparate subset of patients but which patient will respond to which therapy remains unpredictable. Reliable imaging biomarkers for prediction and early detection of treatment response and survival are critical needs in neuro-oncology. In this study, brain tumor MRI 'deep features' extracted via transfer learning techniques were combined with features derived from an explicitly designed radiomics model to search for MRI markers predictive of overall survival (OS) in GBM patients. Two pre-trained convolutional neural network (CNN) models were utilized as the deep learning models and the elastic net-Cox model was performed to distinguish GBM patients into two survival groups. Two patient cohorts were included in this study. One was 50 GBM patients from our hospital and the other was 128 GBM patients from the Cancer Genome Atlas (TCGA) and the Cancer Image Archive (TCIA). The combined feature framework was predictive of OS in both data set with log-rank test p-value < 0.05 and may merit further study for reproducible prediction of treatment response.
In this paper, we describe an enhanced DICOM Secondary Capture (SC) that integrates Image Quantification (IQ) results, Regions of Interest (ROIs), and Time Activity Curves (TACs) with screen shots by embedding extra medical imaging information into a standard DICOM header. A software toolkit of DICOM IQSC has been developed to implement the SC-centered information integration of quantitative analysis for routine practice of nuclear medicine. Primary experiments show that the DICOM IQSC method is simple and easy to implement seamlessly integrating post-processing workstations with PACS for archiving and retrieving IQ information. Additional DICOM IQSC applications in routine nuclear medicine and clinic research are also discussed.
Standard Single Photon Emission Computed Tomography (SPECT) has a limited field of view (FOV) and cannot
provide a 3D image of an entire long whole body SPECT. To produce a 3D whole body SPECT image, two to five
overlapped SPECT FOVs from head to foot are acquired and assembled using image stitching. Most commercial
software from medical imaging manufacturers applies a direct mid-slice stitching method to avoid blurring or ghosting
from 3D image blending. Due to intensity changes across the middle slice of overlapped images, direct mid-slice
stitching often produces visible seams in the coronal and sagittal views and maximal intensity projection (MIP). In this
study, we proposed an optimized algorithm to reduce the visibility of stitching edges. The new algorithm computed,
based on transition error minimization (TEM), a 3D stitching interface between two overlapped 3D SPECT images. To
test the suggested algorithm, four studies of 2-FOV whole body SPECT were used and included two different
reconstruction methods (filtered back projection (FBP) and ordered subset expectation maximization (OSEM)) as well as
two different radiopharmaceuticals (Tc-99m MDP for bone metastases and I-131 MIBG for neuroblastoma tumors).
Relative transition errors of stitched whole body SPECT using mid-slice stitching and the TEM-based algorithm were
measured for objective evaluation. Preliminary experiments showed that the new algorithm reduced the visibility of the
stitching interface in the coronal, sagittal, and MIP views. Average relative transition errors were reduced from 56.7% of
mid-slice stitching to 11.7% of TEM-based stitching. The proposed algorithm also avoids blurring artifacts by preserving
the noise properties of the original SPECT images.
A pipeline of image analysis algorithm is developed for automatic analysis and quantification of neurons in microscopic
images of zebrafish embryos. Key steps of pipeline include segmentation of zebrafish embryos from background,
detection of the ROI, and quantitative measurement of neurons in the ROI. First, morphological operations are used to
segment the zebrafish embryo from the background. Then based on the prior information that the torso has two
approximately parallel boundaries corresponding to the back and abdomen, the algorithm automatically creates a ROI
enclosing the torso. Finally, the number of neurons is obtained by improved Hough transform. Our results show that the
image analysis algorithm has a high accuracy and fast computational speed. Development of such an automated image
analysis pipeline represents a step toward high-throughput screening of zebrafish images with an accurate and
reproducible quantification of neurons.
KEYWORDS: General packet radio service, Land mines, Signal processing, Wave propagation, Explosives, Reflectors, Transmitters, Receivers, Mining, Fourier transforms
In this paper, we use an optimized frequency-wavenumber (F- K) migration method to localize subsurface objects form ground penetrating radar (GPR) array dat. F-K migration coherently processes waves collected at different positions by a GPR array by back-propagating the recorded waves to the underground objects, according to the wave equation. Performance of F-K migration on GPR measurement depends on accurate estimation of wave propagation velocity. Due to measurement noise and random ground surface, F-K migration may lose its resolution and accuracy. We propose an optimized method to improve the performance of F-K migration. The optimized method searches for a better velocity estimate in the framework of Tikhonov regularization. The Tikhonov regularization uses minimum entropy as the regularizer. By trying to minimize entropy of F-K migration results, better performance is achieved in terms of resolution and accuracy. Examples from applying the optimized F-K migration on real data are used to demonstrate its performance.
KEYWORDS: General packet radio service, Mining, Signal detection, Data processing, Receivers, Signal processing, Interference (communication), Sensors, Statistical analysis, Mathematical modeling
We apply high-dimensional analysis of variance (HANOVA) and sequential probability ratio test (SPRT) to detect buried land mines from array ground penetrating radar (GPR) measurements. The GPR array surveys a region of interest in a progressive manner starting at a known position and moving step by step in a fixed direction. Our detection method consists of two stages. Because, at each stop of the array the path lengths are different from every transmitter/receiver pair to a mien target, there exists statistically significant difference among received signals when a mine target is presented. Thus, the first step in our processing consists of a HANOVA test to detect this statistical difference at each stop. HANOVA does not incorporate new data as the GPR array moves down-track. So secondly, we resort to a sequential probability ratio test to look for changes in the HANOVA statistics as the array proceeds down track. The SPRT allows for real-time processing as anew data are obtained by the GPR array. Finally, real sensor data are processed to verify the method.
KEYWORDS: Mining, General packet radio service, Receivers, Interference (communication), Transmitters, Land mines, Signal detection, Ground penetrating radar, Signal attenuation, Sensors
We consider the problem of detecting and localizing buried landmines from a ground penetrating radar (GPR) array. A simplified, ray-optics-based physical mode for time domain GPR returns is presented. Under this model in the absence of an object from the field of view of the array, there exist well defined symmetries in the structure of the radar returns. In particular, for a bistatic system composed of one length M transmit array and a second length M array of receivers, we identify M subsets of signals from the M2 transmit array and a second length M array of receivers, we identify M subsets of signals from the M2 total transmitter/receiver paris such that the mean value of the signals within each subset should be the same when no object is present. This relationship then forms the basis for a modified Hotelling's T2-test to detect the presence of objects when there is noise in the signal. Simulation results demonstrate the validity of these methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.