G. Maffeis,1 A. Pifferi,1 A. Dalla Mora,1 L. Di Sieno,1 R. Cubeddu,1 A. Tosi,1 E. Conca,1 A. Giudice,2 A. Ruggeri,2 S. Tisa,2 A. Flocke,3 B. Rosinski,4 J.-M Dinten,5 M. Perriollat,5 C. Fraschini,6 J. Lavaud,6 S. Arridge,7 G. Di Sciacca,7 A. Farinahttps://orcid.org/0000-0002-3180-6328,8 P. Panizza,9 E. Venturini,9 P. Gordebeke,10 Paola Taroni1
1Politecnico di Milano (Italy) 2Micro Photon Devices S.r.l. (Italy) 3iC-Haus GmbH (Germany) 4Vermon S.A. (France) 5CEA-LETI (France) 6SuperSonic Imagine (France) 7Univ. College London (United Kingdom) 8CNR-Istituto di Fotonica e Nanotecnologie (Italy) 9Ospedale San Raffaele - Milano (Italy) 10European Institute for Biomedical Imaging Research (Austria)
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.
A machine learning classification algorithm is applied to the SOLUS database to discriminate benign and malignant breast lesions, based on absorption and composition properties retrieved through diffuse optical tomography. The Mann-Whitney test indicates oxy-hemoglobin (p-value = 0.0007) and lipids (0.0387) as the most significant constituents for lesion classification, but work is in progress for further analysis. Together with sensitivity (91%), specificity (75%) and the Area Under the ROC Curve (0.83), special metrics for imbalanced datasets (27% of malignant lesions) are applied to the machine learning outcome: balanced accuracy (83%) and Matthews Correlation Coefficient (0.65). The initial results underline the promising informative content of optical data.
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.
The alert did not successfully save. Please try again later.
G. Maffeis, A. Pifferi, A. Dalla Mora, L. Di Sieno, R. Cubeddu, A. Tosi, E. Conca, A. Giudice, A. Ruggeri, S. Tisa, A. Flocke, B. Rosinski, J.-M Dinten, M. Perriollat, C. Fraschini, J. Lavaud, S. Arridge, G. Di Sciacca, A. Farina, P. Panizza, E. Venturini, P. Gordebeke, Paola Taroni, "Breast lesion classification based on absorption and composition parameters: a look at SOLUS first outcomes," Proc. SPIE 12376, Optical Tomography and Spectroscopy of Tissue XV, 123760K (7 March 2023); https://doi.org/10.1117/12.2648945