%0 Conference Paper %F Oral %T Leveraging Global Diagnosis For Tumor Localization In Dynamic Cell Imaging Of Breast Cancer Tissue Towards Fast Biopsying %+ Analyse d'images biologiques - Biological Image Analysis (BIA) %+ LLTech SAS Paris %+ Cancer Campus %A Mandache, D. %A Guillaume, E. Benoit a La %A Mathieu, M.-C. %A Olivo-Marin, J.-C. %A Meas-Yedid, V. %Z The authors acknowledge financial support of the ANRT (grant CIFRE no 2018/0139) and the Inception program (Investissement d’Avenir grant ANR-16-CONV-0005) for providing the computing resources, as well as the help of Quang tru Huynh on using them. %< avec comité de lecture %B 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) %C Nice, France %I IEEE %S 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) %P 320-323 %8 2021-04-13 %D 2021 %R 10.1109/ISBI48211.2021.9434110 %K dynamic full field optical coherence tomography %K classification %K segmentation %K convolutional neural network %K aid to diagnosis %K breast cancer %Z Computer Science [cs]/Image Processing [eess.IV] %Z Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] %Z Computer Science [cs]/Machine Learning [cs.LG] %Z Life Sciences [q-bio]/Human health and pathology/Urology and Nephrology %Z Life Sciences [q-bio]/Cancer %Z Life Sciences [q-bio]/Immunology/ImmunotherapyConference papers %X We propose a fast aid-to-diagnosis biopsy assessment method convenient at the point-of-care, on account of both the imaging technique and the algorithm applied. The procedure implies a pipeline of classification and localization of tumors in breast cancer biopsies imaged with a recently developed non-invasive imaging modality: Dynamic Cell Imaging (aka Dynamic Full Field Optical Coherence Tomography). This allows for fast and interpretable extemporaneous cancer detection with high confidence; we obtained a performance of 96% classification accuracy together with a coarse localization of tumors, even so for single isolated invasive cells. %G English %L pasteur-03721547 %U https://pasteur.hal.science/pasteur-03721547 %~ PASTEUR %~ CNRS %~ ANR %~ BIOLOGICAL-IMAGE-ANALYSIS %~ UMR3691