Diana Mandache

Diana Mandache

Biomedical Image Analysis | ML Engineer | PhD @ LLTech and Institut Pasteur

Publications

Blind Source Separation in Dynamic Cell Imaging using NonNegative Matrix Factorization applied to Breast Cancer Biopsies

Published in International Symposium on Biomedical Imaging (ISBI), 2021

We propose a method to fully exploit the dynamic signal produced by a recently developed non-invasive imaging modality: Dynamic Cell Imaging based on Full Field Optical Coherence Tomography, towards fast extemporaneous tissue assessment. The non-negative matrix factorisation method is used in an interpretable and quantifiable fashion to extract the signals coming from different structures of breast tissue in order to characterize cancerous tissue.

Recommended citation: D. Mandache, E. B. á. l. Guillaume, J. . -C. Olivo-Marin and V. Meas-Yedid, "Blind Source Separation In Dynamic Cell Imaging Using Non-Negative Matrix Factorization Applied To Breast Cancer Biopsies," 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), 2021, pp. 1605-1608. https://doi.org/10.1109/ISBI48211.2021.9434128

Leveraging Global Diagnosis For Tumor Localization In Dynamic Cell Imaging Of Breast Cancer Tissue Towards Fast Biopsying

Published in International Symposium on Biomedical Imaging (ISBI), 2021

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.

Recommended citation: D. Mandache, E. B. à. l. Guillaume, M. . -C. Mathieu, J. . -C. Olivo-Marin and V. Meas-Yedid, "Leveraging Global Diagnosis For Tumor Localization In Dynamic Cell Imaging Of Breast Cancer Tissue Towards Fast Biopsying," 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), 2021, pp. 320-323. https://doi.org/10.1109/ISBI48211.2021.9434110

Basal Cell Carcinoma (BCC) detection in Full-Field Optical Coherence Tomography (FFOCT) images using Convolutional Neural Networks (CNN)

Published in International Symposium on Biomedical Imaging (ISBI), 2018

In this paper we introduce a new application that exploits the emerging imaging modality of full field optical coherence tomography (FFOCT) as a means of optical biopsy. The objective is to build a computer-aided diagnosis (CAD) tool that can speed up the detection of tumoral areas in skin excisions resulting from Mohs surgery. Since there is little prior knowledge about the appearance of cancer cell morphology in this type of imagery, deep learning techniques are applied. Using convolutional neural networks (CNN), we train a feature extractor able to find representative characteristics for FFOCT data and a classifier that learns a generalized distribution of the data. With a dataset of 40 high-resolution images, we obtained a classification accuracy of 95.93%.

Recommended citation: D. Mandache, E. Dalimier, J. R. Durkin, C. Boccara, J. -C. Olivo-Marin and V. Meas-Yedid, "Basal cell carcinoma detection in full field OCT images using convolutional neural networks," 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018, pp. 784-787. https://doi.org/10.1109/ISBI.2018.8363689