Magnetic Resonance Imaging Virtual Histopathology from Weakly Paired Data

Amaury Leroy, Kumar Shreshtha, Marvin Lerousseau, Théophraste Henry, Théo Estienne, Marion Classe, Nikos Paragios, Vincent Grégoire, Eric Deutsch
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 156:140-150, 2021.

Abstract

The pathological analysis of biopsy specimens is essential to cancer diagnosis, treatment selection and prognosis. However, biopsies are only taken from part of the tumor and cannot assess the full cellular extension. Such information is essential to delineate as accurately as possible the tumor volume on a three-dimensional basis. Furthermore, they require highly qualified personnel and are associated with significant risks. The aim of our work is to provide alternative means to gather clinical information related to histology through MR image translation towards virtual pathological content generation. Conventional approaches to address this objective exploit paired data that is cumbersome to achieve due to tissue collapse and deformation, different resolution scales and absence of plane correspondences. In this paper, we introduce a versatile, scalable and robust closed-loop dual synthesis concept that composes two generation mechanisms - cycle-consistent generative adversarial networks -, one exploring weakly paired data and a subsequent harnessing virtually generated paired correspondences. The clinical relevance and interest of our framework are demonstrated in prostate cancer patients. Qualitative clinical assessment and quantitative reconstruction measurements demonstrate the potential of our approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v156-leroy21a, title = {Magnetic Resonance Imaging Virtual Histopathology from Weakly Paired Data}, author = {Leroy, Amaury and Shreshtha, Kumar and Lerousseau, Marvin and Henry, Th\'eophraste and Estienne, Th\'eo and Classe, Marion and Paragios, Nikos and Gr\'egoire, Vincent and Deutsch, Eric}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {140--150}, year = {2021}, editor = {Atzori, Manfredo and Burlutskiy, Nikolay and Ciompi, Francesco and Li, Zhang and Minhas, Fayyaz and Müller, Henning and Peng, Tingying and Rajpoot, Nasir and Torben-Nielsen, Ben and van der Laak, Jeroen and Veta, Mitko and Yuan, Yinyin and Zlobec, Inti}, volume = {156}, series = {Proceedings of Machine Learning Research}, month = {27 Sep}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v156/leroy21a/leroy21a.pdf}, url = {https://proceedings.mlr.press/v156/leroy21a.html}, abstract = {The pathological analysis of biopsy specimens is essential to cancer diagnosis, treatment selection and prognosis. However, biopsies are only taken from part of the tumor and cannot assess the full cellular extension. Such information is essential to delineate as accurately as possible the tumor volume on a three-dimensional basis. Furthermore, they require highly qualified personnel and are associated with significant risks. The aim of our work is to provide alternative means to gather clinical information related to histology through MR image translation towards virtual pathological content generation. Conventional approaches to address this objective exploit paired data that is cumbersome to achieve due to tissue collapse and deformation, different resolution scales and absence of plane correspondences. In this paper, we introduce a versatile, scalable and robust closed-loop dual synthesis concept that composes two generation mechanisms - cycle-consistent generative adversarial networks -, one exploring weakly paired data and a subsequent harnessing virtually generated paired correspondences. The clinical relevance and interest of our framework are demonstrated in prostate cancer patients. Qualitative clinical assessment and quantitative reconstruction measurements demonstrate the potential of our approach.} }
Endnote
%0 Conference Paper %T Magnetic Resonance Imaging Virtual Histopathology from Weakly Paired Data %A Amaury Leroy %A Kumar Shreshtha %A Marvin Lerousseau %A Théophraste Henry %A Théo Estienne %A Marion Classe %A Nikos Paragios %A Vincent Grégoire %A Eric Deutsch %B Proceedings of the MICCAI Workshop on Computational Pathology %C Proceedings of Machine Learning Research %D 2021 %E Manfredo Atzori %E Nikolay Burlutskiy %E Francesco Ciompi %E Zhang Li %E Fayyaz Minhas %E Henning Müller %E Tingying Peng %E Nasir Rajpoot %E Ben Torben-Nielsen %E Jeroen van der Laak %E Mitko Veta %E Yinyin Yuan %E Inti Zlobec %F pmlr-v156-leroy21a %I PMLR %P 140--150 %U https://proceedings.mlr.press/v156/leroy21a.html %V 156 %X The pathological analysis of biopsy specimens is essential to cancer diagnosis, treatment selection and prognosis. However, biopsies are only taken from part of the tumor and cannot assess the full cellular extension. Such information is essential to delineate as accurately as possible the tumor volume on a three-dimensional basis. Furthermore, they require highly qualified personnel and are associated with significant risks. The aim of our work is to provide alternative means to gather clinical information related to histology through MR image translation towards virtual pathological content generation. Conventional approaches to address this objective exploit paired data that is cumbersome to achieve due to tissue collapse and deformation, different resolution scales and absence of plane correspondences. In this paper, we introduce a versatile, scalable and robust closed-loop dual synthesis concept that composes two generation mechanisms - cycle-consistent generative adversarial networks -, one exploring weakly paired data and a subsequent harnessing virtually generated paired correspondences. The clinical relevance and interest of our framework are demonstrated in prostate cancer patients. Qualitative clinical assessment and quantitative reconstruction measurements demonstrate the potential of our approach.
APA
Leroy, A., Shreshtha, K., Lerousseau, M., Henry, T., Estienne, T., Classe, M., Paragios, N., Grégoire, V. & Deutsch, E.. (2021). Magnetic Resonance Imaging Virtual Histopathology from Weakly Paired Data. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 156:140-150 Available from https://proceedings.mlr.press/v156/leroy21a.html.

Related Material