Our paper on “Breast Histopathology with High-Performance Computing and Deep Learning” (M. Graziani et. al) has been accepted for publication in Computing and Informatics, in the special issue on Providing Computing Solutions for Exascale Challenges.
In this work, we present our modular pipeline for detecting tumorous regions in digital specimens of breast lymph nodes with deep learning models. We evaluate challenges and benefits of training models on high-performance and cloud computing with millions of images.
Our PhD student Mara Graziani discussed the topic of defining machine learning interpretability at CIBM (Center for Biomedical Imaging, Switzerland). She also presented our latest applications to the histopathology domain. In particular, she covered our recent work on the “Evaluation and Comparison of CNN Visual Explanations for Histopathology”. She then explained how interpretability can be used in a proactive way to improve model performance. You can watch her talk online at this link: https://www.youtube.com/watch?v=7hs21U-3hgk&feature=youtu.be
Below, the information about the presentation:
Title: A myth-busting attempt for DL interpretability: discussing taxonomies, methodologies and applications to medical imaging.
Deep Learning (DL) models report almost perfect accuracy on some medical tasks, though this seems to plunge in real-world practices . Started in 2009 as the generation of deep visualizations [2, 3], the field of interpretability has grown and developed over the years, with the intent of understanding why such failures happen and discovering hidden and erroneous behaviors. Several interpretability techniques were then developed to address the fundamentally incomplete problem of evaluating DL models on the sole task performance .
While defining the key terms used in the field, I will try to bust some myths on DL interpretability: are explainable and interpretable the same thing? Is a “transparent” model an “interpretable” model? Besides, within the application in the field of medical imaging, I will describe the risk of confirmation bias and present our work on evaluating the reliability of interpretability methods. Finally, I will bring examples from our previous works on how interpretable AI can be used to improve model performance and reduce the distance between the clinical and the DL ontologies.
 Yune, S., et al. “Real-world performance of deep-learning-based automated detection system for intracranial hemorrhage.” 2018 SIIM Conference on Machine Intelligence in Medical Imaging: San Francisco (2018).
 Erhan, D., et al. “Visualizing Higher-Layer Features of a Deep Network.” (2009).
 Zeiler, Matthew D., and Rob Fergus. “Visualizing and understanding convolutional networks.” European conference on computer vision. Springer, Cham, 2014.
 Doshi-Velez, Finale, and Been Kim. “Towards A Rigorous Science of Interpretable Machine Learning.” stat 1050 (2017): 2.
The “Germaine de Staël” program promotes collaboration between French and Swiss researchers and research teams. Several exchanges between our group (Prof. Henning Müller) and Sorbonne university of histopathology image analysis (Nicolas Lomenie and Camille Kurtz) will be funded by this project to work on deep learning in digital pathology with gigapixel images of hepatic tissue: “BioGigaDeep -Apprentissage profond en pathologie digitale pour l’analyse d’images gigapixels de tissus hépatiques”.
Our paper entitled “InvNet: A Deep Learning Approach to Invert Complex Deformation Fields”, by Marek Wodzinski and Henning Müller, has been accepted for presentation at ISBI 2021, the IEEE International Symposium on Biomedical Imaging to be held virtually on April 13-16, 2021.
Prof. Henning Müller will give a keynote presentation on “Multimodal Medical Data Analysis: Machine Learning in Histopathology” at the MMDLCA workshop at the International Conference on Pattern Recognition (ICPR) 2021, on January 11, 12:00 CET.
In this work, we evaluate the alignment of XAI visualisations to cancer diagnostic procedures for breast tissue. Do the visualizations highlight specific nuclei types? Visual explanations may induce confirmation bias about CNN decisions.
Prof. Henning Müller will give an invited talk on “Machine learning on multimodal histopathology data” at the European Conference on Natural Language Processing and Information Retrieval (ECNLPIR 2021), Stockholm, Sweden, Aug. 13-15, 2021.
We are looking forward to presenting our work at the AIDP2021 workshop at ICPR 2021. The following two papers were accepted for presentation.
“Classification of noisy free-text prostate cancer pathology reports using natural language processing”, by Anjani Dhrangadhariya, Sebastian Otalora, Manfredo Atzori and Henning Mueller
“Semi-supervised learning with a teacher-student paradigm for histopathology classification: a resource to face data heterogeneity and lack of local annotations”, by Niccolò Marini, Sebastian Otalora, Henning Mueller and Manfredo Atzori.
The project IMAGINE (Radiomics for comprehensive patient and disease phenotyping in personalized health), a Swiss-wide initiative to promote image-based personalized medicine, had a dedicated Swiss Personalized Health Network (SPHN) webinar on Oct. 7 2020 to detail the recent progress of the consortium. You can view it under this link: https://sphn.ch/seminar-training/imagine/
The recording “In buone mani” (In good hands) was presented at a scientific show of the Swiss Radio-television in Italian language (RSI). The show described the projects ProHand and MeganePro , targeting the development of robotic hands with advanced technologies, such as 3D scanning, additive manufacturing and machine learning.
Our journal paper entitled “A lung graph model for the radiological assessment of chronic thromboembolic pulmonary hypertension in CT” by O. Jimenez del Toro, Y. Dicente Cid, A. Platon, A-L. Hachulla Lemaire, F. Lador, P-A. Poletti and H. Müller has been accepted for publication in Computers in Biology and Medicine.