News

Our article entitled “Empowering Digital Pathology Applications through Explainable Knowledge Extraction Tools” has been published in Journal of Pathology Informatics.

The Semantic Knowledge Extractor Tool (SKET) is an unsupervised hybrid system that combines rule-based techniques with pre-trained machine learning models to extract key pathological concepts from diagnostic reports. SKET is a viable solution to reduce pathologists’ workload and can be used as a first, cheap solution to bootstrap supervised models in absence of manual annotations.

The SKET eXplained (SKET X) is a web-based system that supports pathologists and domain experts in the visual understanding of SKET predictions. SKET X can refine parameters and rules over time, thus improving the system effectiveness and increasing user’s trust and confidence

Our paper on Unleashing the potential of digital pathology data by training computer-aided diagnosis models without human annotations, by Niccolò Marini et al., has been published in npj Digital Medicine and is available in open access.

This work presents an approach that removes the need for human experts to annotate data, using an automatic analysis of healthcare reports to create automatic annotations that can be used to train deep learning models. A case study on the classification of colon whole slide images shows the benefit of the approach to best exploit the potential of healthcare data from hospital workflows.

Our work on A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences, by Mara Graziani et al. has been published in Artificial Intelligence Review, Springer.

On April 29th, 2021, we organized a debate to bring together researchers from multidisciplinary backgrounds to collaborate on a global definition of interpretability that may be used with high versatility in the documentation of social, cognitive, philosophical, ethical and legal concerns about AI. One of the many interesting outcomes is the definition of interpretable AI that was reached:

“An AI system is interpretable if it is possible to translate its working principles and outcomes in human-understandable language without affecting the validity of the system”.

The article is published and available online in open access.

Prof. Henning Müller has been announced one of ten digital shapers of Switzerland in the medical field. This nomination recognizes his and his tream’s contribution as eMedics, i.e. people who use digital transformation to enhance different aspects of well-being, health and medicine.

Congratulations to the other 99 Digital Shapers for driving digital innovation and change!

Our article entitled “Unleashing the potential of digital pathology data by training computer-aided diagnosis models without human annotations“, by Niccolò Marini et al. has been published in npj Digital Medicine from Nature Portfolio.

In this work, we present an approach that removes the need for medical experts when building assisting tools for clinical decision support, paving the way for the exploitation of exa-scale sources of medical data collected worldwide from hospital workflows. 

The combination of large amounts of healthcare data with new artificial intelligence technologies are leading to the creation of new systems to assist medical experts during the diagnosis. 

However, the potential of the combination is not fully exploited because of a bottleneck represented by the need of medical experts to analyze and annotate healthcare data. 

This study presents an approach aiming to remove the need of human experts to annotate data: the reports corresponding to healthcare data (that can be CT scans, MRI, whole slide images) are automatically analyzed in order to create automatic annotations that can be used to train deep learning models. 

The approach involves two components: a natural language processing algorithm, called SKET (Semantic Knowledge Extractor Tool) that analyzes the reports and extracts meaningful concepts, and a computer vision algorithm, a convolutional neural network trained to classify medical images using the concepts extracted from SKET as weak labels.

The code is available in our GitHub repository for the computer vision algorithm and the natural language processing algorithm.

Henning Müller and Mara Graziani gave lectures, hands-on and mentoring at the VISion Understanding and Machine intelligence – VISUM 2022 summer school, in Porto.

• Henning gave an excellent lecture on Explainable AI.

• Mara organized a hands-on on Interpretable AI, awarded the best hands-on by the students! The tutorial is available on github: https://github.com/maragraziani/InterpretabilityVISUM22

• Under Mara’s mentorship, Laura O’Mahony from University of Limerick was awarded the best mentorship pitch ! Within the very short duration of the summer school, Laura and Mara came up with an interesting small project on using interpretability for model compression.

Last week, we met at the Solalex hut in Gryon to enjoy a team building day, what we call Green Day. We invited our colleagues from the TranslationalML Laboratory (CHUV/UNIL) led by Jonas Richiardi. We worked together on strengthening our collaboration on Machine Learning and Medical Imaging projects, as well as identifying challenges in science, communication and research.

The HECKTOR challenge at MICCAI 2022 was featured in RSIP VISION – Computer Vision News.

This article can be read in the current issue: https://www.rsipvision.com/ComputerVisionNews-2022June/58/

Thanks to Ralph Anzarouth for the interview and for this great article.

Our work on automatic template detection for microscopy images “Steer’n’Detect: Fast 2D Template Detection with Accurate Orientation Estimation“, by V. Uhlmann, Z. Püspöki, A. Depeursinge, M. Unser, D. Sage and J. Fageot., has been accepted for publication in the Bioiformatics jounal.

In this work, we introduce Steer’n’Detect, an ImageJ plugin to detect patterns of interest at any orientation with high accuracy from a single template in 2D images.

Our paper on “Segmentation and Classification of Head and Neck Nodal Metastases and Primary Tumors in PET/CT”, by V. Andrearczyk, V. Oreiller, M. Jreige, J.Castelli, J. O. Prior and A. Depeursinge has been accepted for presentation at the IEEE International Engineering in Medicine and Biology Conference (EMBC), held in Glasgow, 11-15 July 2022.

The prediction of cancer characteristics, treatment planning and patient outcome from medical images generally requires tumor delineation. In Head and Neck cancer (H\&N), the automatic segmentation and differentiation of primary Gross Tumor Volumes (GTVt) and malignant lymph nodes (GTVn) is a necessary step for large-scale radiomics studies. We developed a bi-modal 3D U-Net model to automatically individually segment GTVt and GTVn in PET/CT images. The model is trained for multi-class and multi-components segmentation on the multi-centric HECKTOR 2020 dataset.

We are pleased to announce that the HECKTOR (HEad and neCK TumOR segmentation and outcome prediction in PET/CT images) challenge has been renewed for a third edition at MICCAI 2022 (September 18-22, 2022, Singapore).

This challenge was created in 2020 to create an opportunity for the comparison of automated algorithms dedicated to the segmentation of head and neck primary tumors in FDG PET/CT multimodal images. This first edition relied on a dataset of 254 patients from 5 centers and attracted about 20 challengers. In 2021, the challenge was renewed with a larger dataset (325 patients from 6 centers) with the addition of a second task, the prediction of progression-free survival (PFS). This second edition was quite successful, with twice the number of submissions (~40) for the first task and 30 for the second task [2].

This year, challengers are again invited to compete in the same tasks, although the segmentation one now includes the fully automated detection and segmentation of lymph nodes in addition to the primary tumor, and the dataset should contain more than a thousand patients collected from 9 participating centers.

For 2022, the challenge is now hosted on the platform grand-challenge.org: https://hecktor.grand-challenge.org/. Registrations will open soon.

The full list of MICCAI challenges is now online: https://conferences.miccai.org/2022/en/MICCAI2022-CHALLENGES.html

Our paper “DISTANT-CTO: A Zero Cost, Distantly Supervised Approach to Improve Low-Resource Entity Extraction Using Clinical Trials Literature”, by A. Dhrangadhariya and H. Müller is accepted for presentation at the BioNLP workshop at ACL2022 (Dublin, 22-27 May).

The paper takes strides toward democratizing entity/span level PICO recognition by automatically creating a large entity annotated dataset using open-access resources. PICO extraction is a vital but tiring process for writing systematic reviews.

The approach uses gestalt pattern matching and a modified version of the match scoring to flexibly align structured terms from http://clinicaltrials.gov onto the unstructured text and select high-confidence match candidates.

The method is extensible and data-centric which allows for constant extension of the dataset, and for optimization of the automatic annotation method for the recall-oriented PICO recognition.

Our work on “Grading diabetic retinopathy and prostate cancer diagnostic images with deep quantum ordinal regression“, by S. Toledo-Cortés D. H. Useche H. Müller and F. A. González, has been published in Computers in Biology and Medicine (Elsevier).

A new end-to-end neural probabilistic ordinal regression method is proposed to predict a probability distributions over a range of grades. The model, evaluated on prostate cancer diagnosis and diabetic retinopathy grade estimation, can also quantify its uncertainty.

Overview of the proposed approach for diabetic retinopathy (DR) grading. An Inception-V3 network was used as feature extractor for the eye fundus image. These features were
the input for the regressor model, which yielded a posterior probability distribution over the DR grades.

Congratulations to Marek Wodzinski, Niccolò Marini and Henning Müller for winning the BraTS-Reg challenge hosted at ISBI 2022.

The goal of the challenge was to propose the most accurate medical image registration method to align pre-operative to follow-up MRIs. Our team proposed a hybrid approach based on a multilevel deep network combined with an iterative, instance optimization.

Our paper on nucleus segmentation with local rotation invariance has been accepted for poster presentation at the Medical Imaging with Deep Learning (MIDL) conference 2022. As one of the first in-person conferences (hybrid) in our field, MIDL, held in Zürich, 6 – 8 July 2022, will be a great opportunity to catch up with researchers in our field and discuss our work.

Full paper “Multi-Organ Nucleus Segmentation Using a Locally Rotation Invariant Bispectrum U-Net“, V. Oreiller, J. Fageot, V. Andrearczyk, J. O. Prior and A. Depeursinge, available online: https://openreview.net/forum?id=paGzvj2t_x

Our work on Assessing radiomics feature stability with simulated CT acquisitions has been published in Nature Scientific Reports. The authors K. Flouris, O. Jimenez-del-Toro, C. Aberle, M. Bach, R. Schaer, M. M. Obmann, B. Stieltjes, H. Müller, A. Depeursinge and E. Konukoglu developed and validated a Computed Tomography (CT) simulator and showed that the variability, stability and discriminative power of the radiomics features extracted from the virtual phantom images are similar to those observed in a tandem phantom study. They also demonstrated that the simulator can be utilised to assess radiomics features’ stability and discriminative power.

More details in the article available online: https://www.nature.com/articles/s41598-022-08301-1

The proceedings of the HEad and neCK TumOR segmentation and outcome prediction in PET/CT images (HECKTOR) 2021 challenge, at MICCAI, are now available in a Springer LNCS book.

https://link.springer.com/book/10.1007/978-3-030-98253-9

The participants papers describe the various innovative methods, and our overview paper provides a description of the challenge, the data, the methods and the results.

Stay tuned for the next edition of the challenge: HECKTOR 2022 !

A randomized clinical trial (RCT) “Amblyopia and Stereoptic Games for Vision” developed by Dr.Paul Matusz through his SNSF Ambizione career grant has been discussed in Le Figaro.

https://www.lefigaro.fr/sciences/il-y-a-urgence-a-freiner-l-epidemie-de-myopie-chez-les-enfants-20220306#:~:text=Partout%20dans%20le%20monde%2C%20le,concern%C3%A9es%20par%20ce%20trouble%20visuel

In our paper “Cleaning Radiotherapy Contours for Radiomics Studies, is it Worth it? A Head and Neck Cancer Study“, published in ctRO (Elsevier), we study the benefit of delineating tumor contours specifically for radiomics analyses (automatic prognostic prediction of patients with Head and Neck cancer). The contours originating from radiotherapy often include parts of surrounding organs (e.g. trachea, bones) which impact the extraction of visual features that characterize the tumor.

In 2021, the Swiss innovation agency Innosuisse has launched the funding scheme Flagship aimed at stimulating systemic innovation and transdisciplinary collaboration to solve future challenges relevant for the Swiss economy and society. Among the 15 supported projects out of 84 submitted, Innosuisse has financed with 11.2 MCHF over 5 years the project SwissNeuroRehab.

As part of a large Swiss consortium working on this project, our group at the University of Applied Science of Western Switzerland (HES-SO) will lead the “Data” sub project.

SwissNeuroRehab aims at developing a novel model of neurorehabilitation along the continuum of care, from the hospital to home. In the first phase, the project will focus on stroke, traumatic brain injury and spinal cord injury. Through the partnership between university hospitals, research centers, neurorehabilitation clinics, therapists and the industry, SwissNeuroRehab will combine the best available approaches for neuro-rehabilitation with new digital and techonological methods to create innovative and efficient therapeutic programs tailored to the individual needs of patients and their
families.

More details available here (in french).