In this paper, we delve into the susceptibility of federated medical image analysis systems to adversarial attacks.
Federated learning offers a privacy-preserving framework for medical image analysis but exposes the system to adversarial attacks.
1 code implementation • 30 Aug 2023 • Jianning Li, Antonio Pepe, Christina Gsaxner, Gijs Luijten, Yuan Jin, Narmada Ambigapathy, Enrico Nasca, Naida Solak, Gian Marco Melito, Viet Duc Vu, Afaque R. Memon, Xiaojun Chen, Jan Stefan Kirschke, Ezequiel de la Rosa, Patrick Ferdinand Christ, Hongwei Bran Li, David G. Ellis, Michele R. Aizenberg, Sergios Gatidis, Thomas Küstner, Nadya Shusharina, Nicholas Heller, Vincent Andrearczyk, Adrien Depeursinge, Mathieu Hatt, Anjany Sekuboyina, Maximilian Löffler, Hans Liebl, Reuben Dorent, Tom Vercauteren, Jonathan Shapey, Aaron Kujawa, Stefan Cornelissen, Patrick Langenhuizen, Achraf Ben-Hamadou, Ahmed Rekik, Sergi Pujades, Edmond Boyer, Federico Bolelli, Costantino Grana, Luca Lumetti, Hamidreza Salehi, Jun Ma, Yao Zhang, Ramtin Gharleghi, Susann Beier, Arcot Sowmya, Eduardo A. Garza-Villarreal, Thania Balducci, Diego Angeles-Valdez, Roberto Souza, Leticia Rittner, Richard Frayne, Yuanfeng Ji, Soumick Chatterjee, Florian Dubost, Stefanie Schreiber, Hendrik Mattern, Oliver Speck, Daniel Haehn, Christoph John, Andreas Nürnberger, João Pedrosa, Carlos Ferreira, Guilherme Aresta, António Cunha, Aurélio Campilho, Yannick Suter, Jose Garcia, Alain Lalande, Emmanuel Audenaert, Claudia Krebs, Timo Van Leeuwen, Evie Vereecke, Rainer Röhrig, Frank Hölzle, Vahid Badeli, Kathrin Krieger, Matthias Gunzer, Jianxu Chen, Amin Dada, Miriam Balzer, Jana Fragemann, Frederic Jonske, Moritz Rempe, Stanislav Malorodov, Fin H. Bahnsen, Constantin Seibold, Alexander Jaus, Ana Sofia Santos, Mariana Lindo, André Ferreira, Victor Alves, Michael Kamp, Amr Abourayya, Felix Nensa, Fabian Hörst, Alexander Brehmer, Lukas Heine, Lars E. Podleska, Matthias A. Fink, Julius Keyl, Konstantinos Tserpes, Moon-Sung Kim, Shireen Elhabian, Hans Lamecker, Dženan Zukić, Beatriz Paniagua, Christian Wachinger, Martin Urschler, Luc Duong, Jakob Wasserthal, Peter F. Hoyer, Oliver Basu, Thomas Maal, Max J. H. Witjes, Ti-chiun Chang, Seyed-Ahmad Ahmadi, Ping Luo, Bjoern Menze, Mauricio Reyes, Christos Davatzikos, Behrus Puladi, Jens Kleesiek, Jan Egger
MedShapeNet is created as an alternative to these commonly used shape benchmarks to facilitate the translation of data-driven vision algorithms to medical applications, and it extends the opportunities to adapt SOTA vision algorithms to solve critical medical problems.
We propose an unsupervised fine-tuning method that optimizes the consistency of attention maps and show that it improves both classification performance and the quality of attention maps.
no code implementations • 15 Aug 2022 • Carole H. Sudre, Kimberlin Van Wijnen, Florian Dubost, Hieab Adams, David Atkinson, Frederik Barkhof, Mahlet A. Birhanu, Esther E. Bron, Robin Camarasa, Nish Chaturvedi, Yuan Chen, Zihao Chen, Shuai Chen, Qi Dou, Tavia Evans, Ivan Ezhov, Haojun Gao, Marta Girones Sanguesa, Juan Domingo Gispert, Beatriz Gomez Anson, Alun D. Hughes, M. Arfan Ikram, Silvia Ingala, H. Rolf Jaeger, Florian Kofler, Hugo J. Kuijf, Denis Kutnar, Minho Lee, Bo Li, Luigi Lorenzini, Bjoern Menze, Jose Luis Molinuevo, Yiwei Pan, Elodie Puybareau, Rafael Rehwald, Ruisheng Su, Pengcheng Shi, Lorna Smith, Therese Tillin, Guillaume Tochon, Helene Urien, Bas H. M. van der Velden, Isabelle F. van der Velpen, Benedikt Wiestler, Frank J. Wolters, Pinar Yilmaz, Marius de Groot, Meike W. Vernooij, Marleen de Bruijne
This challenge aimed to promote the development of methods for automated detection and segmentation of small and sparse imaging markers of cerebral small vessel disease, namely enlarged perivascular spaces (EPVS) (Task 1), cerebral microbleeds (Task 2) and lacunes of presumed vascular origin (Task 3) while leveraging weak and noisy labels.
The models are trained by using the input image and only the classification labels as ground-truth in a supervised fashion - without using any information about the location of the region of interest (i. e. the segmentation labels), making the segmentation training of the models weakly-supervised through classification labels.
We evaluate an ImageNet pre-trained Mask R-CNN, a standard deep learning model for object detection, on the task of patient detection using our own curated dataset of 45 videos of hospital patients.
To evaluate the method, we compared manual and automatic assessment (computed using ten-fold cross-validation) with respect to 1) the agreement with an independent observer's assessment (available in a random subset of 47 scans); 2) the accuracy in delineating ICAC as judged via blinded visual comparison by an expert; 3) the association with first stroke incidence from the scan date until 2012.
Optimization plays a key role in the training of deep neural networks.
Automated seizure detection and classification from electroencephalography (EEG) can greatly improve seizure diagnosis and treatment.
Previous studies have shown that it is possible to adversarially manipulate automated segmentations produced by neural networks in a targeted manner in the white-box attack setting.
We propose a semi-supervised machine learning training strategy to improve event detection performance on sequential data, such as video recordings, when only sparse labels are available, such as event start times without their corresponding end times.
2 code implementations • 18 Jun 2020 • Soumick Chatterjee, Kartik Prabhu, Mahantesh Pattadkal, Gerda Bortsova, Chompunuch Sarasaen, Florian Dubost, Hendrik Mattern, Marleen de Bruijne, Oliver Speck, Andreas Nürnberger
The deep learning model based on U-Net Multi-Scale Supervision was trained using the training subset and was made equivariant to elastic deformations in a self-supervised manner using deformation-aware learning to improve the generalisation performance.
1 code implementation • 11 Jun 2020 • Gerda Bortsova, Cristina González-Gonzalo, Suzanne C. Wetstein, Florian Dubost, Ioannis Katramados, Laurens Hogeweg, Bart Liefers, Bram van Ginneken, Josien P. W. Pluim, Mitko Veta, Clara I. Sánchez, Marleen de Bruijne
Firstly, we study the effect of weight initialization (ImageNet vs. random) on the transferability of adversarial attacks from the surrogate model to the target model.
Data augmentation is of paramount importance in biomedical image processing tasks, characterized by inadequate amounts of labelled data, to best use all of the data that is present.
We showed that networks optimized using only weak labels reflecting WMH volume generalized better for WMH volume prediction than networks optimized with voxel-wise segmentations of WMH.
For diagnosis and treatment planning of scoliosis, spinal curvature can be estimated using Cobb angles.
In this paper, we propose a novel semi-supervised method that, in addition to supervised learning on labeled training images, learns to predict segmentations consistent under a given class of transformations on both labeled and unlabeled images.
Deep learning has been successfully demonstrated in MRI reconstruction of accelerated acquisitions.
We show the potential of this approach to detect enlarged perivascular spaces in white matter on a large brain MRI dataset with an independent test set of 1000 scans.
We propose and demonstrate a joint model of anatomical shapes, image features and clinical indicators for statistical shape modeling and medical image analysis.
1 code implementation • 1 Jul 2019 • Florian Dubost, Marleen de Bruijne, Marco Nardin, Adrian V. Dalca, Kathleen L. Donahue, Anne-Katrin Giese, Mark R. Etherton, Ona Wu, Marius de Groot, Wiro Niessen, Meike Vernooij, Natalia S. Rost, Markus D. Schirmer
In this work, we propose to automatically assess the quality of registration to an atlas in clinical FLAIR MRI scans of the brain.
For comparison, we modify state-of-the-art methods to compute attention maps for weakly supervised object detection, by using a global regression objective instead of the more conventional classification objective.
In order to validate the biomarker ordering obtained using nDEBM, we also present a framework for Simulation of Imaging Biomarkers' Temporal Evolution (SImBioTE) that mimics neurodegeneration in brain regions.
We propose an end-to-end deep learning method that learns to estimate emphysema extent from proportions of the diseased tissue.
The proposed method reached an intraclass correlation coefficient between ground truth and network predictions of 0. 73 on the first task and 0. 84 on the second task, only using between 25 and 30 scans with a single global label per scan for training.
We compare our method with random forest and a single neural network approach.
We propose a convolutional network regression method to quantify the extent of EPVS in the basal ganglia from 3D brain MRI.
In this paper, we propose a method for automatic segmentation of ICAC; the first to our knowledge.
We train a regression network with a fully convolutional architecture combined with a global pooling layer to aggregate the 3D output into a scalar indicating the lesion count.
We propose a novel hands-free method to interactively segment 3D medical volumes.