no code implementations • 11 Jan 2024 • John Kalkhof, Arlene Kühn, Yannik Frisch, Anirban Mukhopadhyay
Denoising Diffusion Models (DDMs) have become the leading generative technique for synthesizing high-quality images but are often constrained by their UNet-based architectures that impose certain limitations.
1 code implementation • 1 Nov 2023 • Amin Ranem, Camila González, Daniel Pinto dos Santos, Andreas M. Bucher, Ahmed E. Othman, Anirban Mukhopadhyay
Continual learning (CL) methods designed for natural image classification often fail to reach basic quality standards for medical image segmentation.
no code implementations • 25 Oct 2023 • Christian Harder, Moritz Fuchs, Yuri Tolkach, Anirban Mukhopadhyay
We thoroughly evaluate the impact of the employed generative models on state-of-the-art neural networks in terms of accuracy, convergence speed and ensembling.
no code implementations • 30 Sep 2023 • Amin Ranem, Niklas Babendererde, Moritz Fuchs, Anirban Mukhopadhyay
Medical imaging plays a critical role in the diagnosis and treatment planning of various medical conditions, with radiology and pathology heavily reliant on precise image segmentation.
1 code implementation • 6 Sep 2023 • John Kalkhof, Anirban Mukhopadhyay
Medical image segmentation relies heavily on large-scale deep learning models, such as UNet-based architectures.
1 code implementation • 3 Aug 2023 • Yannik Frisch, Moritz Fuchs, Antoine Sanner, Felix Anton Ucar, Marius Frenzel, Joana Wasielica-Poslednik, Adrian Gericke, Felix Mathias Wagner, Thomas Dratsch, Anirban Mukhopadhyay
Motivated by this, we analyse cataract surgery video data for the worst-performing phases of a pre-trained downstream tool classifier.
2 code implementations • 7 Feb 2023 • John Kalkhof, Camila González, Anirban Mukhopadhyay
Access to the proper infrastructure is critical when performing medical image segmentation with Deep Learning.
no code implementations • 9 Jan 2023 • Xiangyu Li, Gongning Luo, Kuanquan Wang, Hongyu Wang, Jun Liu, Xinjie Liang, Jie Jiang, Zhenghao Song, Chunyue Zheng, Haokai Chi, Mingwang Xu, Yingte He, Xinghua Ma, Jingwen Guo, Yifan Liu, Chuanpu Li, Zeli Chen, Md Mahfuzur Rahman Siddiquee, Andriy Myronenko, Antoine P. Sanner, Anirban Mukhopadhyay, Ahmed E. Othman, Xingyu Zhao, Weiping Liu, Jinhuang Zhang, Xiangyuan Ma, Qinghui Liu, Bradley J. MacIntosh, Wei Liang, Moona Mazher, Abdul Qayyum, Valeriia Abramova, Xavier Lladó, Shuo Li
It is intended to resolve the above-mentioned problems and promote the development of both intracranial hemorrhage segmentation and anisotropic data processing.
1 code implementation • 29 Sep 2022 • Nicolas Wagner, Moritz Fuchs, Yuri Tolkach, Anirban Mukhopadhyay
As a solution, we propose BottleGAN, a generative model that can computationally align the staining styles of many laboratories and can be trained in a privacy-preserving manner to foster federated learning in computational pathology.
1 code implementation • 20 Sep 2022 • Amin Ranem, John Kalkhof, Caner Özer, Anirban Mukhopadhyay, Ilkay Oksuz
In cardiovascular magnetic resonance imaging (CMR), respiratory motion represents a major challenge in terms of acquisition quality and therefore subsequent analysis and final diagnosis.
no code implementations • 5 Aug 2022 • Camila Gonzalez, Amin Ranem, Ahmed Othman, Anirban Mukhopadhyay
Most continual learning methods are validated in settings where task boundaries are clearly defined and task identity information is available during training and testing.
no code implementations • 5 Aug 2022 • Camila Gonzalez, Karol Gotkowski, Moritz Fuchs, Andreas Bucher, Armin Dadras, Ricarda Fischbach, Isabel Kaltenborn, Anirban Mukhopadhyay
Automatic segmentation of ground glass opacities and consolidations in chest computer tomography (CT) scans can potentially ease the burden of radiologists during times of high resource utilisation.
1 code implementation • 1 Aug 2022 • Jonathan Stieber, Moritz Fuchs, Anirban Mukhopadhyay
FrOoDo is an easy-to-use and flexible framework for Out-of-Distribution detection tasks in digital pathology.
1 code implementation • 17 Apr 2022 • Amin Ranem, Camila González, Anirban Mukhopadhyay
Our evaluation on hippocampus segmentation shows that Transformer mechanisms mitigate catastrophic forgetting for medical image segmentation compared to purely convolutional architectures, and demonstrates that regularising ViT modules should be done with caution.
no code implementations • 26 Jan 2022 • Hendrik Alexander Mehrtens, Camila González, Anirban Mukhopadhyay
Calibration and uncertainty estimation are crucial topics in high-risk environments.
no code implementations • 14 Jan 2022 • John Kalkhof, Camila González, Anirban Mukhopadhyay
This separation enables us to perform a domain transfer and thus convert data from new sources into the training domain.
no code implementations • 16 Dec 2021 • Camila Gonzalez, Christian Harder, Amin Ranem, Ricarda Fischbach, Isabel Kaltenborn, Armin Dadras, Andreas Bucher, Anirban Mukhopadhyay
It is, however, crucial to continuously monitor the performance of the model.
no code implementations • 3 Sep 2021 • Antoine Sanner, Camila Gonzalez, Anirban Mukhopadhyay
In this work, we evaluate OoD Generalization solutions for the problem of hippocampus segmentation in MR data using both fully- and semi-supervised training.
1 code implementation • 19 Jul 2021 • Marius Memmel, Camila Gonzalez, Anirban Mukhopadhyay
Deep learning for medical imaging suffers from temporal and privacy-related restrictions on data availability.
no code implementations • 13 Jul 2021 • Camila Gonzalez, Karol Gotkowski, Andreas Bucher, Ricarda Fischbach, Isabel Kaltenborn, Anirban Mukhopadhyay
Automatic segmentation of lung lesions in computer tomography has the potential to ease the burden of clinicians during the Covid-19 pandemic.
no code implementations • 2 Mar 2021 • Manish Sahu, Anirban Mukhopadhyay, Stefan Zachow
Conclusion: We show that our proposed approach can successfully exploit the unlabeled real endoscopic video frames and improve generalization performance over pure simulation-based training and the previous state-of-the-art.
1 code implementation • 26 Feb 2021 • Sarthak Pati, Siddhesh P. Thakur, İbrahim Ethem Hamamcı, Ujjwal Baid, Bhakti Baheti, Megh Bhalerao, Orhun Güley, Sofia Mouchtaris, David Lang, Spyridon Thermos, Karol Gotkowski, Camila González, Caleb Grenko, Alexander Getka, Brandon Edwards, Micah Sheller, Junwen Wu, Deepthi Karkada, Ravi Panchumarthy, Vinayak Ahluwalia, Chunrui Zou, Vishnu Bashyam, Yuemeng Li, Babak Haghighi, Rhea Chitalia, Shahira Abousamra, Tahsin M. Kurc, Aimilia Gastounioti, Sezgin Er, Mark Bergman, Joel H. Saltz, Yong Fan, Prashant Shah, Anirban Mukhopadhyay, Sotirios A. Tsaftaris, Bjoern Menze, Christos Davatzikos, Despina Kontos, Alexandros Karargyris, Renato Umeton, Peter Mattson, Spyridon Bakas
Deep Learning (DL) has the potential to optimize machine learning in both the scientific and clinical communities.
no code implementations • 19 Jan 2021 • Simon Bohlender, Ilkay Oksuz, Anirban Mukhopadhyay
Since the advent of U-Net, fully convolutional deep neural networks and its many variants have completely changed the modern landscape of deep learning based medical image segmentation.
1 code implementation • 5 Jan 2021 • Henry Krumb, Dhritimaan Das, Romol Chadda, Anirban Mukhopadhyay
Domain-translated points are fine-tuned to reduce error in the bench domain.
no code implementations • 5 Dec 2020 • Adit Agarwal, Dr. K. K. Shukla, Arjan Kuijper, Anirban Mukhopadhyay
The ability to interpret decisions taken by Machine Learning (ML) models is fundamental to encourage trust and reliability in different practical applications.
2 code implementations • 4 Dec 2020 • Nicolas Wagner, Anirban Mukhopadhyay
Super-Selfish is an easy to use PyTorch framework for image-based self-supervised learning.
no code implementations • 21 Oct 2020 • Camila Gonzalez, Nick Lemke, Georgios Sakas, Anirban Mukhopadhyay
Continual learning protocols are attracting increasing attention from the medical imaging community.
no code implementations • 22 Jul 2020 • Manish Sahu, Ronja Strömsdörfer, Anirban Mukhopadhyay, Stefan Zachow
Surgical tool segmentation in endoscopic videos is an important component of computer assisted interventions systems.
no code implementations • 5 Jul 2020 • Sumanta Ray, Snehalika Lall, Anirban Mukhopadhyay, Sanghamitra Bandyopadhyay, Alexander Schönhuth
Here, we combine three networks, two of which are year-long curated, and one of which, on SARS-CoV-2-human host-virus protein interactions, was published only most recently (30th of April 2020), raising a novel network that puts drugs, human and virus proteins into mutual context.
no code implementations • 1 Jul 2020 • Karol Gotkowski, Camila Gonzalez, Andreas Bucher, Anirban Mukhopadhyay
M3d-CAM is an easy to use library for generating attention maps of CNN-based PyTorch models improving the interpretability of model predictions for humans.
1 code implementation • 26 Jun 2020 • David Kügler, Marc Uecker, Arjan Kuijper, Anirban Mukhopadhyay
Despite recent successes, the advances in Deep Learning have not yet been fully translated to Computer Assisted Intervention (CAI) problems such as pose estimation of surgical instruments.
no code implementations • 13 Sep 2018 • Salome Kazeminia, Christoph Baur, Arjan Kuijper, Bram van Ginneken, Nassir Navab, Shadi Albarqouni, Anirban Mukhopadhyay
Generative Adversarial Networks (GANs) and their extensions have carved open many exciting ways to tackle well known and challenging medical image analysis problems such as medical image de-noising, reconstruction, segmentation, data simulation, detection or classification.
no code implementations • 12 Sep 2018 • Arun CS Kumar, Shefali Srivastava, Anirban Mukhopadhyay, Suchendra M. Bhandarkar
The proposed scheme reasons about correspondence between disparate images using high-level global shape cues derived from low-level local feature descriptors.
no code implementations • 26 Jun 2018 • Anirban Mukhopadhyay
We define the process of interpretation as a finite communication between a known model and a black-box model to optimally map the black box's decision process in the known model.
no code implementations • 25 Jun 2018 • David Kügler, Alexander Distergoft, Arjan Kuijper, Anirban Mukhopadhyay
Failure cases of black-box deep learning, e. g. adversarial examples, might have severe consequences in healthcare.
no code implementations • 20 Jun 2018 • David Kügler, Anirban Mukhopadhyay
In the application of surgical instrument pose estimation, where precision has a direct clinical impact on patient outcome, studying the effect of \emph{noisy annotations} on deep learning pose estimation techniques is of supreme importance.
no code implementations • 26 Feb 2018 • David Kügler, Jannik Sehring, Andrei Stefanov, Igor Stenin, Julia Kristin, Thomas Klenzner, Jörg Schipper, Anirban Mukhopadhyay
Purpose: Accurate estimation of the position and orientation (pose) of surgical instruments is crucial for delicate minimally invasive temporal bone surgery.
no code implementations • 27 Oct 2016 • Manish Sahu, Anirban Mukhopadhyay, Angelika Szengel, Stefan Zachow
A transfer learning method for generating features suitable for surgical tools and phase recognition from the ImageNet classification features [1] is proposed here.