Search Results for author: Anirban Mukhopadhyay

Found 38 papers, 13 papers with code

Frequency-Time Diffusion with Neural Cellular Automata

no code implementations11 Jan 2024 John Kalkhof, Arlene Kühn, Yannik Frisch, Anirban Mukhopadhyay

Despite considerable success, large Denoising Diffusion Models (DDMs) with UNet backbone pose practical challenges, particularly on limited hardware and in processing gigapixel images.

Denoising Image Generation +1

Continual atlas-based segmentation of prostate MRI

1 code implementation1 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.

Continual Learning Image Classification +6

From Pointwise to Powerhouse: Initialising Neural Networks with Generative Models

no code implementations25 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.

Exploring SAM Ablations for Enhancing Medical Segmentation in Radiology and Pathology

no code implementations30 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.

Brain Tumor Segmentation Image Segmentation +2

M3D-NCA: Robust 3D Segmentation with Built-in Quality Control

1 code implementation6 Sep 2023 John Kalkhof, Anirban Mukhopadhyay

Medical image segmentation relies heavily on large-scale deep learning models, such as UNet-based architectures.

Hippocampus Image Segmentation +3

Med-NCA: Robust and Lightweight Segmentation with Neural Cellular Automata

2 code implementations7 Feb 2023 John Kalkhof, Camila González, Anirban Mukhopadhyay

Access to the proper infrastructure is critical when performing medical image segmentation with Deep Learning.

Hippocampus Image Generation +4

Federated Stain Normalization for Computational Pathology

1 code implementation29 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.

Federated Learning Privacy Preserving

Detecting respiratory motion artefacts for cardiovascular MRIs to ensure high-quality segmentation

1 code implementation20 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.

Distance-based detection of out-of-distribution silent failures for Covid-19 lung lesion segmentation

no code implementations5 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.

Hippocampus Lesion Segmentation +3

Task-agnostic Continual Hippocampus Segmentation for Smooth Population Shifts

no code implementations5 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.

Continual Learning Hippocampus +1

FrOoDo: Framework for Out-of-Distribution Detection

1 code implementation1 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.

Out-of-Distribution Detection

Continual Hippocampus Segmentation with Transformers

1 code implementation17 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.

Continual Learning Hippocampus +5

Disentanglement enables cross-domain Hippocampus Segmentation

no code implementations14 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.

Disentanglement Hippocampus +1

How Reliable Are Out-of-Distribution Generalization Methods for Medical Image Segmentation?

no code implementations3 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.

Hippocampus Image Segmentation +3

Simulation-to-Real domain adaptation with teacher-student learning for endoscopic instrument segmentation

no code implementations2 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.

Scene Understanding Segmentation +1

A survey on shape-constraint deep learning for medical image segmentation

no code implementations19 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.

Image Segmentation Medical Image Segmentation +2

CycleGAN for Interpretable Online EMT Compensation

1 code implementation5 Jan 2021 Henry Krumb, Dhritimaan Das, Romol Chadda, Anirban Mukhopadhyay

Domain-translated points are fine-tuned to reduce error in the bench domain.


Understanding Interpretability by generalized distillation in Supervised Classification

no code implementations5 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.

Classification General Classification

Super-Selfish: Self-Supervised Learning on Images with PyTorch

2 code implementations4 Dec 2020 Nicolas Wagner, Anirban Mukhopadhyay

Super-Selfish is an easy to use PyTorch framework for image-based self-supervised learning.

Self-Supervised Learning

Predicting potential drug targets and repurposable drugs for COVID-19 via a deep generative model for graphs

no code implementations5 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.

M3d-CAM: A PyTorch library to generate 3D data attention maps for medical deep learning

no code implementations1 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.

AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation

1 code implementation26 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.

Pose Estimation

GANs for Medical Image Analysis

no code implementations13 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.

General Classification

Deep Spectral Correspondence for Matching Disparate Image Pairs

no code implementations12 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.

Matching Disparate Images

A Theory of Diagnostic Interpretation in Supervised Classification

no code implementations26 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.

Classification General Classification

Exploring Adversarial Examples: Patterns of One-Pixel Attacks

no code implementations25 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.

Pose Estimation

How Bad is Good enough: Noisy annotations for instrument pose estimation

no code implementations20 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.

Pose Estimation regression

i3PosNet: Instrument Pose Estimation from X-Ray in temporal bone surgery

no code implementations26 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.

Image Registration Pose Estimation +2

Tool and Phase recognition using contextual CNN features

no code implementations27 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.

Classification General Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.