Search Results for author: Debesh Jha

Found 57 papers, 28 papers with code

Explainable Transformer Prototypes for Medical Diagnoses

1 code implementation11 Mar 2024 Ugur Demir, Debesh Jha, Zheyuan Zhang, Elif Keles, Bradley Allen, Aggelos K. Katsaggelos, Ulas Bagci

Deployments of artificial intelligence in medical diagnostics mandate not just accuracy and efficacy but also trust, emphasizing the need for explainability in machine decisions.

Harmonized Spatial and Spectral Learning for Robust and Generalized Medical Image Segmentation

no code implementations18 Jan 2024 Vandan Gorade, Sparsh Mittal, Debesh Jha, Rekha Singhal, Ulas Bagci

This paper presents a novel approach that synergies spatial and spectral representations to enhance domain-generalized medical image segmentation.

Cardiac Segmentation Image Segmentation +2

Adaptive Smooth Activation for Improved Disease Diagnosis and Organ Segmentation from Radiology Scans

no code implementations29 Nov 2023 Koushik Biswas, Debesh Jha, Nikhil Kumar Tomar, Gorkem Durak, Alpay Medetalibeyoglu, Matthew Antalek, Yury Velichko, Daniela Ladner, Amir Bohrani, Ulas Bagci

We apply this new activation function to two important and commonly used general tasks in medical image analysis: automatic disease diagnosis and organ segmentation in CT and MRI.

Image Classification Organ Segmentation +2

Rethinking Intermediate Layers design in Knowledge Distillation for Kidney and Liver Tumor Segmentation

no code implementations28 Nov 2023 Vandan Gorade, Sparsh Mittal, Debesh Jha, Ulas Bagci

HLFD strategically distills knowledge from a combination of middle layers to earlier layers and transfers final layer knowledge to intermediate layers at both the feature and pixel levels.

Knowledge Distillation Tumor Segmentation

SynergyNet: Bridging the Gap between Discrete and Continuous Representations for Precise Medical Image Segmentation

no code implementations26 Oct 2023 Vandan Gorade, Sparsh Mittal, Debesh Jha, Ulas Bagci

When evaluating skin lesion and brain tumor segmentation datasets, we observe a remarkable improvement of 1. 71% in Intersection-over Union scores for skin lesion segmentation and of 8. 58% for brain tumor segmentation.

Brain Tumor Segmentation Image Segmentation +5

EMIT-Diff: Enhancing Medical Image Segmentation via Text-Guided Diffusion Model

no code implementations19 Oct 2023 Zheyuan Zhang, Lanhong Yao, Bin Wang, Debesh Jha, Elif Keles, Alpay Medetalibeyoglu, Ulas Bagci

We leverage recent diffusion probabilistic models to generate realistic and diverse synthetic medical image data that preserve the essential characteristics of the original medical images by incorporating edge information of objects to guide the synthesis process.

Data Augmentation Image Generation +4

DSFNet: Dual-GCN and Location-fused Self-attention with Weighted Fast Normalized Fusion for Polyps Segmentation

1 code implementation15 Aug 2023 Juntong Fan, Debesh Jha, Tieyong Zeng, Dayang Wang

Polyps segmentation poses a significant challenge in medical imaging due to the flat surface of polyps and their texture similarity to surrounding tissues.

Brain Tumor Segmentation Image Segmentation +1

Prototype Learning for Out-of-Distribution Polyp Segmentation

no code implementations7 Aug 2023 Nikhil Kumar Tomar, Debesh Jha, Ulas Bagci

Our model is designed to perform effectively on out-of-distribution (OOD) datasets from multiple centers.

Image Segmentation Segmentation +1

TransRUPNet for Improved Out-of-Distribution Generalization in Polyp Segmentation

no code implementations3 Jun 2023 Debesh Jha, Nikhil Kumar Tomar, Debayan Bhattacharya, Ulas Bagci

We develop a novel real-time deep learning based architecture, TransRUPNet that is based on a Transformer and residual upsampling network for colorectal polyp segmentation to improve OOD generalization.

Out-of-Distribution Generalization

Self-Supervised Learning for Organs At Risk and Tumor Segmentation with Uncertainty Quantification

no code implementations4 May 2023 Ilkin Isler, Debesh Jha, Curtis Lisle, Justin Rineer, Patrick Kelly, Bulent Aydogan, Mohamed Abazeed, Damla Turgut, Ulas Bagci

In this study, our goal is to show the impact of self-supervised pre-training of transformers for organ at risk (OAR) and tumor segmentation as compared to costly fully-supervised learning.

Segmentation Self-Supervised Learning +2

Vision Transformer for Efficient Chest X-ray and Gastrointestinal Image Classification

no code implementations23 Apr 2023 Smriti Regmi, Aliza Subedi, Ulas Bagci, Debesh Jha

Convolutional neural networks (CNNs) have become the de-facto standard in medical image analysis tasks because of their ability to learn complex features from the available datasets, which makes them surpass humans in many image-understanding tasks.

Benchmarking Data Augmentation +1

Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation

1 code implementation5 Apr 2023 Zheyuan Zhang, Bin Wang, Lanhong Yao, Ugur Demir, Debesh Jha, Ismail Baris Turkbey, Boqing Gong, Ulas Bagci

In real-world scenarios, however, it is common for models to encounter data from new and different domains to which they were not exposed to during training.

Domain Generalization Image Segmentation +2

TransNetR: Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing

1 code implementation13 Mar 2023 Debesh Jha, Nikhil Kumar Tomar, Vanshali Sharma, Ulas Bagci

Therefore, we intend to develop a novel real-time deep learning based architecture, Transformer based Residual network (TransNetR), for colon polyp segmentation and evaluate its diagnostic performance.

Benchmarking Medical Image Segmentation +2

RUPNet: Residual upsampling network for real-time polyp segmentation

no code implementations6 Jan 2023 Nikhil Kumar Tomar, Ulas Bagci, Debesh Jha

Here, we propose a novel architecture, Residual Upsampling Network (RUPNet) for colon polyp segmentation that can process in real-time and show high recall and precision.

Medical Image Segmentation

Domain Generalization with Correlated Style Uncertainty

1 code implementation20 Dec 2022 Zheyuan Zhang, Bin Wang, Debesh Jha, Ugur Demir, Ulas Bagci

In this regard, style augmentation is a strong DG method taking advantage of instance-specific feature statistics containing informative style characteristics to synthetic novel domains.

Domain Generalization Retrieval

A Critical Appraisal of Data Augmentation Methods for Imaging-Based Medical Diagnosis Applications

no code implementations14 Dec 2022 Tara M. Pattilachan, Ugur Demir, Elif Keles, Debesh Jha, Derk Klatte, Megan Engels, Sanne Hoogenboom, Candice Bolan, Michael Wallace, Ulas Bagci

Current data augmentation techniques and transformations are well suited for improving the size and quality of natural image datasets but are not yet optimized for medical imaging.

Data Augmentation Medical Diagnosis

Multi-Scale Fusion Methodologies for Head and Neck Tumor Segmentation

no code implementations29 Oct 2022 Abhishek Srivastava, Debesh Jha, Bulent Aydogan, Mohamed E. Abazeed, Ulas Bagci

Head and Neck (H\&N) organ-at-risk (OAR) and tumor segmentations are essential components of radiation therapy planning.

Tumor Segmentation

DilatedSegNet: A Deep Dilated Segmentation Network for Polyp Segmentation

1 code implementation24 Oct 2022 Nikhil Kumar Tomar, Debesh Jha, Ulas Bagci

DilatedSegNet is an encoder-decoder network that uses pre-trained ResNet50 as the encoder from which we extract four levels of feature maps.

Segmentation

COROID: A Crowdsourcing-based Companion Drones to Tackle Current and Future Pandemics

no code implementations19 Jul 2022 Ashish Rauniyar, Desta Haileselassie Hagos, Debesh Jha, Jan Erik Håkegård

Therefore, we believe that the COROID drone is innovative and has a huge potential to tackle COVID-19 and future pandemics.

TransResU-Net: Transformer based ResU-Net for Real-Time Colonoscopy Polyp Segmentation

1 code implementation17 Jun 2022 Nikhil Kumar Tomar, Annie Shergill, Brandon Rieders, Ulas Bagci, Debesh Jha

With high efficacy in our performance metrics, we concluded that TransResU-Net could be a strong benchmark for building a real-time polyp detection system for the early diagnosis, treatment, and prevention of colorectal cancer.

Medical Image Segmentation

Video Capsule Endoscopy Classification using Focal Modulation Guided Convolutional Neural Network

1 code implementation16 Jun 2022 Abhishek Srivastava, Nikhil Kumar Tomar, Ulas Bagci, Debesh Jha

We compare our FocalConvNet with other SOTA on Kvasir-Capsule, a large-scale VCE dataset with 44, 228 frames with 13 classes of different anomalies.

Medical Image Classification

Automatic Polyp Segmentation with Multiple Kernel Dilated Convolution Network

2 code implementations13 Jun 2022 Nikhil Kumar Tomar, Abhishek Srivastava, Ulas Bagci, Debesh Jha

The detection and removal of precancerous polyps through colonoscopy is the primary technique for the prevention of colorectal cancer worldwide.

Transformer based Generative Adversarial Network for Liver Segmentation

1 code implementation21 May 2022 Ugur Demir, Zheyuan Zhang, Bin Wang, Matthew Antalek, Elif Keles, Debesh Jha, Amir Borhani, Daniela Ladner, Ulas Bagci

The premise behind this choice is that the self-attention mechanism of the Transformers allows the network to aggregate the high dimensional feature and provide global information modeling.

Generative Adversarial Network Image Segmentation +3

TGANet: Text-guided attention for improved polyp segmentation

1 code implementation9 May 2022 Nikhil Kumar Tomar, Debesh Jha, Ulas Bagci, Sharib Ali

Even though there are deep learning methods developed for this task, variability in polyp size can impact model training, thereby limiting it to the size attribute of the majority of samples in the training dataset that may provide sub-optimal results to differently sized polyps.

Attribute Medical Image Segmentation +1

PAANet: Progressive Alternating Attention for Automatic Medical Image Segmentation

no code implementations20 Nov 2021 Abhishek Srivastava, Sukalpa Chanda, Debesh Jha, Michael A. Riegler, Pål Halvorsen, Dag Johansen, Umapada Pal

We develop progressive alternating attention dense (PAAD) blocks, which construct a guiding attention map (GAM) after every convolutional layer in the dense blocks using features from all scales.

Decision Making Image Segmentation +3

MedAI: Transparency in Medical Image Segmentation

1 code implementation Nordic Machine Intelligence 2021 Steven Hicks, Debesh Jha, Vajira Thambawita, Pål Halvorsen, Bjørn-Jostein Singstad, Sachin Gaur, Klas Pettersen, Morten Goodwin, Sravanthi Parasa, Thomas de Lange, Michael Riegler

MedAI: Transparency in Medical Image Segmentation is a challenge held for the first time at the Nordic AI Meet that focuses on medical image segmentation and transparency in machine learning (ML)-based systems.

Image Segmentation Medical Image Segmentation +2

A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation

1 code implementation26 Jul 2021 Debesh Jha, Pia H. Smedsrud, Dag Johansen, Thomas de Lange, Håvard D. Johansen, Pål Halvorsen, Michael A. Riegler

To explore the generalization capability of ResUNet++ on different publicly available polyp datasets, so that it could be used in a real-world setting, we performed an extensive cross-dataset evaluation.

Medical Image Segmentation

Exploring Deep Learning Methods for Real-Time Surgical Instrument Segmentation in Laparoscopy

no code implementations5 Jul 2021 Debesh Jha, Sharib Ali, Nikhil Kumar Tomar, Michael A. Riegler, Dag Johansen, Håvard D. Johansen, Pål Halvorsen

Minimally invasive surgery is a surgical intervention used to examine the organs inside the abdomen and has been widely used due to its effectiveness over open surgery.

Medical Image Segmentation Segmentation

A multi-centre polyp detection and segmentation dataset for generalisability assessment

3 code implementations8 Jun 2021 Sharib Ali, Debesh Jha, Noha Ghatwary, Stefano Realdon, Renato Cannizzaro, Osama E. Salem, Dominique Lamarque, Christian Daul, Michael A. Riegler, Kim V. Anonsen, Andreas Petlund, Pål Halvorsen, Jens Rittscher, Thomas de Lange, James E. East

To our knowledge, this is the most comprehensive detection and pixel-level segmentation dataset (referred to as \textit{PolypGen}) curated by a team of computational scientists and expert gastroenterologists.

Medical Image Segmentation

Meta-learning with implicit gradients in a few-shot setting for medical image segmentation

no code implementations6 Jun 2021 Rabindra Khadga, Debesh Jha, Steven Hicks, Vajira Thambawita, Michael A. Riegler, Sharib Ali, Pål Halvorsen

To our knowledge, this is the first work that exploits iMAML for medical image segmentation and explores the strength of the model on scenarios such as meta-training on unique and mixed instances of lesion datasets.

Few-Shot Learning Image Segmentation +3

NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy

3 code implementations22 Apr 2021 Debesh Jha, Nikhil Kumar Tomar, Sharib Ali, Michael A. Riegler, Håvard D. Johansen, Dag Johansen, Thomas de Lange, Pål Halvorsen

To utilize automated methods in clinical settings, it is crucial to design lightweight models with low latency such that they can be integrated with low-end endoscope hardware devices.

Colorectal Polyps Characterization Instrument Recognition +4

FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation

1 code implementation31 Mar 2021 Nikhil Kumar Tomar, Debesh Jha, Michael A. Riegler, Håvard D. Johansen, Dag Johansen, Jens Rittscher, Pål Halvorsen, Sharib Ali

We propose a novel architecture called feedback attention network (FANet) that unifies the previous epoch mask with the feature map of the current training epoch.

Hard Attention Image Segmentation +2

DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation

4 code implementations8 Jun 2020 Debesh Jha, Michael A. Riegler, Dag Johansen, Pål Halvorsen, Håvard D. Johansen

The encouraging results, produced on various medical image segmentation datasets, show that DoubleU-Net can be used as a strong baseline for both medical image segmentation and cross-dataset evaluation testing to measure the generalizability of Deep Learning (DL) models.

Cell Segmentation Colorectal Polyps Characterization +6

ResUNet++: An Advanced Architecture for Medical Image Segmentation

6 code implementations16 Nov 2019 Debesh Jha, Pia H. Smedsrud, Michael A. Riegler, Dag Johansen, Thomas de Lange, Pal Halvorsen, Havard D. Johansen

Accurate computer-aided polyp detection and segmentation during colonoscopy examinations can help endoscopists resect abnormal tissue and thereby decrease chances of polyps growing into cancer.

Colorectal Polyps Characterization Image Segmentation +3

Kvasir-SEG: A Segmented Polyp Dataset

no code implementations16 Nov 2019 Debesh Jha, Pia H. Smedsrud, Michael A. Riegler, Pål Halvorsen, Thomas de Lange, Dag Johansen, Håvard D. Johansen

In this paper, we present Kvasir-SEG: an open-access dataset of gastrointestinal polyp images and corresponding segmentation masks, manually annotated by a medical doctor and then verified by an experienced gastroenterologist.

 Ranked #1 on Polyp Segmentation on Kvasir-SEG (DSC metric)

Image Segmentation Medical Image Segmentation +2

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