mlsanityData to 14 Oct 2026

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

arXiv 2303.07428 ↗First posted 13 Mar 2023eess.IV cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Colonoscopy is considered the most effective screening test to detect colorectal cancer (CRC) and its precursor lesions, i.e., polyps. However, the procedure experiences high miss rates due to polyp heterogeneity and inter-observer dependency. Hence, several deep learning powered systems have been proposed considering the criticality of polyp detection and segmentation in clinical practices. Despite achieving improved outcomes, the existing automated approaches are inefficient in attaining real-time processing speed. Moreover, they suffer from a significant performance drop when evaluated on inter-patient data, especially those collected from different centers. 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. The proposed architecture, TransNetR, is an encoder-decoder network that consists of a pre-trained ResNet50 as the encoder, three decoder blocks, and an upsampling layer at the end of the network. TransNetR obtains a high dice coefficient of 0.8706 and a mean Intersection over union of 0.8016 and retains a real-time processing speed of 54.60 on the Kvasir-SEG dataset. Apart from this, the major contribution of the work lies in exploring the generalizability of the TransNetR by testing the proposed algorithm on the out-of-distribution (test distribution is unknown and different from training distribution) dataset. As a use case, we tested our proposed algorithm on the PolypGen (6 unique centers) dataset and two other popular polyp segmentation benchmarking datasets. We obtained state-of-the-art performance on all three datasets during out-of-distribution testing. The source code of TransNetR will be made publicly available at https://github.com/DebeshJha.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 12 of its 25 references that are in the map. First posted on arXiv 13 Mar 2023.

Builds on

12 of 25 references.

References · 12

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  3. 2019Kvasir-SEG: A Segmented Polyp Datasetcited by 589
  4. 2021Concealed Object Detectioncited by 212
  5. 2019ResUNet++: An Advanced Architecture for Medical Image Segmentationcited by 211
  6. 2022UNeXt: MLP-based Rapid Medical Image Segmentation Networkcited by 185
  7. 2021HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPScited by 71
  8. 2021A multi-centre polyp detection and segmentation dataset for generalisability assessmentcited by 63
  9. 2021UACANet: Uncertainty Augmented Context Attention for Polyp Segmentationcited by 61
  10. 2021NeoUNet: Towards accurate colon polyp segmentation and neoplasm detectioncited by 51
  11. 2018Polyp Segmentation in Colonoscopy Images Using Fully Convolutional Networkcited by 33
  12. 2022ColonFormer: An Efficient Transformer based Method for Colon Polyp Segmentationcited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 12; 2025: 7; 2026: 3.

26 papers.

Sort:

By area:

  1. 2023A Survey on Deep Learning for Polyp Segmentation: Techniques, Challenges and Future Trendscited by 12
  2. 2024EndoOmni: Zero-Shot Cross-Dataset Depth Estimation in Endoscopy by Robust Self-Learning from Noisy Labelscited by 12
  3. 2024Polyp SAM 2: Advancing Zero shot Polyp Segmentation in Colorectal Cancer Detectioncited by 8
  4. 2024CT Liver Segmentation via PVT-based Encoding and Refined Decodingcited by 6
  5. 2024Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Modelcited by 6
  6. 2024Colorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Surveycited by 5
  7. 2025A Reverse Mamba Attention Network for Pathological Liver Segmentationcited by 3
  8. 2025LGPS: A Lightweight GAN-Based Approach for Polyp Segmentation in Colonoscopy Imagescited by 3
  9. 2024Detection of Peri-Pancreatic Edema using Deep Learning and Radiomics Techniquescited by 2
  10. 2024SAM-EG: Segment Anything Model with Egde Guidance framework for efficient Polyp Segmentationcited by 2
  11. 2025Uni-Hema: Unified Model for Digital Hematopathologycited by 2
  12. 2025When CNNs Outperform Transformers and Mambas: Revisiting Deep Architectures for Dental Caries Segmentationcited by 2
14 more
  1. 2023TransRUPNet for Improved Polyp Segmentationcited by 1
  2. 2023Adaptive Smooth Activation for Improved Disease Diagnosis and Organ Segmentation from Radiology Scanscited by 1
  3. 2024Exploiting Scale-Variant Attention for Segmenting Small Medical Objectscited by 1
  4. 2023KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentationcited by 0
  5. 2024A Novel Momentum-Based Deep Learning Techniques for Medical Image Classification and Segmentationcited by 0
  6. 2024Transformer-Enhanced Iterative Feedback Mechanism for Polyp Segmentationcited by 0
  7. 2024Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic Modelcited by 0
  8. 2024Multi-scale and Multi-path Cascaded Convolutional Network for Semantic Segmentation of Colorectal Polypscited by 0
  9. 2025The Power of Certainty: How Confident Models Lead to Better Segmentationcited by 0
  10. 2025MSA2-Net: Utilizing Self-Adaptive Convolution Module to Extract Multi-Scale Information in Medical Image Segmentationcited by 0
  11. 2025PVTAdpNet: Polyp Segmentation using Pyramid vision transformer with a novel Adapter blockcited by 0
  12. 2026APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigmscited by 0
  13. 2026Distilling Temporal Coherence into 2D Networks for Transrectal Ultrasound Prostate Video Segmentationcited by 0
  14. 2026Metrics or Mirage? An Audit of Evaluation Inconsistencies in Colonoscopy Polyp Segmentation Benchmarkscited by 0