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

arXiv: https://arxiv.org/abs/2303.07428 · HTML: https://mlsanity.com/paper/2303.07428/

## 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 (most cited first, 12 of 12)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [ResUNet++: An Advanced Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1911.07067/) (2019)
- [UNeXt: MLP-based Rapid Medical Image Segmentation Network](https://mlsanity.com/paper/2203.04967/) (2022)
- [HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS](https://mlsanity.com/paper/2101.07172/) (2021)
- [A multi-centre polyp detection and segmentation dataset for generalisability assessment](https://mlsanity.com/paper/2106.04463/) (2021)
- [UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation](https://mlsanity.com/paper/2107.02368/) (2021)
- [NeoUNet: Towards accurate colon polyp segmentation and neoplasm detection](https://mlsanity.com/paper/2107.05023/) (2021)
- [Polyp Segmentation in Colonoscopy Images Using Fully Convolutional Network](https://mlsanity.com/paper/1802.00368/) (2018)
- [ColonFormer: An Efficient Transformer based Method for Colon Polyp Segmentation](https://mlsanity.com/paper/2205.08473/) (2022)

## Built on by (most cited first, 26 of 26)

- [A Survey on Deep Learning for Polyp Segmentation: Techniques, Challenges and Future Trends](https://mlsanity.com/paper/2311.18373/) (2023)
- [EndoOmni: Zero-Shot Cross-Dataset Depth Estimation in Endoscopy by Robust Self-Learning from Noisy Labels](https://mlsanity.com/paper/2409.05442/) (2024)
- [Polyp SAM 2: Advancing Zero shot Polyp Segmentation in Colorectal Cancer Detection](https://mlsanity.com/paper/2408.05892/) (2024)
- [CT Liver Segmentation via PVT-based Encoding and Refined Decoding](https://mlsanity.com/paper/2401.09630/) (2024)
- [Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model](https://mlsanity.com/paper/2409.09484/) (2024)
- [Colorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Survey](https://mlsanity.com/paper/2401.11734/) (2024)
- [A Reverse Mamba Attention Network for Pathological Liver Segmentation](https://mlsanity.com/paper/2502.18232/) (2025)
- [LGPS: A Lightweight GAN-Based Approach for Polyp Segmentation in Colonoscopy Images](https://mlsanity.com/paper/2503.18294/) (2025)
- [Detection of Peri-Pancreatic Edema using Deep Learning and Radiomics Techniques](https://mlsanity.com/paper/2404.17064/) (2024)
- [SAM-EG: Segment Anything Model with Egde Guidance framework for efficient Polyp Segmentation](https://mlsanity.com/paper/2406.14819/) (2024)
- [Uni-Hema: Unified Model for Digital Hematopathology](https://mlsanity.com/paper/2511.13889/) (2025)
- [When CNNs Outperform Transformers and Mambas: Revisiting Deep Architectures for Dental Caries Segmentation](https://mlsanity.com/paper/2511.14860/) (2025)
- [TransRUPNet for Improved Polyp Segmentation](https://mlsanity.com/paper/2306.02176/) (2023)
- [Adaptive Smooth Activation for Improved Disease Diagnosis and Organ Segmentation from Radiology Scans](https://mlsanity.com/paper/2312.11480/) (2023)
- [Exploiting Scale-Variant Attention for Segmenting Small Medical Objects](https://mlsanity.com/paper/2407.07720/) (2024)
- [KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation](https://mlsanity.com/paper/2312.08555/) (2023)
- [A Novel Momentum-Based Deep Learning Techniques for Medical Image Classification and Segmentation](https://mlsanity.com/paper/2408.05692/) (2024)
- [Transformer-Enhanced Iterative Feedback Mechanism for Polyp Segmentation](https://mlsanity.com/paper/2409.05875/) (2024)
- [Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic Model](https://mlsanity.com/paper/2410.01210/) (2024)
- [Multi-scale and Multi-path Cascaded Convolutional Network for Semantic Segmentation of Colorectal Polyps](https://mlsanity.com/paper/2412.02443/) (2024)
- [The Power of Certainty: How Confident Models Lead to Better Segmentation](https://mlsanity.com/paper/2507.10490/) (2025)
- [MSA2-Net: Utilizing Self-Adaptive Convolution Module to Extract Multi-Scale Information in Medical Image Segmentation](https://mlsanity.com/paper/2509.01498/) (2025)
- [PVTAdpNet: Polyp Segmentation using Pyramid vision transformer with a novel Adapter block](https://mlsanity.com/paper/2509.23751/) (2025)
- [APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms](https://mlsanity.com/paper/2606.30577/) (2026)
- [Distilling Temporal Coherence into 2D Networks for Transrectal Ultrasound Prostate Video Segmentation](https://mlsanity.com/paper/2606.31198/) (2026)
- [Metrics or Mirage? An Audit of Evaluation Inconsistencies in Colonoscopy Polyp Segmentation Benchmarks](https://mlsanity.com/paper/2607.08203/) (2026)

## 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.