# Semi-supervised Learning for Segmentation of Bleeding Regions in Video Capsule Endoscopy

arXiv: https://arxiv.org/abs/2308.02869 · HTML: https://mlsanity.com/paper/2308.02869/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 5 Aug 2023.

## Builds on (most cited first, 14 of 14)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation](https://mlsanity.com/paper/1707.03718/) (2017)
- [Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks](https://mlsanity.com/paper/1803.02579/) (2018)
- [Deep Co-Training for Semi-Supervised Image Segmentation](https://mlsanity.com/paper/1903.11233/) (2019)
- [Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery](https://mlsanity.com/paper/2305.11692/) (2023)
- [Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translation](https://mlsanity.com/paper/2007.07867/) (2020)
- [LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion](https://mlsanity.com/paper/2307.02452/) (2023)
- [Image Quality-aware Diagnosis via Meta-knowledge Co-embedding](https://mlsanity.com/paper/2303.15038/) (2023)
- [Two-stage Contextual Transformer-based Convolutional Neural Network for Airway Extraction from CT Images](https://mlsanity.com/paper/2212.07651/) (2022)
- [Deep Reinforcement Learning-Based Control for Stomach Coverage Scanning of Wireless Capsule Endoscopy](https://mlsanity.com/paper/2305.10955/) (2023)

## Built on by (most cited first, 3 of 3)

- [Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replay](https://mlsanity.com/paper/2308.14100/) (2023)
- [Learning to Adapt Foundation Model DINOv2 for Capsule Endoscopy Diagnosis](https://mlsanity.com/paper/2406.10508/) (2024)
- [V2-SfMLearner: Learning Monocular Depth and Ego-motion for Multimodal Wireless Capsule Endoscopy](https://mlsanity.com/paper/2412.17595/) (2024)

## Abstract (arXiv)

In the realm of modern diagnostic technology, video capsule endoscopy (VCE) is a standout for its high efficacy and non-invasive nature in diagnosing various gastrointestinal (GI) conditions, including obscure bleeding. Importantly, for the successful diagnosis and treatment of these conditions, accurate recognition of bleeding regions in VCE images is crucial. While deep learning-based methods have emerged as powerful tools for the automated analysis of VCE images, they often demand large training datasets with comprehensive annotations. Acquiring these labeled datasets tends to be time-consuming, costly, and requires significant domain expertise. To mitigate this issue, we have embraced a semi-supervised learning (SSL) approach for the bleeding regions segmentation within VCE. By adopting the `Mean Teacher' method, we construct a student U-Net equipped with an scSE attention block, alongside a teacher model of the same architecture. These models' parameters are alternately updated throughout the training process. We use the Kvasir-Capsule dataset for our experiments, which encompasses various GI bleeding conditions. Notably, we develop the segmentation annotations for this dataset ourselves. The findings from our experiments endorse the efficacy of the SSL-based segmentation strategy, demonstrating its capacity to reduce reliance on large volumes of annotations for model training, without compromising on the accuracy of identification.