Scholarlink

Purpose <p>Colorectal cancer (CRC) is a leading cause of mortality worldwide. Early detection of precancerous lesions can significantly reduce CRC incidence by allowing for the removal of polyps during colonoscopy or early intervention in cases of detected cancer. Colonoscopy remains the gold standard for identifying these polyps, but smaller lesions can often be missed. Computer-aided detection (CAD) systems assist in enhancing detection accuracy. However, traditional U-Net models struggle with capturing intricate details, especially for smaller polyps.</p> Method <p>This thesis introduces an advanced U-Net architecture incorporating Dilated Convolution with Learnable Spacings (DCLS) to overcome these limitations. DCLS dynamically adjusts the receptive field based on input data, capturing fine details of minor polyps and long-range dependencies.</p> Results <p>This approach reduces the risk of overfitting to training data while ensuring fewer number of parameters. ADL-UNet achieved a 7.4% increase in Dice score on validation and a 6.0% improvement on the test set, demonstrating its reliability in clinical applications. Additionally, ADL-UNet has approximately 50% fewer parameters than the baseline U-Net, highlighting its efficiency.</p> Conclusion <p>These results indicate that the DCLS-enhanced U-Net significantly improves colorectal polyp segmentation performance, advancing CAD systems for early CRC diagnosis and screening, ultimately improving patient outcomes. The complete codebase and trained models are available at <a href="https://github.com/MeghaDeySarkar/ADL-Unet.git">https://github.com/MeghaDeySarkar/ADL-Unet.git</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

ADL-UNet: adaptive dilated learning U-Net architecture for advanced colorectal polyp segmentation

  • 期刊论文

  • 发表日期：

    2026年1月7日

查看全文
  • Megha Dey Sarkar,
  • Binayak Kar,
  • Satyajit Padhy,
  • Shashank

摘要

Purpose

Colorectal cancer (CRC) is a leading cause of mortality worldwide. Early detection of precancerous lesions can significantly reduce CRC incidence by allowing for the removal of polyps during colonoscopy or early intervention in cases of detected cancer. Colonoscopy remains the gold standard for identifying these polyps, but smaller lesions can often be missed. Computer-aided detection (CAD) systems assist in enhancing detection accuracy. However, traditional U-Net models struggle with capturing intricate details, especially for smaller polyps.

Method

This thesis introduces an advanced U-Net architecture incorporating Dilated Convolution with Learnable Spacings (DCLS) to overcome these limitations. DCLS dynamically adjusts the receptive field based on input data, capturing fine details of minor polyps and long-range dependencies.

Results

This approach reduces the risk of overfitting to training data while ensuring fewer number of parameters. ADL-UNet achieved a 7.4% increase in Dice score on validation and a 6.0% improvement on the test set, demonstrating its reliability in clinical applications. Additionally, ADL-UNet has approximately 50% fewer parameters than the baseline U-Net, highlighting its efficiency.

Conclusion

These results indicate that the DCLS-enhanced U-Net significantly improves colorectal polyp segmentation performance, advancing CAD systems for early CRC diagnosis and screening, ultimately improving patient outcomes. The complete codebase and trained models are available at https://github.com/MeghaDeySarkar/ADL-Unet.git.