By Dave DeFusco
Colorectal cancer remains one of the deadliest forms of cancer worldwide, claiming hundreds of thousands of lives each year. The key to reducing its toll is early detection鈥攕pecifically, the identification and removal of precancerous polyps during routine colonoscopies. However, polyp detection is an arduous task. Their varying size, shape, color and texture, along with visual obstructions like reflections and bowel contents, make them easy to miss.
To address this challenge, Katz School researchers have developed PolypSEAG-Net鈥攁 novel deep learning model that enhances polyp segmentation in colonoscopy images. Their work, recently presented at the ACM/IEEE International Conference on Connected Health, will contribute to the advancement of medical image analysis and colorectal cancer detection.
鈥淒espite advancements in artificial intelligence and deep learning, automatic polyp detection remains difficult,鈥 said Dengyi Liu, lead author of the study, a Katz School Ph.D. student in mathematics and a 2024 graduate of the M.S. in Data Analytics and Visualization. 鈥淭raditional computer-aided detection methods rely on handcrafted features, which often fail to generalize across different datasets and clinical conditions.鈥
Deep learning models, particularly convolutional neural networks (CNNs), have significantly improved medical image segmentation, yet many existing architectures struggle with false positives, poor boundary delineation and difficulty generalizing across diverse polyp appearances. PolypSEAG-Net builds on the strengths of established deep learning architectures while integrating two powerful techniques鈥攁ttention gates (AGs) and squeeze-and-excitation (SE) blocks鈥攖o refine feature extraction and improve accuracy.
The model鈥檚 key contributions include:
- Enhanced Feature Extraction: PolypSEAG-Net employs advanced convolutional layers to capture intricate details of polyps, reducing false positives and improving segmentation accuracy.
- Attention Gates (AGs): These mechanisms enable the model to focus on the most relevant regions of an image, filtering out irrelevant background noise and distractions.
- Squeeze-and-Excitation (SE) Bloc