Research on gastrointestinal polyp detection method based on improved YOLOv7 - Takeaways - MDSpire

Research on gastrointestinal polyp detection method based on improved YOLOv7

  • By

  • Yiyan Zhang

  • Baojie Zhang

  • Ketao Ma

  • Yujie Chen

  • June 10, 2026

  • 0 min

Share

  • 1

    The proposed method enhances gastrointestinal polyp detection using an improved YOLOv7 model with ECANet attention mechanism.

  • 2

    The model replaces the CIoU loss function with EIoU, improving the accuracy of bounding box predictions for polyps.

  • 3

    On the Kvasir-SEG dataset, the improved YOLOv7 achieved 94% precision, 88.7% recall, and 92.9% mean average precision.

  • 4

    The enhanced model demonstrates strong robustness and generalization ability in detecting gastrointestinal polyps.

  • 5

    This approach addresses challenges in polyp detection, providing a more accurate and efficient method for identifying lesions.

Original Source(s)

Research on gastrointestinal polyp detection method based on improved YOLOv7

  • by Yiyan Zhang, Baojie Zhang, Ketao Ma, Yujie Chen

  • June 10, 2026

Related Content

Association of preoperative CT-derived visceral adipose tissue index with synchronous metastasis and metastasis-free survival after curative-intent surgery in colorectal cancer

Identification, design, and in vivo proof of concept of a shared APC neoantigen delivered via a self-amplifying RNA containing virus-like nanoparticle for cancer vaccination

Incidence and Survival of Gastro-Entero-Pancreatic Neuroendocrine Neoplasms in the Contemporary Era