Efficient polyp detection algorithm based on deep learning.
Uloženo v:
| Název: | Efficient polyp detection algorithm based on deep learning. |
|---|---|
| Autoři: | Sun X; College of Medical Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, China., Ma J; College of Medical Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, China., Li Y; College of Medical Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, China. |
| Zdroj: | Scandinavian journal of gastroenterology [Scand J Gastroenterol] 2025 Jun; Vol. 60 (6), pp. 502-515. Date of Electronic Publication: 2025 May 13. |
| Způsob vydávání: | Journal Article |
| Jazyk: | English |
| Informace o časopise: | Publisher: Informa Healthcare Country of Publication: England NLM ID: 0060105 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1502-7708 (Electronic) Linking ISSN: 00365521 NLM ISO Abbreviation: Scand J Gastroenterol Subsets: MEDLINE |
| Imprint Name(s): | Publication: London : Informa Healthcare Original Publication: Oslo : Universitetsforlager |
| Výrazy ze slovníku MeSH: | Colonic Polyps*/diagnosis , Colonic Polyps*/diagnostic imaging , Deep Learning* , Detection Algorithms* , Image Interpretation, Computer-Assisted*/methods, Humans ; Colonoscopy ; Colorectal Neoplasms |
| Abstrakt: | Objective: Colon polyp detection is crucial in reducing the incidence of colorectal cancer. However, due to the diverse morphology of colon polyps, their high similarity to surrounding tissues, and the difficulty of detecting small target polyps, false negatives and false positives are common problems. Methods: To address this, we propose a lightweight and efficient colon polyp detection model based on YOLOv10, a deep learning-based object detection method-EP-YOLO (Efficient for Polyp). By introducing the GBottleneck module, we reduce the number of parameters and accelerate inference; a lightweight GHead detection head and an additional small target detection layer are designed to enhance small target recognition ability; we propose the SE_SPPF module to improve attention on polyps while suppressing background noise interference; the loss function is replaced with Wise-IoU to optimize gradient distribution and improve generalization ability. Results: Experimental results on the publicly available LDPolypVideo (7,681 images), Kvasir-SEG (1,000 images) and CVC-ClinicDB (612 images) datasets show that EP-YOLO achieves precision scores of 94.17%, 94.32% and 93.21%, respectively, representing improvements of 2.10%, 2.05% and 1.42% over the baseline algorithm, while reducing the number of parameters by 16%. Conclusion: Compared with other mainstream object detection methods, EP-YOLO demonstrates significant advantages in accuracy, computational load and FPS, making it more suitable for practical medical scenarios in colon polyp detection. |
| Contributed Indexing: | Keywords: Colon polyp detection; artificial intelligence; colorectal cancer; deep learning; medical images |
| Entry Date(s): | Date Created: 20250513 Date Completed: 20250526 Latest Revision: 20250613 |
| Update Code: | 20250613 |
| DOI: | 10.1080/00365521.2025.2503297 |
| PMID: | 40358097 |
| Databáze: | MEDLINE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | Objective: Colon polyp detection is crucial in reducing the incidence of colorectal cancer. However, due to the diverse morphology of colon polyps, their high similarity to surrounding tissues, and the difficulty of detecting small target polyps, false negatives and false positives are common problems.<br />Methods: To address this, we propose a lightweight and efficient colon polyp detection model based on YOLOv10, a deep learning-based object detection method-EP-YOLO (Efficient for Polyp). By introducing the GBottleneck module, we reduce the number of parameters and accelerate inference; a lightweight GHead detection head and an additional small target detection layer are designed to enhance small target recognition ability; we propose the SE_SPPF module to improve attention on polyps while suppressing background noise interference; the loss function is replaced with Wise-IoU to optimize gradient distribution and improve generalization ability.<br />Results: Experimental results on the publicly available LDPolypVideo (7,681 images), Kvasir-SEG (1,000 images) and CVC-ClinicDB (612 images) datasets show that EP-YOLO achieves precision scores of 94.17%, 94.32% and 93.21%, respectively, representing improvements of 2.10%, 2.05% and 1.42% over the baseline algorithm, while reducing the number of parameters by 16%.<br />Conclusion: Compared with other mainstream object detection methods, EP-YOLO demonstrates significant advantages in accuracy, computational load and FPS, making it more suitable for practical medical scenarios in colon polyp detection. |
|---|---|
| ISSN: | 1502-7708 |
| DOI: | 10.1080/00365521.2025.2503297 |