Colorectal Polyp Detection Model by Using Super-Resolution Reconstruction and YOLO

被引:4
作者
Wang, Shaofang [1 ]
Xie, Jun [1 ]
Cui, Yanrong [1 ]
Chen, Zhongju [1 ]
机构
[1] Yangtze Univ, Sch Comp Sci, Jingzhou 434023, Peoples R China
基金
中国国家自然科学基金;
关键词
polyp detection; colonoscopy; medical image processing; deep learning; SRGAN; YOLO; ACmix; Res2net; CANCER DIAGNOSIS; CLASSIFICATION;
D O I
10.3390/electronics13122298
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Colorectal cancer (CRC) is the second leading cause of cancer-related deaths worldwide. Colonoscopy is the primary method to prevent CRC. However, traditional polyp detection methods face problems such as low image resolution and the possibility of missing polyps. In recent years, deep learning techniques have been extensively employed in the detection of colorectal polyps. However, these algorithms have not yet addressed the issue of detection in low-resolution images. In this study, we propose a novel YOLO-SRPD model by integrating SRGAN and YOLO to address the issue of low-resolution colonoscopy images. Firstly, the SRGAN with integrated ACmix is used to convert low-resolution images to high-resolution images. The generated high-resolution images are then used as the training set for polyp detection. Then, the C3_Res2Net is integrated into the YOLOv5 backbone to enhance multiscale feature extraction. Finally, CBAM modules are added before the prediction head to enhance attention to polyp information. The experimental results indicate that YOLO-SRPD achieves a mean average precision (mAP) of 94.2% and a precision of 95.2%. Compared to the original model (YOLOv5), the average accuracy increased by 1.8% and the recall rate increased by 5.6%. These experimental results confirm that YOLO-SRPD can address the low-resolution problem during colorectal polyp detection and exhibit exceptional robustness.
引用
收藏
页数:17
相关论文
共 52 条
[1]   Artificial Intelligence in Gastrointestinal Endoscopy [J].
Abadir, Alexander P. ;
Ali, Mohammed Fahad ;
Karnes, William ;
Samarasena, Jason B. .
CLINICAL ENDOSCOPY, 2020, 53 (02) :132-141
[2]  
Ali S., 2019, arXiv
[3]   WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians [J].
Bernal, Jorge ;
Javier Sanchez, F. ;
Fernandez-Esparrach, Gloria ;
Gil, Debora ;
Rodriguez, Cristina ;
Vilarino, Fernando .
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2015, 43 :99-111
[4]  
Bishop C.M., 2006, Springer google schola, V2, P1122
[5]   Highly accurate and fast YOLOv4-based polyp detection✩ [J].
Carrinho, Pedro ;
Falcao, Gabriel .
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 232
[6]   A self-attention based faster R-CNN for polyp detection from colonoscopy images [J].
Chen, Bo-Lun ;
Wan, Jing-Jing ;
Chen, Tai-Yue ;
Yu, Yong-Tao ;
Ji, Min .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2021, 70
[7]   Improving deep learning-based polyp detection using feature extraction and data augmentation [J].
Chou, Yung-Chien ;
Chen, Chao-Chun .
MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (11) :16817-16837
[8]   Detection of Colorectal Polyps from Colonoscopy Using Machine Learning: A Survey on Modern Techniques [J].
ELKarazle, Khaled ;
Raman, Valliappan ;
Then, Patrick ;
Chua, Caslon .
SENSORS, 2023, 23 (03)
[9]   Res2Net: A New Multi-Scale Backbone Architecture [J].
Gao, Shang-Hua ;
Cheng, Ming-Ming ;
Zhao, Kai ;
Zhang, Xin-Yu ;
Yang, Ming-Hsuan ;
Torr, Philip .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (02) :652-662
[10]   Improved polyp detection from colonoscopy images using finetuned YOLO-v5 [J].
Ghose, Priyanka ;
Ghose, Arpan ;
Sadhukhan, Deboleena ;
Pal, Saurabh ;
Mitra, Madhuchanda .
MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (14) :42929-42954