Constructing an artificial intelligence assisted system for colonoscopy quality control based on various deep learning architectures
10.3969/j.issn.1005-202X.2024.11.018
- VernacularTitle:基于不同深度学习架构建立结肠镜质量控制的人工智能辅助系统
- Author:
Jian CHEN
1
;
Zihao ZHANG
;
Ganhong WANG
;
Zhenni WANG
;
Kaijian XIA
;
Xiaodan XU
Author Information
1. 常熟市第一人民医院/苏州大学附属常熟医院消化内科,江苏苏州 215500
- Keywords:
deep learning;
Transformer;
colonoscopy quality control;
colonoscopy;
model deployment
- From:
Chinese Journal of Medical Physics
2024;41(11):1443-1452
- CountryChina
- Language:Chinese
-
Abstract:
Objective To develop deep learning models for colonoscopy quality control using various deep learning architectures,and to delve into the decision-making mechanisms.Methods The colonoscopy images were selected from two datasets separately constructed by the HyperKvasir and Changshu Hospital Affiliated to Soochow University,encompassing intestines of varying degrees of cleanliness,polyps,and cecums.After image preprocessing and enhancement,transfer learning was carried out using the pre-trained models based on convolutional neural network(CNN)and Transformer.The model training adopted cross-entropy loss functions and Adam optimizer,and simultaneously implemented learning rate scheduling.To enhance model transparency,a thorough interpretability analysis was conducted using Grad-CAM,Guided Grad-CAM,and SHAP.The final model was converted to ONNX format and deployed on various equipment terminals to achieve real-time colonoscopy quality control.Results In a dataset of 3 831 colonoscopy images,EfficientNet model outperformed the other models on the test set,achieving an accuracy of 0.992 which was higher than those of the other models based on CNN(DenseNet121,ResNet50,VGG19)and Transformer(ViT,Swin,CvT),with a precision,recall rate,and F1 score of 0.991,0.989,and 0.990.On an external test set of 358 images,EfficientNet model had an average AUC,precision,and recall rate of 0.996,0.948,and 0.952,respectively.Although EfficientNet model is high-performing,some misjudgments still occurred.Interpretability analysis highlighted key image areas affecting decision-making.In addition,EfficientNet model was successfully converted to ONNX format and deployed on multiple platforms and devices,and it ensured real-time colonoscopy quality control with an inference speed of over 60 frames per second.Conclusion Among the 7 models developed for colonoscopy quality control based on CNN and Transformer,EfficientNet demonstrated exemplary performance across all categories and is deployed for real-time predictions on multiple terminals,aiming to provide patients with better medical care.
