文献检索，用中文搜 PubMed

OBJECTIVE

Convolutional Neural Network(CNN) is increasingly being applied in the diagnosis of gastric cancer. However, the impact of proportion of internal data in the training set on test results has not been sufficiently studied. Here, we constructed an artificial intelligence (AI) system called EGC-YOLOV4 using the YOLO-v4 algorithm to explore the optimal ratio of training set with the power to diagnose early gastric cancer.

DESIGN

A total of 22,0918 gastroscopic images from Yixing People's Hospital were collected. 7 training set models were established to identify 4 test sets. Respective sensitivity, specificity, Youden index, accuracy, and corresponding thresholds were tested, and ROC curves were plotted.

RESULTS

The EGC-YOLOV4 system completes all tests at an average reading speed of about 15 ms/sheet; 2. The AUC values in training set 1 model were 0.8325, 0.8307, 0.8706, and 0.8279, in training set 2 model were 0.8674, 0.8635, 0.9056, and 0.9249, in training set 3 model were 0.8544, 0.8881, 0.9072, and 0.9237, in training set 4 model were 0.8271, 0.9020, 0.9102, and 0.9316, in training set 5 model were 0.8249, 0.8484, 0.8796, and 0.8931, in training set 6 model were 0.8235, 0.8539, 0.9002, and 0.9051, in training set 7 model were 0.7581, 0.8082, 0.8803, and 0.8763.

CONCLUSION

EGC-YOLOV4 can quickly and accurately identify the early gastric cancer lesions in gastroscopic images, and has good generalization.The proportion of positive and negative samples in the training set will affect the overall diagnostic performance of AI.In this study, the optimal ratio of positive samples to negative samples in the training set is 1:1~ 1:2.

OBJECTIVE

DESIGN

RESULTS

The EGC-YOLOV4 system completes all tests at an average reading speed of about 15 ms/sheet; 2. The AUC values in training set 1 model were 0.8325, 0.8307, 0.8706, and 0.8279, in training set 2 model were 0.8674, 0.8635, 0.9056, and 0.9249, in training set 3 model were 0.8544, 0.8881, 0.9072, and 0.9237, in training set 4 model were 0.8271, 0.9020, 0.9102, and 0.9316, in training set 5 model were 0.8249, 0.8484, 0.8796, and 0.8931, in training set 6 model were 0.8235, 0.8539, 0.9002, and 0.9051, in training set 7 model were 0.7581, 0.8082, 0.8803, and 0.8763.

CONCLUSION

目的

卷积神经网络（CNN）在胃癌诊断中的应用日益广泛。然而，训练集中内部数据比例对测试结果的影响尚未得到充分研究。在此，我们使用YOLO-v4算法构建了一个名为EGC-YOLOV4的人工智能（AI）系统，以探索具有诊断早期胃癌能力的训练集的最佳比例。

设计

收集了来自宜兴市人民医院的220918张胃镜图像。建立了7个训练集模型以识别4个测试集。测试了各自的灵敏度、特异性、约登指数、准确性及相应阈值，并绘制了ROC曲线。

结果

EGC-YOLOV4系统以约15毫秒/张的平均读取速度完成所有测试；2. 训练集1模型的AUC值分别为0.8325、0.8307、0.8706和0.8279，训练集2模型的AUC值分别为0.8674、0.8635、0.9056和0.9249，训练集3模型的AUC值分别为0.8544、0.8881、0.9072和0.9237，训练集4模型的AUC值分别为0.8271、0.9020、0.9102和0.9316，训练集5模型的AUC值分别为0.8249、0.8484、0.8796和0.8931，训练集6模型的AUC值分别为0.8235、0.8539、0.9002和0.9051，训练集7模型的AUC值分别为0.7581、0.8082、0.8803和0.8763。