College of Physics and Information Engineering, Fuzhou University, Fuzhou, Fujian 350108, China; Key Lab of Medical Instrumentation & Pharmaceutical Technology of Fujian Province, Fuzhou University, Fuzhou, Fujian 350108, China.
Department of Pathology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, Fujian 350014, China; Fujian Key Laboratory of Translational Cancer Medicine, Fuzhou, Fujian 350014, China.
Cell Rep Med. 2023 Apr 18;4(4):101004. doi: 10.1016/j.xcrm.2023.101004. Epub 2023 Apr 11.
Pathological diagnosis of gastric cancer requires pathologists to have extensive clinical experience. To help pathologists improve diagnostic accuracy and efficiency, we collected 1,514 cases of stomach H&E-stained specimens with complete diagnostic information to establish a pathological auxiliary diagnosis system based on deep learning. At the slide level, our system achieves a specificity of 0.8878 while maintaining a high sensitivity close to 1.0 on 269 biopsy specimens (147 malignancies) and 163 surgical specimens (80 malignancies). The classified accuracy of our system is 0.9034 at the slide level for 352 biopsy specimens (201 malignancies) from 50 medical centers. With the help of our system, the pathologists' average false-negative rate and average false-positive rate on 100 biopsy specimens (50 malignancies) are reduced to 1/5 and 1/2 of the original rates, respectively. At the same time, the average uncertainty rate and the average diagnosis time are reduced by approximately 22% and 20%, respectively.
胃癌的病理诊断需要病理医生具备丰富的临床经验。为了帮助病理医生提高诊断准确性和效率，我们收集了 1514 例具有完整诊断信息的胃 H&E 染色标本，建立了基于深度学习的病理辅助诊断系统。在切片水平上，我们的系统在 269 份活检标本（147 例恶性肿瘤）和 163 份手术标本（80 例恶性肿瘤）上的特异性为 0.8878，同时保持接近 1.0 的高灵敏度。我们的系统在 50 家医疗中心的 352 份活检标本（201 例恶性肿瘤）上的分类准确率为 0.9034。在我们系统的帮助下，病理医生在 100 份活检标本（50 例恶性肿瘤）上的平均假阴性率和平均假阳性率分别降低到原来的 1/5 和 1/2。同时，平均不确定性率和平均诊断时间分别降低了约 22%和 20%。
