当前位置: X-MOL 学术J. Dent. Res. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Histopathology-Based Diagnosis of Oral Squamous Cell Carcinoma Using Deep Learning
Journal of Dental Research ( IF 5.7 ) Pub Date : 2022-04-21 , DOI: 10.1177/00220345221089858
S Y Yang 1 , S H Li 2 , J L Liu 1 , X Q Sun 1 , Y Y Cen 1 , R Y Ren 1 , S C Ying 3 , Y Chen 1 , Z H Zhao 1 , W Liao 1
Affiliation  

Oral squamous cell carcinoma (OSCC) is prevalent around the world and is associated with poor prognosis. OSCC is typically diagnosed from tissue biopsy sections by pathologists who rely on their empirical experience. Deep learning models may improve the accuracy and speed of image classification, thus reducing human error and workload. Here we developed a custom-made deep learning model to assist pathologists in detecting OSCC from histopathology images. We collected and analyzed a total of 2,025 images, among which 1,925 images were included in the training set and 100 images were included in the testing set. Our model was able to automatically evaluate these images and arrive at a diagnosis with a sensitivity of 0.98, specificity of 0.92, positive predictive value of 0.924, negative predictive value of 0.978, and F1 score of 0.951. Using a subset of 100 images, we examined whether our model could improve the diagnostic performance of junior and senior pathologists. We found that junior pathologists were able to delineate OSCC in these images 6.26 min faster when assisted by the model than when working alone. When the clinicians were assisted by the model, their average F1 score improved from 0.9221 to 0.9566 in the case of junior pathologists and from 0.9361 to 0.9463 in the case of senior pathologists. Our findings indicate that deep learning can improve the accuracy and speed of OSCC diagnosis from histopathology images.



中文翻译:

使用深度学习基于组织病理学诊断口腔鳞状细胞癌

口腔鳞状细胞癌 (OSCC) 在世界范围内普遍存在,并且与预后不良有关。OSCC 通常由依靠经验的病理学家从组织活检切片中诊断出来。深度学习模型可以提高图像分类的准确性和速度,从而减少人为错误和工作量。在这里,我们开发了一个定制的深度学习模型,以帮助病理学家从组织病理学图像中检测 OSCC。我们共收集和分析了 2025 幅图像,其中 1925 幅图像包含在训练集中,100 幅图像包含在测试集中。我们的模型能够自动评估这些图像并得出诊断,灵敏度为 0.98,特异性为 0.92,阳性预测值为 0.924,阴性预测值为 0.978,F1 评分为 0.951。使用 100 张图像的子集,我们检查了我们的模型是否可以提高初级和高级病理学家的诊断性能。我们发现,初级病理学家在模型的帮助下能够比单独工作时更快地在这些图像中描绘 OSCC 6.26 分钟。当临床医生在模型的帮助下,初级病理学家的平均 F1 分数从 0.9221 提高到 0.9566,高级病理学家的平均 F1 分数从 0.9361 提高到 0.9463。我们的研究结果表明,深度学习可以提高从组织病理学图像诊断 OSCC 的准确性和速度。在模型的帮助下比单独工作时快 26 分钟。当临床医生在模型的帮助下,初级病理学家的平均 F1 分数从 0.9221 提高到 0.9566,高级病理学家的平均 F1 分数从 0.9361 提高到 0.9463。我们的研究结果表明,深度学习可以提高从组织病理学图像诊断 OSCC 的准确性和速度。在模型的帮助下比单独工作时快 26 分钟。当临床医生在模型的帮助下,初级病理学家的平均 F1 分数从 0.9221 提高到 0.9566,高级病理学家的平均 F1 分数从 0.9361 提高到 0.9463。我们的研究结果表明,深度学习可以提高从组织病理学图像诊断 OSCC 的准确性和速度。

更新日期:2022-04-21
down
wechat
bug