Architecture and Computer Technology department (ATC), Robotics and Technology of Computers Lab (RTC), E.T.S. Ingeniería Informática, Avda. Reina Mercedes s/n, Universidad de Sevilla, Seville, 41012, Spain.
Architecture and Computer Technology department (ATC), Robotics and Technology of Computers Lab (RTC), E.T.S. Ingeniería Informática, Avda. Reina Mercedes s/n, Universidad de Sevilla, Seville, 41012, Spain; Computer Engineering Research Institute (I3US), E.T.S. Ingeniería Informática, Avda. Reina Mercedes s/n, Universidad de Sevilla, Seville, 41012, Spain.
Comput Methods Programs Biomed. 2022 Nov;226:107108. doi: 10.1016/j.cmpb.2022.107108. Epub 2022 Sep 7.
Lung cancer has the highest mortality rate in the world, twice as high as the second highest. On the other hand, pathologists are overworked and this is detrimental to the time spent on each patient, diagnostic turnaround time, and their success rate.
In this work, we design, implement, and evaluate a diagnostic aid system for non-small cell lung cancer detection, using Deep Learning techniques.
The classifier developed is based on Artificial Intelligence techniques, obtaining an automatic classification result between healthy, adenocarcinoma and squamous cell carcinoma, given an histopathological image from lung tissue. Moreover, a report module based on Explainable Deep Learning techniques is included and gives the pathologist information about the image's areas used to classify the sample and the confidence of belonging to each class.
The results show a system accuracy between 97.11 and 99.69%, depending on the number of classes classified, and a value of the area under ROC curve between 99.77 and 99.94%.
The classification results obtain a substantial improvement according to previous works. Thanks to the given report, the time spent by the pathologist and the diagnostic turnaround time can be reduced.
肺癌的死亡率居世界首位，是死亡率第二高疾病的两倍。另一方面，病理学家工作过度，这不利于他们为每位患者分配的时间、诊断周转时间和他们的成功率。
在这项工作中，我们使用深度学习技术设计、实现和评估了一种用于非小细胞肺癌检测的诊断辅助系统。
开发的分类器基于人工智能技术，给定来自肺组织的组织病理学图像，在健康、腺癌和鳞状细胞癌之间获得自动分类结果。此外，还包括一个基于可解释深度学习技术的报告模块，为病理学家提供有关用于对样本进行分类的图像区域以及属于每个类别的置信度的信息。
结果显示，系统的准确率取决于所分类的类别数量，在 97.11%到 99.69%之间，ROC 曲线下的面积值在 99.77%到 99.94%之间。
根据以前的工作，分类结果有了很大的提高。得益于提供的报告，病理学家花费的时间和诊断周转时间可以减少。
