Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, 91052, Germany.
Department of Radiotherapy and Radiation Oncology, Saarland University Medical Center, Homburg/Saar, 66421, Germany.
Diagn Pathol. 2023 Nov 3;18(1):121. doi: 10.1186/s13000-023-01407-8.
Although neural networks have shown remarkable performance in medical image analysis, their translation into clinical practice remains difficult due to their lack of interpretability. An emerging field that addresses this problem is Explainable AI.
Here, we aimed to investigate the ability of Convolutional Neural Networks (CNNs) to classify head and neck cancer histopathology. To this end, we manually annotated 101 histopathological slides of locally advanced head and neck squamous cell carcinoma. We trained a CNN to classify tumor and non-tumor tissue, and another CNN to semantically segment four classes - tumor, non-tumor, non-specified tissue, and background. We applied Explainable AI techniques, namely Grad-CAM and HR-CAM, to both networks and explored important features that contributed to their decisions.
The classification network achieved an accuracy of 89.9% on previously unseen data. Our segmentation network achieved a class-averaged Intersection over Union score of 0.690, and 0.782 for tumor tissue in particular. Explainable AI methods demonstrated that both networks rely on features agreeing with the pathologist's expert opinion.
Our work suggests that CNNs can predict head and neck cancer with high accuracy. Especially if accompanied by visual explanations, CNNs seem promising for assisting pathologists in the assessment of cancer sections.
尽管神经网络在医学图像分析中表现出了显著的性能，但由于缺乏可解释性，它们将其转化为临床实践仍然具有一定的难度。一个新兴的领域——可解释人工智能，正在解决这个问题。
在这里，我们旨在研究卷积神经网络（CNN）对头颈癌组织病理学进行分类的能力。为此，我们手动标注了 101 张局部晚期头颈部鳞状细胞癌的组织病理学幻灯片。我们训练了一个 CNN 来分类肿瘤和非肿瘤组织，另一个 CNN 来语义分割四类 - 肿瘤、非肿瘤、非特定组织和背景。我们应用了可解释性人工智能技术，即 Grad-CAM 和 HR-CAM，对两个网络进行了研究，并探索了对其决策有贡献的重要特征。
分类网络在未见数据上的准确率达到了 89.9%。我们的分割网络的类平均交并比得分为 0.690，特别是肿瘤组织的得分达到了 0.782。可解释性人工智能方法表明，两个网络都依赖于与病理学家专家意见一致的特征。
我们的工作表明，CNN 可以对头颈癌进行高精度的预测。特别是如果有可视解释的辅助，CNN 似乎有希望帮助病理学家评估癌症切片。
