Explainable Hierarchical Semantic Convolutional Neural Network for Lung Cancer Diagnosis

Shiwen Shen, Simon X Han, Denise R Aberle, Alex A Bui, William Hsu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 63-66

While deep learning methods have demonstrated classification performance comparable to human readers in tasks such as computer-aided diagnosis, these models are difficult to interpret, do not incorporate prior domain knowledge, and are often considered as a "black box." We present a novel interpretable deep hierarchical semantic convolutional neural network (HSCNN) to predict whether a given pulmonary nodule observed on a computed tomography (CT) scan is malignant. Our network provides two levels of output: 1) low-level semantic features; and 2) a high-level prediction of nodule malignancy. The low-level outputs reflect diagnostic features often reported by radiologists and serve to explain how the model interprets the images in an expert-interpretable manner. The information from these low-level outputs, along with the representations learned by the convolutional layers, are then combined and used to infer the high-level output. Our experimental results using the Lung Image Database Consortium (LIDC) show that the proposed method not only produces interpretable lung cancer predictions but also achieves comparable results with the state-of-the-art methods.