Shape and Margin-Aware Lung Nodule Classification in Low-dose CT Images via Soft Activation Mapping

Abstract

A number of studies on lung nodule classification lack clinical/biological interpretations of the features extracted by convolutional neural network (CNN). The methods like class activation mapping (CAM) and gradient-based CAM (Grad-CAM) are tailored for interpreting localization and classification tasks while they ignored fine-grained features. Therefore, CAM and Grad-CAM cannot provide optimal interpretation for lung nodule categorization task in low-dose CT images, in that fine-grained pathological clues like discrete and irregular shape and margins of nodules are capable of enhancing sensitivity and specificity of nodule classification with regards to CNN. In this paper, we first develop a soft activation mapping (SAM) to enable fine-grained lung nodule shape \& margin (LNSM) feature analysis with a CNN so that it can access rich discrete features. Secondly, by combining high-level convolutional features with SAM, we further propose a high-level feature enhancement scheme (HESAM) to localize LNSM features. Experiments on the LIDC-IDRI dataset indicate that 1) SAM captures more fine-grained and discrete attention regions than existing methods, 2) HESAM localizes more accurately on LNSM features and obtains the state-of-the-art predictive performance, reducing the false positive rate, and 3) we design and conduct a visually matching experiment which incorporates radiologists study to increase the confidence level of applying our method to clinical diagnosis.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• A Survey on Deep Learning in Medical Image Analysis
• How transferable are features in deep neural networks?
• Brain Tumor Segmentation with Deep Neural Networks
• Understanding deep learning requires rethinking generalization
• Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?
• 3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network
• Learning to detect chest radiographs containing lung nodules using visual attention networks
• On Loss Functions for Deep Neural Networks in Classification
• Dual Path Networks

Cited by in corpus (8)

• Explainable artificial intelligence (XAI) in deep learning-based medical image analysis
• On Interpretability of Artificial Neural Networks: A Survey
• Meta Ordinal Regression Forest for Medical Image Classification with Ordinal Labels
• CLIP-Lung: Textual Knowledge-Guided Lung Nodule Malignancy Prediction
• DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
• Meta Ordinal Regression Forest For Learning with Unsure Lung Nodules
• Learning from Ambiguous Labels for Lung Nodule Malignancy Prediction
• Meta ordinal weighting net for improving lung nodule classification