Relational Learning between Multiple Pulmonary Nodules via Deep Set Attention Transformers

Abstract

Diagnosis and treatment of multiple pulmonary nodules are clinically important but challenging. Prior studies on nodule characterization use solitary-nodule approaches on multiple nodular patients, which ignores the relations between nodules. In this study, we propose a multiple instance learning (MIL) approach and empirically prove the benefit to learn the relations between multiple nodules. By treating the multiple nodules from a same patient as a whole, critical relational information between solitary-nodule voxels is extracted. To our knowledge, it is the first study to learn the relations between multiple pulmonary nodules. Inspired by recent advances in natural language processing (NLP) domain, we introduce a self-attention transformer equipped with 3D CNN, named {NoduleSAT}, to replace typical pooling-based aggregation in multiple instance learning. Extensive experiments on lung nodule false positive reduction on LUNA16 database, and malignancy classification on LIDC-IDRI database, validate the effectiveness of the proposed method.

2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI 2020)

References in corpus (5)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Densely Connected Convolutional Networks
• Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge
• Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Network
• Probabilistic Radiomics: Ambiguous Diagnosis with Controllable Shape Analysis

Cited by in corpus (6)

• Unsupervised Contrastive Learning based Transformer for Lung Nodule Detection
• AlignShift: Bridging the Gap of Imaging Thickness in 3D Anisotropic Volumes
• Learning Tumor Growth via Follow-Up Volume Prediction for Lung Nodules
• MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response
• Hierarchical Classification of Pulmonary Lesions: A Large-Scale Radio-Pathomics Study
• Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification