ADGAN: Attribute-Driven Generative Adversarial Network for Synthesis and Multiclass Classification of Pulmonary Nodules

• Published in: IEEE transaction on neural networks and learning systems Vol. 35; no. 2; pp. 2484 - 2495
• Main Authors: Roy, Rukhmini, Mazumdar, Suparna, Chowdhury, Ananda S.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adversarial machine learning; Adversarial network; Cancer; Classification; Computed tomography; Convolutional neural networks; Datasets; Generative adversarial networks; Generators; Humans; Image reconstruction; Localization; Lung cancer; Lung Neoplasms; Lung nodules; Medical imaging; Modules; multiclass nodule classification; Neural Networks, Computer; nodule synthesis; Nodules; Regularization; self-attention U-Net (SaUN); Semantics; Survival; Synthesis; Tomography, X-Ray Computed - methods; Tumors; United States; United States
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2022.3190331

Lung cancer is the leading cause of cancer-related deaths worldwide. According to the American Cancer Society, early diagnosis of pulmonary nodules in computed tomography (CT) scans can improve the five-year survival rate up to 70% with proper treatment planning. In this article, we propose an attribute-driven Generative Adversarial Network (ADGAN) for synthesis and multiclass classification of Pulmonary Nodules. A self-attention U-Net (SaUN) architecture is proposed to improve the generation mechanism of the network. The generator is designed with two modules, namely, self-attention attribute module (SaAM) and a self-attention spatial module (SaSM). SaAM generates a nodule image based on given attributes whereas SaSM specifies the nodule region of the input image to be altered. A reconstruction loss along with an attention localization loss (AL) is used to produce an attention map prioritizing the nodule regions. To avoid resemblance between a generated image and a real image, we further introduce an adversarial loss containing a regularization term based on KL divergence. The discriminator part of the proposed model is designed to achieve the multiclass nodule classification task. Our proposed approach is validated over two challenging publicly available datasets, namely LIDC-IDRI and LUNGX. Exhaustive experimentation on these two datasets clearly indicate that we have achieved promising classification accuracy as compared to other state-of-the-art methods.