Journal Article

Lung Nodule Malignancy Classification Integrating Deep and Radiomic Features in a Three-Way Attention-Based Fusion Module

Heidarian, Shahin, Mohammadi, Arash, Ganeshan, Balaji, Khademi, Sadaf, Afshar, Parnian, Oikonomou, Anastasia, Nguyen, Elsie T., Sidiqi, Abdul

2025

Overview

In this study, we propose a novel hybrid framework for assessing the invasiveness of an in-house dataset of 114 pathologically proven lung adenocarcinomas presenting as subsolid nodules on Computed Tomography (CT). Nodules were classified into group 1 (G1), which included atypical adenomatous hyperplasia, adenocarcinoma in situ, and minimally invasive adenocarcinomas, and group 2 (G2), which included invasive adenocarcinomas. Our approach includes a three-way Integration of Visual, Spatial, and Temporal features with Attention, referred to as I-VISTA, obtained from three processing algorithms designed based on Deep Learning (DL) and radiomic models, leading to a more comprehensive analysis of nodule variations. The aforementioned processing algorithms are arranged in the following three parallel paths: (i) The Shifted Window (SWin) Transformer path, which is a hierarchical vision Transformer that extracts nodules’ related spatial features; (ii) The Convolutional Auto-Encoder (CAE) Transformer path, which captures informative features related to inter-slice relations via a modified Transformer encoder architecture; and (iii) a 3D Radiomic-based path that collects quantitative features based on texture analysis of each nodule. Extracted feature sets are then passed through the Criss-Cross attention fusion module to discover the most informative feature patterns and classify nodules type. The experiments were evaluated based on a ten-fold cross-validation scheme. I-VISTA framework achieved the best performance of overall accuracy, sensitivity, and specificity (mean ± std) of 93.93 ± 6.80%, 92.66 ± 9.04%, and 94.99 ± 7.63% with an Area under the ROC Curve (AUC) of 0.93 ± 0.08 for lung nodule classification among ten folds. The hybrid framework integrating DL and hand-crafted 3D Radiomic model outperformed the standalone DL and hand-crafted 3D Radiomic model in differentiating G1 from G2 subsolid nodules identified on CT.

• Publisher: MDPI AG,Multidisciplinary Digital Publishing Institute (MDPI)
• Subject: Accuracy / Algorithms / Artificial intelligence / attention fusion / auto-encoder / Biopsy / Classification / Coders / Comparative analysis / Computational linguistics / Computed tomography / COVID-19 / CT imaging / Deep learning / Diagnosis / Identification and classification / Image databases / Image segmentation / Language processing / Lung cancer / Lungs / Machine learning / malignancy classification / Medical diagnosis / Medical imaging / Medical imaging equipment / Medical prognosis / Methods / Modules / Natural language interfaces / Neural networks / Nodules / Physiological aspects / Radiomics / Technology application / Tumors / vision transformer