Parameter-Efficient LoRA-GRL Adaptation for Cross-Center Classification of Benign and Malignant Lung Nodules on Heterogeneous Standard-Dose Chest CT: A Multi-Institutional Study from Palestine
Open Access
- 21 September 2026
- journal article
- research article
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (9) , 461
Abstract
Automated CT lung nodule classification suffers from domain shift across centers. We propose LoRA-GRL, combining Low-Rank Adaptation (LoRA) with adversarial domain harmonization via a Gradient Reversal Layer. Rank-8 LoRA modules were inserted into all attention and feed-forward linear projections (48 sites) of a frozen ViT-S backbone; a domain discriminator encouraged center-invariant features across three centers. Normal vs. Benign and Normal vs. Malignant tasks used 264 patients with patient-level five-fold stratified cross-validation. LoRA-GRL achieved AUCs of 0.9735 and 0.9869, close to full fine-tuning (0.9747 and 0.9863). Differences from strongest baselines fell within overlapping 95% CIs under paired bootstrap, indicating comparable discrimination, not superiority. Efficiency is the main advantage: only 0.789 M trainable parameters, a 96.4% reduction from 21.865 M, and inference latency matched full fine-tuning after adapter merging. Grad-CAM showed nodule-localized predictions but also slice-selection failures. For benign classification, higher AUC than plain LoRA came with higher specificity but lower sensitivity. For malignant classification, sensitivity was 0.9412 (5.9 pp above full fine-tuning) and specificity 0.9697. The small cross-center AUC range (0.0011) reflects internal consistency across participating centers, not unseen-site generalization. LoRA-GRL is a promising parameter-efficient candidate for multi-center lung nodule classification, potentially reducing scanner-specific bias and storage/memory needs, but clinical utility requires external validation and prospective evaluation.Keywords
This publication has 24 references indexed in Scilit:
- A hybrid deep learning approach integrating CNN and transformer for lung cancer classification using CT scansScientific Reports, 2026
- Performance of a deep-learning-based lung nodule detection system using 0.25-mm thick ultra-high-resolution CT imagesJapanese Journal of Radiology, 2025
- High-Precision Lung Cancer Classification with Custom CNN: Evaluation and Transfer Learning for Broader Cancer TypesProcedia Computer Science, 2025
- A benchmark of deep learning approaches to predict lung cancer risk using national lung screening trial cohortScientific Reports, 2025
- GSC-DVIT: A vision transformer based deep learning model for lung cancer classification in CT imagesBiomedical Signal Processing and Control, 2024
- Vision Transformer Based Effective Model for Early Detection and Classification of Lung CancerSN Computer Science, 2024
- Lung Cancer Classification Using Image Enhancement and CNN-Based Pre-Trained Models2023
- Domain-Adversarial Training of Neural Networks2017
- Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic ScreeningNew England Journal of Medicine, 2011
- Computer-aided detection (CAD) of lung nodules in CT scans: radiologist performance and reading time with incremental CAD assistanceEuropean Radiology, 2009