Academic Journal of Computing & Information Science, 2026, 9(5); doi: 10.25236/AJCIS.2026.090509.
Yueying Zhou1, Jianming Dong2
1College of Cyberspace Security, Xizang Minzu University, Xianyang, 712082, China
2College of Cyberspace Security, Xizang Minzu University, Xianyang, 712082, China
Accurate characterization of pulmonary nodules is critical for early lung cancer diagnosis and treatment planning. Recent advances in artificial intelligence (AI) have demonstrated substantial potential in automating nodule detection, segmentation, malignancy classification, and invasiveness prediction. This review summarizes key developments across radiomics, deep learning, pathomics, vision-language models, and liquid biopsy, highlighting the transition from single-modality analysis to multimodal integration. Representative studies are discussed to illustrate the performance gains and remaining challenges in clinical translation, including generalizability, interpretability, and implementation feasibility.
Artificial intelligence; Pulmonary nodules; Radiomics; Deep learning; Multimodal integration; Vision-language models; Liquid biopsy; Pathomics; Malignancy classification; Computed tomography
Yueying Zhou, Jianming Dong. Artificial Intelligence in Pulmonary Nodule Assessment: From Radiomics to Multimodal Integration. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 5: 77-82. https://doi.org/10.25236/AJCIS.2026.090509.
[1] Liu J, Qi L, Wang Y, et al. Development of a combined radiomics and CT feature-based model for differentiating malignant from benign subcentimeter solid pulmonary nodules. Eur Radiol Exp. 2024;8:8.
[2] Digumarthy SR, Padole AM, Rastogi S, et al. Predicting malignant potential of subsolid nodules: can radiomics preempt longitudinal follow up CT? Cancer Imaging. 2019;19:36.
[3] Zhu M, Yang Z, Wang M, et al. A computerized tomography-based radiomic model for assessing the invasiveness of lung adenocarcinoma manifesting as ground-glass opacity nodules. Respir Res. 2022;23:96.
[4] Kim RY. Radiomics-based computer-aided diagnosis for pulmonary nodule risk stratification: a narrative review. Cancer Biomark. 2025. doi:10.3233/CBM-230360.
[5] Selvam M, Ramesh S, Sadanandan A, et al. Radiomics-derived classifier performance evaluation in lung nodule characterization compared with expert radiologists. Sci Rep. 2026. doi:10.1038/s41598-026-47656-7.
[6] Xie L, Xu Y, Zheng M, et al. An Anthropomorphic Diagnosis System of Pulmonary Nodules using Weak Annotation-Based Deep Learning. Comput Med Imaging Graph. 2024;117:102438.
[7] Du H, Wang X, Wang K, et al. Identifying invasiveness to aid lung adenocarcinoma diagnosis using deep learning and pathomics. Sci Rep. 2025;15:4913.
[8] He L, Li Z, Duan Y, et al. Prediction of infiltration degree of ground-glass nodules using a fusion of CT radiomics and deep learning. Sci Rep. 2026. doi:10.1038/s41598-026-50328-1.
[9] Rao KS, Kavitha H, Juluru TK, et al. LungDxFormer: a transformer-CNN hybrid model with dynamic spatial attention for accurate lung cancer detection and classification. Sci Rep. 2026. doi:10.1038/s41598-026-50449-7.
[10] Liu Y, Tang Z, Tang Z, et al. LNMSNet: a multi-task deep learning network for pulmonary nodules segmentation and malignancy classification. Front Med. 2026;13:1773338.
[11] Li H, Wang Y, Wang Y, et al. Application of explainable deep learning in differentiating benign from malignant pulmonary space-occupying lesions and classifying pathological subtypes of lung cancer. Chin J Lung Cancer. 2025;28(10):738-750.
[12] Zhang Y, Yang Z, Chen R, et al. Histopathology images-based deep learning prediction of prognosis and therapeutic response in small cell lung cancer. npj Digit Med. 2024;7:15.
[13] Zong J, Jiang B, Li H, et al. Stacked CT radiomics, deep learning and clinical feature models for differentiating benign and malignant solitary pulmonary nodules. Sci Rep. 2026. doi:10.1038/s41598-026-49720-8.
[14] Khademi S, Heidarian S, Afshar P, et al. I-VISTA: Integrating Visual, Spatial, and Temporal features with Attention for classifying invasiveness of lung adenocarcinoma subsolid nodules on CT. J Imaging. 2025;11:360.
[15] Zhuang L, Tabatabaei SMH, Salehi-Rad R, et al. Vision-language model-based semantic-guided imaging biomarker for lung nodule malignancy prediction. J Biomed Inform. 2025. doi:10.1016/j.jbi.2025.104947.
[16] Xu N, He Q, Wang L, et al. Predicting Invasiveness of Lung Adenocarcinoma from Chest CT with Few-shot Vision-Language Ternary Classification Model. npj Digit Med. 2026;9:60.
[17] Khovanova D, Vasilev Y, Vladymyrskyy A, et al. A comparative accuracy study of multimodal LLMs, VLM and agent-based framework for pulmonary nodule detection on chest radiographs. Front Digit Health. 2026;7:1674835.
[18] Caballero-Vazquez A, Garcia-Cerezo M, Fernandez-Castro LR, et al. Liquid biopsy biomarkers for accurate detection of malignant pulmonary nodules: a meta-analytic approach. Discov Oncol. 2026;17:178.
[19] Fu W, Zou X, He T, et al. The 2025 lung cancer landscape: advances in screening, molecular taxonomy and therapeutic strategy: a narrative review. Transl Lung Cancer Res. 2026;15(3):62.