Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{202668,
        author = {Sahil Yadav and Priyanka Makkar},
        title = {A Systematic Review of Multimodal Deep Learning for Medical Diagnosis (Lung Cancer)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {7236-7243},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202668},
        abstract = {Lung cancer is one of the most serious and life-threatening diseases worldwide, causing numerous cancer-related deaths annually. Early stage disease detection is extremely important for improving treatment effectiveness and increasing patient survival rates. With the rapid growth of artificial intelligence, deep learning techniques have become widely used in medical imaging and computer-aided diagnostic systems (CADs). Recently, multimodal deep learning has gained significant attention because it combines different types of medical data, including CT scans, chest radiographs, histopathology images, and clinical information, to provide more accurate and reliable diagnostic results. By integrating multiple data sources, multimodal systems can capture richer features and improve disease detection, classification, and prognosis prediction compared with traditional single-modality approaches. This review presents a detailed analysis of recent multimodal deep learning methods developed for lung cancer diagnosis and survival prediction. Twenty research papers published between 2020 and 2026 were systematically examined based on imaging modalities, deep learning architectures, fusion strategies, datasets, and clinical applications. The review highlights commonly used datasets, such as LIDC-IDRI, TCIA, LC25000, and ChestX-ray14, while discussing the applications of convolutional neural networks, transformer-based models, explainable artificial intelligence, and hybrid learning frameworks. In addition, this study explores major challenges, including limited annotated datasets, computational complexity, interpretability issues, and multimodal data integration difficulties. Finally, future research opportunities, such as federated learning, self-supervised learning, vision-language models, and explainable multimodal AI, are discussed. This review aims to provide researchers and healthcare professionals with a clear understanding of recent developments and future possibilities of multimodal deep learning for lung cancer diagnosis.},
        keywords = {Lung cancer diagnosis, multimodal deep learning, medical imaging, CT imaging, histopathology, explainable AI, deep learning, multimodal fusion.},
        month = {May},
        }