AI Framework Integrates Radiology and Pathology for Lung Cancer Diagnosis

A new artificial intelligence system has been developed to improve lung cancer diagnosis by combining computed tomography imaging with histopathology analysis. The dual-modal framework addresses limitations in conventional CT scans, which struggle to differentiate between benign and malignant lesions. Using convolutional neural networks, the AI extracts features from both radiology and hematoxylin and eosin-stained tissue samples. Clinical metadata is incorporated to enhance the system's robustness. The technology employs weighted decision-level integration to classify multiple lung cancer subtypes including adenocarcinoma, squamous cell carcinoma, large cell carcinoma, and small cell lung cancer, along with normal tissue identification. Explainable AI techniques such as Grad-CAM and Grad-CAM++ provide interpretable diagnostic insights. Lung cancer continues to be a leading cause of cancer-related mortality worldwide, creating significant need for improved diagnostic tools. The research was published on arXiv with identifier 2604.16104v1.