Artificial Intelligence in Oncologic Imaging: Deep Learning, Radiomics, and Clinical Integration for Precision Cancer Diagnosis
Year: 2026
Type: article
Abstract: Radiological oncology is using AI to analyse complicated images, analyse tumours, and make treatment decisions. This study focuses on deep learning, radiomics, and radiogenomics frameworks for AI applications in breast, lung, prostate, brain, gastrointestinal, and metastatic cancers. Outperforming expert radiologists, these tools have improved lesion identification, segmentation, risk prediction, and molecular phenotype inference. In addition, the review discusses how AI influences workflow triage, report standardization, and radiologist efficiency in digital mammography, MRI, PET/CT, and CT. Despite recent advancements, the need for AI outputs that can be explained in therapeutic contexts, data silos, regulatory uncertainty, and inadequate model generalization across populations and institutions remain obstacles. The objectives include facilitating federated learning, harmonising data from multiple centers, monitoring after deployment, and integrating with PACS/RIS infrastructure. The paper critically analyses the existing situation and proposes safe, equitable, and successful implementation strategies. In order to provide personalized, data-driven oncologic imaging that supports precision treatment, AI is collaborating with radiologists.
Author: Ohmini Krishnamurthy Rajendran
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: bronze
OpenAlex ID: W7164010370