Artificial intelligence (AI) algorithms, such as convolutional neural networks and transformers, have significantly impacted cancer care. For lung cancer, AI holds great potential in addressing smoking cessation, personalized screening, and imaging genomics. And these data could be incorporated to optimize treatment selection. This review highlights the transformative impact of AI in lung cancer management, discusses crucial barriers such as model bias and fairness, and outlines future directions for clinical application.
Personalized medicine has transformed disease management by focusing on individual characteristics, driven by advancements in genome mapping and biomarker discoveries. This study aims to develop a predictive model for the early detection of treatment-related cardiac side effects in breast cancer patients by integrating clinical data, high-sensitivity Troponin-T (hs-TropT), radiomics, and dosiomics. The ultimate goal is to identify subclinical cardiotoxicity before clinical symptoms manifest, enabling personalized surveillance strategies. It is the first study to utilize heart-segmented dosiomics in breast cancer patients.
Artificial intelligence (AI) in oncology refers to the use of advanced computer algorithms and machine learning techniques to analyze vast and complex cancer-related data. AI systems are designed to mimic aspects of human intelligence—such as learning from experience, recognizing patterns, and making predictions. In the field of oncology, AI is transforming how cancer is detected, diagnosed, treated, and monitored. By processing large volumes of medical images, pathology slides, genomic sequences, and electronic health records, AI can identify hidden patterns, support clinical decision-making, and personalize treatment strategies. The integration of AI into cancer care is driving a new era of precision medicine, enabling earlier detection, more accurate diagnosis, and improved outcomes for patients facing a cancer diagnosis.
Ashish Kamat interviews Bishoy Faltas about a multimodal deep learning model for predicting pathologic complete response to neoadjuvant chemotherapy in muscle-invasive bladder cancer. Dr. Faltas explains how his team developed an integrated approach combining histopathology image analysis, RNA expression, and spatial cell type data from the SWOG 1314 trial involving 180 patients. The model uses three neural network branches: gene expression analysis, whole slide image processing with ResNet architecture, and HoverNet for spatial cell mapping. Results demonstrated superior performance with an AUC of 0.72-0.74 when integrating all three data types compared to individual branches. The model autonomously identified biologically relevant features like TP63 expression and basal differentiation programs associated with chemotherapy response. Notably, the team achieved these results without including clinical parameters, suggesting even greater potential when combined with patient data.
The IAEA has launched a new two-year coordinated research project to explore how artificial intelligence can assist with contouring — a crucial step in cancer treatment, in which a tumour and the surrounding tissues are outlined to guide the delivery of radiation therapy. The project will delve into the challenges and limitations of implementing artificial intelligence-based tools within radiotherapy.
Lenovo will provide the IEO Monzino Group with a High Performance Computing (HPC) system to accelerate scientific research in oncology and cardiology at the European Institute of Oncology and the Monzino Cardiology Center. The supercomputer will support the studies of bioinformaticians and researchers working for the Group with the aim of creating predictive, prognostic or diagnostic computational models based on the interactions of protein structures.
In a significant advancement for cancer treatment, researchers have developed a groundbreaking artificial intelligence (AI) tool capable of detecting lung tumors with exceptional accuracy—tracking their movement with every breath a patient takes. The new system, called iSeg, is the first 3D deep learning segmentation tool designed to map tumors as they shift during respiration, offering oncologists a powerful new asset in their mission to deliver precise and effective radiotherapy.
The use of artificial intelligence (AI) technologies and machine learning (ML) algorithms is experiencing tremendous growth in immunology, assisting in various functions such as identifying inflammatory markers related to different immune diseases and frailty, their potential application in designing next-generation monoclonal antibodies and vaccines, and their use to uncover complex patterns in human immune repertoires. The goal of this Research Topic is to highlight the key role of AI/ML in cancer immunotherapy. Given the wealth of existing immunotherapy data and its multi-modal, heterogeneous nature, AI can play a vital role in navigating through this complexity.
Tumor microenvironment signals and circulating factors may jointly influence treatment outcomes in patients with advanced renal cell carcinoma (RCC) who received nivolumab (Opdivo) plus cabozantinib (Cabometyx), according to David A Braun, MD, PhD. At the 2025 American Society of Clinical Oncology Annual Meeting, Braun, Center of Molecular and Cellular Oncology, Yale Cancer Center, Yale School of Medicine, discussed an integrative, post hoc analysis that used a machine learning-based approach to posthumously evaluate the phase 3 CheckMate 9ER trial (NCT03141177) to integrate both tumor and circulating biomarkers.
One of the fastest-growing parts of the economy in the last ten years has been healthcare, and in light of the growing threats of pandemics like the coronavirus outbreak, the industry is set to rise once again. To stay ahead of the curve in demand for healthcare services and solutions, organizations worldwide are turning to advanced techniques like AI, machine learning, and Big Data.
With the rapid advances in artificial intelligence-particularly convolutional neural networks-researchers now exploit CT, PET/CT and other imaging modalities to predict epidermal growth factor receptor (EGFR) mutation status in non-small-cell lung cancer (NSCLC) non-invasively, rapidly and repeatably. End-to-end deep-learning models simultaneously perform feature extraction and classification, capturing not only traditional radiomic signatures such as tumour density and texture but also peri-tumoural micro-environmental cues, thereby offering a higher theoretical performance ceiling than hand-crafted radiomics coupled with classical machine learning. Nevertheless, the need for large, well-annotated datasets, the domain shifts introduced by heterogeneous scanning protocols and preprocessing pipelines, and the "black-box" nature of neural networks all hinder clinical adoption. To address fragmented evidence and scarce external validation, we conducted a systematic review to appraise the true performance of deep-learning and radiomics models for EGFR prediction and to identify barriers to clinical translation, thereby establishing a baseline for forthcoming multicentre prospective studies.
At the 2025 ASCO Annual Meeting, artificial intelligence (AI) moved from theoretical promise to demonstrated clinical utility. Amid the surge of presentations on precision oncology, one theme became increasingly clear: as the number of actionable biomarkers increases, so does the complexity of sequencing treatments. AI may be the only tool agile enough to keep up. The biomarker pool is expanding rapidly. With tumor profiling now yielding dozens of potentially actionable signals, the sequencing question becomes central: Which target do we prioritize? What’s the optimal order of therapies? And how do we make decisions in the absence of head-to-head trials or long-term data?