Big Data

The choice of adjuvant chemotherapy in pancreatic ductal adenocarcinoma (PDAC) is mainly guided by patients' general condition. We hypothesized that tumor morphology may predict differential treatment benefit and tested whether deep learning applied to histology images could derive a biomarker of relative benefit from gemcitabine (GEM) versus modified FOLFIRINOX (mFOLFIRINOX) in resected PDAC.

What is understood regarding the risk of breast cancer is substantial, yet translating this extensive knowledge to optimally inform breast cancer screening practices has proven to be a formidable task in the pre–artificial intelligence era of medicine. Breast cancer screening guidelines issued by major medical organizations vary, with differing recommendations regarding age at screening initiation and cessation, screening interval, and modalities, creating confusion for both patients and clinicians. The common denominator of these guidelines is an emphasis on individualized, risk-based decision making; particularly with a rise in early-onset breast cancers, a one-size-fits-all approach is broadly recognized as insufficient. Yet, effective risk-stratified screening is fundamentally contingent upon accurate and reliable risk estimation, and to date, this has been tricky.

The central myth of AI is that it functions objectively. In reality, an AI model is simply a pattern-matching engine. It learns to associate certain visual features with certain diseases. But it can easily be thrown off by the background color of a person’s skin. In other words, the AI model doesn’t learn to look at the lesion itself. Instead, it picks up on the color of the surrounding skin as a clue. This means that the model’s ability to make accurate predictions essentially degrades to guesses based on skin color.

Treatment effectiveness is hindered by the phenotypic plasticity of cancer and the genetic complexity of tumors. However, CRISPR-Cas-based medicines face challenges with specificity, off-target effects, and tumor heterogeneity adaptability. This work investigates the possible combination of quantum biological processes, artificial intelligence, and nanomaterials to improve CRISPR gene editing and modulate or reverse selected malignant phenotypes. Quantum machine learning (QML) can be used to simulate quantum processes like electron tunneling in DNA repair and spin-dependent enzyme activity. To enable exact tumor phenotypic reversal, these models will be combined with optimization approaches powered by AI to direct CRISPR editing in oncogenic signaling networks. Graphene, gold nanoparticles, and lipid-based vectors are some of the nanomaterials that will be used as carriers to effectively and deliver CRISPR systems in a biocompatible manner to the cancer microenvironment. We hypothesize that selected homeostatic gene-expression states may be partially restored in experimental cancer models through the integration of quantum-informed AI, CRISPR gene alteration, and nanomaterial delivery. This integrated strategy could support future cancer therapies that move beyond tumor suppression toward controlled modulation of malignant cell states, although substantial preclinical and clinical validation remains necessary.

Pancreatic cancer remains one of the deadliest cancers today — with projections that it will become the second-leading cause of cancer death in the U.S. by 2030 since it so often goes undetected until its later stages. Artificial intelligence (AI)-powered detection methods under development at Mayo Clinic Comprehensive Cancer Center are changing that approach, helping physicians detect pancreatic cancer up to three years earlier, when it is more treatable.

Oral cancer is a significant health concern where early detection greatly improves patient outcomes. This study develops and evaluates a deep learning model to automatically detect oral cancer from clinical photographic images. A convolutional neural network (CNN) was trained on a dataset of 750 oral lesion images sourced from Kaggle, using transfer learning with EfficientNet-B0 to compensate for limited sample size. The model's performance was validated on a held-out test set and assessed with accuracy, precision, recall, and receiver operating characteristic (ROC) curve analysis. Results indicate high diagnostic performance: the model achieved approximately 95% overall accuracy in distinguishing cancerous lesions from non-cancerous oral tissue. The CNN demonstrated a sensitivity of about 94% for identifying oral cancers and a specificity of about 95% for correctly recognizing non-cancer cases. The area under the ROC curve was 0.97, indicating excellent discriminative ability. Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations were used as an exploratory interpretability method to identify image regions contributing to model predictions. These heatmaps may suggest overlap between model attention and visually relevant lesion regions, but they do not confirm that the model used clinically meaningful features. These findings suggest that deep learning could serve as a valuable tool in assisting dental professionals with early oral cancer detection, though further clinical validation is required before adoption.

Ensuring trustworthiness is fundamental in cancer diagnostics, where a misdiagnosis can have dire consequences. Current pathology AI models lack systematic solutions to address trustworthiness concerns arising from model limitations and data discrepancies between model deployment and development environments. Here we introduce TRUECAM (Trustworthiness-focused, Uncertainty-aware, End-to-end Cancer diagnosis with Model-agnostic capabilities), a framework designed to ensure both data and model trustworthiness for non-small cell lung cancer subtyping with whole-slide images. TRUECAM integrates (1) a spectral-normalized neural Gaussian process for identifying out-of-scope inputs, (2) an ambiguity-guided tile elimination to filter out highly ambiguous regions, addressing data trustworthiness, and (3) conformal prediction to ensure controlled error rates. We systematically evaluated TRUECAM across multiple cancer datasets using both task-specific and foundation models. Computational experiments suggest that models wrapped with TRUECAM consistently outperformed their unwrapped counterparts in classification accuracy, robustness, interpretability, data efficiency and fairness. These findings establish TRUECAM as a versatile framework for the responsible deployment of pathology AI in real-world settings.

Immune checkpoint inhibitors (ICIs) are a standard treatment across cancers, yet most patients do not respond, and existing biomarkers generalize poorly across tumor types and therapies. Here we present COMPASS, a pan-cancer foundation model that predicts immunotherapy response from bulk tumor transcriptomes using a concept bottleneck transformer. COMPASS encodes gene expression through 44 biologically grounded immune concepts representing immune cell states, tumor−microenvironment interaction and signaling pathways. Trained on 10,184 tumors across 33 cancer types, COMPASS achieves better average performance than 22 methods across 16 clinical cohorts spanning seven cancers and six ICIs, improving accuracy by 8.5% and area under the precision-recall curve by 15.7% on average across cohorts. COMPASS generalizes to cancer types and treatments not represented during fine-tuning and may inform indication selection and patient stratification. In survival analyses, patients classified by COMPASS as responders had longer overall survival (hazard ratio = 4.7, P < 0.0001). Personalized response maps connect gene expression to immune concepts, identifying programs associated with response and resistance; in immune-inflamed non-responders, COMPASS highlights programs including TGFβ signaling, endothelial exclusion, CD4+ T cell dysfunction and B cell deficiency. COMPASS predicts immunotherapy response and provides hypothesis-generating mechanistic insight for trial design and translational studies.

JMIR Publications released a feature News and Perspectives story on technological advances in oncology. Authored by JMIR Correspondent Benedette Cuffari, "AI-Designed Radiopharmaceuticals: How Machine Learning Is Redefining Precision Cancer Therapy" reports on the integration of deep learning and generative AI in radiopharmaceutical medicine, its impact on accelerating drug design, and how personalized dosimetry can improve patient outcomes.

Using artificial intelligence (AI), researchers found that image-based risk scores for breast cancer derived from screening mammograms evolve over time and differ between women who develop cancer and those who do not, opening the door to a new era of dynamic breast cancer risk assessment.

JMIR Publications released a feature News and Perspectives story on technological advances in oncology. Authored by JMIR Correspondent Benedette Cuffari, "AI-Designed Radiopharmaceuticals: How Machine Learning Is Redefining Precision Cancer Therapy" reports on the integration of deep learning and generative AI in radiopharmaceutical medicine, its impact on accelerating drug design, and how personalized dosimetry can improve patient outcomes.