News

Keep up with the latest news from the NCI Center for Biomedical Informatics and Information Technology (CBIIT) and the data science communities.

Deep learning model. Several interconnected points.

Deep Learning Model Proves Useful in Head and Neck Cancer Care

Learn about this model that predicts survival and disease outcome in patients with head and neck squamous cell carcinoma.

Image shows a non-contrast low-dose chest CT scan. Three red dashed lines run across the chest scan and show the sections selected for body composition assessment.

Using AI to Assess Body Composition Could Help in Cancer Care

In a recent study, NCI-funded researchers applied an artificial intelligence model to lung screening computed tomography images to assess body composition. The team used two key indicators of health—skeletal muscle and fat (adipose) tissue—to predict death from lung cancer, cardiovascular disease, and other causes.

Example of a scan using a non-invasive imaging technology. The scan shows a yellow band at the top, a green layer in the middle, and a deep blue band underneath. The colored layers represent skin and the underlying tissues.

NCI SBIR Award Helps Company Use AI to Assess Cancerous Skin Lesions

With the help of an NCI SBIR grant, Enspectra Health, Inc., is blending deep learning algorithms with existing imaging technology to create a new way of obtaining a virtual biopsy.

NCI-funded researchers used artificial intelligence to develop an accurate cancer estimation map for defining tumor margins. They found their model outperformed conventional estimates of tumor margins using imaging alone.

Using Artificial Intelligence to Map Prostate Tumors

NCI-funded researchers used artificial intelligence to develop an accurate cancer estimation map for defining tumor margins. They found their model outperformed conventional estimates of tumor margins using imaging alone.

Pathology image of H&E stained slide showing colorectal cancer

New AI Tool Helps Interpret Pathology Slides to Predict Cancer Recurrence

NCI-funded researchers combined long-term, patient-outcome data with pathology slides from people with colorectal cancer to develop a machine learning tool, called QuantCRC. Using QuantCRC, researchers could predict if a patient’s cancer would recur based on analysis of a single hematoxylin and eosin stained slide of the tumor.

Data points and lines are used to illustrate the figure of a woman, with highlighted circles to indicate breasts and the acronym “AI” appearing at the top.

New Deep Learning System Proves Accurate in Predicting Suspected Breast Cancer

A new, NCI-funded, deep learning technology performed on par with radiologists in interpreting breast cancer images. This tool could help refine diagnosis to reduce the number of unnecessary biopsies.

MRI image of the prostate showing segmentation of the core and peripheral zones.

New Contract Opportunity to Obtain Medical Image Segmentations

NCI is seeking support for developing machine-generated segmentations of images in the radiology collections of the Imaging Data Commons (IDC). Submit your proposals by March 10, 2023.

Figure shows CT scans and corresponding 3-D renderings of tumor vasculature for people who responded to therapy vs. those who didn't. Tumor vasculature in non-responders had more twists and turns than those who responded to treatment.

Tumor Twistedness Serves as AI-Based Biomarker for Lung Cancer Immunotherapy

Using data from routine lung scans, NCI-supported researchers developed an AI-based tool to help predict how patients will respond to therapy.

Illustrated cloud with three small squares displayed in front of it. The squares represent different repositories stored within the cloud.

New Data Set from the National Clinical Trials Network Includes Pediatric Brain Tumor Imaging

This newly released data set provides imaging in pediatric patients with newly diagnosed primitive neuroectodermal tumors throughout their treatment and until any potential relapse.

Childhood cancer patient trying to listen to the heartbeat of their teddy bear with a stethoscope.

See What’s New in the Childhood Cancer Data Catalog

The latest update to the Childhood Cancer Data Catalog includes website improvements and the addition of the database of Genotypes and Phenotypes (dbGaP).

SUBSCRIBE TO UPDATES

Categories

Archive