AI Tool Combines Lung Screening CT with Clinical Data to Predict Lung Cancer without Radiologist Assistance
By MedImaging International staff writers Posted on 28 Oct 2021 |
A new artificial intelligence (AI)-based model that combines lung screening computed tomography (CT) information with clinical data has been shown to better predict lung cancer without the need for manual reading.
The deep learning tool built by scientists at the Vanderbilt University (Nashville, TN, USA) integrates CT features such as nodule size and risk factors including age, pack-years smoked, cancer history, among others. The scientists developed and tested the co-learning model on exams of more than 23,000 patients and found that it outperformed risk models utilizing clinical or imaging data alone, including the popular Brock model.
The scientists developed the deep learning tool by applying a five-fold cross-validation approach to data of 23,505 patients from the National Lung Screening Trial. The team used screening data from close to 150 patients in an in-house program for external testing. The scientists found that the deep learning tool notched an area under the receiver operating characteristic curve score of 0.88, which was higher than published models dependent completely on imaging data (0.86) and clinical risk factors (0.69).
More importantly, the deep learning tool automatically pulls high-risk regions from CT exams without the need for any effort by the radiologist. However, gathering clinical data does involve manual effort from radiologists and physicians. The scientists believe that their co-learning approach could be particularly beneficial as more patients start to qualify for screening exams and the insights from the tool could find low-risk individuals to be actually high-risk.
“Risk estimation among lung screening participants will become even more important with the impending expansion of screening guidelines to include those patients who are considered lower risk only based on age and history of tobacco use,” stated Riqiang Gao, a PhD student in computer science at Vanderbilt University. “The role of [the] radiologist is still irreplaceable in terms of looking for and reporting clinically significant findings (emphysema, pulmonary fibrosis, atelectasis, etc.).”
Related Links:
Vanderbilt University
Latest General/Advanced Imaging News
- Bone Density Test Uses Existing CT Images to Predict Fractures
- AI Predicts Cardiac Risk and Mortality from Routine Chest CT Scans
- Radiation Therapy Computed Tomography Solution Boosts Imaging Accuracy
- PET Scans Reveal Hidden Inflammation in Multiple Sclerosis Patients
- Artificial Intelligence Evaluates Cardiovascular Risk from CT Scans
- New AI Method Captures Uncertainty in Medical Images
- CT Coronary Angiography Reduces Need for Invasive Tests to Diagnose Coronary Artery Disease
- Novel Blood Test Could Reduce Need for PET Imaging of Patients with Alzheimer’s
- CT-Based Deep Learning Algorithm Accurately Differentiates Benign From Malignant Vertebral Fractures
- Minimally Invasive Procedure Could Help Patients Avoid Thyroid Surgery
- Self-Driving Mobile C-Arm Reduces Imaging Time during Surgery
- AR Application Turns Medical Scans Into Holograms for Assistance in Surgical Planning
- Imaging Technology Provides Ground-Breaking New Approach for Diagnosing and Treating Bowel Cancer
- CT Coronary Calcium Scoring Predicts Heart Attacks and Strokes
- AI Model Detects 90% of Lymphatic Cancer Cases from PET and CT Images
- Breakthrough Technology Revolutionizes Breast Imaging