We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us
GLOBETECH PUBLISHING LLC

Download Mobile App




AI System Combines CT Imaging with Clinical and Genetic Data for Early Lung Cancer Detection

By MedImaging International staff writers
Posted on 20 Feb 2024
Image: A new study suggests CT imaging with automated AI system can predict EGFR genotype (Photo courtesy of 123RF)
Image: A new study suggests CT imaging with automated AI system can predict EGFR genotype (Photo courtesy of 123RF)

Lung carcinoma prognosis has evolved significantly with the discovery of molecular targets and their corresponding treatments. Specifically, mutations in the Epidermal Growth Factor Receptor (EGFR) gene, found in lung carcinoma, serve as key targets for specialized therapies. However, in countries with limited resources like India, advanced testing methods such as next-generation sequencing remain inaccessible for widespread use. Challenges also include obtaining sufficient tissue from lung core biopsies and dealing with the inherent intratumoral heterogeneity that complicates the identification of suitable tumor tissues. Now, researchers have demonstrated that an AI-based system can automatically detect and analyze lung nodule features from CT images, predicting the likelihood of EGFR mutations. This innovation aids oncologists and patients in resource-limited settings by providing near-optimal care and guiding appropriate treatment decisions.

Previous studies leveraging AI with CT imaging have shown promise in categorizing and analyzing lung nodules without incurring additional costs. However, most of these methods have focused solely on nodule detection in CT images. Moreover, while AI has been used to extract comprehensive lung information for predicting EGFR genotype and evaluating responses to targeted lung cancer therapy, such efforts have predominantly been centered on White and Chinese populations. With a primary focus on the Indian population, researchers led by the Rajiv Gandhi Cancer Institute and Research Centre (New Delhi, India) set out to develop an AI-based strategy that could not only detect but also characterize lung nodules, indicating the EGFR mutational status in lung carcinoma patients. This would help triage patients requiring extensive molecular profiling of the EGFR-driver gene.

The team created a fully automated AI-based Predictive System (AIPS) using machine learning (ML) and deep learning (DL) algorithms. This system can detect lung nodule features from CT images and assess the probability of an EGFR mutation, thus eliminating the need for time-consuming image annotation by radiologists and complex feature engineering. In addition to incorporating EGFR gene sequencing and CT imaging data from 2277 lung carcinoma patients across three cohorts in India and a White population cohort from TCIA, the researchers used the LIDC-IDRI cohort to train the AIPS-Nodule (AIPS-N) model. This model automatically detects and characterizes lung nodules. The AIPS-N model's combination with clinical factors in the AIPS-Mutation (AIPS-M) model was evaluated for its effectiveness in predicting the EGFR genotype, achieving area under the curve (AUC) values ranging from 0.587 to 0.910. The AIPS-N successfully detected nodules with an average AP50 of 70.19% and predicted scores for five lung nodule properties. This research suggests that CT imaging combined with an automated lung-nodule analysis AI system can non-invasively and cost-effectively predict EGFR genotype, identifying patients with EGFR mutations.

Related Links:
Rajiv Gandhi Cancer Institute and Research Centre

Ultrasound Table
Women’s Ultrasound EA Table
Digital X-Ray Detector Panel
Acuity G4
Portable Color Doppler Ultrasound Scanner
DCU10
Digital Intelligent Ferromagnetic Detector
Digital Ferromagnetic Detector

Channels

Ultrasound

view channel
Image: The new implantable device for chronic pain management is small and flexible (Photo courtesy of The Zhou Lab at USC)

Wireless Chronic Pain Management Device to Reduce Need for Painkillers and Surgery

Chronic pain affects millions of people globally, often leading to long-term disability and dependence on opioid medications, which carry significant risks of side effects and addiction.... Read more

Nuclear Medicine

view channel
Image: The diagnostic tool could improve diagnosis and treatment decisions for patients with chronic lung infections (Photo courtesy of SNMMI)

Novel Bacteria-Specific PET Imaging Approach Detects Hard-To-Diagnose Lung Infections

Mycobacteroides abscessus is a rapidly growing mycobacteria that primarily affects immunocompromised patients and those with underlying lung diseases, such as cystic fibrosis or chronic obstructive pulmonary... Read more

Imaging IT

view channel
Image: The new Medical Imaging Suite makes healthcare imaging data more accessible, interoperable and useful (Photo courtesy of Google Cloud)

New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible

Medical imaging is a critical tool used to diagnose patients, and there are billions of medical images scanned globally each year. Imaging data accounts for about 90% of all healthcare data1 and, until... Read more
Copyright © 2000-2025 Globetech Media. All rights reserved.