AI-Based Radiomics Method for Predicting Disease Onset

ChangeBridge: Patent Apps - Health Informatics (G16H)

Detected March 26th, 2026

Summary

The USPTO has published a patent application (US20260088170A1) detailing an AI-based radiomics method for predicting human disease onset using neural networks and color space analysis. The application, filed by Shubham Chandra, describes a non-invasive approach combining CNNs with CIELAB color space transformation for early disease detection and personalized diagnostics.

View original document View source feed page

What changed

This document is a published patent application (US20260088170A1) from the USPTO, not a final rule or guidance. It describes a novel radiomics-based method for predicting the onset of human diseases using artificial intelligence, specifically Convolutional Neural Networks (CNNs) and CIELAB color space analysis. The method aims to enhance early disease detection by processing medical images (CT, MRI, X-ray) to identify abnormalities and predict disease likelihood, generating reports with heatmaps and probability scores.

While this is a patent application and not a regulatory mandate, it signifies innovation in health informatics and AI-driven diagnostics. Compliance officers in the healthcare and medical device sectors should be aware of such technological advancements as they may influence future regulatory considerations, product development, and clinical practice standards. No immediate compliance actions are required based on this patent application.

Source document (simplified)

← USPTO Patent Applications

RADIOMICS BASED METHOD FOR PREDICTING THE ONSET OF HUMAN DISEASES USING NEURAL NETWORKS AND COLOR SPACE ANALYSIS

Application US20260088170A1 Kind: A1 Mar 26, 2026

Inventors

SHUBHAM CHANDRA

Abstract

The present invention provides a radiomics-based method and system for predicting the onset of human diseases using medical imaging and advanced machine learning techniques. This non-invasive approach combines Convolutional Neural Networks (CNNs) with pseudo-color transformation in the CIELAB color space to enhance early disease detection. The method begins by acquiring grayscale medical images from diagnostic techniques such as CT, MRI, or X-ray, followed by CNN-based feature extraction to identify clinically relevant regions of interest. These regions are then converted into pseudo-color representations using the CIELAB color space, improving tissue contrast and visualization of subtle abnormalities. A machine learning classifier is applied to the pseudo-colored images to predict the likelihood of disease onset, generating an output report that includes a heatmap, probability score, and diagnostic recommendations. The invention offers a fully automated process that facilitates early detection, improved visualization, and personalized diagnostics, providing a versatile solution for various medical conditions.

CPC Classifications

G16H 50/20 G06T 3/4046 G06T 5/60 G06T 5/94 G06T 7/0014 G06T 7/11 G06T 7/90 G06T 11/10 G06T 11/26 G06V 10/25 G06V 10/764 G06V 10/82 A61B 6/032 A61B 6/501 G06T 2207/10024 G06T 2207/20076 G06T 2207/20081 G06T 2207/20084 G06T 2207/20132 G06T 2207/30016 G06T 2207/30096 G06T 2210/41 G06V 2201/031