Deep-learning-based hepatic fat assessment
Inventors
Modanwal, Gourav • Al-Kindi, Sadeer • Walker, Jonathan • Dhamdhere, Rohan • Rajagopalan, Sanjay • Madabhushi, Anant
Assignees
Emory University • Case Western Reserve University • University Hospitals Cleveland Medical Center
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12530770-B2
Publication Date
2026-01-20
Expiration Date
Abstract
The present disclosure relates to a method. The method includes accessing automatically segmented liver data and automatically segmented spleen data from a patient. The automatically segmented liver data is used to determine a liver attenuation and the automatically segmented spleen data is used to determine a spleen attenuation. A liver-to-spleen attenuation ratio is determined from the liver attenuation and the spleen attenuation. A hepatic steatosis determination is made from the liver-to-spleen attenuation ratio.
Core Innovation
The invention accesses automatically segmented liver data and automatically segmented spleen data from a patient, where the automatically segmented liver data includes a region of interest from a digitized image of a liver and the automatically segmented spleen data includes a region of interest from a digitized image of a spleen. It utilizes the automatically segmented liver data to determine a liver attenuation and utilizes the automatically segmented spleen data to determine a spleen attenuation. It then determines a liver-to-spleen attenuation ratio from the liver attenuation and the spleen attenuation.
The invention further makes a hepatic steatosis determination from the liver-to-spleen attenuation ratio. It supports attenuation measurement based on slice-based estimation or volume-based estimation, including determining mean attenuation for the entire liver and the entire spleen. It also supports generating the hepatic steatosis determination by comparing the liver-to-spleen attenuation ratio to an hepatic steatosis threshold.
The invention also includes generating hepatic steatosis-related outputs by operating one or more deep learning models on computed tomography (CT) images comprising a liver and a spleen to segment the liver and spleen and generate automatically segmented liver data and automatically segmented spleen data. In an apparatus form, it includes an attenuation calculation tool configured to measure liver attenuation, measure spleen attenuation, and determine the liver-to-spleen attenuation ratio, and a hepatic steatosis calculation tool configured to generate the hepatic steatosis (HS) determination by comparing the ratio to the threshold.
Claims Coverage
The partial content provided includes three independent claims. They cover: (i) a method from automatically segmented liver/spleen ROIs through attenuation and a liver-to-spleen ratio to a hepatic steatosis determination, (ii) a non-transitory computer-readable medium implementing deep learning segmentation and the same attenuation/ratio/HS determination operations, and (iii) an apparatus with deep learning models plus an attenuation calculation tool and a hepatic steatosis calculation tool that compares the ratio to an HS threshold.
Automatically segmented liver and spleen regions for attenuation and hepatic steatosis determination
Accessing automatically segmented liver data and automatically segmented spleen data from a patient, determining a liver attenuation using the automatically segmented liver data and a spleen attenuation using the automatically segmented spleen data, determining a liver-to-spleen attenuation ratio from the liver attenuation and the spleen attenuation, and making a hepatic steatosis determination from the liver-to-spleen attenuation ratio.
Deep learning segmentation and hepatic steatosis determination from a liver-to-spleen attenuation ratio
Operating one or more deep learning models on one or more computed tomography (CT) images comprising a liver and a spleen to segment the liver and generate automatically segmented liver data and to segment the spleen and generate automatically segmented spleen data; measuring a liver attenuation from the automatically segmented liver data; measuring a spleen attenuation from the automatically segmented spleen data; determining a liver-to-spleen attenuation ratio from the liver attenuation and the spleen attenuation; and generating a hepatic steatosis determination from the liver-to-spleen attenuation ratio.
Attenuation calculation tool and hepatic steatosis calculation tool using an hepatic steatosis threshold
Including one or more deep learning models configured to operate upon one or more digitized images that include a liver and a spleen to generate automatically segmented liver data and automatically segmented spleen data; an attenuation calculation tool configured to utilize the automatically segmented liver data to measure a liver attenuation, to utilize the automatically segmented spleen data to measure a spleen attenuation, and to determine a liver-to-spleen attenuation ratio from the liver attenuation and the spleen attenuation; and a hepatic steatosis calculation tool configured to generate a hepatic steatosis (HS) determination by comparing the liver-to-spleen attenuation ratio to an hepatic steatosis threshold.
Across the independent claims, the core inventive coverage is the combination of automatically segmented liver and spleen data with attenuation measurements, computation of a liver-to-spleen attenuation ratio, and a hepatic steatosis determination derived from that ratio (including generation by comparison to an hepatic steatosis threshold). The claims further specify a deep-learning-based segmentation step on digitized CT images and implement the workflow either as a method, a computer-readable medium, or an apparatus with dedicated tools.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Generating a risk assessment metric from a hepatic steatosis determination, wherein the risk assessment metric corresponds to expected COVID symptom severity and assigning a patient care level based on that metric.
Providing a COVID severity metric and a cardiovascular disease metric based on the hepatic steatosis determination.
Interested in licensing this patent?