Back to results
US 11,238,975 B2Granted
Computer aided diagnosis system for classifying kidneys
AssigneeUniversity of Louisville Research Foundation, Inc.
InventorsAyman S. El-Baz, Amy Dwyer, Ahmed Soliman, Mohamed Shehata, Hisham Abdeltawab, Fahmi Khalifa
Life of this patent
Estimating the term…
Abstract
A computer aided diagnostic system and automated method to classify a kidney utilizes medical image data and clinical biomarkers in evaluation of kidney function pre- and post-transplantation. The system receives image data from a medical scan that includes image data of a kidney, then segments kidney image data from other image data of the medical scan. The kidney is then classified by analyzing at least one feature determined from the kidney image data and the at least one clinical biomarker.
Claims23
A method for classifying a kidney, the method comprising:
- receiving image data associated with an abdomen scan that includes image data of a kidney;
- receiving at least one clinical biomarker;
- segmenting, with at least one processor of a computer, kidney image data associated with the kidney from other image data of the abdomen scan;
- and
- classifying the functionality of the kidney by analyzing at least one feature determined from the kidney image data and the at least one clinical biomarker;
- wherein segmenting kidney image data is based at least in part on a weighted probabilistic shape prior associated with the kidney, the weighted probabilistic shape prior based on a training set of kidney image data, and based at least in part on a Markov-Gibbs random field probabilistic model associated with the kidney.
3 more elements
A method for classifying a kidney, the method comprising:
- receiving image data associated with an abdomen scan that includes image data of a kidney;
- receiving at least one clinical biomarker;
- segmenting, with at least one processor of a computer, kidney image data associated with the kidney from other image data of the abdomen scan;
- and
- classifying the functionality of the kidney by analyzing at least one feature determined from the kidney image data and the at least one clinical biomarker;
- wherein classifying the functionality of the kidney includes classifying the kidney as one of an abnormal transplant or a normal transplant by analyzing the at least one clinical biomarker and at least one feature determined from the kidney image data using a learned model;
- further comprising classifying the abnormal transplant as acute rejection or different renal disease by analyzing the at least one clinical biomarker and at least one feature determined from the kidney image data using the learned model;
- further comprising classifying the acute rejection as T-cell mediated-rejection (TMR) or anti-body mediated-rejection (AMR) by analyzing the at least one clinical biomarker and at least one feature determined from the kidney image data using the learned model.
5 more elements
A system, comprising:
- at least one data processor;
- at least one memory;
- and
- program code stored on the at least one memory and configured to be executed by the at least one processor to cause the at least one processor to:
- receive image data associated with an abdomen scan that includes image data of a kidney;
- receive at least one clinical biomarker;
- segment, with at least one processor of a computer, kidney image data associated with the kidney from other image data of the abdomen scan based at least in part on a weighted probabilistic shape prior associated with the kidney, the weighted probabilistic shape prior based on a training set of kidney image data, and based at least in part on a Markov-Gibbs random field probabilistic model associated with the kidney;
- and
- classify the functionality of the kidney by analyzing at least one feature determined from the kidney image data and the at least one clinical biomarker.
6 more elements
A computer program product comprising:
- a non-transitory computer readable medium;
- and
- program code stored on the computer readable medium and configured upon execution by at least one processor to cause the at least one processor to:
- receive image data associated with an abdomen scan that includes image data of a kidney;
- receive at least one clinical biomarker;
- segment, with at least one processor of a computer, kidney image data associated with the kidney from other image data of the abdomen scan based at least in part on a weighted probabilistic shape associated with the kidney, the weighted probabilistic shape prior based on a training set of kidney image data, and based at least in part on a Markov-Gibbs random field probabilistic model associated with the kidney;
- and
- classify the functionality of the kidney by analyzing at least one feature determined from the kidney image data and the at least one clinical biomarker.
5 more elements
Dependencies are inferred from the claim text.