# US 10,373,310 B2 · Method for analyzing data provided by magnetic resonance imaging with dynamic administration of contrast medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,373,310 B2
- Document ID: US10373310B2
- Status: Granted
- Kind: B2
- Application number: 15/100,311
- Filed: 2014-11-28
- Published: 2016-10-13
- Granted: 2019-08-06
- Earliest claimed: 2013-11-29
- Assignees: Istituto Nazionale Tumori—Fondazione G. Pascale
- Applicants: Istituto Nazionale Tumori—Fondazione G. Pascale
- Inventors: Antonella Petrillo; Roberta Fusco
- Web page: https://patentgrep.com/patent/US10373310B2

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G01R 33/5601: {involving use of a contrast agent for contrast manipulation, e.g. a paramagnetic, super-paramagnetic, ferromagnetic or hyperpolarised contrast agent}
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/30028: Colon; Small intestine
- G06T 2207/30096: Tumor; Lesion
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)

## Abstract

Method for analyzing data provided by Magnetic Resonance Imaging with dynamic administration of contrast medium in patients with locally advanced rectal cancer, after neoadjuvant radio-chemotherapy, comprising: making available pre- and post-treatment digital images, having one or more regions of interest identified; splitting the regions of interest into portions; calculating first and second time-intensity curves for each portion of the regions of pre- and post-treatment interest, respectively; calculating the maximum signal difference and gradient of the wash-out section for the curves calculated; calculating the median value of the maximum signal difference and of the gradient calculated; calculating the percentage variation between the median values of the maximum signal difference and of the gradient of the wash-out section calculated for each of the first and second curves; linearly combining percentage variations of the maximum signal difference and of the gradient of the wash-out section, to define a relative linear classification index.

## Claims

### Claim 1

Method for the analysis of data provided by Magnetic Resonance Imaging with dynamic administration of a contrast medium, called DCE-MRI, in patients suffering from locally advanced rectal cancer, after neoadjuvant radio-chemotherapy treatment, comprising the phases of:
making available pre-treatment digital images obtained by means of said DCE-MRI performed on the patient before he/she undergoes radio-chemotherapy treatment, wherein in each pre-treatment digital image there are identified one or more regions of pre-treatment interest, which identify the outlines of the tumour, the outlines being traced by an operator;
making available post-treatment digital images obtained by means of said DCE-MRI performed on the patient after he/she has undergone radio-chemotherapy treatment, wherein in each post-treatment digital image there are identified one or more regions of post-treatment interest, which identify the outlines of the residual tumour;
splitting said regions of pre- and post-treatment interest into a plurality of portions;
calculating a first set of time-intensity curves for each of said portions of the regions of pre-treatment interest and a second set of time-intensity curves for each of said portions of the regions of post-treatment interest;
calculating the maximum signal difference and the gradient of the wash-out section for each of said first and said second curves so calculated, the gradient of the wash-out section being the section of curve that represents the excretion phase of the contrast medium and that corresponds to the portion which starts at the point where the signal is strongest;
for each digital image, calculating the median value of the maximum signal difference and of the gradient of the wash-out section calculated for said first and for said second curves;
for each set of curves, calculating the percentage variation between the median values of the maximum signal difference and the median values of the gradient of the wash-out section calculated for said first set of curves, and between the median values of the maximum signal difference and the median values of the gradient of the wash-out section calculated for said second set of curves;
across multiple digital images, linearly combining said percentage variation between the median values of the maximum signal difference and said percentage variation between the median values of the gradient of the wash-out section, to define a relative linear classification index;
wherein said relative linear classification index is calculated with the following formula αΔMSD+βΔWOS, where ΔMSD corresponds to said percentage variation of the maximum signal difference, ΔWOS corresponds to said percentage variation of the gradient of the wash-out section, α is a number between 0.5 and 1 and β is a number between 0.5 and 1 and wherein a first cut-off value of said relative linear classification index is between −2% and −4%.

### Claim 2 (depends on 1)

Method according to claim 1, wherein α is 0.778.

### Claim 3 (depends on 1)

Method according to claim 1, wherein β is 0.6157.

### Claim 4 (depends on 1)

Method according to claim 1, wherein said first cut-off value is −3%.

### Claim 5 (depends on 1)

Method according to claim 1, wherein a second cut-off value of said relative linear classification index is between 40% and 60%.

### Claim 6 (depends on 5)

Method according to claim 5, wherein said second cut-off value is 50%.

### Claim 7 (depends on 1)

Method according to claim 1, wherein said portions of the regions of pre- and post-treatment interest correspond to each pixel of the regions themselves.