Computer-implemented method and system for determining the fetus ventricular volume from diffusion-weighted magnetic resonance imaging, and related NMR ventricle volume assessment method

Patent metadata

Field	Value
Publication number	US-12450743-B2
Application number	US-202118255687-A
Country	US
Kind code	B2
Filing date	Nov 29, 2021
Priority date	Dec 4, 2020
Publication date	Oct 21, 2025
Grant date	Oct 21, 2025

Abstract

A computer-implemented method for determining a fetus ventricular volume from DWI images is provided. The computer-implemented method involves acquiring DWI images, with a pre-set voxel height, of a fetus ventricle, the acquisition being made with a single b-value selected in a range between 200 and 1000 s/mm 2 , selecting a ROI on each of the DWI images around the fetus ventricle, automatically clusterizing pixels in the ROI, obtaining clusterized DWI images, and calculating the fetus ventricular volume based on the number of pixels in the ROI for each of the DWI images and the pre-set voxel height. An NMR assessment system and an NMR assessment method implementing the method for determining the fetus ventricular volume are also provided.

First claim

What is claimed is:

1. A computer-implemented method for determining a fetus ventricular volume from magnetic resonance diffusion-weighted imaging (DWI) images, comprising:
A) acquiring DWI images, having a pre-set voxel height, of a fetus ventricle, wherein acquisition is made with a single b-value selected in a range between 200 and 1000 s/mm 2 ;
B) selecting a region of interest (ROI) on each of the DWI images around the fetus ventricle;
C) automatically clusterizing pixels in the ROI, obtaining clusterized DWI images; and
D) calculating the fetus ventricular volume based on the number of pixels in the ROI for each of the DWI images and the pre-set voxel height.

2. The computer-implemented method of claim 1 , wherein the single b-value is between 600 and 800 s/mm 2 .

3. The computer-implemented method of claim 1 , wherein step C) is performed by an expert algorithm.

4. The computer-implemented method of claim 1 , wherein step B) is performed by cutting out the DWI images so as to include portions of cerebral areas different from the fetus ventricle.

5. The computer-implemented method of claim 4 , wherein the portions of cerebral areas of the DWI images have a pixel intensity comparable to a pixel intensity of the fetus ventricle with respect to a same pre-set intensity scale.

6. The computer-implemented method of claim 1 , wherein step D) is performed by summing the number of ventricular pixels for each DWI image and multiplying a sum of the ventricular pixels by a voxel volume.

7. The computer-implemented method of claim 1 , wherein in step A) the DWI images are denoised, and realigned to remove motion artefacts.

8. The computer-implemented method of claim 1 , further comprising
E) measuring a ventricle diameter on the clusterized DWI images.

9. The computer-implemented method of claim 1 , wherein clusterization in step C) is performed by k-means.

10. The computer-implemented method of claim 9 , wherein a value of k is chosen in a range from 3 to 5.

11. The computer-implemented method of claim 10 , wherein the value of k is 4.

12. A non-transitory computer readable medium storing a computer program, comprising code means which, when executed by a computer, cause the computer to perform the method any of claim 1 .

13. A nuclear magnetic resonance (NMR) system, comprising an NMR images acquisition device and a computer connected to the NMR images acquisition device, wherein the computer is configured perform the method of claim 1 .

14. A nuclear magnetic resonance (NMR) assessment method, comprising:
acquiring a gestational age of a fetus;
performing on the fetus, by a computer, steps B)-D) of a method for determining a fetus ventricular volume from magnetic resonance diffusion-weighted imaging (DWI) images, comprising:
A) acquiring DWI images, having a pre-set voxel height, of a fetus ventricle, wherein acquisition is made with a single b-value selected in a range between 200 and 1000 s/mm 2 ;
B) selecting a region of interest (ROI) on each of the DWI images around the fetus ventricle;
C) automatically clusterizing pixels in the ROI, obtaining clusterized DWI images; and
D) calculating the fetus ventricular volume based on the number of pixels in the ROI for each of the DWI images and the pre-set voxel height,
wherein preliminarily in step B) DWI images including a representation of the fetus are taken from a computer memory; and
assessing a difference between the fetus ventricular volume as calculated and a reference curve of a ventricular volume of healthy fetuses as a function of the gestational age.

15. The computer-implemented method of claim 9 , wherein step B) is performed by cutting out the DWI images so as to include portions of cerebral areas different from the fetus ventricle.

Assignees

• Consiglio Nazionale Ricerche
• Univ Degli Studi Di Roma “La Sapienza”

Inventors

• Capuani Silvia
• Borrelli Mattia
• Pratesi Giacomo
• Di Trani Maria Giovanna
• Manganaro Lucia

Classifications

• G06T2207/30044

  Fetus; Embryo · CPC title

• G06T2207/30016

  Brain · CPC title

• G06T2207/20104

  Interactive definition of region of interest [ROI] · CPC title

• G06T2207/10088

  Magnetic resonance imaging [MRI] · CPC title

• G06T7/11

  Region-based segmentation · CPC title