US 12,272,057 B2
System for visual data analysis of ultrasound examinations with and without a contrast medium, for early automated diagnostics of pancreatic pathologies
Aiste Kielaite-Gulla, Vilnius (LT); Renaldas Raisutis, Kaunas (LT); Kestutis Strupas, Vilnius (LT); and Arturas Samuilis, Vilnius (LT)
Assigned to Vilnius University, Vilnius (LT); and Kaunas University of Technology, Kaunas (LT)
Appl. No. 18/016,461
Filed by Vilnius University, Vilnius (LT); and Kaunas University of Technology, Vilnius (LT)
PCT Filed Jul. 16, 2021, PCT No. PCT/IB2021/056443
§ 371(c)(1), (2) Date Jan. 17, 2023,
PCT Pub. No. WO2022/013832, PCT Pub. Date Jan. 20, 2022.
Claims priority of application No. 2020 538 (LT), filed on Jul. 17, 2020.
Prior Publication US 2023/0281803 A1, Sep. 7, 2023
Int. Cl. G06T 7/00 (2017.01)
CPC G06T 7/0012 (2013.01) [G06T 2207/10132 (2013.01); G06T 2207/20081 (2013.01)] 11 Claims
OG exemplary drawing
 
1. A method of automated assessment of ultrasound images and data of a pancreatic tissue for automated diagnosis of pancreatic pathologies, the method comprising:
providing ultrasound images of a reflected ultrasound wave amplitude distribution in the pancreatic tissue in grey scale and contrast medium regimens, and in ultrasound scanning modes both without and with a contrast medium;
detecting a contour of the pancreatic region in said ultrasound images;
creating a multidimensional data module comprising said ultrasound images and the pancreas contour;
processing the multidimensional data module, using a database of characteristic pancreas ultrasound images and parameters, and applying a specialized machine learning software by:
i. determining from the ultrasound images obtained without and with the contrast medium, within the pancreas contour; a necrotic tissue region, and a set of quantitative parameters describing said necrotic region; a viable tissue region, and a set of quantitative parameters describing said viable region,
ii. determining, within the viable tissue region, at least one function of the contrast medium perfusion dynamics, by assessing the perfusion amplitude change-in-time after injecting the contrast medium; and a set of quantitative parameters describing said perfusion dynamics function,
iii. comparing said at least one perfusion dynamics function with perfusion dynamics in aorta and superior mesenteric artery, and therefrom establishing more than one viability levels of the pancreatic tissue within the viable region, and associating said perfusion dynamics function with a viability level, using the database of characteristic ultrasound images and parameters; and
iv. producing by a computer:
at least one perfusion dynamics function curve determined from the viable tissue region, the set of parameters describing said function, and the pancreatic tissue viability level associated with said function; and/or
an image of pancreas tissue in the contour, comprising at least a segment of the pancreas viable tissue associated with a viability level, whereas said viability level is determined from the perfusion dynamics function in that segment.