IP Library Granted Patent US 12,614,628
Granted Patent B2
US 12,614,628 · App. 18/080,886 · Granted Apr 28, 2026

Method for obtaining an indication about the image quality of a digital image

Inventor: Adriyana Danudibroto (Mortsel, BE)
Assignee: AGFA NV
G16H30/20G16H30/40
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,614,628
App. No.
18/080,886
Granted
Apr 28, 2026
Kind
B2
Abstract

The invention relates to a method to give an indication about the image quality of a digital image in comparison to what the expected image quality in terms of image content and technical image quality parameters would be for a similar exposure type. The method evaluates whether parameters of the acquired image such as noise and dynamic range match the expectations for the intended exposure type, and whether certain regions of interest are present and properly presented in the image.

Claims (17)

1 . A method of providing an indication about diagnostic image content quality of an acquired digital X-ray medical diagnostic image during an X-ray radiography acquisition workflow, as interpreted or evaluated by an experienced radiologist, said indication being dependent on body part information and view position information associated with said diagnostic image, the method comprising the steps of:

accessing said diagnostic image at a computing device,

obtaining body part information and view position information for said diagnostic image,

extracting multi-resolution features of various scale levels from said diagnostic image by a trained deep learning backbone network that comprises multi-resolution convolutional layers,

providing said multi-resolution features of various scale levels from said diagnostic image and said body part and view position information as input for a trained feature combination network, and

obtaining said indication about diagnostic image content quality as an output result of an image quality head of said trained feature combination network,

wherein said backbone network and feature combination network are trained simultaneously,

wherein the diagnostic image content quality indication is given by the image quality head as a score of each image content criteria acceptance level,

wherein the diagnostic image content quality includes an assessment of anatomical structure alignment in the X-ray medical diagnostic image, and

wherein the X-ray radiography acquisition workflow consists of a time during which a patient is in a radiology room.

2 . The method of claim 1 , wherein said body part information and view position information is obtained from an exam request that is associated with said diagnostic image and accessible from a radiology information system (RIS) on a computer device.

3 . The method of claim 1 , wherein said body part information and view position information is obtained from DICOM information stored with said diagnostic image.

4 . The method of claim 1 , wherein said body part information and view position information is obtained from a prediction of a trained deep learning model that receives said diagnostic image as an input.

5 . The method of claim 1 , wherein an additional network head of said feature combination network provides a prediction of said body part and view position associated with said diagnostic image.

6 . The method of claim 1 , wherein an additional network head of said feature combination network provides a prediction for a bounding box indicating a location of a region of interest associated with a body part of said diagnostic image.

7 . The method of claim 1 , wherein said backbone network and feature combination network are trained by supervised learning.

8 . The method of claim 1 , wherein said backbone network and feature combination network are trained by unsupervised learning.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 14, 2022
From: DANUDIBROTO, ADRIYANA
To: AGFA NV
Reel/Frame 062085/0327 →
Priority Claims (1)
EP 21214952 · Dec 16, 2021 · regional
Continuity (1)
Related Publication 20230197246A1 · Jun 22, 2023
References Cited (7)
US 10593041B1 · Shaw · 2020 [cited by applicant]
US 10799189B2 · Nye et al. · 2020 [cited by applicant]
US 20120269425A1 · Marchesotti · 2012 [cited by examiner]
US 20220405916A1 · Lu · 2022 [cited by examiner]
CN 112348059A · 2021 [cited by examiner]
Mairhöfer et al., “An AI-based Framework for Diagnostic Quality Assessment of Ankle Radiographs,” [cited by applicant]
Tan et al., “EfficientDet: Scalable and Efficient Object Detection,” Computer Vision Foundation, pp. 10781-10790 (2020). [cited by applicant]