An AI-based algorithm for the automatic evaluation of image quality in canine thoracic radiographs.

Sci Rep

Department of Animal Medicine, Production and Health, University of Padua, Viale dell'Università 16, 35020, Legnaro, Padua, Italy.

Published: October 2023

The aim of this study was to develop and test an artificial intelligence (AI)-based algorithm for detecting common technical errors in canine thoracic radiography. The algorithm was trained using a database of thoracic radiographs from three veterinary clinics in Italy, which were evaluated for image quality by three experienced veterinary diagnostic imagers. The algorithm was designed to classify the images as correct or having one or more of the following errors: rotation, underexposure, overexposure, incorrect limb positioning, incorrect neck positioning, blurriness, cut-off, or the presence of foreign objects, or medical devices. The algorithm was able to correctly identify errors in thoracic radiographs with an overall accuracy of 81.5% in latero-lateral and 75.7% in sagittal images. The most accurately identified errors were limb mispositioning and underexposure both in latero-lateral and sagittal images. The accuracy of the developed model in the classification of technically correct radiographs was fair in latero-lateral and good in sagittal images. The authors conclude that their AI-based algorithm is a promising tool for improving the accuracy of radiographic interpretation by identifying technical errors in canine thoracic radiographs.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10562412PMC
http://dx.doi.org/10.1038/s41598-023-44089-4DOI Listing

Publication Analysis

Top Keywords

thoracic radiographs
16
ai-based algorithm
12
canine thoracic
12
sagittal images
12
image quality
8
technical errors
8
errors canine
8
thoracic
5
radiographs
5
algorithm
5

Similar Publications

Introduction: There is no consensus on postoperative thoracostomy tube management in thoracic patients, specifically whether or not a chest radiograph is required after tube removal.

Methods: Retrospective review of video-assisted thoracoscopic (VATS) lobectomy patients was performed at a large tertiary referral center from January 1, 2019 to December 31, 2020. Patients were grouped as asymptomatic or symptomatic after thoracostomy removal.

View Article and Find Full Text PDF

Background: Degenerative lumbar scoliosis (DLS) represents a distinct subset of adult spinal deformity, frequently co-occurring with thoracolumbar kyphosis (TLK) in the sagittal plane. TLK is typically viewed as detrimental in degenerative spinal conditions and has been linked to increased pain severity and a higher prevalence of mechanical complications (MC) as previously reported. The present study aimed to identify the risk factors associated with the development of MC in patients with DLS and concomitant TLK.

View Article and Find Full Text PDF

Cytomegalovirus (CMV) infection is one of the most common congenital infections. We present a case of an infant who presented with respiratory distress since birth with a normal antenatal history. The infant had bilateral pleural effusion.

View Article and Find Full Text PDF

Anterior Uveitis and Uveal Depigmentation in a Dog With Vitiligo.

Case Rep Vet Med

January 2025

Department of Population Medicine and Diagnostic Sciences, College of Veterinary Medicine, Cornell University, Ithaca, New York, USA.

The objective of this study is to describe the clinical and histologic features of a dog that developed anterior uveitis and uveal depigmentation in association with vitiligo. A 3-year-old, female-spayed, Bernese Mountain Dog with a history of bilateral idiopathic anterior uveitis developed iris depigmentation, leukotrichia, and skin depigmentation. The initial diagnostic evaluation for uveitis was unremarkable, including general bloodwork, urinalysis, infectious disease testing, thoracic radiographs, and abdominal ultrasound.

View Article and Find Full Text PDF

To determine whether relative anterior spinal overgrowth (RASO) occurs regardless of scoliosis segments and severity, and to explore the pattern of vertebral body height changes in adolescent idiopathic scoliosis (AIS). A total of 125 AIS and 179 non-scoliotic adolescents were enrolled. The anterior vertebral body height (VBHa) and posterior vertebral body height (VBHp) were measured on lateral spine radiographs, and the VBHa/VBHp ratio was calculated.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!