Introduction: Device-assisted enteroscopy (DAE) plays a major role in the investigation and endoscopic treatment of small bowel diseases. Recently, the implementation of artificial intelligence (AI) algorithms to gastroenterology has been the focus of great interest. Our aim was to develop an AI model for the automatic detection of protruding lesions in DAE images.
Methods: A deep learning algorithm based on a convolutional neural network was designed. Each frame was evaluated for the presence of enteric protruding lesions. The area under the curve, sensitivity, specificity, and positive and negative predictive values were used to assess the performance of the convolutional neural network.
Results: A total of 7,925 images from 72 patients were included. Our model had a sensitivity and specificity of 97.0% and 97.4%, respectively. The area under the curve was 1.00.
Discussion: Our model was able to efficiently detect enteric protruding lesions. The development of AI tools may enhance the diagnostic capacity of deep enteroscopy techniques.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9400931 | PMC |
| http://dx.doi.org/10.14309/ctg.0000000000000514 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Atypical anal itching lesion associated with a protruding rectal polyp.
Acta Gastroenterol Belg
January 2024
Abdominal Surgery department, Clinique Saint-Pierre Ottignies, Ottignies-Louvain-la-Neuve, Belgium.
A new anatomical finding: the paramastoid diverticulum of the sigmoid sinus.
Surg Radiol Anat
December 2024
Division of Anatomy, Faculty of Dentistry, "Carol Davila" University of Medicine and Pharmacy, Bucharest, 020021, Romania.
Purpose: The sigmoid sinus (SS) is a major surgical landmark. The paramastoid process (PMP) occurs rarely. Inferior diverticula of the SS were not found or reported previously.
View Article and Find Full Text PDFMinimal-invasive, image guided, 360-degree resection of ilio-lumbo-sacral ostechondroma, planned on the 3D model in a child with hereditary multiple ostechondroma (HMO).
Eur Spine J
December 2024
Department of Orthopedics, Umeå University Hospital, Umeå, Sweden.
Background: Hereditary Multiple Osteochondromas (HMO), previously known as Multiple Hereditary Exostoses (MHE), is a genetic disorder characterized by the formation of multiple, benign, exostoses (osteochondromas) growing from the metaphyseal region of long bones as well as from the axial skeleton. Lesions originating from the lumbar spine region are rare, and are most common growing from the posterior element of the vertebrae. HMO associated osteochondromas are difficult to treat due to continuous and incontrollable growth of these lesions and a lifetime risk for malignant transformation.
View Article and Find Full Text PDFIntraosseous Ganglion Protruding Into the Spinoglenoid Notch With Suprascapular Nerve Entrapment: A Case Report.
Cureus
November 2024
Department of Orthopaedic Surgery, Iwaki City Medical Center, Iwaki, JPN.
Suprascapular nerve entrapment caused by intraosseous cystic lesions is a rare condition. We present the case of a 49-year-old man with right shoulder numbness, slight infraspinatus (ISP) weakness, and shoulder pain. He underwent open surgery and arthroscopic evaluation.
View Article and Find Full Text PDFMagnetic resonance imaging features of uterine adenosarcoma: case series and systematic review.
Abdom Radiol (NY)
December 2024
Department of Radiology, The Jikei University School of Medicine, Tokyo, Japan.
Objectives: To comprehensively summarize the characteristics of magnetic resonance imaging (MRI) findings of uterine adenosarcoma through a systematic review and case series analysis.
Methods: A literature search was conducted in MEDLINE, Scopus, and Embase databases on June 3, 2024. In total, 25 cases from 23 articles were selected, and five cases from the authors' institution were included.
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!