Enhancing knee MRI bone marrow lesion detection with artificial intelligence: An external validation study

Background: Magnetic resonance imaging (MRI) is a sensitive imaging modality for identifying knee bone marrow edema, a significant biomarker in osteoarthritis and injury assessment. The precision of bone marrow edema detection is contingent upon the radiologist's expertise, and segmentation eff...

Full description

Saved in:
Bibliographic Details
Main Authors: Kevin Maarek, Philippine Cordelle, Tom Vesoul, Pascal Zille, Gaspard d'Assignies, Antoine Feydy, Guillaume Herpe
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Research in Diagnostic and Interventional Imaging
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772652525000067
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239284060520448
author Kevin Maarek
Philippine Cordelle
Tom Vesoul
Pascal Zille
Gaspard d'Assignies
Antoine Feydy
Guillaume Herpe
author_facet Kevin Maarek
Philippine Cordelle
Tom Vesoul
Pascal Zille
Gaspard d'Assignies
Antoine Feydy
Guillaume Herpe
author_sort Kevin Maarek
collection DOAJ
description Background: Magnetic resonance imaging (MRI) is a sensitive imaging modality for identifying knee bone marrow edema, a significant biomarker in osteoarthritis and injury assessment. The precision of bone marrow edema detection is contingent upon the radiologist's expertise, and segmentation efficiency demands substantial time. Purpose: This study evaluated artificial intelligence's (AI) impact on enhancing general radiologists' diagnostic accuracy for bone marrow edema detection in knee MRI. Materials and methods: A multicenter, multireader, multicase methodology was used in this retrospective diagnostic study, which relied on an external dataset of 198 examinations. Mean age was 46 years with a standard deviation (SD) of 15.8 years and a female/male ratio of 49 %/51 %.An AI algorithm from the AI solution Keros, comprising three orientation-specific 3D-UNet models, was deployed for bone marrow edema segmentation on T2/proton density with fat suppression sequences.The ground truth was set by expert musculoskeletal radiologists.The purpose was to externally validate the AI algorithm and compare the performance and speed of bone marrow edema identification by less experienced radiologists when using the algorithm versus not using it Results: A total of 184 patients were included. With AI, readers’ sensitivity for bone marrow edema detection significantly increased by 6.1 % from 79.3 % without AI (95 % confidence interval [95 % CI]: 77.2–80.3 %) to 85.4 % (95 % CI: 84–86.2 %) with AI (p = 0). Specificity significantly increased by 5 % with AI assistance, reaching 93.9 % (95 % CI: 93.7–94.6 %) from 88.9 % (95 % CI: 88.6–89.4 %) (p = 0). Reading times were reduced by 42 % (0.66 min per exam, p = 3.81e-41). Conclusion: AI significantly increased the sensitivity and specificity of bone marrow edema detection for general radiologists and shortened the reading process. AI-assisted detection of bone edema in the knee also opens up new perspectives for the longitudinal monitoring of patients with knee osteoarthritis.
format Article
id doaj-art-372a0cb3593d4f0d8052e4ac4f22d467
institution Kabale University
issn 2772-6525
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Research in Diagnostic and Interventional Imaging
spelling doaj-art-372a0cb3593d4f0d8052e4ac4f22d4672025-08-20T04:01:03ZengElsevierResearch in Diagnostic and Interventional Imaging2772-65252025-09-011510006310.1016/j.redii.2025.100063Enhancing knee MRI bone marrow lesion detection with artificial intelligence: An external validation studyKevin Maarek0Philippine Cordelle1Tom Vesoul2Pascal Zille3Gaspard d'Assignies4Antoine Feydy5Guillaume Herpe6Université de Paris, 85, boulevard Saint-Germain, 75006 Paris, France; Corresponding author.Incepto Medical, Paris, FranceIncepto Medical, Paris, FranceIncepto Medical, Paris, FranceGroupe hospitalier du Havre, 76083 Le Havre, FranceHôpital Cochin, 27, rue du Faubourg-Saint-Jacques, 75016 Paris, FranceCHU de Poitiers, 2, rue de la Milétrie, 86000 Poitiers, FranceBackground: Magnetic resonance imaging (MRI) is a sensitive imaging modality for identifying knee bone marrow edema, a significant biomarker in osteoarthritis and injury assessment. The precision of bone marrow edema detection is contingent upon the radiologist's expertise, and segmentation efficiency demands substantial time. Purpose: This study evaluated artificial intelligence's (AI) impact on enhancing general radiologists' diagnostic accuracy for bone marrow edema detection in knee MRI. Materials and methods: A multicenter, multireader, multicase methodology was used in this retrospective diagnostic study, which relied on an external dataset of 198 examinations. Mean age was 46 years with a standard deviation (SD) of 15.8 years and a female/male ratio of 49 %/51 %.An AI algorithm from the AI solution Keros, comprising three orientation-specific 3D-UNet models, was deployed for bone marrow edema segmentation on T2/proton density with fat suppression sequences.The ground truth was set by expert musculoskeletal radiologists.The purpose was to externally validate the AI algorithm and compare the performance and speed of bone marrow edema identification by less experienced radiologists when using the algorithm versus not using it Results: A total of 184 patients were included. With AI, readers’ sensitivity for bone marrow edema detection significantly increased by 6.1 % from 79.3 % without AI (95 % confidence interval [95 % CI]: 77.2–80.3 %) to 85.4 % (95 % CI: 84–86.2 %) with AI (p = 0). Specificity significantly increased by 5 % with AI assistance, reaching 93.9 % (95 % CI: 93.7–94.6 %) from 88.9 % (95 % CI: 88.6–89.4 %) (p = 0). Reading times were reduced by 42 % (0.66 min per exam, p = 3.81e-41). Conclusion: AI significantly increased the sensitivity and specificity of bone marrow edema detection for general radiologists and shortened the reading process. AI-assisted detection of bone edema in the knee also opens up new perspectives for the longitudinal monitoring of patients with knee osteoarthritis.http://www.sciencedirect.com/science/article/pii/S2772652525000067RadiologyBone marrow edemaOsteoarthritisArtificial intelligenceRetrospective study
spellingShingle Kevin Maarek
Philippine Cordelle
Tom Vesoul
Pascal Zille
Gaspard d'Assignies
Antoine Feydy
Guillaume Herpe
Enhancing knee MRI bone marrow lesion detection with artificial intelligence: An external validation study
Research in Diagnostic and Interventional Imaging
Radiology
Bone marrow edema
Osteoarthritis
Artificial intelligence
Retrospective study
title Enhancing knee MRI bone marrow lesion detection with artificial intelligence: An external validation study
title_full Enhancing knee MRI bone marrow lesion detection with artificial intelligence: An external validation study
title_fullStr Enhancing knee MRI bone marrow lesion detection with artificial intelligence: An external validation study
title_full_unstemmed Enhancing knee MRI bone marrow lesion detection with artificial intelligence: An external validation study
title_short Enhancing knee MRI bone marrow lesion detection with artificial intelligence: An external validation study
title_sort enhancing knee mri bone marrow lesion detection with artificial intelligence an external validation study
topic Radiology
Bone marrow edema
Osteoarthritis
Artificial intelligence
Retrospective study
url http://www.sciencedirect.com/science/article/pii/S2772652525000067
work_keys_str_mv AT kevinmaarek enhancingkneemribonemarrowlesiondetectionwithartificialintelligenceanexternalvalidationstudy
AT philippinecordelle enhancingkneemribonemarrowlesiondetectionwithartificialintelligenceanexternalvalidationstudy
AT tomvesoul enhancingkneemribonemarrowlesiondetectionwithartificialintelligenceanexternalvalidationstudy
AT pascalzille enhancingkneemribonemarrowlesiondetectionwithartificialintelligenceanexternalvalidationstudy
AT gasparddassignies enhancingkneemribonemarrowlesiondetectionwithartificialintelligenceanexternalvalidationstudy
AT antoinefeydy enhancingkneemribonemarrowlesiondetectionwithartificialintelligenceanexternalvalidationstudy
AT guillaumeherpe enhancingkneemribonemarrowlesiondetectionwithartificialintelligenceanexternalvalidationstudy