{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["37(5)"],"submitter":["Cakir M"],"pubmed_abstract":["Our study aims to evaluate the potential of a deep learning (DL) algorithm for differentiating the signal intensity of bone marrow between osteomyelitis (OM), Charcot neuropathic osteoarthropathy (CNO), and trauma (TR). The local ethics committee approved this retrospective study. From 148 patients, segmentation resulted in 679 labeled regions for T1-weighted images (comprising 151 CNO, 257 OM, and 271 TR) and 714 labeled regions for T2-weighted images (consisting of 160 CNO, 272 OM, and 282 TR). We employed both multi-class classification (MCC) and binary-class classification (BCC) approaches to compare the classification outcomes of CNO, TR, and OM. The ResNet-50 and the EfficientNet-b0 accuracy values were computed at 96.2% and 97.1%, respectively, for T1-weighted images. Additionally, "],"journal":["Journal of imaging informatics in medicine"],"pagination":["2454-2465"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11522243"],"repository":["biostudies-literature"],"pubmed_title":["Differential Diagnosis of Diabetic Foot Osteomyelitis and Charcot Neuropathic Osteoarthropathy with Deep Learning Methods."],"pmcid":["PMC11522243"],"pubmed_authors":["Aralasmak A","Tulum G","Cuce F","Yilmaz KB","Isik MI","Canbolat H","Cakir M"],"additional_accession":[]},"is_claimable":false,"name":"Differential Diagnosis of Diabetic Foot Osteomyelitis and Charcot Neuropathic Osteoarthropathy with Deep Learning Methods.","description":"Our study aims to evaluate the potential of a deep learning (DL) algorithm for differentiating the signal intensity of bone marrow between osteomyelitis (OM), Charcot neuropathic osteoarthropathy (CNO), and trauma (TR). The local ethics committee approved this retrospective study. From 148 patients, segmentation resulted in 679 labeled regions for T1-weighted images (comprising 151 CNO, 257 OM, and 271 TR) and 714 labeled regions for T2-weighted images (consisting of 160 CNO, 272 OM, and 282 TR). We employed both multi-class classification (MCC) and binary-class classification (BCC) approaches to compare the classification outcomes of CNO, TR, and OM. The ResNet-50 and the EfficientNet-b0 accuracy values were computed at 96.2% and 97.1%, respectively, for T1-weighted images. Additionally, ","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Oct","modification":"2026-07-15T17:47:24.198Z","creation":"2025-04-06T15:30:11.421Z"},"accession":"S-EPMC11522243","cross_references":{"pubmed":["38491234"],"doi":["10.1007/s10278-024-01067-0"]}}