A comprehensive deep learning approach to improve enchondroma detection on X-ray images

Abstract An enchondroma is a benign neoplasm of mature hyaline cartilage that proliferates from the medullary cavity toward the cortical bone. This results in the formation of a significant endogenous mass within the medullary cavity. Although enchondromas are predominantly asymptomatic, they may ex...

Full description

Saved in:
Bibliographic Details
Main Authors: Ayhan Aydin, Caner Ozcan, Safak Aydın Simsek, Ferhat Say
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-07978-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226390820356096
author Ayhan Aydin
Caner Ozcan
Safak Aydın Simsek
Ferhat Say
author_facet Ayhan Aydin
Caner Ozcan
Safak Aydın Simsek
Ferhat Say
author_sort Ayhan Aydin
collection DOAJ
description Abstract An enchondroma is a benign neoplasm of mature hyaline cartilage that proliferates from the medullary cavity toward the cortical bone. This results in the formation of a significant endogenous mass within the medullary cavity. Although enchondromas are predominantly asymptomatic, they may exhibit various clinical manifestations contingent on the size of the lesion, its localization, and the characteristics observed on radiological imaging. This study aimed to identify and present cases of bone tissue enchondromas to field specialists as preliminary data. In this study, authentic X-ray radiographs of patients were obtained following ethical approval and subjected to preprocessing. The images were then annotated by orthopedic oncology specialists using advanced, state-of-the-art object detection algorithms trained with diverse architectural frameworks. All processes, from preprocessing to identifying pathological regions using object detection systems, underwent rigorous cross-validation and oversight by the research team. After performing various operations and procedural steps, including modifying deep learning architectures and optimizing hyperparameters, enchondroma formation in bone tissue was successfully identified. This achieved an average precision of 0.97 and an accuracy rate of 0.98, corroborated by medical professionals. A comprehensive study incorporating 1055 authentic patient data from multiple healthcare centers will be a pioneering investigation that introduces innovative approaches for delivering preliminary insights to specialists concerning bone radiography.
format Article
id doaj-art-e8ed0b3704094a2fb6090c6cafc7abee
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e8ed0b3704094a2fb6090c6cafc7abee2025-08-24T11:25:34ZengNature PortfolioScientific Reports2045-23222025-08-011511910.1038/s41598-025-07978-4A comprehensive deep learning approach to improve enchondroma detection on X-ray imagesAyhan Aydin0Caner Ozcan1Safak Aydın Simsek2Ferhat Say3Faculty of Engineering, Ondokuz Mayis UniversityFaculty of Engineering, Karabuk UniversityFaculty of Medicine, Ondokuz Mayıs UniversityFaculty of Medicine, Ondokuz Mayıs UniversityAbstract An enchondroma is a benign neoplasm of mature hyaline cartilage that proliferates from the medullary cavity toward the cortical bone. This results in the formation of a significant endogenous mass within the medullary cavity. Although enchondromas are predominantly asymptomatic, they may exhibit various clinical manifestations contingent on the size of the lesion, its localization, and the characteristics observed on radiological imaging. This study aimed to identify and present cases of bone tissue enchondromas to field specialists as preliminary data. In this study, authentic X-ray radiographs of patients were obtained following ethical approval and subjected to preprocessing. The images were then annotated by orthopedic oncology specialists using advanced, state-of-the-art object detection algorithms trained with diverse architectural frameworks. All processes, from preprocessing to identifying pathological regions using object detection systems, underwent rigorous cross-validation and oversight by the research team. After performing various operations and procedural steps, including modifying deep learning architectures and optimizing hyperparameters, enchondroma formation in bone tissue was successfully identified. This achieved an average precision of 0.97 and an accuracy rate of 0.98, corroborated by medical professionals. A comprehensive study incorporating 1055 authentic patient data from multiple healthcare centers will be a pioneering investigation that introduces innovative approaches for delivering preliminary insights to specialists concerning bone radiography.https://doi.org/10.1038/s41598-025-07978-4EnchondromaDeep learningYoloDetectronRadiographTumor
spellingShingle Ayhan Aydin
Caner Ozcan
Safak Aydın Simsek
Ferhat Say
A comprehensive deep learning approach to improve enchondroma detection on X-ray images
Scientific Reports
Enchondroma
Deep learning
Yolo
Detectron
Radiograph
Tumor
title A comprehensive deep learning approach to improve enchondroma detection on X-ray images
title_full A comprehensive deep learning approach to improve enchondroma detection on X-ray images
title_fullStr A comprehensive deep learning approach to improve enchondroma detection on X-ray images
title_full_unstemmed A comprehensive deep learning approach to improve enchondroma detection on X-ray images
title_short A comprehensive deep learning approach to improve enchondroma detection on X-ray images
title_sort comprehensive deep learning approach to improve enchondroma detection on x ray images
topic Enchondroma
Deep learning
Yolo
Detectron
Radiograph
Tumor
url https://doi.org/10.1038/s41598-025-07978-4
work_keys_str_mv AT ayhanaydin acomprehensivedeeplearningapproachtoimproveenchondromadetectiononxrayimages
AT canerozcan acomprehensivedeeplearningapproachtoimproveenchondromadetectiononxrayimages
AT safakaydınsimsek acomprehensivedeeplearningapproachtoimproveenchondromadetectiononxrayimages
AT ferhatsay acomprehensivedeeplearningapproachtoimproveenchondromadetectiononxrayimages
AT ayhanaydin comprehensivedeeplearningapproachtoimproveenchondromadetectiononxrayimages
AT canerozcan comprehensivedeeplearningapproachtoimproveenchondromadetectiononxrayimages
AT safakaydınsimsek comprehensivedeeplearningapproachtoimproveenchondromadetectiononxrayimages
AT ferhatsay comprehensivedeeplearningapproachtoimproveenchondromadetectiononxrayimages