Two-Phase Deep Learning Algorithm for Detection and Differentiation of Ewing Sarcoma and Acute Osteomyelitis in Paediatric Radiographs.
Artificial intelligence
Ewing sarcoma
deep learning
early diagnosis
osteomyelitis
transfer learning
tumor detection
Journal
Anticancer research
ISSN: 1791-7530
Titre abrégé: Anticancer Res
Pays: Greece
ID NLM: 8102988
Informations de publication
Date de publication:
Sep 2022
Sep 2022
Historique:
received:
28
04
2022
revised:
19
05
2022
accepted:
01
07
2022
entrez:
30
8
2022
pubmed:
31
8
2022
medline:
1
9
2022
Statut:
ppublish
Résumé
Ewing sarcoma is a highly malignant tumour predominantly found in children. The radiological signs of this malignancy can be mistaken for acute osteomyelitis. These entities require profoundly different treatments and result in completely different prognoses. The purpose of this study was to develop an artificial intelligence algorithm, which can determine imaging features in a common radiograph to distinguish osteomyelitis from Ewing sarcoma. A total of 182 radiographs from our Sarcoma Centre (118 healthy, 44 Ewing, 20 osteomyelitis) from 58 different paediatric (≤18 years) patients were collected. All localisations were taken into consideration. Cases of acute, acute on chronic osteomyelitis and intraosseous Ewing sarcoma were included. Chronic osteomyelitis, extra-skeletal Ewing sarcoma, malignant small cell tumour and soft tissue-based primitive neuroectodermal tumours were excluded. The algorithm development was split into two phases and two different classifiers were built and combined with a Transfer Learning approach to cope with the very limited amount of data. In phase 1, pathological findings were differentiated from healthy findings. In phase 2, osteomyelitis was distinguished from Ewing sarcoma. Data augmentation and median frequency balancing were implemented. A data split of 70%, 15%, 15% for training, validation and hold-out testing was applied, respectively. The algorithm achieved an accuracy of 94.4% on validation and 90.6% on test data in phase 1. In phase 2, an accuracy of 90.3% on validation and 86.7% on test data was achieved. Grad-CAM results revealed regions, which were significant for the algorithms decision making. Our AI algorithm can become a valuable support for any physician involved in treating musculoskeletal lesions to support the diagnostic process of detection and differentiation of osteomyelitis from Ewing sarcoma. Through a Transfer Learning approach, the algorithm was able to cope with very limited data. However, a systematic and structured data acquisition is necessary to further develop the algorithm and increase results to clinical relevance.
Sections du résumé
BACKGROUND/AIM
OBJECTIVE
Ewing sarcoma is a highly malignant tumour predominantly found in children. The radiological signs of this malignancy can be mistaken for acute osteomyelitis. These entities require profoundly different treatments and result in completely different prognoses. The purpose of this study was to develop an artificial intelligence algorithm, which can determine imaging features in a common radiograph to distinguish osteomyelitis from Ewing sarcoma.
MATERIALS AND METHODS
METHODS
A total of 182 radiographs from our Sarcoma Centre (118 healthy, 44 Ewing, 20 osteomyelitis) from 58 different paediatric (≤18 years) patients were collected. All localisations were taken into consideration. Cases of acute, acute on chronic osteomyelitis and intraosseous Ewing sarcoma were included. Chronic osteomyelitis, extra-skeletal Ewing sarcoma, malignant small cell tumour and soft tissue-based primitive neuroectodermal tumours were excluded. The algorithm development was split into two phases and two different classifiers were built and combined with a Transfer Learning approach to cope with the very limited amount of data. In phase 1, pathological findings were differentiated from healthy findings. In phase 2, osteomyelitis was distinguished from Ewing sarcoma. Data augmentation and median frequency balancing were implemented. A data split of 70%, 15%, 15% for training, validation and hold-out testing was applied, respectively.
RESULTS
RESULTS
The algorithm achieved an accuracy of 94.4% on validation and 90.6% on test data in phase 1. In phase 2, an accuracy of 90.3% on validation and 86.7% on test data was achieved. Grad-CAM results revealed regions, which were significant for the algorithms decision making.
CONCLUSION
CONCLUSIONS
Our AI algorithm can become a valuable support for any physician involved in treating musculoskeletal lesions to support the diagnostic process of detection and differentiation of osteomyelitis from Ewing sarcoma. Through a Transfer Learning approach, the algorithm was able to cope with very limited data. However, a systematic and structured data acquisition is necessary to further develop the algorithm and increase results to clinical relevance.
Identifiants
pubmed: 36039445
pii: 42/9/4371
doi: 10.21873/anticanres.15937
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4371-4380Informations de copyright
Copyright © 2022 International Institute of Anticancer Research (Dr. George J. Delinasios), All rights reserved.