Application of Machine Learning for Differentiating Bone Malignancy on Imaging: A Systematic Review
Применение машинного обучения для дифференциации злокачественных опухолей костей по данным визуализации: систематический обзор
2023-03-18
SCID: 54.1/c5dvt6gz
Discuss with AI
bone malignancybone tumor differentiationmachine learningmedical imagingsystematic review
Figures from the paper
Abstract (AI)
An accurate diagnosis of bone tumours on imaging is crucial for appropriate and successful treatment. The advent of Artificial intelligence (AI) and machine learning methods to characterize and assess bone tumours on various imaging modalities may assist in the diagnostic workflow. The purpose of this review article is to summarise the most recent evidence for AI techniques using imaging for differentiating benign from malignant lesions, the characterization of various malignant bone lesions, and their potential clinical application. A systematic search through electronic databases (PubMed, MEDLINE, Web of Science, and clinicaltrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 34 articles were retrieved from the databases and the key findings were compiled and summarised. A total of 34 articles reported the use of AI techniques to distinguish between benign vs. malignant bone lesions, of which 12 (35.3%) focused on radiographs, 12 (35.3%) on MRI, 5 (14.7%) on CT and 5 (14.7%) on PET/CT. The overall reported accuracy, sensitivity, and specificity of AI in distinguishing between benign vs. malignant bone lesions ranges from 0.44-0.99, 0.63-1.00, and 0.73-0.96, respectively, with AUCs of 0.73-0.96. In conclusion, the use of AI to discriminate bone lesions on imaging has achieved a relatively good performance in various imaging modalities, with high sensitivity, specificity, and accuracy for distinguishing between benign vs. malignant lesions in several cohort studies. However, further research is necessary to test the clinical performance of these algorithms before they can be facilitated and integrated into routine clinical practice.
Key Findings
1
AI demonstrated relatively strong diagnostic performance in several cohorts, but additional research is required before routine clinical integration.
2
Radiographs and MRI each accounted for 12 studies (35.3%), while CT and PET/CT each accounted for 5 studies (14.7%).
3
Reported AI performance for distinguishing benign from malignant bone lesions ranged from 0.44–0.99 accuracy, 0.63–1.00 sensitivity, and 0.73–0.96 specificity.
4
Reported area under the curve values ranged from 0.73–0.96 across imaging-based AI approaches.
5
The systematic review identified 34 studies applying artificial intelligence to imaging-based differentiation of benign and malignant bone lesions.
Research Object
Bone tumors and lesions assessed on medical imaging
Research Subject
Machine-learning-based differentiation and characterization of benign versus malignant bone lesions, including diagnostic performance across imaging modalities
Publication Details
Publication Date
2023-03-18
Journal
Publisher
ISSN
Cited by
47
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
The PRISMA 2020 statement: an updated guideline for reporting systematic reviews2021
The PRISMA statement for reporting systematic reviews and meta-analyses of studies that evaluate healthcare interventions: explanation and elaboration2009
Deep learning in cancer diagnosis, prognosis and treatment selection2021
Bone metastasis: mechanisms, therapies, and biomarkers2020