Application of radiomics and machine learning to thyroid diseases in nuclear medicine: a systematic review

Abstract

Background: In the last years growing evidences on the role of radiomics and machine learning (ML) applied to different nuclear medicine imaging modalities for the assessment of thyroid diseases are starting to emerge. The aim of this systematic review was therefore to analyze the diagnostic performances of these technologies in this setting. Methods: A wide literature search of the PubMed/MEDLINE, Scopus and Web of Science databases was made in order to find relevant published articles about the role of radiomics or ML on nuclear medicine imaging for the evaluation of different thyroid diseases. Results: Seventeen studies were included in the systematic review. Radiomics and ML were applied for assessment of thyroid incidentalomas at 18 F-FDG PET, evaluation of cytologically indeterminate thyroid nodules, assessment of thyroid cancer and classification of thyroid diseases using nuclear medicine techniques. Conclusion: Despite some intrinsic limitations of radiomics and ML may have affect the results of this review, these technologies seem to have a promising role in the assessment of thyroid diseases. Validation of preliminary findings in multicentric studies is needed to translate radiomics and ML approaches in the clinical setting.

Machine learning diagnosis of active Juvenile Idiopathic Arthritis on blood pool [99MTc] Tc-MDP scintigraphy images

“…State-of-the-art results of AI have been used in nuclear medicine. For instance, advanced algorithms of AI have been applied for diagnosis of disease in nuclear medicine imaging [20].…”

Thyroid Cancer Radiomics: Navigating Challenges in a Developing Landscape

“…Moreover, in the era of "big data", radiomics features should be assessed by integrating clinical data to build predictive models combining all sources of medical information (holomics); thus, this latter comprehensive approach should be employed and investigated in patients with DTC for whom clinical, laboratory, imaging, histopathological and genetic data are fundamental for management [10,11]. More recently, two systematic reviews were published on the topic, one focused on lymph node assessment [12] and one on nuclear medicine applications [13], both confirming the encouraging findings while highlighting similar limitations for the included radiomics studies, as previously done by Cao et al [1]. Finally, it is worth mentioning that the first few pieces of FDA-and CEcertified dedicated software for automated thyroid nodule characterization on ultrasound have been made commercially available (https://grand-challenge.org/aiforradiology/, accessed on 30 November 2023).…”