BACKGROUND: Here, we conducted a scoping review to (i) establish which machine learning (ML) methods have been applied to hematological malignancy imaging; (ii) establish how ML is being applied to hematological cancer radiology; and (iii) identify addressable research gaps. METHODS: The review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews guidelines. The inclusion criteria were (i) pediatric and adult patients with suspected or confirmed hematological malignancy undergoing imaging (population); (ii) any study using ML techniques to derive models using radiological images to apply to the clinical management of these patients (concept); and (iii) original research articles conducted in any setting globally (context). Quality Assessment of Diagnostic Accuracy Studies 2 criteria were used to assess diagnostic and segmentation studies, while the Newcastle-Ottawa scale was used to assess the quality of observational studies. RESULTS: Of 53 eligible studies, 33 applied diverse ML techniques to diagnose hematological malignancies or to differentiate them from other diseases, especially discriminating gliomas from primary central nervous system lymphomas (n=18); 11 applied ML to segmentation tasks, while 9 applied ML to prognostication or predicting therapeutic responses, especially for diffuse large B-cell lymphoma. All studies reported discrimination statistics, but no study calculated calibration statistics. Every diagnostic/segmentation study had a high risk of bias due to their case-control design; many studies failed to provide adequate details of the reference standard; and only a few studies used independent validation. CONCLUSION: To deliver validated ML-based models to radiologists managing hematological malignancies, future studies should (i) adhere to standardized, high-quality reporting guidelines such as the Checklist for Artificial Intelligence in Medical Imaging; (ii) validate models in independent cohorts; (ii) standardize volume segmentation methods for segmentation tasks; (iv) establish comprehensive prospective studies that include different tumor grades, comparisons with radiologists, optimal imaging modalities, sequences, and planes; (v) include side-by-side comparisons of different methods; and (vi) include low- and middle-income countries in multicentric studies to enhance generalizability and reduce inequity.

• Klíčová slova
• artificial intelligence, hematological malignancy, machine learning, radiology, scoping review,
• Publikační typ
• časopisecké články MeSH
• scoping review MeSH

The primary objective of the present prospective study was to compare the diagnostic performance of conventional radiography (CR) and whole-body low-dose computed tomography (WBLDCT) with a comparable radiation dose reconstructed using hybrid iterative reconstruction technique, in terms of the detection of bone lesions, skeletal fractures, vertebral compressions and extraskeletal findings. The secondary objective was to evaluate lesion attenuation in relation to its size. A total of 74 patients underwent same-day skeletal survey by CR and WBLDCT. In CR and WBLDCT, two readers assessed the number of osteolytic lesions at each region and stage according to the International Myeloma Working Group (IMWG) criteria. A single reader additionally assessed extraskeletal findings and their significance, the number of vertebral compressions and bone fractures. The radiation exposure was 2.7±0.9 mSv for WBLDCT and 2.5±0.9 mSv for CR (P=0.054). CR detected bone involvement in 127 out of 486 regions (26%; P<0.0001), confirmed by WBLDCT. CR underestimated the disease stage in 16% and overestimated it in 8% of the patients (P=0.0077). WBLDCT detected more rib fractures compared with CR (188 vs. 47; P<0.0001), vertebral compressions (93 vs. 67; P=0.010) and extraskeletal findings (194 vs. 52; P<0.0001). There was no correlation observed between lesion size (≥5 mm) and its attenuation (r=-0.006; P=0.93). The inter-observer agreement for the presence of osteolytic lesions was κ=0.76 for WBLDCT, and κ=0.55 for CR. The present study concluded that WBLDCT with hybrid iterative reconstruction technique demonstrates superiority to CR with an identical radiation dose in the detection of bone lesions, skeletal fractures, vertebral compressions and extraskeletal findings, which results in up- or downstaging in 24% patients according to the IMWG criteria. The attenuation of osteolytic lesions can be measured with the avoidance of the partial volume effect.

• Klíčová slova
• computed tomography, osteolytic lesion, plasma cell disorder, staging, x-ray,
• Publikační typ
• časopisecké články MeSH