Abstract
Objectives
Radiomics involves the extraction and analysis of numerous quantitative features of
medical imaging which can add more information from radiological images often beyond
initial comprehension of a clinician. Unlike deep learning, radiomics allows some
understanding of identified quantitative features for clinical prediction. We sought
to explore the current state of radiomics applications in the skull base literature.
Methods
A systematic review of studies evaluating radiomics in skull base was performed, including
those with and without machine-learning approaches. Studies were summarized into thematic
elements as well as specific pathologies.
Results
A total of 102 studies with 26,280 radiographic images were included. The earliest
radiomic study was published in 2017 with exponential growth in research since then.
Most studies focused on tumor diagnosis (40.8%), followed by tumor prognosis (31.1%),
automated segmentation (16.5%), other applications (7.8%), and lastly prediction of
intraoperative features (3.9%). Pituitary adenomas (41.7%) and vestibular schwannomas
(18.4%) represented the most commonly evaluated pathologies; however, radiomics could
be applied to a heterogeneous collection of skull base pathologies. The average study
included 258 ± 677 cases (range 4; 6,755).
Conclusion
Radiomics offers many functions in treating skull base pathology and will likely be
an essential component of future clinical care. Larger sample sizes, validation of
predictive models, and clinical application are needed. Further investigation into
the strengths and weaknesses of radiomic applications in skull base treatments is
warranted.
Keywords
radiomics - artificial intelligence - machine learning - skull base - pituitary adenoma
- vestibular schwannoma - head and neck cancer
