Abstract
Radiomics is a rapidly growing area of research within radiology that involves the extraction and modeling of high-dimensional quantitative imaging features using machine learning/artificial intelligence (ML/AI) methods. In this review, we describe the published clinical evidence on the application of ML methods to improve the performance of ultrasound (US) in head and neck oncology. A systematic search of electronic databases (MEDLINE, PubMed, clinicaltrials.gov) was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Of 15,080 initial articles identified, 34 studies were selected for in-depth analysis. Twenty-five out of 34 studies (74%) focused on the diagnostic application of US radiomics while 6 (18%) studies focused on response assessment and 3 (8%) studies utilized US radiomics for modeling normal tissue toxicity. Support vector machine (SVM) was the most commonly employed ML method (47%) followed by multivariate logistic regression (24%) and k-nearest neighbor analysis (21%). Only 11/34 (~32%) of the studies included an independent validation set. A majority of studies were retrospective in nature (76%) and based on single-center evaluation (85%) with variable numbers of patients (12-1609) and imaging datasets (32-1624). Despite these limitations, the application of ML methods resulted in improved diagnostic and prognostic performance of US highlighting the potential clinical utility of this approach.
Highlights
The term ‘head and neck cancer’ is used to describe a heterogeneous group of neoplasms that can arise in multiple sites within this anatomic region including the mucosal epithelium of the oral and nasal cavities, larynx, pharynx, thyroid, and salivary glands [1].Ultrasound (US) is a noninvasive imaging modality that is routinely employed in head and neck cancer patients to determine the anatomic extent and vascularity of tumors and nodal masses [2–4]
Given this ability of radiomics to extract quantitative, high-throughput, multi-dimensional information, it is assumed that such radiomic “phenotypes” may better capture the heterogeneity within the tumor microenvironment and as a consequence, exhibit improved performance for diagnostic and prognostic applications compared to traditional radiologic or clinical assessment criteria used in head and neck oncology [8]
Databases were searched for the following terms: “head and neck cancer”, OR “oral cancer,” OR “tongue cancer”, OR “thyroid cancer”, OR “lymph node”, OR “salivary gland”, OR “parotid gland,” AND “ultrasound,” AND “radiomics” OR “texture analysis”
Summary
The term ‘head and neck cancer’ is used to describe a heterogeneous group of neoplasms that can arise in multiple sites within this anatomic region including the mucosal epithelium of the oral and nasal cavities, larynx, pharynx, thyroid, and salivary glands [1].Ultrasound (US) is a noninvasive imaging modality that is routinely employed in head and neck cancer patients to determine the anatomic extent and vascularity of tumors and nodal masses [2–4]. US methods are utilized for diagnostic evaluation of suspicious thyroid nodules [5], and the differential diagnosis of salivary gland neoplasms [6] These applications rely on the ability of US to detect changes in size, shape, margins, structure (e.g., echogenicity, presence of calcifications), and vascularity (blood flow and velocity). Textural features are calculated based on the shape, distribution of voxel intensity, and spatial relationships between neighboring voxels and subsequently modeled through statistical algorithms (“machine learning”) Given this ability of radiomics to extract quantitative, high-throughput, multi-dimensional information, it is assumed that such radiomic “phenotypes” may better capture the heterogeneity within the tumor microenvironment and as a consequence, exhibit improved performance for diagnostic and prognostic applications compared to traditional radiologic or clinical assessment criteria used in head and neck oncology [8]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
