Applications of artificial intelligence in magnetic resonance imaging of primary pediatric cancers: a scoping review and CLAIM score assessment.

PURPOSES: To review the uses of AI for magnetic resonance (MR) imaging assessment of primary pediatric cancer and identify common literature topics and knowledge gaps. To assess the adherence of the existing literature to the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines. MATERIALS AND METHODS: A scoping literature search using MEDLINE, EMBASE and Cochrane databases was performed, including studies of > 10 subjects with a mean age of < 21 years. Relevant data were summarized into three categories based on AI application: detection, characterization, treatment and monitoring. Readers independently scored each study using CLAIM guidelines, and inter-rater reproducibility was assessed using intraclass correlation coefficients. RESULTS: Twenty-one studies were included. The most common AI application for pediatric cancer MR imaging was pediatric tumor diagnosis and detection (13/21 [62%] studies). The most commonly studied tumor was posterior fossa tumors (14 [67%] studies). Knowledge gaps included a lack of research in AI-driven tumor staging (0/21 [0%] studies), imaging genomics (1/21 [5%] studies), and tumor segmentation (2/21 [10%] studies). Adherence to CLAIM guidelines was moderate in primary studies, with an average (range) of 55% (34%-73%) CLAIM items reported. Adherence has improved over time based on publication year. CONCLUSION: The literature surrounding AI applications of MR imaging in pediatric cancers is limited. The existing literature shows moderate adherence to CLAIM guidelines, suggesting that better adherence is required for future studies.

Ultrasonography in the Assessment of Tumors of the Cheek: Water Mouth Distension Technique.

PURPOSE: To describe a new B-mode ultrasound examination technique to assess cheek tumors. MATERIALS AND METHODS: 30 cheek oral cavity lesions of different histological types (11 benign and 19 malignant) from 23 patients (11 women and 12 men, 7-82 years old, mean age of 49.5 years) were analyzed. Transcutaneous oral B-mode ultrasound (5-12 MHz transducer) was carried out in two stages. Initially it was performed conventionally with an empty mouth. Next, the patient was asked to keep their oral cavity filled with water (like when using a mouthwash) during imaging for the new test examination technique. The anatomical layers of this region and the characteristics of the tumors were evaluated. Lesions were classified as ill defined, partially defined, or defined. Conventional findings were compared to those of the new technique using the Wilcoxon signed-rank test. Ultrasound results were compared to histological findings analyzed by an independent team. RESULTS: The conventional empty mouth technique was able to confidently define lesion extension in only 6 of the 30 lesions, while the water-filled mouth technique was able to confidently define lesion extension in 29 of the 30 lesions (p<0.00001). CONCLUSION: We present a novel technique that dramatically improves ultrasound staging of cheek oral cavity tumors. In addition to the increase in ultrasound accuracy, this technique does not require any special equipment or extra cost, is very well tolerated by patients, and thus should be considered in the evaluation of every patient undergoing transcutaneous cheek ultrasound for oral cavity lesion characterization.