Diagnostic performance of deep learning in ultrasound diagnosis of breast cancer: a systematic review.

Deep learning (DL) has been widely investigated in breast ultrasound (US) for distinguishing between benign and malignant breast masses. This systematic review of test diagnosis aims to examine the accuracy of DL, compared to human readers, for the diagnosis of breast cancer in the US under clinical settings. Our literature search included records from databases including PubMed, Embase, Scopus, and Cochrane Library. Test accuracy outcomes were synthesized to compare the diagnostic performance of DL and human readers as well as to evaluate the assistive role of DL to human readers. A total of 16 studies involving 9238 female participants were included. There were no prospective studies comparing the test accuracy of DL versus human readers in clinical workflows. Diagnostic test results varied across the included studies. In 14 studies employing standalone DL systems, DL showed significantly lower sensitivities in 5 studies with comparable specificities and outperformed human readers at higher specificities in another 4 studies; in the remaining studies, DL models and human readers showed equivalent test outcomes. In 12 studies that assessed assistive DL systems, no studies proved the assistive role of DL in the overall diagnostic performance of human readers. Current evidence is insufficient to conclude that DL outperforms human readers or enhances the accuracy of diagnostic breast US in a clinical setting. Standardization of study methodologies is required to improve the reproducibility and generalizability of DL research, which will aid in clinical translation and application.

Factors associated with complex oral treatment device usage in patients with head and neck cancer.

PURPOSE: The objective was to identify clinical and epidemiological factors associated with utilization of a complex oral treatment device (COTD), which may decrease toxicity in patients undergoing radiation therapy for head and neck cancer (HNC). MATERIALS AND METHODS: We retrospectively reviewed data from 1992 to 2013 in the Surveillance, Epidemiology, and End Results (SEER)-Medicare databases to analyze COTD usage during intensity-modulated radiation therapy (IMRT) for patients diagnosed with cancer of the tongue, floor of mouth, nasopharynx, tonsil, or oropharynx. Patients with a radiation simulation and complex treatment device code within 4 weeks before the first IMRT claim were identified as meeting COTD usage criteria. Demographic, regional, tumor, and treatment data were analyzed. RESULTS: Out of 4511 patients who met eligibility criteria, 1932 patients (42.8%) did not utilize a COTD while 2579 (57.2%) met usage criteria. COTD utilization increased over time (36.36% usage in 1992 vs. 67.44% usage in 2013, p < .0001). Patients less likely to receive a COTD included those aged 86 years or older compared to those aged 66-70 (OR = 0.713, 95% CI: 0.528-0.962), male patients (OR = 0.817, 95% CI: 0.710-0.941), non-Hispanic Black patients compared to non-Hispanic White patients (OR = 0.750, 95% CI: 0.582-0.966), and Louisiana residents (OR = 0.367, 95% CI: 0.279-0.483). Cancer site, grade, stage, or function of IMRT had no significant association with COTD usage. CONCLUSIONS: This study serves as the first known SEER-Medicare review of COTD utilization. Despite an increase in COTD usage over time, our results indicate age, gender, and geographic disparities are associated with utilization. Further research and development into methods that increase availability of COTDs may help increase utilization in specific patient populations.

Multisystem inflammatory syndrome in children (MIS-C) and the coronavirus pandemic: Current knowledge and implications for public health.

The coronavirus disease 2019 (COVID-19) pandemic has caused widespread mortality and morbidity. Though children are largely spared from severe illness, a novel childhood hyperinflammatory syndrome presumed to be associated with and subsequent to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection has emerged with potentially severe outcomes. Multisystem inflammatory disorder in children (MIS-C) most commonly affects young, school-aged children and is characterized by persistent fever, systemic hyperinflammation, and multisystem organ dysfunction. While uncommon and generally treatable, MIS-C presents potentially life-altering medical sequelae, complicated by a dearth of information regarding its etiology, pathophysiology, and long-term outcomes. The severity of MIS-C may warrant the need for increased awareness and continued COVID-19 mitigation efforts, particularly until potential factors conferring a predisposition to MIS-C can be clarified through additional research. Well-informed guidelines will be critical as the school year progresses. In this article, current knowledge on MIS-C is reviewed and the potential implications of this novel syndrome are discussed from a public health perspective.

A prospective parallel design study testing non-inferiority of customized oral stents made using 3D printing or manually fabricated methods.

BACKGROUND AND PURPOSE: Customized mouth-opening-tongue-depressing-stents (MOTDs) may reduce toxicity in patients with head and neck cancers (HNC) receiving radiotherapy (RT). However, making MOTDs requires substantial resources, which limits their utilization. Previously, we described a workflow for fabricating customized 3D-printed MOTDs. This study reports the results of a prospective trial testing the non-inferiority of 3D-printed to standard and commercially-available (TruGuard) MOTDs as measured by patient reported outcomes (PROs). MATERIALS AND METHODS: PROs were collected at 3 time points: (t1) simulation, (t2) prior to RT, (t3) between fractions 15-25 of RT. Study participants received a 3D-printed MOTDs (t1, t2, t3), a wax-pattern (t1), an acrylic-MOTDs (t2, t3) and an optional TruGuard (t1, t2, t3). Patients inserted the stents for 5-10 min and completed a PRO-questionnaire covering ease-of-insertion and removal, gagging, jaw-pain, roughness and stability. Inter-incisal opening and tongue-displacement were recorded. With 39 patients, we estimated 90% power to detect a non-inferiority margin of 2 at a significance level of 0.025. Matched pairs and t-test were used for statistics. RESULTS: 41 patients were evaluable. The 3D-printed MOTDs achieved a significantly better overall PRO score compared to the wax-stent (p = 0.0007) and standard-stent (p = 0.0002), but was not significantly different from the TruGuard (p = 0.41). There was no difference between 3D-printed and standard MOTDs in terms of inter-incisal opening (p = 0.4) and position reproducibility (p = 0.98). The average 3D-printed MOTDs turn-around time was 8 vs 48 h for the standard-stent. CONCLUSIONS: 3D-printed stents demonstrated non-inferior PROs compared to TruGuard and standard-stents. Our 3D-printing process may expand utilization of MOTDs.

Creating customized oral stents for head and neck radiotherapy using 3D scanning and printing.

BACKGROUND: To evaluate and establish a digital workflow for the custom designing and 3D printing of mouth opening tongue-depressing (MOTD) stents for patients receiving radiotherapy for head and neck cancer. METHODS: We retrospectively identified 3 patients who received radiation therapy (RT) for primary head and neck cancers with MOTD stents. We compared two methods for obtaining the digital impressions of patients' teeth. The first method involved segmentation from computed tomography (CT) scans, as previously established by our group, and the second method used 3D scanning of the patients' articulated stone models that were made during the conventional stent fabrication process. Three independent observers repeated the process to obtain digital impressions which provided data to design customized MOTD stents. For each method, we evaluated the time efficiency, dice similarity coefficient (DSC) for reproducibility, and the 3D printed stents' accuracy. For the 3D scanning method, we evaluated the registration process using manual and automatic approaches. RESULTS: For all patients, the 3D scanning method demonstrated a significant advantage over the CT scanning method in terms of time efficiency with over 60% reduction in time consumed (p < 0.0001) and reproducibility with significantly higher DSC (p < 0.001). The printed stents were tested over the articulated dental stone models, and the trueness of fit and accuracy of dental anatomy was found to be significantly better for MOTD stents made using the 3D scanning method. The automated registration showed higher accuracy with errors < 0.001 mm compared to manual registration. CONCLUSIONS: We developed an efficient workflow for custom designing and 3D-printing MOTD radiation stents. This workflow represents a considerable improvement over the CT-derived segmentation method. The application of this rapid and efficient digital workflow into radiation oncology practices can expand the use of these toxicity sparing devices to practices that do not currently have the support to make them.