Introduction Benign and malignant myxoid soft tissue tumors have shared clinical, imaging, and histologic features that can make diagnosis challenging. The purpose of this study is comparison of the diagnostic performance of a radiomic based machine learning (ML) model to musculoskeletal radiologists. Methods Manual segmentation of 90 myxoid soft tissue tumors (45 myxomas and 45 myxofibrosarcomas) was performed on axial T1, and T2FS or STIR magnetic resonance imaging sequences. Eighty-seven radiomic features from each modality were extracted. Five ML models were trained to classify tumors as benign or malignant in 40 tumors and then tested with an additional 50 tumors using cross validation. The accuracy of the best ML model based on area under the receiver operating characteristic curve (AUC) was compared to the consensus diagnosis of three musculoskeletal radiologists. Correlation between radiologist confidence (equivocal, probably, consistent with) and accuracy was tested. Results The best ML classifier was a logistic regression model (AUC 0.792). Using T1 + T2/STIR images, the ML model classified 78% (39/50) of tumors correctly at a similar rate compared to 74% (37/50) by radiologists. When radiologists disagreed, the consensus diagnosis classified 50% of tumors (7/14) correctly compared to 86% (12/14) by the ML model, though this did not reach statistical significance. Radiologists had a cumulative accuracy of 91% (30/33) when they rated their confidence ‘consistent with’ compared to 61% (31/51) when they rated their confidence ‘equivocal/probably’ (P = 0.006). For cases when radiologists rated their confidence ‘equivocal/probably’, the ML model had 76% accuracy (39/51). Conclusions A radiomic based ML model predicted benign or malignant diagnosis in myxoid soft tissue tumors similarly to the consensus diagnosis by three musculoskeletal radiologists. Radiologist confidence in the diagnosis strongly correlated with their diagnostic accuracy. Though radiomics and radiologists perform similarly overall, radiomics may provide novel diagnostic utility when radiologist confidence is low, or when radiologists disagree.

Myxofibrosarcoma is a rare, malignant myxoid soft tissue tumor. It can be challenging to distinguish it from a benign myxoma in clinical practice as there exists imaging and histologic feature overlap between these two entities. Some previous works used radiomics features of T1-weighted images to differentiate myxoid tumors, but few have used multimodality data. In this project, we collect a dataset containing 20 myxomas and 20 myxofibrosarcomas, each with a T1- weighted image, a T2-weighted image, and clinical features. Radiomics features from multi-modality images and clinical features are used to train multiple machine learning models. Our experiment results show that the prediction accuracy using the multi-modality features surpasses the results from a single modality. The radiomics features Gray Level Variance, Gray Level Non-uniformity Normalized extracted from the Gray Level Run Length Matrix (GLRLM) of the T2 images, and age are the top three features selected by the least absolute shrinkage and selection operator (LASSO) feature reduction model

Rationale and Objectives: Engaging medical students during a radiology course can be challenging. We sought a way to actively engage students with live cases, allow them to interact with the picture archiving and communication system workstation, and experience what it is like to be a radiologist. Materials and Methods: Medical students enrolled in one of three radiology courses between May 2016 and June 2017 were eligible. The "Look Ahead" technique is as follows: a preceptor identifies several nonurgent imaging studies and allows the students to view the images first and make independent observations and conclusions. When ready, the students present their findings, receive feedback, and observe the preceptor generate a final report. Students completed the postcourse survey comparing the "Look Ahead" technique with the current standard (observing a preceptor interpret imaging studies with accompanying teaching points). Results: Thirty-four (56.7%) of 60 potential respondents completed the postcourse survey. Of these 34, 24 (70.6%) reported at least one reading room case (mean 4.6) in which the technique was employed, with a mean of 2.4 unique preceptors. When compared to the current standard (0 = not to 100 = very interested/engaged/valuable/memorable), the "Look Ahead" technique was associated with increased student-reported interest (92.5 vs 75.1, p < 0.01), engagement (94.0 vs 70.3, p < 0.01), educational value (92.5 vs 73.2, p < 0.01), memorability of the case (88.5 vs 73.2, p < 0.01) and of accompanying teaching points (90.1 vs 76.7, p < 0.01). Conclusion: The "Look Ahead" technique is a meaningful and engaging teaching method, which students find "interesting," "valuable," and "memorable."

Radiation-associated malignancy and malignant transformation are risks associated with stereotactic radiosurgery (SRS); however, incidence is uncertain. The purpose of our study is to present the rate of radiation-associated malignancy and malignant transformation at our institution. After IRB approval, we undertook a retrospective cohort study evaluating patients treated with Gamma Knife® or linac-based SRS between 1990 and 2014 for benign CNS pathology with at least 5 years of clinical follow-up. Risk of transformation was calculated using the Kaplan-Meier method. A total of 273 patients met selection criteria. Median clinical follow-up after SRS was 11 years (range 5-27). Over 3,216 patient-years following SRS, we found zero cases of radiation-associated malignancy and two cases of radiation-associated malignant transformation for a crude rate of 0.73% or case rate of 0.62 per 1,000 patient-years. The Kaplan-Meier risk of malignant transformation at 5, 10, and 15 years was 0.4% (95% CI 0.05% 2.6%). These data support the continued use of SRS for benign intracranial pathology without significant concern for secondary malignancy.

PURPOSE:Radiation therapy is a valuable, yet time- and resource-intense therapy. Patients experiencing homelessness (PEH) face many barriers related to the timely receipt of radiation therapy. Owing to a paucity of data regarding cancer treatment and homelessness, clinicians have a limited evidence base when recommending therapy to PEH. This study was performed to evaluate adherence to radiation therapy treatment regimens in PEH with cancer.METHODS AND MATERIALS:The study cohort was primarily derived from the Vanderbilt University Medical Center Homeless Health Services program. Patients in the Homeless Health Services program with radiation oncology visits were identified by query of the electronic medical record. Manual chart review was performed to gather standard treatment parameters and data describing missed appointments. A comparison group of patients not experiencing homelessness (non-PEH) was generated by aggregating appointment data for all other patients receiving similar treatments at Vanderbilt University Medical Center during multiple, consecutive years.RESULTS:In the study, 3408 PEH were identified, of whom 48 underwent radiation oncology consultation. Thirty-two were prescribed at least 1 course of radiation therapy, for a total of 54 unique courses. Out of these courses, 34 (62.9%) were completed as prescribed without delay, 12 (22.2%) were completed with delay(s), and 8 (14.8%) were not fully completed. Although the PEH cohort had significantly higher rates of delayed and undelivered fractions, the proportion of delayed or incomplete courses was not significantly different from the comparison group of non-PEH, particularly for courses with 10 or fewer fractions. Reasons for missed appointments for PEH were variable.CONCLUSIONS:This is the first publication describing adherence to radiation therapy in PEH. Our data suggest that PEH are as likely as non-PEH to complete a course of radiation therapy, albeit with more treatment interruptions. When treatment courses of >10 fractions are expected, PEH may benefit from more hypofractionated regimens, provided they have equivalent clinical efficacy to longer regimens. Documenting reasons for missed appointments will be essential to further understanding the needs of PEH. This study serves as a foundation for further analysis regarding homelessness and radiation therapy.

Abstract Long-term outcomes and sequalae of pediatric stereotactic radiosurgery (SRS) for benign neurologic disease are poorly understood. We sought to explore the efficacy and late effects of SRS in pediatric patients treated our institution. After institutional review board approval, we performed a retrospective analysis of patients age 21 or younger treated between 1990 and 2016. Covariates were summarized with descriptive statistics. 56 consecutive patients were enrolled. Patients were primarily Caucasian (n=51, 93%) males (n=30, 54%). Diagnoses included arterio-venous malformation (n=41, 73%) and functional pituitary adenoma (n=9, 16%) as well as vestibular schwannoma, craniopharyngioma, meningioma, papilloma, and ganglioglioma. Average age was 14 years (95% CI 13–16 years). SRS was often the first intervention (n=22, 44%); treatments prior to SRS included embolization (n=18, 36%) and surgery (n=10, 20%). SRS was typically single fraction (n=45, 94%) with a median total dose of 16 Gy (IQR 15–18 Gy). Most patients had no acute side effects of SRS (n=40, 87%). Median follow-up time after SRS was 12 years (IQR 6–18 years, max 26 years). 91% of patients had no late sequelae of SRS. One patient was diagnosed with radionecrosis one year after repeat SRS for residual malformation. Two patients had malformation hemorrhage. One patient with brainstem malformation developed focal weakness after ischemia from treatment effect; another patient with malformation developed seizures related to SRS edema. Over 673 patient-years following SRS, no patient developed radiation-induced malignancy or malignant transformation. Median disease-free survival after SRS was 6 years (IQR 3–13) with 66% overall local control; 84% of local failures occurred within 5 years of SRS. At last follow-up, 95% of patients remained without evidence of disease with 100% overall survival. These data support the long-term safety and efficacy of pediatric SRS.

Pathologic complete response following neoadjuvant therapy (NAT) is used as a short-term surrogate marker of eventual outcome in patients with breast cancer. Analyzing voxel-level heterogeneity in MRI-derived parametric maps, obtained before and after the first cycle of NAT ([Formula: see text]), in conjunction with receptor status, may improve the predictive accuracy of tumor response to NAT. Toward that end, we incorporated two MRI-derived parameters, the apparent diffusion coefficient and efflux rate constant, with receptor status in a logistic ridge-regression model. The area under the curve (AUC) and Brier score of the model computed via 10-fold cross validation were 0.94 (95% CI: 0.85, 0.99) and 0.11 (95% CI: 0.06, 0.16), respectively. These two statistics strongly support the hypothesis that our proposed model outperforms the other models that we investigated (namely, models without either receptor information or voxel-level information). The contribution of the receptor information was manifested by an 8% to 15% increase in AUC and a 14% to 21% decrease in Brier score. These data indicate that combining multiparametric MRI with hormone receptor status has a high likelihood of improved prediction of pathologic response to NAT in breast cancer.

To evaluate the survival benefit of adding vaginal brachytherapy (BT) to pelvic external beam radiotherapy (EBRT) in women with stage III endometrial cancer. The National Cancer Data Base was used to identify patients with stage III endometrial cancer from 2004 to 2013. Only women who received adjuvant EBRT were analyzed. Women were grouped according to receipt of BT. Logistic regression modeling was used to identify predictors of receiving BT. Log-rank statistics were used to compare survival outcomes. Cox proportional hazards modeling was used to evaluate the effect of BT on survival. A propensity score-matched analysis was also conducted among women with cervical involvement. We evaluated 12,988 patients with Stage III endometrial carcinoma, 39% of whom received EBRT+BT. Women who received BT were more likely to have endocervical or cervical stromal involvement (OR: 2.03 and OR: 1.77; p<0.01, respectively). For patients receiving EBRT alone, the 5-year survival was 66% vs. 69% with the addition of BT at 5 years (p<0.01). Brachytherapy remained significantly predictive of decreased risk of death (HR: 0.86; p<0.01) on multivariate Cox regression. The addition of BT to EBRT did not affect survival among women without cervical involvement (p=0.84). For women with endocervical or cervical stromal invasion, the addition of BT significantly improved survival (log-rank p<0.01). Receipt of EBRT+BT was associated with improved survival in women with positive and negative surgical margins, and receiving chemotherapy did not alter the benefit of BT. Propensity score matched analysis results confirmed the benefit of BT among women with cervical involvement (HR: 0.80; p=0.01). In this population of women with stage III endometrial cancer the addition of BT to EBRT was associated with an improvement in survival for women with endocervical or cervical stromal invasion.

To assess the utilization and outcomes of adjuvant monotherapy with hypofractionated radiation (RT) among elderly patients not receiving traditional adjuvant chemoradiotherapy (cRT) for glioblastoma multiforme (GBM). A retrospective analysis using the National Cancer Data Base with GBM patients aged 65 years or older treated between 2005 and 2012 was conducted. Patients who underwent hypofractionated RT (40 Gy), conventional RT (60 Gy), chemotherapy, or best supportive care alone were included. Statistical methods included logistic regression for utilization and Cox regression for survival analysis. A total of 9556 patients were analyzed. On multivariate analysis (compared to those receiving conventional RT), patients more likely to be treated with hypofractionated RT were older (75–84 years old OR 2.05; p < 0.01 and ≥ 85 years old OR 3.32; p < 0.01), with a Charlson/Deyo score of 2 or higher (OR 1.80; p = 0.05), from communities > 50 miles from their treatment facility (50–100 miles OR 8.03; p < 0.01 and > 100 miles OR 7.16; p < 0.01), treated at an Academic/Research facility (OR 2.85; p = 0.04), and diagnosed between 2011 and 2012 (OR 4.15; p < 0.01). On Cox regression, hypofractionated RT (HR 0.65; p < 0.01), conventional RT (HR 0.60; p < 0.01), and chemotherapy alone (HR 0.69; p < 0.01) were all associated with decreased risk of death compared to no adjuvant therapy. Among patients receiving adjuvant treatment, utilization of hypofractionated RT increased from 7 to 19% during the study period. Among elderly patients with GBM not receiving cRT, the utilization of adjuvant monotherapy with hypofractionated RT has increased over time. Retrospective evidence suggests it may be better than best supportive care alone and as good as conventionally fractionated RT alone.

Purpose: To evaluate the survival benefit of adding vaginal brachytherapy (BT) to pelvic external beam radiation therapy (EBRT) in women with stage III endometrial cancer.Methods and Materials: The National Cancer Data Base was used to identify patients with stage III endometrial cancer from 2004 to 2013. Only women who received adjuvant EBRT were analyzed. Women were grouped according to receipt of BT. Logistic regression modeling was used to identify predictors of receiving BT. Log rank statistics were used to compare survival outcomes. Cox proportional hazards modeling was used to evaluate the effect of BT on survival. A propensity score matched analysis was also conducted among women with cervical involvement.Results: We evaluated 12,988 patients with stage III endometrial carcinoma, 39% of whom received EBRT plus BT. Women who received BT were more likely to have endocervical or cervical stromal involvement (odds ratios 2.03 and 1.77; P<.01, respectively). For patients receiving EBRT alone, the 5-year survival was 66% versus 69% with the addition of BT at 5 years (P<.01). Brachytherapy remained significantly predictive of decreased risk of death (hazard ratio 0.86; P<.01) on multivariate Cox regression. The addition of BT to EBRT did not affect survival among women without cervical involvement (P=.84). For women with endocervical or cervical stromal invasion, the addition of BT significantly improved survival (log rank P<.01). Receipt of EBRT plus BT was associated with improved survival in women with positive and negative surgical margins, and receiving chemotherapy did not alter the benefit of BT. Propensity score matched analysis results confirmed the benefit of BT among women with cervical involvement (hazard ratio 0.80; P=.01). Conclusions: In this population of women with stage III endometrial cancer the addition of BT to EBRT was associated with an improvement in survival for women with endocervical or cervical stromal invasion. (C) 2017 Elsevier Inc. All rights reserved.

Cutaneous malignancies make up the majority of periocular tumors diagnosed and treated by ophthalmologists. In this review, we examine literature regarding ethnic and socioeconomic disparities in incidence and clinical outcomes of the three most common cutaneous periocular tumors: basal cell carcinoma, squamous cell carcinoma, and melanoma. In all three tumor types, the literature shows an increased incidence among two groups: those with lightly pigmented skin and those of higher socioeconomic status. While incidence is high in these groups, clinical outcomes for these patients tend to be good. Those with lower socioeconomic status and ethnic minorities, on the other hand, have a low incidence but are more likely to have poor clinical outcomes. These disparities are likely the result of both biologic and behavioral differences between patients and could provide opportunities for intervention to change risk perception and improve outcomes.