Characterization of renal masses with MRI-based radiomics: assessment of inter-package and inter-observer reproducibility in a prospective pilot study.

OBJECTIVES: To evaluate radiomics features' reproducibility using inter-package/inter-observer measurement analysis in renal masses (RMs) based on MRI and to employ machine learning (ML) models for RM characterization. METHODS: 32 Patients (23M/9F; age 61.8 ± 10.6 years) with RMs (25 renal cell carcinomas (RCC)/7 benign masses; mean size, 3.43 ± 1.73 cm) undergoing resection were prospectively recruited. All patients underwent 1.5 T MRI with T2-weighted (T2-WI), diffusion-weighted (DWI)/apparent diffusion coefficient (ADC), and pre-/post-contrast-enhanced T1-weighted imaging (T1-WI). RMs were manually segmented using volume of interest (VOI) on T2-WI, DWI/ADC, and T1-WI pre-/post-contrast imaging (1-min, 3-min post-injection) by two independent observers using two radiomics software packages for inter-package and inter-observer assessments of shape/histogram/texture features common to both packages (104 features; n = 26 patients). Intra-class correlation coefficients (ICCs) were calculated to assess inter-observer and inter-package reproducibility of radiomics measurements [good (ICC ≥ 0.8)/moderate (ICC = 0.5-0.8)/poor (ICC < 0.5)]. ML models were employed using reproducible features (between observers and packages, ICC > 0.8) to distinguish RCC from benign RM. RESULTS: Inter-package comparisons demonstrated that radiomics features from T1-WI-post-contrast had the highest proportion of good/moderate ICCs (54.8-58.6% for T1-WI-1 min), while most features extracted from T2-WI, T1-WI-pre-contrast, and ADC exhibited poor ICCs. Inter-observer comparisons found that radiomics measurements from T1-WI pre/post-contrast and T2-WI had the greatest proportion of features with good/moderate ICCs (95.3-99.1% T1-WI-post-contrast 1-min), while ADC measurements yielded mostly poor ICCs. ML models generated an AUC of 0.71 [95% confidence interval = 0.67-0.75] for diagnosis of RCC vs. benign RM. CONCLUSION: Radiomics features extracted from T1-WI-post-contrast demonstrated greater inter-package and inter-observer reproducibility compared to ADC, with fair accuracy for distinguishing RCC from benign RM. CLINICAL RELEVANCE: Knowledge of reproducibility of MRI radiomics features obtained on renal masses will aid in future study design and may enhance the diagnostic utility of radiomics models for renal mass characterization.

Implementation of Medical Students as Radiology Reading Room Coordinators.

OBJECTIVE: Effort has been made to minimize the burden of non-interpretive tasks (NITs), in particular by hiring and training non-radiologist support staff as reading room coordinators (RRCs). Our medical center recruited and trained senior medical students from our affiliated school of medicine to work alongside on-call radiology residents as RRCs. METHODS: A 12-month Malpractice Carrier monetary grant was acquired to fund medical students at with the aim to reduce malpractice risk. After the first year, residents were surveyed regarding the impact of the RRCs on perceived on-call efficiency and morale. Furthermore, report turnaround times (TAT) on call shifts that were and were not accompanied by a RRC were compared. RESULTS: 89 % of residents strongly agreed that the RRC improved workflow efficiency, decreased distractions, and felt less stressed during the call shift when the RRC was on duty. 78 % strongly agreed to be more likely to contact a referring clinician when the RRC was able to help coordinate. The mean TAT in the presence of a RRC was 36.8 min, and the mean TAT in the absence of a RRC was 36.9 min DISCUSSION: After hiring medical students to assist on-call radiology residents with noninterpretive tasks, residents reported subjective indicators of program success, but average report turnaround time was unaffected. Nevertheless, we predict that this type of program will continue to grow among academic radiology departments, though additional research is required to evaluate national trends and impacts on radiologist productivity and well-being.

Prognosis, counseling, and indications for termination of pregnancy.

As the coincidence of pregnancy and cancer rise, clinicians must be prepared to counsel their patients on the complex relationship between maternal and fetal health. In most types of cancer, maternal prognosis mirrors that of non-pregnant women. However, challenges associated with the timing of diagnosis and treatment can present additional risks. Consequently, pregnant cancer patients must be counseled early and effectively with regard to how their pregnancy status affects treatment options and the range of expected outcomes for both mother and fetus. Some patients choose to terminate pregnancy after such counseling, though the specific course of action depends on the cancer in question, the stage at diagnosis, and the personal priorities and values of the patient.

Repeatability, robustness, and reproducibility of texture features on 3 Tesla liver MRI.

OBJECTIVE: Texture features are proposed for classification and prognostication, with lacking information about variability. We assessed 3 T liver MRI feature variability. METHODS: Five volunteers underwent standard 3 T MRI, and repeated with identical and altered parameters. Two readers placed regions of interest using 3DSlicer. Repeatability (between standard and repeat scan), robustness (between standard and parameter changed scan), and reproducibility (two reader variation) were computed using coefficient of variation (CV). RESULTS: 67%, 49%, and 61% of features had good-to-excellent (CV ≤ 10%) repeatability on ADC, T1, and T2, respectively, least frequently for first order (19-35%). 22%, 19%, and 21% of features had good-to-excellent robustness on ADC, T1, and T2, respectively. 52%, 35%, and 25% of feature measurements had good-to-excellent inter-reader reproducibility on ADC, T1, and T2, respectively, with highest good-to-excellent reproducibility for first order features on ADC/T1. CONCLUSION: We demonstrated large variations in texture features on 3 T liver MRI. Further study should evaluate methods to reduce variability.

Bosniak IIF and III Renal Cysts: Can Apparent Diffusion Coefficient-Derived Texture Features Discriminate Between Malignant and Benign IIF and III Cysts?

OBJECTIVE: The aim of this study was to determine which apparent diffusion coefficient-derived texture features are associated with malignancy in Bosniak IIF and III renal cystic lesions. METHODS: Twenty benign and 7 malignant Bosniak IIF (22) or III (5) renal cysts, as evaluated with magnetic resonance imaging, were assessed for progression to pathology-confirmed malignancy. Whole-cyst volumes of interest were manually segmented from apparent diffusion coefficient maps. Texture features were extracted from each volume of interest, including first-order histogram-based features and higher-order features, and data were analyzed with the Mann-Whitney U test to predict malignant progression. RESULTS: Eleven of 17 first-order features were significantly greater in benign compared with malignant cysts. Eight higher-order gray-level co-occurrence matrix (GLCM) texture features were significantly different between groups, 5 of which were greater in the benign population. CONCLUSIONS: Apparent diffusion coefficient-derived texture measures may help differentiate between benign and malignant Bosniak IIF and III cysts.