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.

Longitudinal assessment of hepatocellular carcinoma response to stereotactic body radiation using gadoxetate-enhanced MRI: A case series.

PURPOSE: To describe the longitudinal response in patients with hepatocellular carcinoma (HCC) treated with stereotactic body radiation therapy (SBRT) and who underwent liver transplant (LT) using gadoxetate-enhanced MRI. METHODS: Five men (median age 61y, range 57-64y) with 6 HCCs treated with SBRT (median dose 50 Gy) who subsequently underwent LT were included in this retrospective study. Patients underwent gadoxetate-enhanced MRI before and after SBRT over a period of 3-18 months. Response was assessed using RECIST1.1, mRECIST, LI-RADS and image subtraction, by 2 observers in consensus. Percentage of pathologic tumor necrosis was evaluated. RESULTS: LT was performed 278 days (IQR, 148-418d) after completion of SBRT and 48d after the last MRI. Histopathology demonstrated tumor necrosis of 48 ± 42% (range, 10-100%). Mean tumor size at baseline and last post-treatment MRIs pre-LT were 2.6 ± 0.8 cm and 2.4 ± 0.9 cm. Enhancing tumor component size at baseline MRI and last post-treatment MRI pre-LT were 1.6 ± 0.8 cm and 0.9 ± 1.0 cm. Responses assessed at the last LRI pre-LT were: partial response (PR, n = 3), stable disease (SD, n = 3) using RECIST1.1; complete response (CR, n = 2), partial response (PR, n = 2), stable disease (SD, n = 2) using mRECIST; and LR-TR viable (n = 4), LR-TR non-viable (n = 2) using LI-RADS. At the last MRI pre-LT, per-lesion features of arterial phase hyperenhancement (APHE, 4/6), portal venous washout (3/6) and capsule (3/6) were observed. 5/6 lesions displayed a hypointense perilesional halo on hepatobiliary phase with a mean delay of 3.1 months post-SBRT. CONCLUSIONS: This case-series showed decreased size, persistent APHE, and incomplete pathologic necrosis in most HCCs treated with SBRT undergoing transplant.

Characterization and Prediction of Signal Intensity Changes in Normal Liver Parenchyma on Gadoxetic Acid-enhanced MRI Scans after Liver-directed Radiation Therapy.

Purpose To better characterize and understand the significance of focal liver reaction (FLR) development in a large cohort of patients who underwent gadoxetic acid-enhanced MRI after being treated with radiation therapy (RT) for hepatobiliary tumors. Materials and Methods This retrospective study evaluated 100 patients (median age, 65 years [first and third quartiles, 60-69 years]; 80 men) who underwent RT for hepatocellular carcinoma, bile duct tumors, or liver metastases at Mount Sinai Hospital between March 1, 2018, and February 29, 2020. CT simulation scans were fused to MRI scans obtained 1-6 months and 6-12 months after RT, using the hepatobiliary phase of the MRI. To define FLR volume, two radiation oncologists independently delineated the borders of the hypointensity observed on MRI scans in the liver region where RT was delivered. Biologically effective dose (BED) thresholds for the formation of FLRs were calculated, along with albumin-bilirubin (ALBI) scores and grades, and overall survival. Results Most patients developed FLRs, which decreased in volume over time. Median BED threshold values for FLR development were 63.6 Gy at 1-6 months and 88.7 Gy at 6-12 months. While higher baseline ALBI scores were associated with a lower rate of FLRs, there was a significant association between FLR volume and increase in ALBI score at 1-6 months (P = .048). Twelve- and 24-month survival estimates for the cohort were 81% and 48%, respectively. Histopathologic analysis of seven explanted liver specimens demonstrated findings consistent with radiation-induced liver disease. Conclusion FLRs were a clear measure of liver damage after RT and were associated with the development of liver dysfunction and focal radiation-induced liver disease. Keywords: MRI, Radiation Therapy Supplemental material is available for this article. © RSNA, 2022.

Multisystem Imaging Manifestations of COVID-19, Part 2: From Cardiac Complications to Pediatric Manifestations.

Infection with severe acute respiratory syndrome coronavirus 2 results in coronavirus disease 2019 (COVID-19), which was declared an official pandemic by the World Health Organization on March 11, 2020. COVID-19 has been reported in most countries, and as of August 15, 2020, there have been over 21 million cases of COVID-19 reported worldwide, with over 800 000 COVID-19-associated deaths. Although COVID-19 predominantly affects the respiratory system, it has become apparent that many other organ systems can also be involved. Imaging plays an essential role in the diagnosis of all manifestations of the disease and its related complications, and proper utilization and interpretation of imaging examinations is crucial. A comprehensive understanding of the diagnostic imaging hallmarks, imaging features, multisystem involvement, and evolution of imaging findings is essential for effective patient management and treatment. In part 1 of this article, the authors described the viral pathogenesis, diagnostic imaging hallmarks, and manifestations of the pulmonary and peripheral and central vascular systems of COVID-19. In part 2 of this article, the authors focus on the key imaging features of the varied pathologic manifestations of COVID-19, involving the cardiac, neurologic, abdominal, dermatologic and ocular, and musculoskeletal systems, as well as the pediatric and pregnancy-related manifestations of the virus. Online supplemental material is available for this article. ©RSNA, 2020.

Multisystem Imaging Manifestations of COVID-19, Part 1: Viral Pathogenesis and Pulmonary and Vascular System Complications.

Infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) results in coronavirus disease 2019 (COVID-19), which was declared an official pandemic by the World Health Organization on March 11, 2020. The infection has been reported in most countries around the world. As of August 2020, there have been over 21 million cases of COVID-19 reported worldwide, with over 800 000 COVID-19-associated deaths. It has become apparent that although COVID-19 predominantly affects the respiratory system, many other organ systems can also be involved. Imaging plays an essential role in the diagnosis of all manifestations of the disease, as well as its related complications, and proper utilization and interpretation of imaging examinations is crucial. With the growing global COVID-19 outbreak, a comprehensive understanding of the diagnostic imaging hallmarks, imaging features, multisystemic involvement, and evolution of imaging findings is essential for effective patient management and treatment. To date, only a few articles have been published that comprehensively describe the multisystemic imaging manifestations of COVID-19. The authors provide an inclusive system-by-system image-based review of this life-threatening and rapidly spreading infection. In part 1 of this article, the authors discuss general aspects of the disease, with an emphasis on virology, the pathophysiology of the virus, and clinical presentation of the disease. The key imaging features of the varied pathologic manifestations of this infection that involve the pulmonary and peripheral and central vascular systems are also described. Part 2 will focus on key imaging features of COVID-19 that involve the cardiac, neurologic, abdominal, dermatologic and ocular, and musculoskeletal systems, as well as pediatric and pregnancy-related manifestations of the virus. Vascular complications pertinent to each system will be also be discussed in part 2. Online supplemental material is available for this article. ©RSNA, 2020.