CT radiomics for differentiating oncocytoma from renal cell carcinomas: Systematic review and meta-analysis.

BACKGROUND: Radiomics is a type of quantitative analysis that provides a more objective approach to detecting tumor subtypes using medical imaging. The goal of this paper is to conduct a comprehensive assessment of the literature on computed tomography (CT) radiomics for distinguishing renal cell carcinomas (RCCs) from oncocytoma. METHODS: From February 15th 2012 to 2022, we conducted a broad search of the current literature using the PubMed/MEDLINE, Google scholar, Cochrane Library, Embase, and Web of Science. A meta-analysis of radiomics studies concentrating on discriminating between oncocytoma and RCCs was performed, and the risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies method. The pooled sensitivity, specificity, and diagnostic odds ratio were evaluated via a random-effects model, which was applied for the meta-analysis. This study is registered with PROSPERO (CRD42022311575). RESULTS: After screening the search results, we identified 6 studies that utilized radiomics to distinguish oncocytoma from other renal tumors; there were a total of 1064 lesions in 1049 patients (288 oncocytoma lesions vs 776 RCCs lesions). The meta-analysis found substantial heterogeneity among the included studies, with pooled sensitivity and specificity of 0.818 [0.619-0.926] and 0.808 [0.537-0.938], for detecting different subtypes of RCCs (clear cell RCC, chromophobe RCC, and papillary RCC) from oncocytoma. Also, a pooled sensitivity and specificity of 0.83 [0.498-0.960] and 0.92 [0.825-0.965], respectively, was found in detecting oncocytoma from chromophobe RCC specifically. CONCLUSIONS: According to this study, CT radiomics has a high degree of accuracy in distinguishing RCCs from RO, including chromophobe RCCs from RO. Radiomics algorithms have the potential to improve diagnosis in scenarios that have traditionally been ambiguous. However, in order for this modality to be implemented in the clinical setting, standardization of image acquisition and segmentation protocols as well as inter-institutional sharing of software is warranted.

Deep learning-based decision forest for hereditary clear cell renal cell carcinoma segmentation on MRI.

BACKGROUND: von Hippel-Lindau syndrome (VHL) is an autosomal dominant hereditary syndrome with an increased predisposition of developing numerous cysts and tumors, almost exclusively clear cell renal cell carcinoma (ccRCC). Considering the lifelong surveillance in such patients to monitor the disease, patients with VHL are preferentially imaged using MRI to eliminate radiation exposure. PURPOSE: Segmentation of kidney and tumor structures on MRI in VHL patients is useful in lesion characterization (e.g., cyst vs. tumor), volumetric lesion analysis, and tumor growth prediction. However, automated tasks such as ccRCC segmentation on MRI is sparsely studied. We develop segmentation methodology for ccRCC on T1 weighted precontrast, corticomedullary, nephrogenic, and excretory contrast phase MRI. METHODS: We applied a new neural network approache using a novel differentiable decision forest, called hinge forest (HF), to segment kidney parenchyma, cyst, and ccRCC tumors in 117 images from 115 patients. This data set represented an unprecedented 504 ccRCCs with 1171 cystic lesions obtained at five different MRI scanners. The HF architecture was compared with U-Net on 10 randomized splits with 75% used for training and 25% used for testing. Both methods were trained with Adam using default parameters ( α = 0.001 , ß 1 = 0.9 , ß 2 = 0.999 $\alpha = 0.001,\ \beta _1 = 0.9,\ \beta _2 = 0.999$ ) over 1000 epochs. We further demonstrated some interpretability of our HF method by exploiting decision tree structure. RESULTS: The HF achieved an average kidney, cyst, and tumor Dice similarity coefficient (DSC) of 0.75 ± 0.03, 0.44 ± 0.05, 0.53 ± 0.04, respectively, while U-Net achieved an average kidney, cyst, and tumor DSC of 0.78 ± 0.02, 0.41 ± 0.04, 0.46 ± 0.05, respectively. The HF significantly outperformed U-Net on tumors while U-Net significantly outperformed HF when segmenting kidney parenchymas ( α < 0.01 $\alpha < 0.01$ ). CONCLUSIONS: For the task of ccRCC segmentation, the HF can offer better segmentation performance compared to the traditional U-Net architecture. The leaf maps can glean hints about deep learning features that might prove to be useful in other automated tasks such as tumor characterization.

Automatic segmentation of clear cell renal cell tumors, kidney, and cysts in patients with von Hippel-Lindau syndrome using U-net architecture on magnetic resonance images.

We demonstrate automated segmentation of clear cell renal cell carcinomas (ccRCC), cysts, and surrounding normal kidney parenchyma in patients with von Hippel-Lindau (VHL) syndrome using convolutional neural networks (CNN) on Magnetic Resonance Imaging (MRI). We queried 115 VHL patients and 117 scans (3 patients have two separate scans) with 504 ccRCCs and 1171 cysts from 2015 to 2021. Lesions were manually segmented on T1 excretory phase, co-registered on all contrast-enhanced T1 sequences and used to train 2D and 3D U-Net. The U-Net performance was evaluated on 10 randomized splits of the cohort. The models were evaluated using the dice similarity coefficient (DSC). Our 2D U-Net achieved an average ccRCC lesion detection Area under the curve (AUC) of 0.88 and DSC scores of 0.78, 0.40, and 0.46 for segmentation of the kidney, cysts, and tumors, respectively. Our 3D U-Net achieved an average ccRCC lesion detection AUC of 0.79 and DSC scores of 0.67, 0.32, and 0.34 for kidney, cysts, and tumors, respectively. We demonstrated good detection and moderate segmentation results using U-Net for ccRCC on MRI. Automatic detection and segmentation of normal renal parenchyma, cysts, and masses may assist radiologists in quantifying the burden of disease in patients with VHL.

An MRI-based radiomics model to predict clear cell renal cell carcinoma growth rate classes in patients with von Hippel-Lindau syndrome.

PURPOSE: Upfront knowledge of tumor growth rates of clear cell renal cell carcinoma in von Hippel-Lindau syndrome (VHL) patients can allow for a more personalized approach to either surveillance imaging frequency or surgical planning. In this study, we implement a machine learning algorithm utilizing radiomic features of renal tumors identified on baseline magnetic resonance imaging (MRI) in VHL patients to predict the volumetric growth rate category of these tumors. MATERIALS AND METHODS: A total of 73 VHL patients with 173 pathologically confirmed Clear Cell Renal Cell Carcinoma (ccRCCs) underwent MRI at least at two different time points between 2015 and 2021. Each tumor was manually segmented in excretory phase contrast T1 weighed MRI and co-registered on pre-contrast, corticomedullary and nephrographic phases. Radiomic features and volumetric data from each tumor were extracted using the PyRadiomics library in Python (4544 total features). Tumor doubling time (DT) was calculated and patients were divided into two groups: DT < = 1 year and DT > 1 year. Random forest classifier (RFC) was used to predict the DT category. To measure prediction performance, the cohort was randomly divided into 100 training and test sets (80% and 20%). Model performance was evaluated using area under curve of receiver operating characteristic curve (AUC-ROC), as well as accuracy, F1, precision and recall, reported as percentages with 95% confidence intervals (CIs). RESULTS: The average age of patients was 47.2 ± 10.3 years. Mean interval between MRIs for each patient was 1.3 years. Tumors included in this study were categorized into 155 Grade 2; 16 Grade 3; and 2 Grade 4. Mean accuracy of RFC model was 79.0% [67.4-90.6] and mean AUC-ROC of 0.795 [0.608-0.988]. The accuracy for predicting DT classes was not different among the MRI sequences (P-value = 0.56). CONCLUSION: Here we demonstrate the utility of machine learning in accurately predicting the renal tumor growth rate category of VHL patients based on radiomic features extracted from different T1-weighted pre- and post-contrast MRI sequences.