The potential role of MR based radiomic biomarkers in the characterization of focal testicular lesions

Abstract

How to differentiate with MRI-based techniques testicular germ (TGCTs) and testicular non-germ cell tumors (TNGCTs) is still under debate and Radiomics may be the turning key. Our purpose is to investigate the performance of MRI-based Radiomics signatures for the preoperative prediction of testicular neoplasm histology. The aim is twofold: (i), differentiating TGCTs and TNGCTs status and (ii) differentiating seminomas (SGCTs) from non-seminomatous (NSGCTs). Forty-two patients with pathology-proven testicular neoplasms and referred for pre-treatment MRI, were retrospectively enrolled. Thirty-two out of 44 lesions were TGCTs. Twelve out of 44 were TNGCTs or other histologies. Two radiologists segmented the volume of interest on T2-weighted images. Approximately 500 imaging features were extracted. Least Absolute Shrinkage and Selection Operator (LASSO) was applied as method for variable selection. A linear model and a linear support vector machine (SVM) were trained with selected features to assess discrimination scores for the two endpoints. LASSO identified 3 features that were employed to build fivefold validated linear discriminant and linear SVM classifiers for the TGCT-TNGCT endpoint giving an overall accuracy of 89%. Four features were employed to build another SVM for the SGCT-SNGCT endpoint with an overall accuracy of 86%. The data obtained proved that T2-weighted-based Radiomics is a promising tool in the diagnostic workup of testicular neoplasms by discriminating germ cell from non-gem cell tumors, and seminomas from non-seminomas.

When to ask for an MRI of the scrotum

“…In particular, the 10th percentile ADC yielded the highest AUC, with a sensitivity and specificity of 100% and 92.86%, respectively 69 . T2WI‐based radiomics also proved helpful to discriminate between seminomas and non‐seminomas 79 …”

“…The literature search found a total of 1106 articles (tumors, n = 584; acute scrotum, n = 193; undescended testes, n = 178; and infertility, n = 151). Ultimately, 83 articles were deemed relevant and used as the literature basis of this review (tumors, n = 50; acute scrotum, n = 6; undescended testes, n = 7; and infertility, n = 20) 6–9,13,24–33,35,43,48–110 . The flow chart of the selection process is shown in Figure 1.…”

“…Recently, whole‐lesion ADC histogram analysis and T2WI‐based radiomics provided promising results in the characterization of the histologic type of TGCNs 69,79 . A significant reduction in the median 10th, 25th, 50th, 75th, and 90th percentiles and the mean, minimum, and maximum ADC, and a significant increase in the median kurtosis and skewness of ADC was found in seminomas compared with non‐seminomas, in a retrospective study of 24 TGCNs 69 .…”

Contemporary options and future perspectives: three examples highlighting the challenges in testicular cancer imaging

“…Scrotal MRI has been investigated as another technique to improve the characterization of equivocal testicular masses [25]. New analytic methods from the MRI sequences, such as histogram, radiomics and diffusion-weighted imaging (DWI) have shown good results in distinguishing between seminomas and non-seminomas [26][27][28][29][30]. Feliciani et al were able to determine the histology of testicular tumors with an overall accuracy of 86%-89% via MRI radiomics signature [29].…”

“…New analytic methods from the MRI sequences, such as histogram, radiomics and diffusion-weighted imaging (DWI) have shown good results in distinguishing between seminomas and non-seminomas [26][27][28][29][30]. Feliciani et al were able to determine the histology of testicular tumors with an overall accuracy of 86%-89% via MRI radiomics signature [29]. The results are limited by the small number of the assessed lesions (n = 44) as well as the lack of external validation and should therefore be considered rather as a proof of concept.…”