Dataset Information

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.

SUBMITTER: Feliciani G

PROVIDER: S-EPMC7875983 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND AND PURPOSE:Distinct molecular subgroups of pediatric medulloblastoma confer important differences in prognosis and therapy. Currently, tissue sampling is the only method to obtain information for classification. Our goal was to develop and validate radiomic and machine learning approaches for predicting molecular subgroups of pediatric medulloblastoma. MATERIALS AND METHODS:In this multi-institutional retrospective study, we evaluated MR imaging datasets of 109 pediatric patients with medulloblastoma from 3 children's hospitals from January 2001 to January 2014. A computational framework was developed to extract MR imaging-based radiomic features from tumor segmentations, and we tested 2 predictive models: a double 10-fold cross-validation using a combined dataset consisting of all 3 patient cohorts and a 3-dataset cross-validation, in which training was performed on 2 cohorts and testing was performed on the third independent cohort. We used the Wilcoxon rank sum test for feature selection with assessment of area under the receiver operating characteristic curve to evaluate model performance. RESULTS:Of 590 MR imaging-derived radiomic features, including intensity-based histograms, tumor edge-sharpness, Gabor features, and local area integral invariant features, extracted from imaging-derived tumor segmentations, tumor edge-sharpness was most useful for predicting sonic hedgehog and group 4 tumors. Receiver operating characteristic analysis revealed superior performance of the double 10-fold cross-validation model for predicting sonic hedgehog, group 3, and group 4 tumors when using combined T1- and T2-weighted images (area under the curve = 0.79, 0.70, and 0.83, respectively). With the independent 3-dataset cross-validation strategy, select radiomic features were predictive of sonic hedgehog (area under the curve = 0.70-0.73) and group 4 (area under the curve = 0.76-0.80) medulloblastoma. CONCLUSIONS:This study provides proof-of-concept results for the application of radiomic and machine learning approaches to a multi-institutional dataset for the prediction of medulloblastoma subgroups.

Project description:PurposeTo assess the performance of computer-extracted dynamic contrast material-enhanced (DCE) magnetic resonance (MR) imaging kinetic and morphologic features in the differentiation of invasive versus noninvasive breast lesions and metastatic versus nonmetastatic breast lesions.Materials and methodsIn this institutional review board-approved HIPAA-compliant study, in which the requirement for informed patient consent was waived, breast MR images were retrospectively collected. The images had been obtained with a 1.5-T MR unit by using a gadodiamide-enhanced T1-weighted spoiled gradient-recalled acquisition in the steady state sequence. The breast MR imaging database contained 132 benign, 71 ductal carcinoma in situ (DCIS), and 150 invasive ductal carcinoma (IDC) lesions. Fifty-four IDC lesions were associated with metastasis-positive lymph nodes (LNs), and 64 IDC lesions were associated with negative LNs. Lesion segmentation and extraction of morphologic and kinetic features were automatically performed by a laboratory-developed computer workstation. Features were first selected by using stepwise linear discriminant analysis and then merged by using Bayesian neural networks. Lesion classification performance was assessed with receiver operating characteristic analysis.ResultsDifferentiation of DCIS from IDC lesions yielded an area under the receiver operating characteristic curve (AUC) of 0.83 +/- 0.03 (standard error). AUCs were 0.85 +/- 0.02 for differentiation between IDC and benign lesions and 0.79 +/- 0.03 for differentiation between DCIS and benign lesions. Differentiation between IDC lesions associated with positive LNs and IDC lesions associated with negative LNs yielded an AUC of 0.82 +/- 0.04. AUCs were 0.86 +/- 0.03 for differentiation between IDC lesions associated with positive LNs and benign lesions and 0.83 +/- 0.03 for differentiation between IDC lesions associated with negative LNs and benign lesions.ConclusionComputer-aided diagnosis of breast DCE MR imaging-depicted lesions was extended from the task of discriminating between malignant and benign lesions to the prognostic tasks of distinguishing between noninvasive and invasive lesions and discriminating between metastatic and nonmetastatic lesions, yielding MR imaging-based prognostic markers.Supplemental materialhttp://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.09090838/-/DC1.

Dataset Information

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets