No abstract

ObjectiveTo evaluate a combination of texture features and machine learning-based analysis of apparent diffusion coefficient (ADC) maps for the prediction of Grade Group (GG) upgrading in Gleason score (GS) ≤6 prostate cancer (PCa) (GG1) and GS 3 + 4 PCa (GG2).Materials and methodsFifty-nine patients who were biopsy-proven to have GG1 or GG2 and underwent MRI examination with the same MRI scanner prior to transrectal ultrasound (TRUS)-guided systemic biopsy were included. All these patients received radical prostatectomy to confirm the final GG. Patients were divided into training cohort and test cohort. 94 texture features were extracted from ADC maps for each patient. The independent sample t-test or Mann−Whitney U test was used to identify the texture features with statistically significant differences between GG upgrading group and GG non-upgrading group. Texture features of GG1 and GG2 were compared based on the final pathology of radical prostatectomy. We used the least absolute shrinkage and selection operator (LASSO) algorithm to filter features. Four supervised machine learning methods were employed. The prediction performance of each model was evaluated by area under the receiver operating characteristic curve (AUC). The statistical comparison between AUCs was performed.ResultsSix texture features were selected for the machine learning models building. These texture features were significantly different between GG upgrading group and GG non-upgrading group (P < 0.05). The six features had no significant difference between GG1 and GG2 based on the final pathology of radical prostatectomy. All machine learning methods had satisfactory predictive efficacy. The diagnostic performance of nearest neighbor algorithm (NNA) and support vector machine (SVM) was better than random forests (RF) in the training cohort. The AUC, sensitivity, and specificity of NNA were 0.872 (95% CI: 0.750−0.994), 0.967, and 0.778, respectively. The AUC, sensitivity, and specificity of SVM were 0.861 (95%CI: 0.732−0.991), 1.000, and 0.722, respectively. There had no significant difference between AUCs in the test cohort.ConclusionA combination of texture features and machine learning-based analysis of ADC maps could predict PCa GG upgrading from biopsy to radical prostatectomy non-invasively with satisfactory predictive efficacy.

Purpose To compare the performance of histogram analysis and intra-perinodular textural transition (Ipris) for distinguishing between benign and malignant testicular lesions. Patients and Methods This retrospective study included 76 patients with 80 pathologically confirmed testicular lesions (55 malignant, 25 benign). All patients underwent preoperative T2-weighted imaging (T2WI) on a 3.0T MR scanner. All testicular lesions were manually segmented on axial T2WI, and histogram and Ipris features were extracted. Thirty enrolled patients were randomly selected to estimate the robustness of the features. We used intraclass correlation coefficients (ICCs) to evaluate intra- and interobserver agreement of features, independent t -test or Mann–Whitney U -test to compare features between benign and malignant lesions, and receiver operating characteristic curve analysis to evaluate the diagnostic performance of features. Results Eighteen histogram features and forty-eight Ipris features were extracted from T2WI of each lesion. Most (60/66) histogram and Ipris features had good robustness (ICC of both intra- and interobserver variabilities >0.6). Three histogram and nine Ipris features were significantly different between the benign and malignant groups. The area under the curve values for Energy, TotalEnergy, and Ipris_shell1_id_std were 0.807, 0.808, and 0.708, respectively, which were relatively higher than those of other features. Conclusion Ipris features may be useful for identifying benign and malignant testicular tumors but have no significant advantage over conventional histogram features.