Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer

Abstract

ObjectiveTo develop and validate a noninvasive radiomic-based machine learning (ML) model to identify P504s/P63 status and further achieve the diagnosis of prostate cancer (PCa).MethodsA retrospective dataset of patients with preoperative prostate MRI examination and P504s/P63 pathological immunohistochemical results between June 2016 and February 2021 was conducted. As indicated by P504s/P63 expression, the patients were divided into label 0 (atypical prostatic hyperplasia), label 1 (benign prostatic hyperplasia, BPH) and label 2 (PCa) groups. This study employed T2WI, DWI and ADC sequences to assess prostate diseases and manually segmented regions of interest (ROIs) with Artificial Intelligence Kit software for radiomics feature acquisition. Feature dimensionality reduction and selection were performed by using a mutual information algorithm. Based on screened features, P504s/P63 prediction models were established by random forest (RF), gradient boosting decision tree (GBDT), logistic regression (LR), adaptive boosting (AdaBoost) and k-nearest neighbor (KNN) algorithms. The performance was evaluated by the area under the ROC curve (AUC) and accuracy.ResultsA total of 315 patients were enrolled. Among the 851 radiomic features, the 32 top features were derived from T2WI, in which the gray-level run length matrix (GLRLM) and gray-level cooccurrence matrix (GLCM) features accounted for the largest proportion. Among the five models, the RF algorithm performed best in general evaluations (microaverage AUC=0.920, macroaverage AUC=0.870) and provided the most accurate result in further sublabel prediction (the accuracies of label 0, 1, and 2 were 0.831, 0.831, and 0.932, respectively). In comparative sequence analyses, T2WI was the best single-sequence candidate (microaverage AUC=0.94 and macroaverage AUC=0.78). The merged datasets of T2WI, DWI, and ADC yielded optimal AUCs (microaverage AUC=0.930 and macroaverage AUC=0.900).ConclusionsThe radiomic-based RF classifier has the potential to be used to evaluate the presurgical P504s/P63 status and further diagnose PCa noninvasively and accurately.

A noninvasive method for predicting clinically significant prostate cancer using magnetic resonance imaging combined with PRKY promoter methylation level: a machine learning study

“…Additionally, the AUC of T2WI was higher than that of ADC in our study, which is different from the findings of several previous studies [ 25 , 31 ]. However, Liu et al observed the same phenomenon as in our research [ 24 ]. The reason might be related to the following points.…”

“…The T2WI-clinic-combined model exhibited an AUC of 0.94, and the T2-methylation-clinic-combined model reached a higher AUC of 0.97. Previous studies have shown the high predictive value of MRI features for prostate cancer, Liu et al used multiphase MRI features to predict P504s/P63 Immunohistochemical Expression and reached an AUC of 0.93, Qiao et al also constructed a prediction model for Gleason grade group with T2 and DWI features, and the AUC of which was 0.92 [ 24 , 25 ]. The same results were observed in our research, which demonstrated greater efficacy in csPCA diagnosis.…”

Assessing the diagnostic impact of P63, PSA and BCL-2 proteins in premalignant and malignant prostate tissues

“…13 There is a possibility that prostate-associated antigens will be produced as a consequence of abnormalities in the development of prostate epithelial cells. 14 Prostatespecific antigen (PSA)-a secreted protease, prostatespecific membrane antigen (PSMA)-a highly specific membrane antigen found on their plasma membrane, p63a rare positive prostatic adenocarcinoma, and BCL-2 family proteins-essential regulators of pathways involved in cell death are all examples of these antigens. 12 From this study using IHC analysis, the expressions of PSA, P63 and BCL-2 were expressed in 80 retrieved blocks of prostatic tissues with 40 BPH and 40 CaP.…”

Prognostic Value and Quantitative CT Analysis in RANKL Expression of Spinal GCTB in the Denosumab Era: A Machine Learning Approach

“…Tumor multi-omics can be combined with predictive machine learning models, which could be the new digital method on the road to precision cancer medicine. In previous studies of biomarkers for tumor types such as lung cancer, glioma, breast cancer, and prostate cancer, radiomics is found to have the potential as a means to non-invasively predict the status of tumor biomarkers [ 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 ]. Radiomics approaches combined with a noninvasive machine learning model with tumor immunohistochemistry could improve treatment selection.…”