Search

Purpose: This study aimed to investigate the performance of multiparametric magnetic resonance imaging (mpMRI) radiomic feature-based machine learning (ML) models in classifying the Gleason grade group (GG) of prostate cancer. Methods: In this retrospective study, a total of 203 patients with histopathologically confirmed prostate cancer who underwent mpMRI before prostate biopsy were included. After manual segmentation, radiomic features (RFs) were extracted from T2-weighted, apparent diffusion coefficient, and high b-value diffusion-weighted magnetic resonance imaging (DWMRI). Patients were split into training sets and testing sets according to a ratio of 8:2. A pipeline considering combinations of two feature selection (FS) methods and six ML classifiers was developed and evaluated. The performance of models was assessed using the accuracy, sensitivity, precision, F1-measure, and the area under curve (AUC). Results: On high b-value DWMRI-derived features, a combination of FS method recursive feature elimination (RFE) and classifier random forest achieved the highest performance for classification of prostate cancer into five GGs, with 97.0% accuracy, 98.0% sensitivity, 98.0% precision, and 97.0% F1-measure. The method also achieved an average AUC for GG of 98%. Conclusion: Preoperative mpMRI radiomic analysis based on ML, as a noninvasive approach, showed good performance for classification of prostate cancer into five GGs. Advances in Knowledge: Herein, radiomic models based on preoperative mpMRI and ML were developed to classify prostate cancer into 5 GGs. Our study provides evidence that analysis of quantitative RFs extracted from high b-value DWMRI images based on a combination of FS method RFE and classifier random forest can be applied for multiclass grading of prostate cancer with an accuracy of 97.0%. [ABSTRACT FROM AUTHOR]

Background: Current cancer treatments include surgery, radiotherapy, chemotherapy, and immunotherapy. Despite these treatments, a main issue in cancer treatment is early detection. microRNAs (miRNAs) can be used as markers to diagnose and treat cancers. This study investigated the effect of radiotherapy on miR-374 expression, and APC and GSK-3β, two of its target genes, in the WNT pathway, in peripheral blood samples from radiotherapy-treated colorectal cancer (CRC) patients. Methods: Peripheral blood was collected from 25 patients before and after radiotherapy. RNA was extracted from the blood and cDNA synthesized. miR-374, APC, and GSK-3β expression was determined by real-time polymerase chain reaction (RT-PCR) and the amplicons were sequenced. Finally, the data were statistically evaluated. Results: Quantitative RT-PCR revealed significant down-regulation of miR-374 (0.63-fold) and upregulation of APC (1.12-fold) and GSK-3β (1.22-fold) in CRC patients after five weeks of radiotherapy. Sequencing of PCR-produced amplicons confirmed the conservation of mature and precursor sequences encoding miR-374. miR-374 expression changed with time after radiotherapy treatment and related tumor grading. Increased age and tumor grade positively correlated with decreased miR-374 expression. Conclusions: miR-374 expression, and that of its two target genes, APC and GSK-3β, changed after radiotherapy. These genes can likely be used as diagnostic radiotherapy markers in CRC. [ABSTRACT FROM AUTHOR]

Background: The WNT-pathway is involved in several cancers, including colorectal cancer (CRC). Many cell signaling components and pathways are controlled by microRNAs. The main purpose of the present study was to investigate the expression of hsa-miR-374, and its two target genes of the Wnt-pathway in CRC clinical samples. Methods: In this study, we predicted the miRNAs targeting key genes of WNT-pathway using bioinformatics algorithms. The expression levels of hsa-miR-374, APC and GSK-3ß on 48 pairs of Formalin-Fixed Paraffin-Embedded (FFPE) CRC tumors and marginal-tumors were evaluated using real time-PCR. Additionally, the hsa-miR-374a-5p precursor sequence was amplified by whole-blood DNA as a template. This amplicon was cloned into pEGFP-c1 expression vector and transfected into SW742 cells. Aside from this, MTT assay was performed to evaluate the effect of miR-374 on cell viability. Results: The bioinformatics analysis indicated that hsa-miR-374 binds to the regulatory region the key components of WNT-pathway, including APC and GSK-3ß considering the recognition elements and mirSVR scores. Our results revealed significant down-regulation of GSK-3ß (0.94 times, p= 0.0098) and APC (0.96 times, p= 0.03) and up-regulation of miR-374 (1.22 times, p= 0.0071) on tumor samples compared with their normal pairs. Meanwhile, the results of the over-expression of miR-374 showed down-regulation of APC and GSK-3ß. MTT-assay also indicated that the miR-374 increased cell survival. Conclusions: The results of our study indicated a concomitant change in the expression of miR-374 and its two related target genes, in clinical samples of CRC. Hsa-miR-374 might be as a helpful biomarker or therapeutic target in CRC. [ABSTRACT FROM AUTHOR]