Pathological Characteristics of Prostate Cancer in Men Aged < 50 Years Treated with Radical Prostatectomy: a Multi-Centre Study in Korea

Clinicopathological and molecular characteristics of prostate cancer diagnosed in young men aged up to 45 years

AIMS

To characterise and compare the poorly understood clinicopathological and molecular characteristics of prostatic adenocarcinoma (PCa) in very young patients.

METHODS AND RESULTS

We compared the clinicopathological and molecular characteristics of PCa diagnosed in 90 patients aged ≤45 years with those of PCa diagnosed in 200 patients of typical screening age (i.e. 60-65 years). Patients diagnosed at a younger age had a higher frequency of a family history of PCa and lower prostate-specific antigen (PSA) levels than those diagnosed at regular screening age. There were no statistically significant differences in clinical stage or pathological characteristics of the core biopsy specimens between the groups. Young patients had a higher frequency of Grade Group 1 disease at radical prostatectomy. A subset of 13 aggressive PCa cases from young patients underwent successful DNA-based next-generation sequencing. In all, 46.2% (6/13) had TMPRSS2 rearrangements and 23.1% (3/13) had relevant pathogenic variants in DNA damage repair genes, including a mismatch repair-deficient case with biallelic inactivation of MLH1. No statistically significant differences were observed in PCa-specific recurrence/progression between the younger and older patients, including after adjustment for clinical stage, PSA level, and Grade Group.

CONCLUSIONS

In this study, the clinicopathological and molecular features of PCa diagnosed in young patients were comparable to those of PCa diagnosed in patients of screening age. Early-onset PCa cases were not enriched in any of the known molecular PCa subtypes in this small series.

An Efficient Lightweight CNN and Ensemble Machine Learning Classification of Prostate Tissue Using Multilevel Feature Analysis

Prostate carcinoma is caused when cells and glands in the prostate change their shape and size from normal to abnormal. Typically, the pathologist’s goal is to classify the staining slides and differentiate normal from abnormal tissue. In the present study, we used a computational approach to classify images and features of benign and malignant tissues using artificial intelligence (AI) techniques. Here, we introduce two lightweight convolutional neural network (CNN) architectures and an ensemble machine learning (EML) method for image and feature classification, respectively. Moreover, the classification using pre-trained models and handcrafted features was carried out for comparative analysis. The binary classification was performed to classify between the two grade groups (benign vs. malignant) and quantile-quantile plots were used to show their predicted outcomes. Our proposed models for deep learning (DL) and machine learning (ML) classification achieved promising accuracies of 94.0% and 92.0%, respectively, based on non-handcrafted features extracted from CNN layers. Therefore, these models were able to predict nearly perfectly accurately using few trainable parameters or CNN layers, highlighting the importance of DL and ML techniques and suggesting that the computational analysis of microscopic anatomy will be essential to the future practice of pathology.

Clinicopathological characteristics of localized prostate cancer in younger men aged ≤ 50 years treated with radical prostatectomy in the PSA era: A systematic review and meta-analysis

Objectives

With the rapid increase in younger age prostate cancer (PCa) patients, the impact of younger age on decision‐making for PCa treatment needs to be revaluated in the new era.

Materials and Methods

A systematic literature search was performed using PubMed, EMBASE, and Web of Science up to October 2019 to identify the eligible radical prostatectomy (RP) studies focusing on understanding the impact of age on clinicopathological features and oncological prognosis in patients with localized PCa in PSA era. Meta‐analyses were conducted using available hazard ratios (HRs) from both univariate and multivariate analyses.

Results

Twenty‐six studies including 391 068 patients with RP treatments from the PSA era were included. Of these studies, age of 50 years old (age50) is the most commonly used cut‐off age to separate the younger patient group (including either age < 50 or age ≤ 50) from the older patient group. In these studies, the incidence of younger patients varied between 2.6% and 16.6% with a median of 8.3%. Younger patients consistently showed more favorable clinicopathological features correlated with better BCR prognosis. Meta‐analyses showed a 1.38‐fold improved BCR survival of younger patients in multivariate analysis. Among the high‐risk PCa patients, younger age was independently associated with worse oncological outcomes in multivariate analyses.

Conclusion

In this study, we found younger age correlated with favorable clinicopathological characteristics and better BCR prognosis in low‐ to intermediate‐risk patients. In high‐risk group patients, younger patients often showed significantly worse oncological outcomes. Our study results suggest that age 50 could be used as a practical cut‐off age to separate younger age patients from older age PCa patients.

Multi-Features Classification of Prostate Carcinoma Observed in Histological Sections: Analysis of Wavelet-Based Texture and Colour Features

Microscopic biopsy images are coloured in nature because pathologists use the haematoxylin and eosin chemical colour dyes for biopsy examinations. In this study, biopsy images are used for histological grading and the analysis of benign and malignant prostate tissues. The following PCa grades are analysed in the present study: benign, grade 3, grade 4, and grade 5. Biopsy imaging has become increasingly important for the clinical assessment of PCa. In order to analyse and classify the histological grades of prostate carcinomas, pixel-based colour moment descriptor (PCMD) and gray-level co-occurrence matrix (GLCM) methods were used to extract the most significant features for multilayer perceptron (MLP) neural network classification. Haar wavelet transformation was carried out to extract GLCM texture features, and colour features were extracted from RGB (red/green/blue) colour images of prostate tissues. The MANOVA statistical test was performed to select significant features based on F-values and P-values using the R programming language. We obtained an average highest accuracy of 92.7% using level-1 wavelet texture and colour features. The MLP classifier performed well, and our study shows promising results based on multi-feature classification of histological sections of prostate carcinomas.