Role of transrectal ultrasonography in the prediction of prostate cancer: artificial neural network analysis

A systematic review of the applications of Expert Systems (ES) and machine learning (ML) in clinical urology

BACKGROUND

Testing a hypothesis for 'factors-outcome effect' is a common quest, but standard statistical regression analysis tools are rendered ineffective by data contaminated with too many noisy variables. Expert Systems (ES) can provide an alternative methodology in analysing data to identify variables with the highest correlation to the outcome. By applying their effective machine learning (ML) abilities, significant research time and costs can be saved. The study aims to systematically review the applications of ES in urological research and their methodological models for effective multi-variate analysis. Their domains, development and validity will be identified.

METHODS

The PRISMA methodology was applied to formulate an effective method for data gathering and analysis. This study search included seven most relevant information sources: WEB OF SCIENCE, EMBASE, BIOSIS CITATION INDEX, SCOPUS, PUBMED, Google Scholar and MEDLINE. Eligible articles were included if they applied one of the known ML models for a clear urological research question involving multivariate analysis. Only articles with pertinent research methods in ES models were included. The analysed data included the system model, applications, input/output variables, target user, validation, and outcomes. Both ML models and the variable analysis were comparatively reported for each system.

RESULTS

The search identified n = 1087 articles from all databases and n = 712 were eligible for examination against inclusion criteria. A total of 168 systems were finally included and systematically analysed demonstrating a recent increase in uptake of ES in academic urology in particular artificial neural networks with 31 systems. Most of the systems were applied in urological oncology (prostate cancer = 15, bladder cancer = 13) where diagnostic, prognostic and survival predictor markers were investigated. Due to the heterogeneity of models and their statistical tests, a meta-analysis was not feasible.

CONCLUSION

ES utility offers an effective ML potential and their applications in research have demonstrated a valid model for multi-variate analysis. The complexity of their development can challenge their uptake in urological clinics whilst the limitation of the statistical tools in this domain has created a gap for further research studies. Integration of computer scientists in academic units has promoted the use of ES in clinical urological research.

Focal lesion at the midline of the prostate on transrectal ultrasonography: take it or leave it?

PURPOSE

The purpose of this study was to analyze the detection rate of prostate cancers from targeted biopsy specimens of midline focal lesions and to investigate the ultrasonographic findings to reduce unnecessary additional targeted biopsies.

METHODS

Ninety-eight men with midline focal lesions detected on transrectal ultrasonography were enrolled. Additional targeted biopsies for midline focal lesions were performed after 12-core random systematic biopsies. Correlations between the ultrasonographic characteristics of midline focal lesions and the pathologic results were analyzed.

RESULTS

Twenty of 98 targeted biopsy cores (20.4%) were positive for malignancy. In a univariate analysis, midline focal lesions without bulging contours (P=0.023), with involved margins (P=0.001), without hypoechoic perilesional rims (P=0.005), and with longer diameters (P=0.005) were statistically significant for cancer detection. In a multivariate analysis, involved margin (P=0.027), having longer diameter (P=0.011) or absence of hypoechoic perilesional rim (P=0.025) made a statistically significant contribution to cancer detection.

CONCLUSION

Biopsy of midline focal lesions was not always non-significant in the detection of prostate cancer. Additional targeted biopsies should be considered in cases of midline focal lesions with involved margins but without hypoechoic perilesional rims.

Artificial neural networks and prostate cancer--tools for diagnosis and management

Artificial neural networks (ANNs) are mathematical models that are based on biological neural networks and are composed of interconnected groups of artificial neurons. ANNs are used to map and predict outcomes in complex relationships between given 'inputs' and sought-after 'outputs' and can also be used find patterns in datasets. In medicine, ANN applications have been used in cancer diagnosis, staging and recurrence prediction since the mid-1990s, when an enormous effort was initiated, especially in prostate cancer detection. Modern ANNs can incorporate new biomarkers and imaging data to improve their predictive power and can offer a number of advantages as clinical decision making tools, such as easy handling of distribution-free input parameters. Most importantly, ANNs consider nonlinear relationships among input data that cannot always be recognized by conventional analyses. In the future, complex medical diagnostic and treatment decisions will be increasingly based on ANNs and other multivariate models.

Beyond diagnosis: evolving prostate biopsy in the era of focal therapy

Despite decades of use as the “gold standard” in the detection of prostate cancer, the optimal biopsy regimen is still not universally agreed upon. While important aspects such as the need for laterally placed biopsies and the importance of apical cancer are known, repeated studies have shown significant patients with cancer on subsequent biopsy when the original biopsy was negative and an ongoing suspicion of cancer remained. Attempts to maximise the effectiveness of repeat biopsies have given rise to the alternate approaches of saturation biopsy and the transperineal approach. Recent interest in focal treatment of prostate cancer has further highlighted the need for accurate detection of prostate cancer, and in response, the introduction of transperineal template-guided biopsy. While the saturation biopsy approach and the transperineal template approach increase the detection rate of cancer in men with a previous negative biopsy and appear to have acceptable morbidity, there is a lack of clinical trials evaluating the different biopsy strategies. This paper reviews the evolution of prostatic biopsy and current controversies.

Image-based clinical decision support for transrectal ultrasound in the diagnosis of prostate cancer: comparison of multiple logistic regression, artificial neural network, and support vector machine

PURPOSE

We developed a multiple logistic regression model, an artificial neural network (ANN), and a support vector machine (SVM) model to predict the outcome of a prostate biopsy, and compared the accuracies of each model.

METHOD

One thousand and seventy-seven consecutive patients who had undergone transrectal ultrasound (TRUS)-guided prostate biopsy were enrolled in the study. Clinical decision models were constructed from the input data of age, digital rectal examination findings, prostate-specific antigen (PSA), PSA density (PSAD), PSAD in transitional zone, and TRUS findings. The patients were divided into the training and test groups in a randomized fashion. Areas under the receiver operating characteristic (ROC) curve (AUC, Az) were calculated to summarize the overall performance of each decision model for the task of prostate cancer prediction.

RESULTS

The Az values of the ROC curves for the use of multiple logistic regression analysis, ANN, and the SVM were 0.768, 0.778, and 0.847, respectively. Pairwise comparison of the ROC curves determined that the performance of the SVM was superior to that of the ANN or the multiple logistic regression model.

CONCLUSION

Image-based clinical decision support models allow patients to be informed of the actual probability of having a prostate cancer.

Techniques and predictive models to improve prostate cancer detection

The use of prostate-specific antigen (PSA) as a screening test remains controversial. There have been several attempts to refine PSA measurements to improve its predictive value. These modifications, including PSA density, PSA kinetics, and the measurement of PSA isoforms, have met with limited success. Therefore, complex statistical and computational models have been created to assess an individual's risk of prostate cancer more accurately. In this review, the authors examined the methods used to modify PSA as well as various predictive models used in prostate cancer detection. They described the mathematical underpinnings of these techniques along with their intrinsic strengths and weaknesses, and they assessed the accuracy of these methods, which have been shown to be better than physicians' judgment at predicting a man's risk of cancer. Without understanding the design and limitations of these methods, they can be applied inappropriately, leading to incorrect conclusions. These models are important components in counseling patients on their risk of prostate cancer and also help in the design of clinical trials by stratifying patients into different risk categories. Thus, it is incumbent on both clinicians and researchers to become familiar with these tools. Cancer 2009;115(13 suppl):3085-99. (c) 2009 American Cancer Society.

Classification of focal prostatic lesions on transrectal ultrasound (TRUS) and the accuracy of TRUS to diagnose prostate cancer

Objective

To improve the diagnostic efficacy of transrectal ultrasound (TRUS)-guided targeted prostatic biopsies, we have suggested the use of a new scoring system for the prediction of malignancies regarding the characteristics of focal suspicious lesions as depicted on TRUS.

Materials and Methods

A total of 350 consecutive patients with or without prostate cancer who underwent targeted biopsies for 358 lesions were included in the study. The data obtained from participants were randomized into two groups; the training set (n = 240) and the test set (n = 118). The characteristics of focal suspicious lesions were evaluated for the training set and the correlation between TRUS findings and the presence of a malignancy was analyzed. Multiple logistic regression analysis was used to identify variables capable of predicting prostatic cancer. A scoring system that used a 5-point scale for better malignancy prediction was determined from the training set. Positive predictive values for malignancy prediction and the diagnostic accuracy of the scored components with the use of receiver operating characteristic curve analysis were evaluated by test set analyses.

Results

Subsequent multiple logistic regression analysis determined that shape, margin irregularity, and vascularity were factors significantly and independently associated with the presence of a malignancy. Based on the use of the scoring system for malignancy prediction derived from the significant TRUS findings and the interactions of characteristics, a positive predictive value of 80% was achieved for a score of 4 when applied to the test set. The area under the receiver operating characteristic curve (AUC) for the overall lesion score was 0.81.

Conclusion

We have demonstrated that a scoring system for malignancy prediction developed for the characteristics of focal suspicious lesions as depicted on TRUS can help predict the outcome of TRUS-guided biopsies.

Computer-aided prostate cancer detection using texture features and clinical features in ultrasound image

In this paper, we propose a new prostate detection method using multiresolution autocorrelation texture features and clinical features such as location and shape of tumor. With the proposed method, we can detect cancerous tissues efficiently with high specificity (about 90-95%)and high sensitivity (about 92-96%) by the measurement of the number of correctly classified pixels. Multiresolution autocorrelation can detect cancerous tissues efficiently, and clinical knowledge helps to discriminate the cancer region by location and shape of the region and increases specificity. The support vector machine is used to classify tissues based on those features. The proposed method will be helpful in formulating a more reliable diagnosis, increasing diagnosis efficiency.

PSA and new biomarkers within multivariate models to improve early detection of prostate cancer

This review gives an overview of the use of prostate-specific antigen (PSA) and percent free-PSA (%fPSA)-based artificial neural networks (ANNs) and logistic regression models (LR) to reduce unnecessary prostate biopsies. There is a clear advantage in including clinical data such as age, digital rectal examination and transrectal ultrasound (TRUS) variables like prostate volume and PSA density as additional factors to tPSA and %fPSA within ANNs and LR models. There is also positive impact of tPSA and fPSA assays on the outcome of ANNs. New markers provide additional value within ANNs but to prove their clinical usefulness further testing is necessary.