Integrative Machine Learning Prediction of Prostate Biopsy Results From Negative Multiparametric MRI

Diagnostic Performance of Prostate-specific Antigen Density for Detecting Clinically Significant Prostate Cancer in the Era of Magnetic Resonance Imaging: A Systematic Review and Meta-analysis

CONTEXT

There has been a dramatic increase in the use of prostate magnetic resonance imaging (MRI) in the diagnostic workup. With prostate volume calculated from MRI, prostate-specific antigen density (PSAD) now is a ready-to-use parameter for prostate cancer (PCa) risk stratification before prostate biopsy, especially among patients with negative MRI or equivocal lesions.

OBJECTIVE

In this review, we aimed to evaluate the diagnostic performance of PSAD for clinically significant prostate cancer (CSPCa) among patients who received MRI before prostate biopsy.

EVIDENCE ACQUISITION

Two investigators performed a systematic review according of the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) criteria. Studies (published between January 1, 2012, and December 31, 2021) reporting the diagnostic performance (outcomes) of PSAD (intervention) for CSPCa among men who received prebiopsy prostate MRI and subsequent prostate biopsy (patients), using biopsy pathology as the gold standard (comparison), were eligible for inclusion.

EVIDENCE SYNTHESIS

A total of 1536 papers were identified in PubMed, Scopus, and Embase. Of these, 248 studies were reviewed in detail and 39 were qualified. The pooled sensitivity (SENS) and specificity (SPEC) for diagnosing CSPCa among patients with positive MRI were, respectively, 0.87 and 0.35 for PSAD of 0.1 ng/ml/ml, 0.74 and 0.61 for PSAD of 0.15 ng/ml/ml, and 0.51 and 0.81 for PSAD of 0.2 ng/ml/ml. The pooled SENS and SPEC for diagnosing CSPCa among patients with negative MRI were, respectively, 0.85 and 0.36 for PSAD of 0.1 ng/ml/ml, 0.60 and 0.66 for PSAD of 0.15 ng/ml/ml, and 0.33 and 0.84 for PSAD of 0.2 ng/ml/ml. The pooled SENS and SPEC among patients with Prostate Imaging Reporting and Data System (PI-RADS) 3 or Likert 3 lesions were, respectively, 0.87 and 0.39 for PSAD of 0.1 ng/ml/ml, 0.61 and 0.69 for PSAD of 0.15 ng/ml/ml, and 0.42 and 0.82 for PSAD of 0.2 ng/ml/ml. The post-test probability for CSPCa among patients with negative MRI was 6% if PSAD was <0.15 ng/ml/ml and dropped to 4% if PSAD was <0.10 ng/ml/ml.

CONCLUSIONS

In this systematic review, we quantitatively evaluated the diagnosis performance of PSAD for CSPCa in combination with prostate MRI. It demonstrated a complementary performance and predictive value, especially among patients with negative MRI and PI-RADS 3 or Likert 3 lesions. Integration of PSAD into decision-making for prostate biopsy may facilitate improved risk-adjusted care.

PATIENT SUMMARY

Prostate-specific antigen density is a ready-to-use parameter in the era of increased magnetic resonance imaging (MRI) use in clinically significant prostate cancer (CSPCa) diagnosis. Findings suggest that the chance of having CSPCa was very low (4% or 6% for those with negative prebiopsy MRI or Prostate Imaging Reporting and Data System (Likert) score 3 lesion, respectively, if the PSAD was <0.10 ng/ml/ml), which may lower the need for biopsy in these patients.

AtPCa-Net: anatomical-aware prostate cancer detection network on multi-parametric MRI

Multi-parametric MRI (mpMRI) is widely used for prostate cancer (PCa) diagnosis. Deep learning models show good performance in detecting PCa on mpMRI, but domain-specific PCa-related anatomical information is sometimes overlooked and not fully explored even by state-of-the-art deep learning models, causing potential suboptimal performances in PCa detection. Symmetric-related anatomical information is commonly used when distinguishing PCa lesions from other visually similar but benign prostate tissue. In addition, different combinations of mpMRI findings are used for evaluating the aggressiveness of PCa for abnormal findings allocated in different prostate zones. In this study, we investigate these domain-specific anatomical properties in PCa diagnosis and how we can adopt them into the deep learning framework to improve the model's detection performance. We propose an anatomical-aware PCa detection Network (AtPCa-Net) for PCa detection on mpMRI. Experiments show that the AtPCa-Net can better utilize the anatomical-related information, and the proposed anatomical-aware designs help improve the overall model performance on both PCa detection and patient-level classification.

AI-powered radiomics: revolutionizing detection of urologic malignancies

PURPOSE OF REVIEW

This review aims to highlight the integration of artificial intelligence-powered radiomics in urologic oncology, focusing on the diagnostic and prognostic advancements in the realm of managing prostate, kidney, and bladder cancers.

RECENT FINDINGS

As artificial intelligence continues to shape the medical imaging landscape, its integration into the field of urologic oncology has led to impressive results. For prostate cancer diagnostics, machine learning has shown promise in refining clinically-significant lesion detection, with some success in deciphering ambiguous lesions on multiparametric MRI. For kidney cancer, radiomics has emerged as a valuable tool for better distinguishing between benign and malignant renal masses and predicting tumor behavior from CT or MRI scans. Meanwhile, in the arena of bladder cancer, there is a burgeoning emphasis on prediction of muscle invasive cancer and forecasting disease trajectory. However, many studies showing promise in these areas face challenges due to limited sample sizes and the need for broader external validation.

SUMMARY

Radiomics integrated with artificial intelligence offers a pioneering approach to urologic oncology, ushering in an era of enhanced diagnostic precision and reduced invasiveness, guiding patient-tailored treatment plans. Researchers must embrace broader, multicentered endeavors to harness the full potential of this field.

iPCa-Net: A CNN-based framework for predicting incidental prostate cancer using multiparametric MRI

Incidental prostate cancer (iPCa) is an early stage of clinically significant prostate cancer (csPCa) and is typically asymptomatic, making it difficult to detect in clinical practice. The objective of this study is to predict iPCa by analyzing prostatic MRIs using deep convolutional neural network (CNN). While CNN-based models in medical image analysis have made significant advancements, the iPCa prediction task presents two challenging problems: subtler differences in MRIs that are imperceptible to human eyes and a lower incidence rate, resulting in a more pronounced sample imbalance compared to routine cancer prediction. To address these two challenges, we propose a new CNN-based framework called iPCa-Net, which is designed to jointly optimize two tasks: prostate transition zone segmentation and iPCa prediction. To evaluate the performance of our model, we construct a prostatic MRI dataset comprising 9536 prostate MRI slices from 448 patients diagnosed with benign prostatic hyperplasia (BPH) at our institution. In our study, the incidence rate of iPCa is 5.13% (23 out of 448) . We compare our model with eight state-of-the-art methods for segmentation task and nine established methods for prediction task respectively using our dataset, and experimental results demonstrate the superior performance of our model. Specifically, in the prostate transition zone segmentation task, our iPCa-Net outperforms the top-performing method by 1.23% with respect to mIoU. In the iPCa prediction task, our iPCa-Net surpasses the top-performing method by 2.06% with respect to F1 score. In conclusion, our iPCa-Net demonstrates superior performance in the early identification of iPCa patients compared to state-of-the-art methods. This advancement holds great significance for appropriate disease management and is highly beneficial for patients.

What benefit can be obtained from magnetic resonance imaging diagnosis with artificial intelligence in prostate cancer compared with clinical assessments?

The present study aimed to explore the potential of artificial intelligence (AI) methodology based on magnetic resonance (MR) images to aid in the management of prostate cancer (PCa). To this end, we reviewed and summarized the studies comparing the diagnostic and predictive performance for PCa between AI and common clinical assessment methods based on MR images and/or clinical characteristics, thereby investigating whether AI methods are generally superior to common clinical assessment methods for the diagnosis and prediction fields of PCa. First, we found that, in the included studies of the present study, AI methods were generally equal to or better than the clinical assessment methods for the risk assessment of PCa, such as risk stratification of prostate lesions and the prediction of therapeutic outcomes or PCa progression. In particular, for the diagnosis of clinically significant PCa, the AI methods achieved a higher summary receiver operator characteristic curve (SROC-AUC) than that of the clinical assessment methods (0.87 vs. 0.82). For the prediction of adverse pathology, the AI methods also achieved a higher SROC-AUC than that of the clinical assessment methods (0.86 vs. 0.75). Second, as revealed by the radiomics quality score (RQS), the studies included in the present study presented a relatively high total average RQS of 15.2 (11.0-20.0). Further, the scores of the individual RQS elements implied that the AI models in these studies were constructed with relatively perfect and standard radiomics processes, but the exact generalizability and clinical practicality of the AI models should be further validated using higher levels of evidence, such as prospective studies and open-testing datasets.

Multiparametric MRI-based radiomics model to predict pelvic lymph node invasion for patients with prostate cancer

OBJECTIVE

To identify which patient with prostate cancer (PCa) could safely avoid extended pelvic lymph node dissection (ePLND) by predicting lymph node invasion (LNI), via a radiomics-based machine learning approach.

METHODS

An integrative radiomics model (IRM) was proposed to predict LNI, confirmed by the histopathologic examination, integrating radiomics features, extracted from prostatic index lesion regions on MRI images, and clinical features via SVM. The study cohort comprised 244 PCa patients with MRI and followed by radical prostatectomy (RP) and ePLND within 6 months between 2010 and 2019. The proposed IRM was trained in training/validation set and evaluated in an internal independent testing set. The model's performance was measured by area under the curve (AUC), sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). AUCs were compared via Delong test with 95% confidence interval (CI), and the rest measurements were compared via chi-squared test or Fisher's exact test.

RESULTS

Overall, 17 (10.6%) and 14 (16.7%) patients with LNI were included in training/validation set and testing set, respectively. Shape and first-order radiomics features showed usefulness in building the IRM. The proposed IRM achieved an AUC of 0.915 (95% CI: 0.846-0.984) in the testing set, superior to pre-existing nomograms whose AUCs were from 0.698 to 0.724 (p < 0.05).

CONCLUSION

The proposed IRM could be potentially feasible to predict the risk of having LNI for patients with PCa. With the improved predictability, it could be utilized to assess which patients with PCa could safely avoid ePLND, thus reduce the number of unnecessary ePLND.

KEY POINTS

• The combination of MRI-based radiomics features with clinical information improved the prediction of lymph node invasion, compared with the model using only radiomics features or clinical features. • With improved prediction performance on predicting lymph node invasion, the number of extended pelvic lymph node dissection (ePLND) could be reduced by the proposed integrative radiomics model (IRM), compared with the existing nomograms.

Machine Learning-Based Models Enhance the Prediction of Prostate Cancer

Purpose

PSA is currently the most commonly used screening indicator for prostate cancer. However, it has limited specificity for the diagnosis of prostate cancer. We aim to construct machine learning-based models and enhance the prediction of prostate cancer.

Methods

The data of 551 patients who underwent prostate biopsy were retrospectively retrieved and divided into training and test datasets in a 3:1 ratio. We constructed five PCa prediction models with four supervised machine learning algorithms, including tPSA univariate logistic regression (LR), multivariate LR, decision tree (DT), random forest (RF), and support vector machine (SVM). The five prediction models were compared based on model performance metrics, such as the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, calibration curve, and clinical decision curve analysis (DCA).

Results

All five models had good calibration in the training dataset. In the training dataset, the RF, DT, and multivariate LR models showed better discrimination, with AUCs of 1.0, 0.922 and 0.91, respectively, than the tPSA univariate LR and SVM models. In the test dataset, the multivariate LR model exhibited the best discrimination (AUC=0.918). The multivariate LR model and SVM model had better extrapolation and generalizability, with little change in performance between the training and test datasets. Compared with the DCA curves of the tPSA LR model, the other four models exhibited better net clinical benefits.

Conclusion

The results of the current retrospective study suggest that machine learning techniques can predict prostate cancer with significantly better AUC, accuracy, and net clinical benefits.