A machine learning-assisted decision-support model to better identify patients with prostate cancer requiring an extended pelvic lymph node dissection

Can Machine Learning Models Detect and Predict Lymph Node Involvement in Prostate Cancer? A Comprehensive Systematic Review

(1) Background: Recently, Artificial Intelligence (AI)-based models have been investigated for lymph node involvement (LNI) detection and prediction in Prostate cancer (PCa) patients, in order to reduce surgical risks and improve patient outcomes. This review aims to gather and analyze the few studies available in the literature to examine their initial findings. (2) Methods: Two reviewers conducted independently a search of MEDLINE databases, identifying articles exploring AI's role in PCa LNI. Sixteen studies were selected, and their methodological quality was appraised using the Radiomics Quality Score. (3) Results: AI models in Magnetic Resonance Imaging (MRI)-based studies exhibited comparable LNI prediction accuracy to standard nomograms. Computed Tomography (CT)-based and Positron Emission Tomography (PET)-CT models demonstrated high diagnostic and prognostic results. (4) Conclusions: AI models showed promising results in LN metastasis prediction and detection in PCa patients. Limitations of the reviewed studies encompass retrospective design, non-standardization, manual segmentation, and limited studies and participants. Further research is crucial to enhance AI tools' effectiveness in this area.

Biopsy-free AI-aided precision MRI assessment in prediction of prostate cancer biochemical recurrence

BACKGROUND

To investigate the predictive ability of high-throughput MRI with deep survival networks for biochemical recurrence (BCR) of prostate cancer (PCa) after prostatectomy.

METHODS

Clinical-MRI and histopathologic data of 579 (train/test, 463/116) PCa patients were retrospectively collected. The deep survival network (iBCR-Net) is based on stepwise processing operations, which first built an MRI radiomics signature (RadS) for BCR, and predicted the T3 stage and lymph node metastasis (LN+) of tumour using two predefined AI models. Subsequently, clinical, imaging and histopathological variables were integrated into iBCR-Net for BCR prediction.

RESULTS

RadS, derived from 2554 MRI features, was identified as an independent predictor of BCR. Two predefined AI models achieved an accuracy of 82.6% and 78.4% in staging T3 and LN+. The iBCR-Net, when expressed as a presurgical model by integrating RadS, AI-diagnosed T3 stage and PSA, can match a state-of-the-art histopathological model (C-index, 0.81 to 0.83 vs 0.79 to 0.81, p > 0.05); and has maximally 5.16-fold, 12.8-fold, and 2.09-fold (p < 0.05) benefit to conventional D'Amico score, the Cancer of the Prostate Risk Assessment (CAPRA) score and the CAPRA Postsurgical score.

CONCLUSIONS

AI-aided iBCR-Net using high-throughput MRI can predict PCa BCR accurately and thus may provide an alternative to the conventional method for PCa risk stratification.

Development and External Validation of a Machine Learning Model for Prediction of Lymph Node Metastasis in Patients with Prostate Cancer

BACKGROUND

Pelvic lymph node dissection (PLND) is the gold standard for diagnosis of lymph node involvement (LNI) in patients with prostate cancer. The Roach formula, Memorial Sloan Kettering Cancer Center (MSKCC) calculator, and Briganti 2012 nomogram are elegant and simple traditional tools used to estimate the risk of LNI and select patients for PLND.

OBJECTIVE

To determine whether machine learning (ML) can improve patient selection and outperform currently available tools for predicting LNI using similar readily available clinicopathologic variables.

DESIGN, SETTING, AND PARTICIPANTS

Retrospective data for patients treated with surgery and PLND between 1990 and 2020 in two academic institutions were used.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

We trained three models (two logistic regression models and one gradient-boosted trees-based model [XGBoost]) on data provided from one institution (n = 20267) with age, prostate-specific antigen (PSA) levels, clinical T stage, percentage positive cores, and Gleason scores as inputs. We externally validated these models using data from another institution (n = 1322) and compared their performance to that of the traditional models using the area under the receiver operating characteristic curve (AUC), calibration, and decision curve analysis (DCA).

RESULTS AND LIMITATIONS

LNI was present in 2563 patients (11.9%) overall, and in 119 patients (9%) in the validation data set. XGBoost had the best performance among all the models. On external validation, its AUC outperformed that of the Roach formula by 0.08 (95% confidence interval [CI] 0.042-0.12), the MSKCC nomogram by 0.05 (95% CI 0.016-0.070), and the Briganti nomogram by 0.03 (95% CI 0.0092-0.051; all p < 0.05). It also had better calibration and clinical utility in terms of net benefit on DCA across relevant clinical thresholds. The main limitation of the study is its retrospective design.

CONCLUSIONS

Taking all measures of performance together, ML using standard clinicopathologic variables outperforms traditional tools in predicting LNI.

PATIENT SUMMARY

Determining the risk of cancer spread to the lymph nodes in patients with prostate cancer allows surgeons to perform lymph node dissection only in patients who need it and avoid the side effects of the procedure in those who do not. In this study, we used machine learning to develop a new calculator to predict the risk of lymph node involvement that outperformed traditional tools currently used by oncologists.

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.

Development, comparison, and validation of four intelligent, practical machine learning models for patients with prostate-specific antigen in the gray zone

Purpose

Machine learning prediction models based on LogisticRegression, XGBoost, GaussianNB, and LGBMClassifier for patients in the prostate-specific antigen gray zone are to be developed and compared, identifying valuable predictors. Predictive models are to be integrated into actual clinical decisions.

Methods

Patient information was collected from December 01, 2014 to December 01, 2022 from the Department of Urology, The First Affiliated Hospital of Nanchang University. Patients with a pathological diagnosis of prostate hyperplasia or prostate cancer (any PCa) and having a prostate-specific antigen (PSA) level of 4-10 ng/mL before prostate puncture were included in the initial information collection. Eventually, 756 patients were selected. Age, total prostate-specific antigen (tPSA), free prostate-specific antigen (fPSA), fPSA/tPSA, prostate volume (PV), prostate-specific antigen density (PSAD), (fPSA/tPSA)/PSAD, and the prostate MRI results of these patients were recorded. After univariate and multivariate logistic analyses, statistically significant predictors were screened to build and compare machine learning models based on LogisticRegression, XGBoost, GaussianNB, and LGBMClassifier to determine more valuable predictors.

Results

Machine learning prediction models based on LogisticRegression, XGBoost, GaussianNB, and LGBMClassifier exhibit higher predictive power than individual metrics. The area under the curve (AUC) (95% CI), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score of the LogisticRegression machine learning prediction model were 0.932 (0.881-0.983), 0.792, 0.824, 0.919, 0.652, 0.920, and 0.728, respectively; of the XGBoost machine learning prediction model were 0.813 (0.723-0.904), 0.771, 0.800, 0.768, 0.737, 0.793 and 0.767, respectively; of the GaussianNB machine learning prediction model were 0.902 (0.843-0.962), 0.813, 0.875, 0.819, 0.600, 0.909, and 0.712, respectively; and of the LGBMClassifier machine learning prediction model were 0.886 (0.809-0.963), 0.833, 0.882, 0.806, 0.725, 0.911, and 0.796, respectively. The LogisticRegression machine learning prediction model has the highest AUC among all prediction models, and the difference between the AUC of the LogisticRegression prediction model and those of XGBoost, GaussianNB, and LGBMClassifier is statistically significant (p < 0.001).

Conclusion

Machine learning prediction models based on LogisticRegression, XGBoost, GaussianNB, and LGBMClassifier algorithms exhibit superior predictability for patients in the PSA gray area, with the LogisticRegression model yielding the best prediction. The aforementioned predictive models can be used for actual clinical decision-making.​.

The Evidence for Using Artificial Intelligence to Enhance Prostate Cancer MR Imaging

PURPOSE OF REVIEW

The purpose of this review is to summarize the current status of artificial intelligence applied to prostate cancer MR imaging.

RECENT FINDINGS

Artificial intelligence has been applied to prostate cancer MR imaging to improve its diagnostic accuracy and reproducibility of interpretation. Multiple models have been tested for gland segmentation and volume calculation, automated lesion detection, localization, and characterization, as well as prediction of tumor aggressiveness and tumor recurrence. Studies show, for example, that very robust automated gland segmentation and volume calculations can be achieved and that lesions can be detected and accurately characterized. Although results are promising, we should view these with caution. Most studies included a small sample of patients from a single institution and most models did not undergo proper external validation. More research is needed with larger and well-design studies for the development of reliable artificial intelligence tools.

Preoperative prediction of pelvic lymph nodes metastasis in prostate cancer using an ADC-based radiomics model: comparison with clinical nomograms and PI-RADS assessment

PURPOSE

To develop and test radiomics models based on manually corrected or automatically gained masks on ADC maps for pelvic lymph node metastasis (PLNM) prediction in patients with prostate cancer (PCa).

METHODS

A primary cohort of 474 patients with PCa who underwent prostate mpMRI were retrospectively enrolled for PLNM prediction between January 2017 and January 2020. They were then randomly split into training/validation (n = 332) and test (n = 142) groups for model development and internal testing. Four radiomics models were developed using four masks (manually corrected/automatic prostate gland and PCa lesion segmentation) based on the ADC maps using the primary cohort. Another cohort of 128 patients who underwent radical prostatectomy (RP) with extended pelvic lymph node dissection (ePLND) for PCa was used as the testing cohort between February 2020 and October 2021. The performance of the models was evaluated in terms of discrimination and clinical usefulness using the area under the curve (AUC) and decision curve analysis (DCA). The optimal radiomics model was further compared with Memorial Sloan Kettering Cancer Center (MSKCC) and Briganti 2017 nomograms, and PI-RADS assessment.

RESULTS

17 (13.28%) Patients with PLNM were included in the testing cohort. The radiomics model based on the mask of automatically segmented prostate obtained the highest AUC among the four radiomics models (0.73 vs. 0.63 vs. 0.70 vs. 0.56). Briganti 2017, MSKCC nomograms, and PI-RADS assessment-yielded AUCs of 0.69, 0.71, and 0.70, respectively, and no significant differences were found compared with the optimal radiomics model (P = 0.605-0.955).

CONCLUSION

The radiomics model based on the mask of automatically segmented prostate offers a non-invasive method to predict PLNM for patients with PCa. It shows comparable accuracy to the current MKSCC and Briganti nomograms.

Evaluating Incidence, Location, and Predictors of Positive Surgical Margin Among Chinese Men Undergoing Robot-Assisted Radical Prostatectomy

Purpose

To evaluate the incidence and locations of positive surgical margin (PSM) among Chinese men undergoing RARP and identify the preoperative predictors for PSM.

Methods

We retrospectively identified 393 patients who underwent RARP according to inclusion criteria by single surgeon in our hospital. PSM was defined as the presence of cancer adjacent to inked surface of the specimen and categorized into four groups based on locations: apex, posterolateral, base, and multifocal. Logistic regression analysis was performed to identify the predictors of overall and location-specific PSM.

Results

The overall PSM rate was 133/393 (34%). The PSM rates for pT2, pT3, and pT4 stage were 63/278 (23%), 50/89 (56%), and 20/26 (77%), respectively. The estimated rates for apical, posterolateral, basal, and multifocal PSM were 8%, 4%, 7%, and 14%, respectively. In univariate analysis, overall PSM related to tPSA, f/tPSA, percentage of positive needles, and Gleason score. Multifocal PSM correlated with smoking history, drinking history, tPSA, f/tPSA, percentage of positive needles, and Gleason score. In multivariate analysis, percentage of positive needles reminded the only independent predictor for overall (OR = 10.5, 95% CI: 2.58–44.4) and basal PSM (OR = 24.0, 95% CI: 3.22–179.4). The f/tPSA (OR = 2.59, 95% CI: 2.18–5.71) and percentage of positive needles (OR = 31.0, 95% CI: 3.17–303) were independent risk factors for multifocal PSM.

Conclusion

The multifocal sites were the most common location of positive surgical margin, followed by apical and basal sites among Chinese patients undergoing RARP. The percentage of positive needles was an independent predictor for overall, basal, and multifocal PSM.

Development and validation of the 3D U-Net algorithm for segmentation of pelvic lymph nodes on diffusion-weighted images

Background

The 3D U-Net model has been proved to perform well in the automatic organ segmentation. The aim of this study is to evaluate the feasibility of the 3D U-Net algorithm for the automated detection and segmentation of lymph nodes (LNs) on pelvic diffusion-weighted imaging (DWI) images.

Methods

A total of 393 DWI images of patients suspected of having prostate cancer (PCa) between January 2019 and December 2020 were collected for model development. Seventy-seven DWI images from another group of PCa patients imaged between January 2021 and April 2021 were collected for temporal validation. Segmentation performance was assessed using the Dice score, positive predictive value (PPV), true positive rate (TPR), and volumetric similarity (VS), Hausdorff distance (HD), the Average distance (AVD), and the Mahalanobis distance (MHD) with manual annotation of pelvic LNs as the reference. The accuracy with which the suspicious metastatic LNs (short diameter > 0.8 cm) were detected was evaluated using the area under the curve (AUC) at the patient level, and the precision, recall, and F1-score were determined at the lesion level. The consistency of LN staging on an hold-out test dataset between the model and radiologist was assessed using Cohen’s kappa coefficient.

Results

In the testing set used for model development, the Dice score, TPR, PPV, VS, HD, AVD and MHD values for the segmentation of suspicious LNs were 0.85, 0.82, 0.80, 0.86, 2.02 (mm), 2.01 (mm), and 1.54 (mm) respectively. The precision, recall, and F1-score for the detection of suspicious LNs were 0.97, 0.98 and 0.97, respectively. In the temporal validation dataset, the AUC of the model for identifying PCa patients with suspicious LNs was 0.963 (95% CI: 0.892–0.993). High consistency of LN staging (Kappa = 0.922) was achieved between the model and expert radiologist.

Conclusion

The 3D U-Net algorithm can accurately detect and segment pelvic LNs based on DWI images.

Artificial Intelligence Combined With Big Data to Predict Lymph Node Involvement in Prostate Cancer: A Population-Based Study

Background

A more accurate preoperative prediction of lymph node involvement (LNI) in prostate cancer (PCa) would improve clinical treatment and follow-up strategies of this disease. We developed a predictive model based on machine learning (ML) combined with big data to achieve this.

Methods

Clinicopathological characteristics of 2,884 PCa patients who underwent extended pelvic lymph node dissection (ePLND) were collected from the U.S. National Cancer Institute’s Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2015. Eight variables were included to establish an ML model. Model performance was evaluated by the receiver operating characteristic (ROC) curves and calibration plots for predictive accuracy. Decision curve analysis (DCA) and cutoff values were obtained to estimate its clinical utility.

Results

Three hundred and forty-four (11.9%) patients were identified with LNI. The five most important factors were the Gleason score, T stage of disease, percentage of positive cores, tumor size, and prostate-specific antigen levels with 158, 137, 128, 113, and 88 points, respectively. The XGBoost (XGB) model showed the best predictive performance and had the highest net benefit when compared with the other algorithms, achieving an area under the curve of 0.883. With a 5%~20% cutoff value, the XGB model performed best in reducing omissions and avoiding overtreatment of patients when dealing with LNI. This model also had a lower false-negative rate and a higher percentage of ePLND was avoided. In addition, DCA showed it has the highest net benefit across the whole range of threshold probabilities.

Conclusions

We established an ML model based on big data for predicting LNI in PCa, and it could lead to a reduction of approximately 50% of ePLND cases. In addition, only ≤3% of patients were misdiagnosed with a cutoff value ranging from 5% to 20%. This promising study warrants further validation by using a larger prospective dataset.

Standardized Reporting of Machine Learning Applications in Urology: The STREAM-URO Framework

The Standardized Reporting of Machine Learning Applications in Urology (STREAM-URO) framework was developed to provide a set of recommendations to help standardize how machine learning studies in urology are reported. This framework serves three purposes: (1) to promote high-quality studies and streamline the peer review process; (2) to enhance reproducibility, comparability, and interpretability of results; and (3) to improve engagement and literacy of machine learning within the urological community.

Applications of artificial intelligence in prostate cancer imaging

PURPOSE OF REVIEW

The purpose of this review was to identify the most recent lines of research focusing on the application of artificial intelligence (AI) in the diagnosis and staging of prostate cancer (PCa) with imaging.

RECENT FINDINGS

The majority of studies focused on the improvement in the interpretation of bi-parametric and multiparametric magnetic resonance imaging, and in the planning of image guided biopsy. These initial studies showed that AI methods based on convolutional neural networks could achieve a diagnostic performance close to that of radiologists. In addition, these methods could improve segmentation and reduce inter-reader variability. Methods based on both clinical and imaging findings could help in the identification of high-grade PCa and more aggressive disease, thus guiding treatment decisions. Though these initial results are promising, only few studies addressed the repeatability and reproducibility of the investigated AI tools. Further, large-scale validation studies are missing and no diagnostic phase III or higher studies proving improved outcomes regarding clinical decision making have been conducted.

SUMMARY

AI techniques have the potential to significantly improve and simplify diagnosis, risk stratification and staging of PCa. Larger studies with a focus on quality standards are needed to allow a widespread introduction of AI in clinical practice.

Integration of clinicopathologic identification and deep transferrable image feature representation improves predictions of lymph node metastasis in prostate cancer

Background

Accurate identification of pelvic lymph node metastasis (PLNM) in patients with prostate cancer (PCa) is crucial for determining appropriate treatment options. Here, we built a PLNM-Risk calculator to obtain a precisely informed decision about whether to perform extended pelvic lymph node dissection (ePLND).

Methods

The PLNM-Risk calculator was developed in 280 patients and verified internally in 71 patients and externally in 50 patients by integrating a set of radiologists’ interpretations, clinicopathological factors and newly refined imaging indicators from MR images with radiomics machine learning and deep transfer learning algorithms. Its clinical applicability was compared with Briganti and Memorial Sloan Kettering Cancer Center (MSKCC) nomograms.

Findings

The PLNM-Risk achieved good diagnostic discrimination with areas under the receiver operating characteristic curve (AUCs) of 0.93 (95% CI, 0.90-0.96), 0.92 (95% CI, 0.84-0.97) and 0.76 (95% CI, 0.62-0.87) in the training/validation, internal test and external test cohorts, respectively. If the number of ePLNDs missed was controlled at < 2%, PLNM-Risk provided both a higher number of ePLNDs spared (PLNM-Risk 59.6% vs MSKCC 44.9% vs Briganti 38.9%) and a lower number of false positives (PLNM-Risk 59.3% vs MSKCC 70.1% and Briganti 72.7%). In follow-up, patients stratified by the PLNM-Risk calculator showed significantly different biochemical recurrence rates after surgery.

Interpretation

The PLNM-Risk calculator offers a noninvasive clinical biomarker to predict PLNM for patients with PCa. It shows improved accuracy of diagnosis support and reduced overtreatment burdens for patients with findings suggestive of PCa.

Funding

This work was supported by the Key Research and Development Program of Jiangsu Province (BE2017756) and the Suzhou Science and Technology Bureau-Science and Technology Demonstration Project (SS201808).

Machine learning-assisted decision-support models to better predict patients with calculous pyonephrosis

Background

To develop a machine learning (ML)-assisted model capable of accurately identifying patients with calculous pyonephrosis before making treatment decisions by integrating multiple clinical characteristics.

Methods

We retrospectively collected data from patients with obstructed hydronephrosis who underwent retrograde ureteral stent insertion, percutaneous nephrostomy (PCN), or percutaneous nephrolithotomy (PCNL). The study cohort was divided into training and testing datasets in a 70:30 ratio for further analysis. We developed 5 ML-assisted models from 22 clinical features using logistic regression (LR), LR optimized by least absolute shrinkage and selection operator (Lasso) regularization (Lasso-LR), support vector machine (SVM), extreme gradient boosting (XGBoost), and random forest (RF). The area under the curve (AUC) was applied to determine the model with the highest discrimination. Decision curve analysis (DCA) was used to investigate the clinical net benefit associated with using the predictive models.

Results

A total of 322 patients were included, with 225 patients in the training dataset, and 97 patients in the testing dataset. The XGBoost model showed good discrimination with the AUC, accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 0.981, 0.991, 0.962, 1.000, 1.000, and 0.989, respectively, followed by SVM [AUC =0.985, 95% confidence interval (CI): 0.970–1.000], Lasso-LR (AUC =0.977, 95% CI: 0.958–0.996), LR (AUC =0.936, 95% CI: 0.905–0.968), and RF (AUC =0.920, 95% CI: 0.870–0.970). Validation of the model showed that SVM yielded the highest AUC (0.977, 95% CI: 0.952–1.000), followed by Lasso-LR (AUC =0.959, 95% CI: 0.921–0.997), XGBoost (AUC =0.958, 95% CI: 0.902–1.000), LR (AUC =0.932, 95% CI: 0.878–0.987), and RF (AUC =0.868, 95% CI: 0.779–0.958) in the testing dataset.

Conclusions

Our ML-based models had good discrimination in predicting patients with obstructed hydronephrosis at high risk of harboring pyonephrosis, and the use of these models may be greatly beneficial to urologists in treatment planning, patient selection, and decision-making.

Multivariable Models Incorporating Multiparametric Magnetic Resonance Imaging Efficiently Predict Results of Prostate Biopsy and Reduce Unnecessary Biopsy

Purpose

We sought to develop diagnostic models incorporating mpMRI examination to identify PCa (Gleason score≥3+3) and CSPCa (Gleason score≥3+4) to reduce overdiagnosis and overtreatment.

Methods

We retrospectively identified 784 patients according to inclusion criteria between 2016 and 2020. The cohort was split into a training cohort of 548 (70%) patients and a validation cohort of 236 (30%) patients. Age, PSA derivatives, prostate volume, and mpMRI parameters were assessed as predictors for PCa and CSPCa. The multivariable models based on clinical parameters were evaluated using area under the curve (AUC), calibration plots, and decision curve analysis (DCA).

Results

Univariate analysis showed that age, tPSA, PSAD, prostate volume, MRI-PCa, MRI-seminal vesicle invasion, and MRI-lymph node invasion were significant predictors for both PCa and CSPCa (each p≤0.001). PSAD has the highest diagnostic accuracy in predicting PCa (AUC=0.79) and CSPCa (AUC=0.79). The multivariable models for PCa (AUC=0.92, 95% CI: 0.88–0.96) and CSPCa (AUC=0.95, 95% CI: 0.92–0.97) were significantly higher than the combination of derivatives for PSA (p=0.041 and 0.009 for PCa and CSPCa, respectively) or mpMRI (each p<0.001) in diagnostic accuracy. And the multivariable models for PCa and CSPCa illustrated better calibration and substantial improvement in DCA at threshold above 10%, compared with PSA or mpMRI derivatives. The PCa model with a 30% cutoff or CSPCa model with a 20% cutoff could spare the number of biopsies by 53%, and avoid the number of benign biopsies over 80%, while keeping a 95% sensitivity for detecting CSPCa.

Conclusion

Our multivariable models could reduce unnecessary biopsy without comprising the ability to diagnose CSPCa. Further prospective validation is required.