Accuracy Of Prostate Cancer Detection Research Articles

Reduction of false positives using zone-specific prostate-specific antigen density for prostate MRI-based biopsy decision strategies.

To develop and test zone-specific prostate-specific antigen density (sPSAD) combined with PI-RADS to guide prostate biopsy decision strategies (BDS). This retrospective study included consecutive patients, who underwent prostate MRI and biopsy (01/2012-10/2018). The whole gland and transition zone (TZ) were segmented at MRI using a retrained deep learning system (DLS; nnU-Net) to calculate PSAD and sPSAD, respectively. Additionally, sPSAD and PI-RADS were combined in a BDS, and diagnostic performances to detect Grade Group ≥ 2 (GG ≥ 2) prostate cancer were compared. Patient-based cancer detection using sPSAD was assessed by bootstrapping with 1000 repetitions and reported as area under the curve (AUC). Clinical utility of the BDS was tested in the hold-out test set using decision curve analysis. Statistics included nonparametric DeLong test for AUCs and Fisher-Yates test for remaining performance metrics. A total of 1604 patients aged 67 (interquartile range, 61-73) with 48% GG ≥ 2 prevalence (774/1604) were evaluated. By employing DLS-based prostate and TZ volumes (DICE coefficients of 0.89 (95% confidence interval, 0.80-0.97) and 0.84 (0.70-0.99)), GG ≥ 2 detection using PSAD was inferior to sPSAD (AUC, 0.71 (0.68-0.74)/0.73 (0.70-0.76); p < 0.001). Combining PI-RADS with sPSAD, GG ≥ 2 detection specificity doubled from 18% (10-20%) to 43% (30-44%; p < 0.001) with similar sensitivity (93% (89-96%)/97% (94-99%); p = 0.052), when biopsies were taken in PI-RADS 4-5 and 3 only if sPSAD was ≥ 0.42 ng/mL/cc as compared to all PI-RADS 3-5 cases. Additionally, using the sPSAD-based BDS, false positives were reduced by 25% (123 (104-142)/165 (146-185); p < 0.001). Using sPSAD to guide biopsy decisions in PI-RADS 3 lesions can reduce false positives at MRI while maintaining high sensitivity for GG ≥ 2 cancers. Transition zone-specific prostate-specific antigen density can improve the accuracy of prostate cancer detection compared to MRI assessments alone, by lowering false-positive cases without significantly missing men with ISUP GG ≥ 2 cancers. • Prostate biopsy decision strategies using PI-RADS at MRI are limited by a substantial proportion of false positives, not yielding grade group ≥ 2 prostate cancer. • PI-RADS combined with transition zone (TZ)-specific prostate-specific antigen density (PSAD) decreased the number of unproductive biopsies by 25% compared to PI-RADS only. • TZ-specific PSAD also improved the specificity of MRI-directed biopsies by 9% compared to the whole gland PSAD, while showing identical sensitivity.

Head-to-head comparison of prostate-specific membrane antigen PET and multiparametric MRI in the diagnosis of pretreatment patients with prostate cancer: a meta-analysis.

To compare prostate-specific membrane antigen (PSMA) PET with multiparametric MRI (mpMRI) in the diagnosis of pretreatment prostate cancer (PCa). Pubmed, Embase, Medline, Web of Science, and Cochrane Library were searched for eligible studies published before June 22, 2022. We assessed risk of bias and applicability by using QUADAS-2 tool. Data synthesis was performed with Stata 17.0 software, using the "midas" and "meqrlogit" packages. We included 29 articles focusing on primary cancer detection, 18 articles about primary staging, and two articles containing them both. For PSMA PET versus mpMRI in primary PCa detection, sensitivities and specificities in the per-patient analysis were 0.90 and 0.84 (p<0.0001), and 0.66 and 0.60 (p <0.0001), and in the per-lesion analysis they were 0.79 and 0.78 (p <0.0001), and 0.84 and 0.82 (p <0.0001). For the per-patient analysis of PSMA PET versus mpMRI in primary staging, sensitivities and specificities in extracapsular extension detection were 0.59 and 0.66 (p =0.005), and 0.79 and 0.76 (p =0.0074), and in seminal vesicle infiltration (SVI) detection they were 0.51 and 0.60 (p =0.0008), and 0.93 and 0.96 (p =0.0092). For PSMA PET versus mpMRI in lymph node metastasis (LNM) detection, sensitivities and specificities in the per-patient analysis were 0.68 and 0.46 (p <0.0001), and 0.91 and 0.90 (p =0.81), and in the per-lesion analysis they were 0.67 and 0.36 (p <0.0001), and 0.99 and 0.99 (p =0.18). PSMA PET has higher diagnostic value than mpMRI in the detection of primary PCa. Regarding the primary staging, mpMRI has potential advantages in SVI detection, while PSMA PET has relative advantages in LNM detection. The integration of prostate-specific membrane antigen (PSMA) PET into the diagnostic pathway may be helpful for improving the accuracy of prostate cancer detection. However, further studies are needed to address the cost implications and evaluate its utility in specific patient populations or clinical scenarios. Moreover, we recommend the combination of PSMA PET and mpMRI for cancer staging. • Prostate-specific membrane antigen PET has higher sensitivity and specificity for primary tumor detection in prostate cancer compared to multiparametric MRI. • Prostate-specific membrane antigen PET also has significantly better sensitivity and specificity for lymph node metastases of prostate cancer compared to multiparametric MRI. • Multiparametric MRI has better accuracy for extracapsular extension and seminal vesicle infiltration compared to ate-specific membrane antigen PET.

Clinical Validation of Artificial Intelligence-Augmented Pathology Diagnosis Demonstrates Significant Gains in Diagnostic Accuracy in Prostate Cancer Detection.

Prostate cancer diagnosis rests on accurate assessment of tissue by a pathologist. The application of artificial intelligence (AI) to digitized whole slide images (WSIs) can aid pathologists in cancer diagnosis, but robust, diverse evidence in a simulated clinical setting is lacking. To compare the diagnostic accuracy of pathologists reading WSIs of prostatic biopsy specimens with and without AI assistance. Eighteen pathologists, 2 of whom were genitourinary subspecialists, evaluated 610 prostate needle core biopsy WSIs prepared at 218 institutions, with the option for deferral. Two evaluations were performed sequentially for each WSI: initially without assistance, and immediately thereafter aided by Paige Prostate (PaPr), a deep learning-based system that provides a WSI-level binary classification of suspicious for cancer or benign and pinpoints the location that has the greatest probability of harboring cancer on suspicious WSIs. Pathologists' changes in sensitivity and specificity between the assisted and unassisted modalities were assessed, together with the impact of PaPr output on the assisted reads. Using PaPr, pathologists improved their sensitivity and specificity across all histologic grades and tumor sizes. Accuracy gains on both benign and cancerous WSIs could be attributed to PaPr, which correctly classified 100% of the WSIs showing corrected diagnoses in the PaPr-assisted phase. This study demonstrates the effectiveness and safety of an AI tool for pathologists in simulated diagnostic practice, bridging the gap between computational pathology research and its clinical application, and resulted in the first US Food and Drug Administration authorization of an AI system in pathology.

Circulating chromatin conformation signatures to enhance PSA positive predictive value and overall accuracy for prostate cancer detection.

e17016 Background: Prostate cancer (PCa) has a high lifetime prevalence (one out of six men), but currently there is no widely accepted screening programme. Widely used prostate specific antigen (PSA) test at cut-off of 3.0 ng/mL does not have sufficient accuracy for detection of any prostate cancer, resulting in numerous unnecessary prostate biopsies in men with benign disease and false reassurance in some men with PCa. We have recently identified circulating chromosome conformation signatures (CCSs, Episwitch PCa test) allowing PCa detection and risk stratification in line with standards of clinical PCa staging. The purpose of this study was to determine whether combining the Episwitch PCa test with the PSA test will increase its diagnostic accuracy. Methods: n = 109 whole blood samples of men enrolled in the PROSTAGRAM screening pilot study and n = 38 samples of patients with established PCa diagnosis and cancer-negative controls from Imperial College NHS Trust were used. Samples were tested for PSA, and the presence of CCSs in the loci encoding for of DAPK1, HSD3B2, SRD5A3, MMP1, and miRNA98 associated with high-risk PCa identified in our previous work. Results: PSA &gt; 3 ng/mL alone showed a low positive predicted value (PPV) of 0.14 and a high negative predicted value (NPV) of 0.93. EpiSwitch alone showed a PPV of 0.91 and a NPV of 0.32. Combining PSA and Episwitch tests has significantly increased the PPV to 0.81 although reducing the NPV to 0.78. Furthermore, integrating PSA, as a continuous variable (rather than a dichotomised 3 ng/mL cut-off), with EpiSwitch in a new multivariant stratification model, Prostate Screening EpiSwitch (PSE) test, has yielded a remarkable combined PPV of 0.93 and NPV of 0.95 when tested on the independent prospective cohort. Conclusions: Our results demonstrate that combining the standard PSA readout with circulating chromosome conformations (PSE test) allows for significantly enhanced PSA PPV and overall accuracy for PCa detection. The PSE test is accurate, rapid, minimally invasive, and inexpensive, suggesting significant screening diagnostic potential to minimise unnecessary referrals for expensive and invasive MRI and/or biopsy testing, with further extended prospective blinded validation of the new combined signature in a screening cohort with low cancer prevalence as the next step for PSE adoption in PCa screening.

Circulating Chromosome Conformation Signatures Significantly Enhance PSA Positive Predicting Value and Overall Accuracy for Prostate Cancer Detection.

Prostate cancer (PCa) has a high lifetime prevalence (one out of six men), but currently there is no widely accepted screening programme. Widely used prostate specific antigen (PSA) test at cut-off of 3.0 ng/mL does not have sufficient accuracy for detection of any prostate cancer, resulting in numerous unnecessary prostate biopsies in men with benign disease and false reassurance in some men with PCa. We have recently identified circulating chromosome conformation signatures (CCSs, Episwitch® PCa test) allowing PCa detection and risk stratification in line with standards of clinical PCa staging. The purpose of this study was to determine whether combining the Episwitch PCa test with the PSA test will increase its diagnostic accuracy. n = 109 whole blood samples of men enrolled in the PROSTAGRAM screening pilot study and n = 38 samples of patients with established PCa diagnosis and cancer-negative controls from Imperial College NHS Trust were used. Samples were tested for PSA, and the presence of CCSs in the loci encoding for of DAPK1, HSD3B2, SRD5A3, MMP1, and miRNA98 associated with high-risk PCa identified in our previous work. PSA > 3 ng/mL alone showed a low positive predicted value (PPV) of 0.14 and a high negative predicted value (NPV) of 0.93. EpiSwitch alone showed a PPV of 0.91 and a NPV of 0.32. Combining PSA and Episwitch tests has significantly increased the PPV to 0.81 although reducing the NPV to 0.78. Furthermore, integrating PSA, as a continuous variable (rather than a dichotomised 3 ng/mL cut-off), with EpiSwitch in a new multivariant stratification model, Prostate Screening EpiSwitch (PSE) test, has yielded a remarkable combined PPV of 0.92 and NPV of 0.94 when tested on the independent prospective cohort. Our results demonstrate that combining the standard PSA readout with circulating chromosome conformations (PSE test) allows for significantly enhanced PSA PPV and overall accuracy for PCa detection. The PSE test is accurate, rapid, minimally invasive, and inexpensive, suggesting significant screening diagnostic potential to minimise unnecessary referrals for expensive and invasive MRI and/or biopsy testing. Further extended prospective blinded validation of the new combined signature in a screening cohort with low cancer prevalence would be the recommended step for PSE adoption in PCa screening.

Biparametric MRI-based radiomics classifiers for the detection of prostate cancer in patients with PSA serum levels of 4∼10 ng/mL.

To investigate the predictive performance of the combined model by integrating clinical variables and radiomic features for the accurate detection of prostate cancer (PCa) in patients with prostate-specific antigen (PSA) serum levels of 4-10 ng/mL. A retrospective study of 136 males (mean age, 67.3 ± 8.4 years) with Prostate Imaging-Reporting and Data System (PI-RADS) v2.1 category ≤3 lesions and PSA serum levels of 4-10 ng/mL were performed. All patients underwent multiparametric MRI at 3.0T and transrectal ultrasound-guided systematic prostate biopsy in their clinical workup. Radiomic features were extracted from axial T2-weighted images (T2WI) and apparent diffusion coefficient (ADC) maps of each patient using PyRadiomics. Pearson correlation coefficient (PCC) and recursive feature elimination (RFE) were implemented to identify the most significant radiomic features. Independent clinic-radiological factors were identified via univariate and multivariate regression analyses. Seven machine-learning algorithms were compared to construct a single-layered radiomic score (ie, radscore) and multivariate regression analysis was applied to construct the fusion radscore. Finally, the radiomic nomogram was further developed by integrating useful clinic-radiological factors and fusion radscore using multivariate regression analysis. The discriminative power of the nomogram was evaluated by area under the curve (AUC), DeLong test, calibration curve, decision curve analysis (DCA), and clinical impact curve (CIC). The transitional zone-specific antigen density was identified as the only independent clinic-radiological factor, which yielded an AUC of 0.592 (95% confidence interval [CI]: 0.527-0.657). The ADC radscore based on six features and Naive Bayes achieved an AUC of 0.779 (95%CI: 0.730-0.828); the T2WI radscore based on 13 features and Support Vector Machine yielded an AUC of 0.808 (95%CI: 0.761-0.855). The fusion radscore obtained an improved AUC of 0.844 (95%CI: 0.801-0.887), which was higher than the single-layered radscores (both P<0.05). The radiomic nomogram achieved the highest value among all models (all P<0.05), with an AUC of 0.872 (95%CI: 0.835-0.909). Calibration curve showed good agreement and DCA together with CIC confirmed the clinical benefits of the radiomic nomogram. The radiomic nomogram holds the potential for accurate and noninvasive identification of PCa in patients with PI-RADS ≤3 lesions and PSA of 4-10 ng/mL, which could reduce unnecessary biopsy.

Advantageous Detection of Significant Prostate Cancer Using a Low-Field, Office-Based MRI System.

Background Methods to diagnose prostate cancer (PCa), a highly prevalent disease, remain inadequate in terms of accuracy, cost, and logistical constraints for both patients and providers. Early and accurate detection of PCa is crucial to patient management, most notably in increasing quality of life and lowering cost burdens when considering the associated treatment and follow-up pathways. This article aims to discuss the impact to care pathways for nine patients whose PCa was detected by a novel Food and Drug Administration-cleared low-field magnetic resonance imager (MRI) for transperineal PCa interventions but was missed by standard-of-care systematic transrectal ultrasound (TRUS). Methodology From December 2020 to March 2022, 41 men with elevated prostate-specific antigen (PSA) levels, positive digital rectal exam findings, and Prostate Imaging Reporting & Data System scores of three or higher were enrolled.Patients first underwent targeted transperineal biopsy guided by a low-field MRI (MRIgTBx) and co-registered with T2-weighted images from a pre-procedural 3-T MRI with suspicious lesions annotated by a board-certified radiologist. Following this procedure, patients underwent standard-of-care systematic transrectal ultrasound-guided biopsy (TRUSgSBx). The entire procedure was supervised by a board-certified urologist. Results Of the 41 enrolled patients, both MRIgTBx and TRUSgSBx biopsies detected PCa in 20 patients. MRIgTBx detected PCa in an additional nine patients that were missed by TRUSgSBx. Five of the nine patients elected to pursue immediate treatment. Patients with suspected PCa and a negative biopsy return to the clinic every three to six months for PSA tests, with additional biopsies performed every year for cases with increasing PSA levels. Conclusions Early detection of PCa in nine of the 41 patients using a novel MRIgTBx method has allowed for change management resulting in an improved quality of life and cost saving for those who opted for immediate treatment. Early intervention in cases where the standard-of-care TRUSgSBx treatment was falsely negative ultimately led to a decrease in additional screening procedures, biopsies, associated tests, and an improved pathway for patient management.

Sensitive electrochemical sensing platform based on Au nanoflower-integrated carbon fiber for detecting interleukin-6 in human serum

Prostate cancer (PCa) is the most prevalent cancer worldwide, with a high mortality rate. The early and accurate detection of PCa is critical in reducing mortality and saving lives. Timely diagnosis can improve the chances of successful treatment using advanced technologies. In recent years, nanomaterial-based electrochemical sensing strategies have been adopted in clinical diagnosis, as they allow sensitive early-biomarker detections to be converged with a cost-effective electronic readout system. Herein, we present a flexible electrochemical immunosensor platform for detecting interleukin-6 (IL-6) based on an Au-integrated flexible carbon fiber (Au/CF) electrode prepared via electrodeposition and chemically modified to capture IL-6 antibodies. Several techniques are used to analyze the prepared Au/CF composite electrodes to confirm their morphology, structure, and elemental composition. Under optimum conditions, the fabricated immunosensor exhibits a wide linear dynamic ranging from 1 fg/mL to 1 μg/mL and a low detection limit of 0.056 fg/mL, with a sensitivity of 62.17 μA/(fg mL−1). The proposed fiber-based immunosensor is used to quantify the concentration of IL-6 in serum samples from clinical PCa patients (T3b and T4 stages), and the results are validated using the commercial Meso Scale Diagnostics (MSD) V-Plex method. The acceptable results yielded by the proposed immunosensor indicate that it can serve as a new platform to realize highly sensitive and cost-effective diagnostic strategies for the early diagnosis of PCa.

Training deep neural networks with noisy clinical labels: toward accurate detection of prostate cancer in US data.

Ultrasound is the standard-of-care to guide the systematic biopsy of the prostate. During the biopsy procedure, up to 12 biopsy cores are randomly sampled from six zones within the prostate, where the histopathology of those cores is used to determine the presence and grade of the cancer. Histopathology reports only provide statistical information on the presence of cancer and do not normally contain fine-grain information of cancer distribution within each core. This limitation hinders the development of machine learning models to detect the presence of cancer in ultrasound so that biopsy can be more targeted to highly suspicious prostate regions. In this paper, we tackle this challenge in the form of training with noisy labels derived from histopathology. Noisy labels often result in the model overfitting to the training data, hence limiting its generalizability. To avoid overfitting, we focus on the generalization of the features of the model and present an iterative data label refinement algorithm to amend the labels gradually. We simultaneously train two classifiers, with the same structure, and automatically stop the training when we observe any sign of overfitting. Then, we use a confident learning approach to clean the data labels and continue with the training. This process is iteratively applied to the training data and labels until convergence. We illustrate the performance of the proposed method by classifying prostate cancer using a dataset of ultrasound images from 353 biopsy cores obtained from 90 patients. We achieve area under the curve, sensitivity, specificity, and accuracy of 0.73, 0.80, 0.63, and 0.69, respectively. Our approach is able to provide clinicians with a visualization of regions that likely contain cancerous tissue to obtain more accurate biopsy samples. The results demonstrate that our proposed method produces superior accuracy compared to the state-of-the-art methods.

Dynamic Contrast Enhanced Study in Multiparametric Examination of the Prostate-Can We Make Better Use of It?

We sought to investigate whether quantitative parameters from a dynamic contrast-enhanced study can be used to differentiate cancer from normal tissue and to determine a cut-off value of specific parameters that can predict malignancy more accurately, compared to the obturator internus muscle as a reference tissue. This retrospective study included 56 patients with biopsy proven prostate cancer (PCa) after multiparametric magnetic resonance imaging (mpMRI), with a total of 70 lesions; 39 were located in the peripheral zone, and 31 in the transition zone. The quantitative parameters for all patients were calculated in the detected lesion, morphologically normal prostate tissue and the obturator internus muscle. Increase in the Ktrans value was determined in lesion-to-muscle ratio by 3.974368, which is a cut-off value to differentiate between prostate cancer and normal prostate tissue, with specificity of 72.86% and sensitivity of 91.43%. We introduced a model to detect prostate cancer that combines Ktrans lesion-to-muscle ratio value and iAUC lesion-to-muscle ratio value, which is of higher accuracy compared to individual variables. Based on this model, we identified the optimal cut-off value with 100% sensitivity and 64.28% specificity. The use of quantitative DCE pharmacokinetic parameters compared to the obturator internus muscle as reference tissue leads to higher diagnostic accuracy for prostate cancer detection.

Improving Accuracy of Prostate Cancer Detection Through Genetics

Improving Accuracy of Prostate Cancer Detection Through Genetics

Development and Validation of an Artificial Intelligence–Powered Platform for Prostate Cancer Grading and Quantification

The Gleason grading system has been the most reliable tool for the prognosis of prostate cancer since its development. However, its clinical application remains limited by interobserver variability in grading and quantification, which has negative consequences for risk assessment and clinical management of prostate cancer. To examine the impact of an artificial intelligence (AI)-assisted approach to prostate cancer grading and quantification. This diagnostic study was conducted at the University of Wisconsin-Madison from August 2, 2017, to December 30, 2019. The study chronologically selected 589 men with biopsy-confirmed prostate cancer who received care in the University of Wisconsin Health System between January 1, 2005, and February 28, 2017. A total of 1000 biopsy slides (1 or 2 slides per patient) were selected and scanned to create digital whole-slide images, which were used to develop and validate a deep convolutional neural network-based AI-powered platform. The whole-slide images were divided into a training set (n = 838) and validation set (n = 162). Three experienced academic urological pathologists (W.H., K.A.I., and R.H., hereinafter referred to as pathologists 1, 2, and 3, respectively) were involved in the validation. Data were collected between December 29, 2018, and December 20, 2019, and analyzed from January 4, 2020, to March 1, 2021. Accuracy of prostate cancer detection by the AI-powered platform and comparison of prostate cancer grading and quantification performed by the 3 pathologists using manual vs AI-assisted methods. Among 589 men with biopsy slides, the mean (SD) age was 63.8 (8.2) years, the mean (SD) prebiopsy prostate-specific antigen level was 10.2 (16.2) ng/mL, and the mean (SD) total cancer volume was 15.4% (20.1%). The AI system was able to distinguish prostate cancer from benign prostatic epithelium and stroma with high accuracy at the patch-pixel level, with an area under the receiver operating characteristic curve of 0.92 (95% CI, 0.88-0.95). The AI system achieved almost perfect agreement with the training pathologist (pathologist 1) in detecting prostate cancer at the patch-pixel level (weighted κ = 0.97; asymptotic 95% CI, 0.96-0.98) and in grading prostate cancer at the slide level (weighted κ = 0.98; asymptotic 95% CI, 0.96-1.00). Use of the AI-assisted method was associated with significant improvements in the concordance of prostate cancer grading and quantification between the 3 pathologists (eg, pathologists 1 and 2: 90.1% agreement using AI-assisted method vs 84.0% agreement using manual method; P < .001) and significantly higher weighted κ values for all pathologists (eg, pathologists 2 and 3: weighted κ = 0.92 [asymptotic 95% CI, 0.90-0.94] for AI-assisted method vs 0.76 [asymptotic 95% CI, 0.71-0.80] for manual method; P < .001) compared with the manual method. In this diagnostic study, an AI-powered platform was able to detect, grade, and quantify prostate cancer with high accuracy and efficiency and was associated with significant reductions in interobserver variability. These results suggest that an AI-powered platform could potentially transform histopathological evaluation and improve risk stratification and clinical management of prostate cancer.

Современные подходы к таргетной биопсии предстательной железы

Currently, prostate cancer (PCa) is the second most common malignancy in men after lung cancer and the fifth leading cause of death worldwide. According to world and national statistics, over the past 20 years, there has been a steady increase in both incidence and mortality from PCa. Prostate biopsy is the cornerstone of the PCa diagnosis. However, recently, systematic transrectal biopsy as a standard approach has been questioned, since it has significant drawbacks that reduce the quality of PCa diagnosis. Considering the clinical importance of accurate PCa staging, MRI-guided targeted biopsy has been developed, which is currently the most accurate technique for taking a sample of tissue from suspicious areas. The optimal approaches to targeted prostate biopsy and the potential possibilities of including multiparametric MRI in the primary diagnostic algorithm are highlighted in this review, based on the results of large studies. The method allows to increase the overall PCa detection rate, the detection rates of clinically significant PCa, reduce the frequency of diagnosis of low-risk tumors and increase the overall accuracy of PCa detection, which has an outmost importance for the patient selection for active surveillance and to control disease progression.

Diagnostic Accuracy of Magnetic Resonance Spectroscopy in Diagnosing Carcinoma Prostate

Background: Magnetic resonance spectroscopy (1H-MRS) produces a non-invasive analysis of the metabolism of the tissue, determining the relative concentrations of their metabolites and the interactions produced between them, which may be used in tumor diagnosis and showed good diagnostic accuracy for prostate cancer detection. Objective: To determine the diagnostic accuracy of Magnetic Resonance Spectroscopy (MRS) in diagnosing prostate cancer. Methodology: This was a cross sectional study, conducted at department of Radiology, Bahawal Vitoria Hospital, Bahawalpur, from July 2019 to June 2020. A total of 206 male patients with clinical suspicion of carcinoma prostate, 50-80 years of age will be included. Patients with already diagnosed carcinoma prostate, prostatic abscess, acute or chronic prostatitis were excluded. Each patient has undergone MRS examination. Each MRS was interpreted by one consultant radiologist and was looked for choline + creatine/citrate ratio for carcinoma prostate. Findings of MRS and histopathology were correlated. Data were analyzed by using SPSS 20. Results: In 120 MRS-positive patients, 108 were True Positive and 12 were False Positive. Among, 86 MRS negative patients, 16 were False Negative whereas 70 were True Negative. Overall sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of magnetic resonance spectroscopy (MRS) in diagnosing carcinoma prostate was 87.10%, 85.37%, 90.0% 81.40%, and 86.41% respectively. Conclusion: This study concluded that Magnetic Resonance Spectroscopy is the non-invasive modality of choice with high diagnostic accuracy in detecting prostate cancer.

Detection Rate of Prostate Cancer by Using Magnetic Resonance Imaging-Transrectal Ultrasound Fusion Image-Guided Prostate Biopsy at Phramongkutklao Hospital

Objective: To determine the accuracy of prostate cancer detection by using magnetic resonance imaging-transrectal ultrasound (MRI-TRUS) fusion image-guided prostate biopsy. Materials and Methods: Retrospective data were collected from the patients that underwent targeted prostate biopsy guided by MRI-TRUS fusion imaging of the prostate between January 2017 and October 2018. The data including age, serum prostate-specific antigen (PSA) levels, PSA density, prostate size, lesion size from multiparametric magnetic resonance imaging of the prostate (mpMRI), Prostate Imaging and Reporting Archiving Data System score (PI-RADS), number of targeted core biopsy, and result from the pathological diagnosis were collected. Detection rate of prostate cancer was analyzed. Results: Ninety-five prostate cancer suspected patients underwent prostate biopsy for 143 lesions. Patients’ analyses showed better overall detection rate of prostate cancer from the MRI-TRUS fusion image-guided prostate biopsy compared to the extended 12-core systematic biopsy at 49.5% versus 17.9%. Significant prostate cancer with a Gleason score of more than 6 was detected by MRI-TRUS fusion image-guided prostate biopsy at 33.7%. Prostate cancer detection rates from MRI-TRUS fusion image-guided prostate biopsy categorized by PI-RADS score 3, 4, and 5 were 21%, 48%, and 74%, respectively, which showed statistically significant detection rate with higher PI-RADS score (p&lt;0.001). Conclusion: The present study showed better prostate cancer detection rate using MRI-TRUS fusion image-guide prostate biopsy with correlation to higher PI-RADS score. Keywords: Gleason score; PI-RADS score; mpMRI; MRI-TRUS fusion image-guided prostate biopsy

MP26-10 CORRELATION OF WHOLE-MOUNT HISTOLOGY WITH FALSE POSITIVES PROSTATE IMAGING REPORTING AND DATA SYSTEMS VERSION 2 CATEGORY 4 AND 5 LESIONS

You have accessJournal of UrologyProstate Cancer: Detection & Screening II (MP26)1 Sep 2021MP26-10 CORRELATION OF WHOLE-MOUNT HISTOLOGY WITH FALSE POSITIVES PROSTATE IMAGING REPORTING AND DATA SYSTEMS VERSION 2 CATEGORY 4 AND 5 LESIONS Yu Xi Terence Law, Edwin Jonathan Aslim, Stephanie Man Chung Fook-Chong, Henry Sun Sien Ho, John Shyi Peng Yuen, Weber Kam On Lau, Lui Shiong Lee, Christopher Wai Sam Cheng, Nye Thane Ngo, Yan Mee Law, and Kae Jack Tay Yu Xi Terence LawYu Xi Terence Law More articles by this author , Edwin Jonathan AslimEdwin Jonathan Aslim More articles by this author , Stephanie Man Chung Fook-ChongStephanie Man Chung Fook-Chong More articles by this author , Henry Sun Sien HoHenry Sun Sien Ho More articles by this author , John Shyi Peng YuenJohn Shyi Peng Yuen More articles by this author , Weber Kam On LauWeber Kam On Lau More articles by this author , Lui Shiong LeeLui Shiong Lee More articles by this author , Christopher Wai Sam ChengChristopher Wai Sam Cheng More articles by this author , Nye Thane NgoNye Thane Ngo More articles by this author , Yan Mee LawYan Mee Law More articles by this author , and Kae Jack TayKae Jack Tay More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000002023.10AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: To describe the radiological, clinical and histological features associated with Prostate Imaging Reporting and Date Systems version2 (PIRADsv2) category 4 and 5 lesions that were found to be benign on whole-mount histology. METHODS: We identified men with organ confined prostate cancer who had multiparametric MRI of the prostate performed before primary radical prostatectomy. The MRI images were retrospectively reassessed to identify and grade suspicious lesions. Those of PIRADSv2 categories 4 and 5 were correlated with wholemount histology, classifying the lesions as benign, high grade (Gleason score (GS) 4-5) or low grade (GS 3) prostate cancer. Multivariate logistic regression was used to identify clinical or radiological factors associated with benign histology. RESULTS: There were 128 PIRADSv2 4/5 lesions detected on MRI in 64 patients. On histology, 22.7% (29/128) were benign, 18.0% (23/128) were low-grade (G3) cancer and 59.3% (76/128) were high-grade (GS 4/5) cancer. In 72 PIRADSv2 4 lesions, 20 lesions (28%) are benign, while in 56 PIRADSv2 5 lesions, 9 lesions (16%) are benign. Factors associated with benign pathology at multivariate analysis were lower prostate specific antigen density (PSAD) (Odds ratio (OR) 0.04; p=0.025), smaller volume of MRI lesions (OR 0.93; p=0.041) and posterior location (OR 3.13; p=0.017). The benign histological findings included benign prostate hyperplasia, inflammation (acute, chronic and granulomatous), atrophic glands and high grade prostatic intraepithelial neoplasia. CONCLUSIONS: There is a significant degree of false positive rates with multiparametric MRI for prostate in its current form. Further refinement in techniques, perhaps incorporating certain predictive factors, may improve the diagnostic accuracy for prostate cancer detection. Source of Funding: N.A. © 2021 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 206Issue Supplement 3September 2021Page: e466-e466 Advertisement Copyright & Permissions© 2021 by American Urological Association Education and Research, Inc.MetricsAuthor Information Yu Xi Terence Law More articles by this author Edwin Jonathan Aslim More articles by this author Stephanie Man Chung Fook-Chong More articles by this author Henry Sun Sien Ho More articles by this author John Shyi Peng Yuen More articles by this author Weber Kam On Lau More articles by this author Lui Shiong Lee More articles by this author Christopher Wai Sam Cheng More articles by this author Nye Thane Ngo More articles by this author Yan Mee Law More articles by this author Kae Jack Tay More articles by this author Expand All Advertisement Loading ...

MP30-07 ADDED PERFORMANCE OF SYSTEMATIC BIOPSY TO 3T MULTIPARAMETRIC MRI DERIVED MR/US FUSION BIOPSY FOR THE DETECTION AND GRADING OF PROSTATE CANCER

You have accessJournal of UrologyProstate Cancer: Detection & Screening III (MP30)1 Sep 2021MP30-07 ADDED PERFORMANCE OF SYSTEMATIC BIOPSY TO 3T MULTIPARAMETRIC MRI DERIVED MR/US FUSION BIOPSY FOR THE DETECTION AND GRADING OF PROSTATE CANCER Sohrab Afshari Mirak, Kyunghyun Sung, Ely Felker, Anthony Sisk, Robert Reiter, and Steven Raman Sohrab Afshari MirakSohrab Afshari Mirak More articles by this author , Kyunghyun SungKyunghyun Sung More articles by this author , Ely FelkerEly Felker More articles by this author , Anthony SiskAnthony Sisk More articles by this author , Robert ReiterRobert Reiter More articles by this author , and Steven RamanSteven Raman More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000002027.07AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Systematic 12-core transrectal ultrasound-guided biopsy (TRUS) is the gold standard for the detection of Prostate Cancer (PCa) lesions, which might result in over diagnosis of clinically insignificant PCa or under diagnosis of clinically significant PCa. MR/US fusion biopsy provides an opportunity for more accurate detection of PCa. In this study, we investigated the performance of 3 Tesla multiparametric MRI (3TmpMRI) with subsequent MR/US fusion prostate biopsy with subcohort analysis of Targeted Biopsy (MRgFBx) & Systematic Biopsy (SB) for the detection & grading of PCa with Whole Mount Histopathology (WMHP) reference. METHODS: This IRB approved, HIPAA compliant observational study included 309 men, who underwent 3TmpMRI with subsequent MRgFBx & SB prior to radical prostatectomy. The per-patient performance of MRgFBx with & without SB for the detection & grading (ISUP groups) of PCa was evaluated & correlated to final WMHP. RESULTS: Mean total & positive cores were 11.4 & 2.9 for SB & 5.4 & 3.3 for MRgFBx, respectively. The per-patient detection rates (DR) for SB & MRgFBx were 86.4% (267/309) & 95.5% (295/309), respectively. MRgFBx ISUP grading was concordant with WMHP in 47.9% (148/309) patients, discordant with upgrading in 27.8% (86/309) & downgrading in 20.1% (62/309) of patients. Among upgraded cases, 69.8% (60/86), 25.6% (22/86) & 4.6% (4/86) cases were upgraded by 1,2 & 3 ISUP groups, respectively. In 12% (37/309) of cases, upgrading was from PCa ISUP group 1 to ISUP group>1. SB increased the DR of PCa & csPCA of MRgFbx by 4.5% (14/309) & 3.6% (11/309.) In cases with lower prediction of grading by MRgFBx, SB increased the ISUP group of the MRgFBx in 9.4% (29/309), among which 5.5%(17/309), 2.6%(8/309) & 1.3%(4/309) were upgraded to the same grading group as WMHP, lower than the group of WMHP & falsely to higher group than WMHP, respectively. In 72.4% (21/29), the upgrading SB cores were ipsilateral to the target in MRgFbx. True upgrading by SB from ISUP group 1 to group >1 was 5.2% (16/309). CONCLUSIONS: MRgFBx has high performance for detection & grading of PCa & csPCa. SB has minimal added value to MRgFBx for improving the detection & grading. Source of Funding: This work was supported by funds from the Integrated Diagnostics Program, Department of Radiological Sciences & Department of Pathology and Laboratory Medicine, David Geffen School of Medicine at UCLA © 2021 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 206Issue Supplement 3September 2021Page: e501-e502 Advertisement Copyright & Permissions© 2021 by American Urological Association Education and Research, Inc.MetricsAuthor Information Sohrab Afshari Mirak More articles by this author Kyunghyun Sung More articles by this author Ely Felker More articles by this author Anthony Sisk More articles by this author Robert Reiter More articles by this author Steven Raman More articles by this author Expand All Advertisement Loading ...

A Comprehensive Study of Data Augmentation Strategies for Prostate Cancer Detection in Diffusion-Weighted MRI Using Convolutional Neural Networks

Data augmentation refers to a group of techniques whose goal is to battle limited amount of available data to improve model generalization and push sample distribution toward the true distribution. While different augmentation strategies and their combinations have been investigated for various computer vision tasks in the context of deep learning, a specific work in the domain of medical imaging is rare and to the best of our knowledge, there has been no dedicated work on exploring the effects of various augmentation methods on the performance of deep learning models in prostate cancer detection. In this work, we have statically applied five most frequently used augmentation techniques (random rotation, horizontal flip, vertical flip, random crop, and translation) to prostate diffusion-weighted magnetic resonance imaging training dataset of 217 patients separately and evaluated the effect of each method on the accuracy of prostate cancer detection. The augmentation algorithms were applied independently to each data channel and a shallow as well as a deep convolutional neural network (CNN) was trained on the five augmented sets separately. We used area under receiver operating characteristic (ROC) curve (AUC) to evaluate the performance of the trained CNNs on a separate test set of 95 patients, using a validation set of 102 patients for finetuning. The shallow network outperformed the deep network with the best 2D slice-based AUC of 0.85 obtained by the rotation method.

ProCDet: A New Method for Prostate Cancer Detection Based on MR Images

Prostate cancer is a malignant tumor that occurs in the male prostate. Prostate cancer lesions have the characteristics of small size and blurry outline, which is a challenge to design a robust prostate cancer detection method. At present, clinical diagnosis of prostate cancer is mainly based on magnetic resonance (MR) imaging. However, it is difficult to obtain prostate cancer data, and the data with true values is also very limited, which further increases the difficulty of prostate cancer detection methods based on MR images. To solve these problems, this paper designs a new method of prostate cancer detection based on MR images, which is recorded as ProCDet. The method consists of three modules: registration of prostate MR images, segmentation of prostate, and segmentation of prostate cancer lesions. First, the registration between different sequences of MR images is performed to find the spatial relationship between the different sequences. Then, the designed prostate segmentation network based on the attention mechanism is used to segment the prostate to remove the interference of background information. Finally, a 3D prostate cancer lesion segmentation network based on Focal Tversky Loss is applied to determine the specific location of prostate cancer. Moreover, in order to take full advantage of unlabeled prostate data, this paper designs a self-supervised learning method to improve the accuracy of prostate cancer detection. The proposed ProCDet has been experimentally verified on the ProstateX dataset. When the average number of false-positive lesions per patient is 0.6275, the true-positive rate is 91.82%. Experimental results show that the ProCDet can obtain competitive detection performance.

Multiparametric MRI-ultrasound fusion prostate biopsy in patients without prior diagnosis of prostate cancer: beyond centers of excellence

Purpose Multiparametric magnetic resonance imaging (mpMRI)-ultrasound (US) fusion prostate biopsy (FBx) has demonstrated increased accuracy for prostate cancer detection at designated centers of excellence. There is a concern if their results can be reproduced in smaller centers. Here, we evaluate the outcomes of FBx from a smaller academic center. Methods A retrospective review of patients without a prior diagnosis of prostate cancer undergoing FBx from January 2014 to November 2019 was performed. Histopathological results were grouped into low-risk disease (Grade Group 1), intermediate-risk disease (Grade Group 2 and 3), and high-risk disease (Grade Group 4 or 5). Clinically significant (CS) prostate cancer was defined as Grade Group ≥ 2. Results Five hundred and six men were included. Median age (IQR) and PSA (IQR) were 65.2 (60.3–70.2) years and 6.9 (5.2–9.7) ng/ml, respectively. There was no difference in overall cancer detection between FBx and SBx (53.6% vs 56.4% p = .1507). CS cancer detection was significantly higher with FBx (39.6% vs 35.3, p = .0275). FBx also outperformed SBx in diagnosing CS disease in patients with prior history of negative prostate biopsy (36.9% vs 27.9%, p < .001). Conclusion FBx detects a higher proportion of clinically significant disease and a lower proportion of clinically insignificant disease compared to SBx, in line with outcomes demonstrated by centers of excellence.