Transrectal Ultrasound Volume Research Articles

Impact of Relative Volume Difference Between Magnetic Resonance Imaging and Three-dimensional Transrectal Ultrasound Segmentation on Clinically Significant Prostate Cancer Detection in Fusion Magnetic Resonance Imaging–targeted Biopsy

BackgroundSegmentation of three-dimensional (3D) transrectal ultrasound (TRUS) images is known to be challenging, and the clinician often lacks a reliable and easy-to-use indicator to assess its accuracy during the fusion magnetic resonance imaging (MRI)-targeted prostate biopsy procedure. ObjectiveTo assess the effect of the relative volume difference between 3D-TRUS and MRI segmentation on the outcome of a targeted biopsy. Design, setting, and participantsAll adult males who underwent an MRI-targeted prostate biopsy for clinically suspected prostate cancer between February 2012 and July 2021 were consecutively included. InterventionAll patients underwent a fusion MRI-targeted prostate biopsy with a Koelis device. Outcome measurements and statistical analysisThree-dimensional TRUS and MRI prostate volumes were calculated using 3D prostate models issued from the segmentations. The primary outcome was the relative segmentation volume difference (SVD) between transrectal ultrasound and MRI divided by the MRI volume (SVD = MRI volume − TRUS volume/MRI volume) and its correlation with clinically significant prostate cancer (eg, International Society of Urological Pathology [ISUP] ≥2) positiveness on targeted biopsy cores. Results and limitationsOverall, 1721 patients underwent a targeted biopsy resulting in a total of 5593 targeted cores. The median relative SVD was significantly lower in patients diagnosed with clinically significant prostate cancer than in those with ISUP 0–1: (6.7% [interquartile range {IQR} –2.7, 13.6] vs 8.0% [IQR 3.3, 16.4], p < 0.01). A multivariate regression analysis showed that a relative SVD of >10% of the MRI volume was associated with a lower detection rate of clinically significant prostate cancer (odds ratio = 0.74 [95% confidence interval: 0.55–0.98]; p = 0.038). ConclusionsA relative SVD of >10% of the MRI segmented volume was associated with a lower detection rate of clinically significant prostate cancer on targeted biopsy cores. The relative SVD can be used as a per-procedure quality indicator of 3D-TRUS segmentation. Patient summaryA discrepancy of ≥10% between segmented magnetic resonance imaging and transrectal ultrasound volume is associated with a reduced ability to detect significant prostate cancer on targeted biopsy cores.

Robotically controlled three-dimensional micro-ultrasound for prostate biopsy guidance.

Prostate imaging to guide biopsy remains unsatisfactory, with current solutions suffering from high complexity and poor accuracy and reliability. One novel entrant into this field is micro-ultrasound (microUS), which uses a high-frequency imaging probe to achieve very high spatial resolution, and achieves prostate cancer detection rates equivalent to multiparametric magnetic resonance imaging (mpMRI). However, the ExactVu transrectal microUS probe has a unique geometry that makes it challenging to acquire controlled, repeatable three-dimensional (3D) transrectal ultrasound (TRUS) volumes. We describe the design, fabrication, and validation of a 3D acquisition system that allows for the accurate use of the ExactVu microUS device for volumetric prostate imaging. The design uses a motorized, computer-controlled brachytherapy stepper to rotate the ExactVu transducer about its axis. We perform geometric validation using a phantom with known dimensions and compare performance with magnetic resonance imaging (MRI) using a commercial quality assurance anthropomorphic prostate phantom. Our geometric validation shows accuracy of 1mm or less in all three directions, and images of an anthropomorphic phantom qualitatively match those acquired using MRI and show good agreement quantitatively. We describe the first system to acquire robotically controlled 3D microUS images using the ExactVu microUS system. The reconstructed 3D microUS images are accurate, which will allow for future applications of the ExactVu microUS system in prostate specimen and in vivo imaging.

Increased prostate volume on transrectal ultrasound and magnetic resonance imaging are potential risk factors for acute urinary retention following transperineal prostate biopsy.

308 Background: Prostate biopsy is one of the most frequently performed procedures in urology. Recently, there has been a nationwide shift towards offering transperineal (TP) biopsies due to a reduced rate of infectious complications compared to the transrectal (TR) route. While infection may be reduced, TP biopsy is not without complication, most notably, acute urinary retention (AUR). Estimates vary as to the true rate of AUR following TP biopsy. Further, some studies have reported higher rates of AUR following TP biopsy than TR. Here we report the rate of AUR following TP biopsy at a single academic institute and relate it to risk factors for developing AUR. Methods: Retrospective case-control study. All biopsies performed with TR ultrasound (TRUS) guidance using TP technique under general anesthesia in dorsal lithotomy with a grid template. TRUS volumes were recorded during the procedure, and MRI volumes were calculated by a trained radiologist pre-biopsy. Charts of men undergoing TP biopsy from 2012 to present were reviewed. AUR was defined as patients who reported inability to urinate within 72 hours post-biopsy and underwent thorough evaluation including PVR and relevant H&amp;P and required catheter placement. Independent samples t-test was run to relate AUR to risk factors pre/post-biopsy. Results: A total of 767 TP biopsies were completed in the study window, but not all had TRUS/MRI data. Total rate of AUR was 5.48% (N=42/767). Risk factors for AUR were increased TRUS (p=0.009, [6.49, 42.30]) and MRI prostate volumes (p=0.027, [2.90, 43.13]). Age, number of cores taken, and number of previous biopsies were not associated with AUR. Conclusions: While data is scant, the rate of AUR at our institution is consistent with current estimates in the literature. There is a growing body of evidence that the rate of AUR post-TP biopsy is higher than TR, but more investigation is needed. There is also a gap in the literature on risk factors predicting AUR after TP biopsy, however our findings are relatively consistent with the few studies currently published. Urologists must recognize patients presenting for TP biopsy with large volume prostates and consider altering management to prevent AUR. [Table: see text]

Is transrectal ultrasound or magnetic resonance imaging better at estimating prostatic volume for patients with prostate cancer?

314 Background: Determining the correct size (volume) of the prostate is imperative for patients with prostate cancer. Prostate size can affect many parameters in patient care such as cores in a biopsy taken and available treatment options. Traditionally, most patients underwent transrectal ultrasound (TRUS) during prostate biopsy to estimate prostatic volume. While TRUS is still used to estimate prostate volume, more recently prostate Magnetic Resonance Imaging (MRI) has also come into favor. Current literature indicates MRI is more accurate than TRUS for prostate size, but few studies exist, and whether differences in the two are clinically significant remains uncertain. The purpose of this study was to compare prostate volumes from TRUS and MRI to gross specimens after prostatectomy. Methods: Patients who underwent radical prostatectomy for prostate cancer between 2017–2022 were identified. TRUS and MRI measurements closest to the date of surgery were obtained. These were compared to gross prostate specimens after surgery, which was considered the gold standard. All TRUS volumes were recorded by a urologist during prostate biopsy using the ellipsoid formula (L*W*H*(π/6)). MRI measurements were done by a radiologist also using the ellipsoid formula. The weight and dimensions of gross specimens were measured by a pathologist. Ellipsoid formula was then used to calculate final volume measurements in gross specimens. Paired samples t-test was used to compare averages of TRUS and MRI to the gross specimen. Results: 83 patients were included in the study with an average age at prostatectomy of 65.47 years. TRUS volume significantly differed from gross specimen volume by an average of –4.56 mL (p=0.017) and gross specimen weight by -14.31 g (p &lt;0.001). MRI volume was not significantly different from gross specimen volume, by an average of –0.56 mL (p=0.771) and was significantly different from prostate weight by –10.32 g (p &lt;0.001). When compared to one another, TRUS and MRI significantly differed on average by –4 mL (p=0.033). Conclusions: MRI is more accurate than TRUS to estimate prostate volume. Both MRI and TRUS underestimate prostate weight. Urologists should be aware of potential inaccuracies when assessing preoperative prostate volume with TRUS, and recognize MRI is the best predictor of size. While imperfect, TRUS is still relatively accurate measuring prostate volume, and given its ease of availability and cost, we feel it is a useful modality to determine prostate size. [Table: see text]

Shadow-Consistent Semi-Supervised Learning for Prostate Ultrasound Segmentation.

Prostate segmentation in transrectal ultrasound (TRUS) image is an essential prerequisite for many prostate-related clinical procedures, which, however, is also a long-standing problem due to the challenges caused by the low image quality and shadow artifacts. In this paper, we propose a Shadow-consistent Semi-supervised Learning (SCO-SSL) method with two novel mechanisms, namely shadow augmentation (Shadow-AUG) and shadow dropout (Shadow-DROP), to tackle this challenging problem. Specifically, Shadow-AUG enriches training samples by adding simulated shadow artifacts to the images to make the network robust to the shadow patterns. Shadow-DROP enforces the segmentation network to infer the prostate boundary using the neighboring shadow-free pixels. Extensive experiments are conducted on two large clinical datasets (a public dataset containing 1,761 TRUS volumes and an in-house dataset containing 662 TRUS volumes). In the fully-supervised setting, a vanilla U-Net equipped with our Shadow-AUG&Shadow-DROP outperforms the state-of-the-arts with statistical significance. In the semi-supervised setting, even with only 20% labeled training data, our SCO-SSL method still achieves highly competitive performance, suggesting great clinical value in relieving the labor of data annotation. Source code is released at https://github.com/DIAL-RPI/SCO-SSL.

Long-Term Complications of Open and Robot-Assisted Laparoscopic Radical Prostatectomy in an Afro-Caribbean Population.

BackgroundWith the Afro-Caribbean population increasing in the United States, their complication profiles following open (ORP) and robot-assisted laparoscopic (RALP) radical prostatectomy warrants investigation. The purpose of this pilot study was to evaluate differences in long-term complications between ORP and RALP in Afro-Caribbeans.MethodsA retrospective review of patients undergoing ORP or RALP between April 2010 and August 2019 at an academic medical center and county hospital was conducted. Patients who identified as Afro-Caribbean with complete data were analyzed. Complications were classified using the Clavien-Dindo system. Age, transrectal ultrasound prostate volume, preoperative prostate-specific antigen, Gleason scores, and long-term complications (persisting to at least 18 months postoperatively) were compared between procedures using the Mann-Whitney U test or Fisher’s exact test for statistical significance. Multivariable logistic regression was used to assess the odds of complications.ResultsThis study included 53 Afro-Caribbean patients (mean age±SD; 65.9±6.8 years, 30 ORP, and 23 RALP). Patients treated by RALP were younger and had lower Gleason scores. Patients who were treated by RALP had a lower association to having ≥1 complications compared to those treated by ORP (OR=0.28, 95%CI 0.09-0.89, p=0.024). In addition, >60% of complications had a Clavien-Dindo grade≤II for both procedures. RALP resulted in fewer grade II complications compared to ORP (OR=0.25, 95%CI 0.08-0.81, p=0.046).ConclusionsTreatment of Afro-Caribbeans with RALP allows for fewer complications, especially Clavien-Dindo Grade II complications. While previous investigations show that Black populations experience more complications when treated with ORP or RALP compared to other groups, their complication profile is likely not homogenous when considering their sub-ethnic background and must be investigated to understand optimal interventions for prostate cancer.

Non-infectious complications following transrectal prostate needle biopsy - Outcomes from over 8000 procedures.

BackgroundProstate needle biopsy (PNB) remains the referent standard for diagnosing prostate cancer. Contemporary data highlight an increase in PNB-related infections particularly when performed transrectally. Non-infectious complications, however, may similarly contribute to biopsy-related morbidity. We review the incidence and predictors of non-infectious complications following transrectal PNB in a large statewide quality registry.MethodsTransrectal ultrasound-guided prostate needle biopsies performed between 2015 and 2018 were retrospectively reviewed. The incidence and distribution of non-infectious complications were annotated. Clinical, demographic, and biopsy variables of interest were evaluated by logistic regression for potential association with specific types of non-infectious complications.ResultsOf 8,102 biopsies, 277 (3.4%) biopsies had reported post-procedure complications including 199 (2.5%) non-infectious and 78 (0.9%) infectious. Among the non-infectious complications, the most common events included urinary or rectal bleeding (74; 0.9%), urinary retention (70, 0.9%), vasovagal syncope (13, 0.2%), and severe post-operative pain (10, 0.1%). Approximately 56% of these non-infectious complications required an Emergency Department visit (111/199) and 27% (54/199) hospital admission for monitoring. Increasing transrectal ultrasound prostate volume was associated with post-procedure urinary retention (Odds ratio (OR) 1.07, 1.02–1.11, p = 0.002). No specific variables noted association with post-biopsy bleeding.ConclusionNon-infectious complications occurred 2.5 times more often than infectious complications following transrectal ultrasound prostate needle biopsies. Larger prostate size was associated with a greater risk of post-procedure urinary retention. These data originating from experience from over 100 urologists across different health systems provide an important framework in counseling patients regarding expectations following transrectal prostate biopsy.

Effect of dataset size, image quality, and image type on deep learning-based automatic prostate segmentation in 3D ultrasound

Three-dimensional (3D) transrectal ultrasound (TRUS) is utilized in prostate cancer diagnosis and treatment, necessitating time-consuming manual prostate segmentation. We have previously developed an automatic 3D prostate segmentation algorithm involving deep learning prediction on radially sampled 2D images followed by 3D reconstruction, trained on a large, clinically diverse dataset with variable image quality. As large clinical datasets are rare, widespread adoption of automatic segmentation could be facilitated with efficient 2D-based approaches and the development of an image quality grading method. The complete training dataset of 6761 2D images, resliced from 206 3D TRUS volumes acquired using end-fire and side-fire acquisition methods, was split to train two separate networks using either end-fire or side-fire images. Split datasets were reduced to 1000, 500, 250, and 100 2D images. For deep learning prediction, modified U-Net and U-Net++ architectures were implemented and compared using an unseen test dataset of 40 3D TRUS volumes. A 3D TRUS image quality grading scale with three factors (acquisition quality, artifact severity, and boundary visibility) was developed to assess the impact on segmentation performance. For the complete training dataset, U-Net and U-Net++ networks demonstrated equivalent performance, but when trained using split end-fire/side-fire datasets, U-Net++ significantly outperformed the U-Net. Compared to the complete training datasets, U-Net++ trained using reduced-size end-fire and side-fire datasets demonstrated equivalent performance down to 500 training images. For this dataset, image quality had no impact on segmentation performance for end-fire images but did have a significant effect for side-fire images, with boundary visibility having the largest impact. Our algorithm provided fast (<1.5 s) and accurate 3D segmentations across clinically diverse images, demonstrating generalizability and efficiency when employed on smaller datasets, supporting the potential for widespread use, even when data is scarce. The development of an image quality grading scale provides a quantitative tool for assessing segmentation performance.

Malament stitch and increased risk of bladder neck stenosis: any association following open prostatectomy in Enugu Southeast Nigeria

BackgroundMalament stitch is one of the effective techniques employed to minimize bleeding in simple open prostatectomy but concerns about possibility of increased risk of bladder neck stenosis has limited its routine use.AimWe studied patients who had open prostatectomy with Malament stitch to determine the incidence of bladder neck stenosis amongst them.Material and methodsThis was a prospective study of 72patients who had simple open prostatectomy in which malament stitch was applied from 2010 to 2020. A proforma was designed to collect data. Pretreatment variables were transrectal ultrasound (TRUS) volume of prostate, pretreatment IPSS value, postvoidal residual urine volume before surgery, weight of enucleated prostate adenoma, time to removal of Malament stitch. Outcome measures were done with post treatment IPSS and PVR at 6 weeks, 3 months and 6 months. Cystoscopy was done at 3 months or 6 months for patients with rising outcome measures to determine presence of bladder neck stenosis.ResultsThe mean age of patients in this study was 68.3 years (SD = 7.1, range 52–82). The mean of the pretreatment score for IPSS was 30.7 (SD = 3.9, range 18–34) and 5.9 (SD = 0.2) for QOLS. The mean weight of prostate estimated with ultrasound was 169.5 g and mean weight of enucleated adenoma of the prostate was 132.5 g. The mean time of removal of Malament stitch was 23.1 h. Only 3 (4.2%) patients required cystoscopy because of increasing IPSS and PVR at 3 months postprostatectomy. 2 (2.8%) patients out of 72patients were confirmed to have bladder neck stenosis at cystoscopy.ConclusionMalament stitch did not lead to significant incidence of bladder neck stenosis in this study.

Effect of urinary retention on the surgical outcome of holmium laser enucleation of the benign prostatic hyperplasia.

To evaluate the effect of urinary retention (UR) on holmium laser enucleation of the prostate (HoLEP) in patients with benign prostatic hyperplasia (BPH) and lower urinary tract symptoms. A retrospective analysis of a prospective cohort of patients who underwent HoLEP between January 2010 and December 2016 was performed. The perioperative factors, including the International Prostate Symptom Score, Overactive Bladder Symptom Score, prostate-specific antigen, urodynamic study results, uroflowmetry results, transrectal ultrasound prostate volume, operative time, morcellation time, enucleation weight, and complications, were evaluated. Postoperative evaluation was performed at 2, 3, and 6 months. Overall, 903 patients were identified. The mean age and follow-up were 68.3 years and 6 months, respectively. Among the patients, 135 (15.0%) patients had a history of acute UR (AUR), and 36 patients (4.0%) had chronic UR (CUR). The mean detrusor pressures at maximum flow were 64.4, 74.3, and 77.7 cmH2O (p<0.001). The mean maximum flow rates (Qmax) were 7.6, 6.6, and 4.8 mL/s (p<0.001). Additionally, the mean bladder outlet obstruction indices were 49.5, 61.1, and 69.4 (p<0.001). The postoperative Qmax improved in all three groups. The mean postvoid residual volumes (PVRs) were 55, 75, and 333 mL preoperatively; 20, 29, and 66 mL at 2 weeks; 16, 23, and 45 mL at 3 months; and 15, 22, and 52 mL at 6 months (p<0.001). Voiding symptoms, PVR, and Qmax of BPH patients with preoperative AUR and CUR significantly improved after Ho-LEP, similar to those without preoperative UR.

Enhancement of prostate cancer diagnosis by machine learning techniques: an algorithm development and validation study.

To investigate the value of machine learning(ML) in enhancing prostate cancer(PCa) diagnosis. Consecutive systematic prostate biopsies performed from Jan 2003-June 2017 were used as the training cohort, and prospective biopsies performed from July 2017-November 2019 were used as validation cohort. Men were included if PSA was 0.4-50 ng/mL, and information of digital rectal examination (DRE), Transrectal ultrasound(TRUS) prostate volume, TRUS abnormality were known. Clinically significant PCa(csPCa) was defined as Gleason 3 + 4 or above cancers. Area-under-curve (AUC) of receiver-operating characteristics (ROC) was compared between PSA, PSA density, European Randomized Study of Screening for Prostate Cancer (ERSPC) risk calculator (ERSPC-RC), and various ML techniques using PSA, DRE and TRUS information. ML techniques used included XGBoost, LightGBM, Catboost, Support vector machine (SVM), Logistic regression (LR), and Random Forest (RF), where cost sensitive learning was applied. Training and validation cohorts included 3881 and 778 consecutive men, respectively. RF model performed better than other ML techniques and PSA, PSA density and ERSPC-RC for prediction of PCa or csPCa in the validation cohort. In csPCa prediction, AUC of PSA, PSA density, ERSPC-RC and RF was 0.71, 0.80, 0.83 and 0.88 respectively. At 90-95% sensitivity for csPCa, RF model achieved a negative predictive value (NPV) of 97.5-98.0% and avoided 38.3-52.2% unnecessary biopsies. Decision curve analyses (DCA) showed RF model provided net clinical benefit over PSA, PSA density and ERSPC-RC. By using the same clinical parameters, ML techniques performed better than ERSPC-RC or PSA density in csPCa predictions, and could avoid up to 50% unnecessary biopsies.

The Comparison of Imaging and Clinical Methods to Estimate Prostate Volume: A Single-Centre Retrospective Study

Background: Prostate volume (PV) is a useful tool in risk stratification, diagnosis, and follow-up of numerous prostatic diseases including prostate cancer and benign prostatic hypertrophy. There is currently no accepted ideal PV measurement method. Objective: This study compares multiple means of PV estimation, including digital rectal examination (DRE), transrectal ultrasound (TRUS), and magnetic resonance imaging (MRI), and radical prostatectomy specimens to determine the best volume measurement style. Methods: A retrospective, observational, single-site study with patients identified using an institutional database was performed. A total of 197 patients who underwent robot-assisted radical prostatectomy were considered. Data collected included age, serum PSA at the time of the prostate biopsy, clinical T stage, Gleason score, and PVs for each of the following methods: DRE, TRUS, MRI, and surgical specimen weight (SPW) and volume. Results: A paired t test was performed, which reported a statistically significant difference between PV measures (DRE, TRUS, MRI ellipsoid, MRI bullet, SP ellipsoid, and SP bullet) and the actual prostate weight. Lowest differences were reported for SP ellipsoid volume (M = −2.37; standard deviation [SD] = 10.227; t[167] = −3.011; and p = 0.003), MRI ellipsoid volume (M = −4.318; SD = 9.53; t[167] = −5.87; and p = 0.000), and MRI bullet volume (M = 5.31; SD = 10.77; t[167] = 6.387; and p = 0.000). Conclusion: The PV obtained by MRI has proven to correlate with the PV obtained via auto-segmentation software as well as actual SPW, while also being more cost-effective and time-efficient. Therefore, demonstrating that MRI estimated the PV is an adequate method for use in clinical practice for therapeutic planning and patient follow-up.

Plasma Kinetic Enucleation vs Holmium Laser Enucleation for Treating Benign Prostatic Hyperplasia: A Randomized Controlled Trial with a 3-Year Follow-Up.

Purpose: To compare the efficacy and safety of plasma kinetic enucleation of the prostate (PKEP) with holmium laser enucleation of the prostate (HoLEP) for treatment of benign prostatic hyperplasia (BPH). Methods: A total of 160 patients with indications for the surgical treatment of BPH were randomly assigned to receive either PKEP or HoLEP prospectively. Baseline characteristics, perioperative data, and postoperative outcomes of the patients were recorded. One hundred twenty-six (78.75%) patients (PKEP 64 vs HoLEP 62) completed the 3-year follow-up assessment. Results: Patients in both groups had similar baseline characteristics. Compared with PKEP, HoLEP was associated with shorter operative time as well as take-out time, lower perioperative hemoglobin decrease, and shorter bladder irrigation time, catheterization time, and hospital stay time. PKEP was superior to HoLEP in terms of the noise of the machine and hospitalization expenses. There were no significant differences in enucleating time, resected weight, and serum sodium levels. Both groups achieved satisfactory results and maintained improvement from baseline in terms of maximum urinary flow rate (Qmax), International Prostatic Symptomatic Score, quality of life, and postvoid residual at 3-year follow-up, with no significant differences between the two procedures. Except for re-catheterization rate, postoperative data such as transrectal ultrasound volume, International Index of Erectile Function-5, and follow-up scores of the flexible cystourethroscopy results, as well as the acute and mid-to long-term complications after surgery, were statistically similar. Conclusion: The 3-year follow-up data of this randomized trial confirmed that both PKEP and HoLEP were effective and safe surgical procedures for the transurethral management of BPH. HoLEP presented certain advantages compared to PKEP, such as reduced operative duration, decreased risk of blood loss, and less bladder irrigation, hospital stay time, and re-catheterization rate, whereas PKEP had lower noise and no additional laser cost. Chinese Clinical Trial Registry (ChiCTR-TRC-13004468).

Relationship between Prostate Volume and International Prostate Symptom Score (IPSS) Degree of Tamed Prostate Enlargement on Transabdominal Ultrasonography (TAUS) and Transrectal Ultrasonography (TRUS) Examination

A B S T R A C TIntroduction: IPSS is the gold standard in measuring clinical symptoms of BPH. 1Prostate volume has been said to have a close relationship with the development ofBPH. 9 The aim of this study was to determine the relationship between prostate volumeas measured by transabdominal ultrasonography (TAUS) and transrectal (TRUS) to thedegree of IPSS. Methods: An analytic observational study with a cross sectional designwas carried out on 303 BPH patients at the General Hospital of Kariadi Hospital,Semarang. The data obtained from the TAUS, TRUS and IPSS prostate volume wereobtained from medical records for the period 2015 - 2020. The data were then analyzedby using the chi square test. Results: Patients with BPH have a TAUS prostate volumein classification I of 0 people 0%, classification II of 16 people (5.3%), classification IIIof 96 people (31.7%), classification IV of 102 people (33.7%) and classification V of 89people (29.4%). While TRUS in classification I was 0% (0 people), classification II was11 people (3.6%), classification III was 92 people (30.4%), classification IV was 110people (36.3%) and classification V of 90 people (29.7%). IPSS obtained severe IPSSdegrees, namely 192 people (63.4%), moderate degrees of 111 people (36.6%), and milddegrees 0% (0 people). The results of the Chi Square test obtained a p-value of 0.000(p &lt;0.05), indicating that there was a significant relationship between prostate volume,whether examined by transabdominal or transrectal ultrasound, and the degree ofIPSS. The correlation coefficient r = 0.925 indicates a very strong relationship betweenprostate volume as measured by both transabdominal and transrectal ultrasound withthe degree of IPSS, a positive result shows that the increase in prostate volume, thedegree of IPSS will also increase. Conclusion: There is a significant relationshipbetween prostate volume as measured by both TAUS and TRUS and the degree of IPSS.

Deep learning-based digitization of prostate brachytherapy needles in ultrasound images.

PurposeTo develop, and evaluate the performance of, a deep learning‐based three‐dimensional (3D) convolutional neural network (CNN) artificial intelligence (AI) algorithm aimed at finding needles in ultrasound images used in prostate brachytherapy.MethodsTransrectal ultrasound (TRUS) image volumes from 1102 treatments were used to create a clinical ground truth (CGT) including 24422 individual needles that had been manually digitized by medical physicists during brachytherapy procedures. A 3D CNN U‐net with 128 × 128 × 128 TRUS image volumes as input was trained using 17215 needle examples. Predictions of voxels constituting a needle were combined to yield a 3D linear function describing the localization of each needle in a TRUS volume. Manual and AI digitizations were compared in terms of the root‐mean‐square distance (RMSD) along each needle, expressed as median and interquartile range (IQR). The method was evaluated on a data set including 7207 needle examples. A subgroup of the evaluation data set (n = 188) was created, where the needles were digitized once more by a medical physicist (G1) trained in brachytherapy. The digitization procedure was timed.ResultsThe RMSD between the AI and CGT was 0.55 (IQR: 0.35–0.86) mm. In the smaller subset, the RMSD between AI and CGT was similar (0.52 [IQR: 0.33–0.79] mm) but significantly smaller (P < 0.001) than the difference of 0.75 (IQR: 0.49–1.20) mm between AI and G1. The difference between CGT and G1 was 0.80 (IQR: 0.48–1.18) mm, implying that the AI performed as well as the CGT in relation to G1. The mean time needed for human digitization was 10 min 11 sec, while the time needed for the AI was negligible.ConclusionsA 3D CNN can be trained to identify needles in TRUS images. The performance of the network was similar to that of a medical physicist trained in brachytherapy. Incorporating a CNN for needle identification can shorten brachytherapy treatment procedures substantially.

Estimation of prostate size by trans-rectal ultrasound and its correlation with DRE and endoscopic grading

Aim: Digital rectal examination (DRE) grading and the grade of prostatomegaly on cystoscopy are routinely used in clinical practice, but its correlation to prostate volume is understudied. This study was done to assess the correlation of DRE and endoscopic grading with the prostate volume on trans-rectal ultrasound (TRUS). Materials and Methods: This study was carried out in 101 eligible patients with prostatomegaly. Each patient was evaluated for three parameters, prostate volume by TRUS examination, DRE and endoscopic grading on cystoscopy. Pearson correlation coefficient was calculated to find the correlation between variables, p<0.05 was taken to be statistically significant. Data were analyzed using the Epi Info (TM) 7.2.2.2. Results: Significant positive correlation (p<0.001) was found between TRUS Volume and DRE grading (Pearson Correlation=0.945) and TRUS volume and Endoscopic grading (Pearson Correlation=0.949). Both the grading were also significantly positively correlated (Pearson Correlation=0.989, p<0.001). Conclusion: Our attempt for correlating the digital rectal grading and endoscopic grading with prostate volume is satisfactorily validated in the clinical setting. These grades are sufficient to provide a rough estimation of the prostate volume and to classify patients with prostatomegaly.

Rates of clinically significant prostate cancer in African Americans increased significantly following the 2012 US Preventative Services Task Force recommendation against prostate specific antigen screening: A Single Institution Retrospective Study.

We determined the impact of the 2012 US Preventative Services Task Force recommendation against prostate specific antigen screening on detection rates and biopsy patterns in African American and Caucasian patients. Demographics, PSA, transrectal ultrasonography volume and pathologic data were collected on patients who underwent their first ultrasound-guided prostate biopsy between January 2007 and June 2018 at a New York City Veteran Affairs Hospital. 609 biopsies were analysed preguideline (113 per year), and 487 were analysed postguideline (81 per year). There was no significant difference in the detection rates of low, intermediate or high grade PCa in Caucasians. In contrast, AfricanAmericans were significantly more likely to be diagnosed with PCa in the postguideline group (56% pre vs 66% post, P=.016), and significantly more likely to be diagnosed with intermediate-high grade PCa (38% pre vs 47% post, P=.038). Before the 2012 USPSTF recommendation, AfricanAmerican and Caucasian patients undergoing their first biopsy were equally likely to be diagnosed with high-grade PCa (11% AA vs 11% CA). After the 2012 decision, we found that AfricanAmericans were 50% more likely than Caucasians to be diagnosed with high-grade PCa on first biopsy (10% AA vs 15% CA, P=.008). In the 6years following the 2012 USPSTF recommendation, detection rates of intermediate-high risk disease remained unchanged for Caucasian patients but have increased significantly for AfricanAmericans. The results of our study strongly support the role of routine PSA screening, particularly in higher risk patients such as AfricanAmericans.

Deformable registration of PET/CT and ultrasound for disease-targeted focal prostate brachytherapy.

We propose a deformable registration algorithm for prostate-specific membrane antigen (PSMA) PET/CT and transrectal ultrasound (TRUS) fusion. Accurate registration of PSMA PET to intraoperative TRUS will allow physicians to customize dose planning based on the regions involved. The inputs to the registration algorithm are the PET/CT and TRUS volumes as well as the prostate segmentations. PET/CT and TRUS volumes are first rigidly registered by maximizing the overlap between the segmented prostate binary masks. Three-dimensional anatomical landmarks are then automatically extracted from the boundary as well as within the prostate. Then, a deformable registration is performed using a regularized thin plate spline where the landmark localization error is optimized between the extracted landmarks that are in correspondence. The proposed algorithm was evaluated on 25 prostate cancer patients treated with low-dose-rate brachytherapy. We registered the postimplant CT to TRUS using the proposed algorithm and computed target registration errors (TREs) by comparing implanted seed locations. Our approach outperforms state-of-the-art methods, with significantly lower ( ) TRE of while being computationally efficient (mean computation time of 38s). The proposed landmark-based PET/CT-TRUS deformable registration algorithm is simple, computationally efficient, and capable of producing quality registration of the prostate boundary as well as the internal gland.

Transrectal Ultrasound Prostate Volume Correlation with Serum Prostate Specific Antigen Level in Patients with Prostatic Enlargement in Portharcourt

Transrectal Ultrasound Prostate Volume Correlation with Serum Prostate Specific Antigen Level in Patients with Prostatic Enlargement in Portharcourt

Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound.

Automatic prostate segmentation in transrectal ultrasound (TRUS) images is of essential importance for image-guided prostate interventions and treatment planning. However, developing such automatic solutions remains very challenging due to the missing/ambiguous boundary and inhomogeneous intensity distribution of the prostate in TRUS, as well as the large variability in prostate shapes. This paper develops a novel 3D deep neural network equipped with attention modules for better prostate segmentation in TRUS by fully exploiting the complementary information encoded in different layers of the convolutional neural network (CNN). Our attention module utilizes the attention mechanism to selectively leverage the multi-level features integrated from different layers to refine the features at each individual layer, suppressing the non-prostate noise at shallow layers of the CNN and increasing more prostate details into features at deep layers. Experimental results on challenging 3D TRUS volumes show that our method attains satisfactory segmentation performance. The proposed attention mechanism is a general strategy to aggregate multi-level deep features and has the potential to be used for other medical image segmentation tasks. The code is publicly available at https://github.com/wulalago/DAF3D.