Value of magnetic resonance angiography before prostatic artery embolization for intervention planning.

Knowledge about anatomical details seems to facilitate the procedure and planning of prostatic artery embolization (PAE) in patients with symptomatic benign prostatic hyperplasia (BPS). The aim of our study was the pre-interventional visualization of the prostatic artery (PA) with MRA and the correlation of iliac elongation and bifurcation angles with technical success of PAE and technical parameters. MRA data of patients with PAE were analysed retrospectively regarding PA visibility, PA type, vessel elongation, and defined angles were correlated with intervention time, fluoroscopy time, dose area product (DAP), cumulative air kerma (CAK), contrast media (CM) dose and technical success of embolization. T-test, ANOVA, Pearson correlation, and Kruskal-Wallis test was applied for statistical analysis. Between April 2018 and March 2021, a total of 78 patients were included. MRA identified the PA origin in 126 of 147 cases (accuracy 86%). Vessel elongation affected time for catheterization of right PA (p = 0.02), fluoroscopy time (p = 0.05), and CM dose (p = 0.02) significantly. Moderate correlation was observed for iliac bifurcation angles with DAP (r = 0.30 left; r = 0.34 right; p = 0.01) and CAK (r = 0.32 left; r = 0.36 right; p = 0.01) on both sides. Comparing the first half and second half of patients, median intervention time (125 vs. 105 min.) and number of iliac CBCT could be reduced (p < 0.001). We conclude that MRA could depict exact pelvic artery configuration, identify PA origin, and might obviate iliac CBCT. Vessel elongation of pelvic arteries increased intervention time and contrast media dose while the PA origin had no significant influence on intervention time and/or technical success.

Evaluation of the effect of prostate diameters on erectile dysfunction in patients who underwent low-anterior resection.

OBJECTIVE: Male erectile dysfunction is an important complication of rectal surgery. In this research, the effect of prostate dimensions on the development of postoperative erectile dysfunction in patients diagnosed with mid-rectum adenocarcinoma who underwent low anterior resection (LAR) is examined. PATIENTS AND METHODS: Thirty-one male patients diagnosed as mid-rectal adenocancer were included. The International Index of Erectile Function (IIEF) questionnaire was used to determine the patients' pre and postoperative erectile dysfunction levels, and the level of relationship between the change in these IIEF scores and prostate measurements determined by computed tomography were evaluated. RESULTS: There were statistically significant differences between IIEF index score and anterior posterior (AP) and transverse (TR) measurements (p≤0.001; p≤0.001), but no statistically significant difference was found between craniocaudal (CC) measurement values (p=0.169). CONCLUSIONS: The risk of nerve injury will be higher in those with a small prostate transverse diameter. Intraoperative nerve monitoring should be recommended primarily in younger patient groups.

Prediction of false-positive PI-RADS 5 lesions on prostate multiparametric MRI: development and internal validation of a clinical-radiological characteristics based nomogram.

BACKGROUND: To develop a risk model including clinical and radiological characteristics to predict false-positive The Prostate Imaging Reporting and Data System (PI-RADS) 5 lesions. METHODS: Data of 612 biopsy-naïve patients who had undergone multiparametric magnetic resonance imaging (mpMRI) before prostate biopsy were collected. Clinical variables and radiological variables on mpMRI were adopted. Lesions were divided into the training and validation cohort randomly. Stepwise multivariate logistic regression analysis with backward elimination was performed to screen out variables with significant difference. A diagnostic nomogram was developed in the training cohort and further validated in the validation cohort. Calibration curve and receiver operating characteristic (ROC) analysis were also performed. RESULTS: 296 PI-RADS 5 lesions in 294 patients were randomly divided into the training and validation cohort (208 : 88). 132 and 56 lesions were confirmed to be clinically significant prostate cancer in the training and validation cohort respectively. The diagnostic nomogram was developed based on prostate specific antigen density, the maximum diameter of lesion, zonality of lesion, apparent diffusion coefficient minimum value and apparent diffusion coefficient minimum value ratio. The C-index of the model was 0.821 in the training cohort and 0.871 in the validation cohort. The calibration curve showed good agreement between the estimation and observation in the two cohorts. When the optimal cutoff values of ROC were 0.288 in the validation cohort, the sensitivity, specificity, PPV, and NPV were 90.6%, 67.9%, 61.7%, and 92.7% in the validation cohort, potentially avoiding 9.7% unnecessary prostate biopsies. CONCLUSIONS: We developed and validated a diagnostic nomogram by including 5 factors. False positive PI-RADS 5 lesions could be distinguished from clinically significant ones, thus avoiding unnecessary prostate biopsy.

Assessment of the accuracy of biparametric MRI/TRUS fusion-guided biopsy for index tumor evaluation using postoperative pathology specimens.

BACKGROUND: Multiparametric MRI (mpMRI) is widely used for the diagnosis, surveillance, and staging of prostate cancer. However, it has several limitations, including higher costs, longer examination times, and the use of gadolinium-based contrast agents. This study aimed to investigate the accuracy of preoperatively assessed index tumors (ITs) using biparametric MRI (bpMRI)/transrectal ultrasound (TRUS) fusion biopsy compared with radical prostatectomy (RP) specimens. METHODS: We included 113 patients diagnosed with prostate cancer through bpMRI/TRUS fusion-guided biopsies of lesions with a Prostate Imaging Reporting and Data System (PI-RADS) category ≥ 3. These patients underwent robot-assisted laparoscopic radical prostatectomy (RARP) at our institution between July 2017 and March 2023. We examined the localization of preoperative and postoperative ITs, the highest Gleason score (GS), and tumor diameter in these patients. RESULTS: The preoperative cT stage matched the postoperative pT stage in 53 cases (47%), while 31 cases (27%) were upstaged, and 29 cases (26%) were downstaged (Weighted Kappa = 0.21). The preoperative and postoperative IT localizations were consistent in 97 cases (86%). The concordance rate between Gleason groups in targeted biopsies and RP specimens was 51%, with an upgrade in 25 cases (23%) and a downgrade in 27 cases (25%) (Weighted Kappa = 0.42). The maximum diameter of the IT and the maximum cancer core length on biopsy were correlated with the RP tumor's maximum diameter (p < 0.001 for both). CONCLUSION: The diagnostic accuracy of bpMRI/TRUS fusion biopsy is comparable to mpMRI, suggesting that it can be a cost-effective and time-saving alternative.

FastMRI Prostate: A public, biparametric MRI dataset to advance machine learning for prostate cancer imaging.

Magnetic resonance imaging (MRI) has experienced remarkable advancements in the integration of artificial intelligence (AI) for image acquisition and reconstruction. The availability of raw k-space data is crucial for training AI models in such tasks, but public MRI datasets are mostly restricted to DICOM images only. To address this limitation, the fastMRI initiative released brain and knee k-space datasets, which have since seen vigorous use. In May 2023, fastMRI was expanded to include biparametric (T2- and diffusion-weighted) prostate MRI data from a clinical population. Biparametric MRI plays a vital role in the diagnosis and management of prostate cancer. Advances in imaging methods, such as reconstructing under-sampled data from accelerated acquisitions, can improve cost-effectiveness and accessibility of prostate MRI. Raw k-space data, reconstructed images and slice, volume and exam level annotations for likelihood of prostate cancer are provided in this dataset for 47468 slices corresponding to 1560 volumes from 312 patients. This dataset facilitates AI and algorithm development for prostate image reconstruction, with the ultimate goal of enhancing prostate cancer diagnosis.

The role of urology and radiology in prostate biopsy: current trends and future perspectives.

PURPOSE: Prostate biopsy is central to the accurate histological diagnosis of prostate cancer. In current practice, the biopsy procedure can be performed using a transrectal or transperineal route with different technologies available for targeting of lesions within the prostate. Historically, the biopsy procedure was performed solely by urologists, but with the advent of image-guided techniques, the involvement of radiologists in prostate biopsy has become more common. Herein, we discuss the pros, cons and future considerations regarding their ongoing role. METHODS: A narrative review regarding the current evidence was completed. PubMed and Cochrane central register of controlled trials were search until January 2024. All study types were of consideration if published after 2000 and an English language translation was available. RESULTS: There are no published studies that directly compare outcomes of prostate biopsy when performed by a urologist or radiologist. In all published studies regarding the learning curve for prostate biopsy, the procedure was performed by urologists. These studies suggest that the learning curve for prostate biopsy is between 10 and 50 cases to reach proficiency in terms of prostate cancer detection and complications. It is recognised that many urologists are poorly able to accurately interpret multi parametric (mp)-MRI of the prostate. Collaboration between the specialities is of importance with urology offering the advantage of being involved in prior and future care of the patient while radiology has the advantage of being able to expertly interpret preprocedure MRI. CONCLUSION: There is no evidence to suggest that prostate biopsy should be solely performed by a specific specialty. The most important factor remains knowledge of the relevant anatomy and sufficient volume of cases to develop and maintain skills.

Evaluación del valor predictivo negativo de la resonancia magnética multiparamétrica de próstata al combinar su puntuación con parámetros del antígeno prostático específico en pacientes con PSA en zona gris / The effect of the combination of prostate-specific antigen derivatives with multiparametric prostate magnetic resonance imaging scores on the negative predictive value of it in grey zone patients

Objetivo Calcular el valor predictivo negativo (VPN) de la resonancia magnética multiparamétrica (RMmp) de próstata negativa, definida como la ausencia de lesiones en las imágenes, cuando se combina con la densidad del PSA (DPSA) y el índice PSA libre/total (PSA l/t) en pacientes cuyo PSA se encuentra en la zona gris (4-10mg/ml). Métodos Se analizaron 191 pacientes con niveles de PSA entre 4 y 10mg/ml y RMmp negativa. El VPN de la RMmp negativa se calculó de acuerdo con un nivel de DPSA<0,15ng/ml/ml, un índice PSA l/t>0,15 y una combinación de ambos. Los pacientes se dividieron en 3 grupos de riesgo según estos dos parámetros, de la siguiente manera: • DPSA 0,01-0,07ng/ml/ml e índice PSA l/t≥25 en el grupo de bajo riesgo. • DPSA 0,08-0,15ng/ml/ml e índice PSA l/t 0,15-0,24 en el grupo de riesgo intermedio. • DPSA>0,15ng/ml/ml e índice PSA l/t<15 en el grupo de riesgo alto. Resultados El VPN de la RMmp negativa fue del 92,6% para el carcinoma de próstata clínicamente significativo (CPCS). El VPN aumentó al 97,5% en el grupo de riesgo bajo, y disminuyó al 33,3% en el de riesgo alto. El resultado al combinar la RMmp negativa con la DPSA<0,15ng/ml/ml fue muy similar al de su combinación con el PSA l/t>15. Conclusión el índice PSA l/t también podría utilizarse para aumentar el VPN de la RMmp, al igual que la DPSA. No recomendamos evitar la biopsia de próstata con una DPSA>0,15ng/ml/ml y un índice PSA l/t<0,15. Sin embargo, se requieren estudios controlados aleatorizados con más pacientes para confirmar los hallazgos de nuestro estudio. (AU)

Objective To calculate the negative predictive value (NPV) of negative multiparametric prostate magnetic resonance imaging (mpMRI), accepted as no lesions on images, when combined with prostate-specific antigen density (PSAD) and free/total prostate-specific antigen ratio (f/t PSA) in grey zone patients. Methods One hundred ninety-one patients with PSA levels between 4-10mg/ml and negative mpMRI were analyzed. The NPV of negative mpMRI was calculated according to a PSAD level of <0.15 ng/ml/ml, f/t PSA ratio of >0.15, and a combination of both. Patients were divided into three risk groups according to these two parameters: • PSAD 0.01-0.07 ng/ml/ml and f/t PSA ratio ≥25 in a low-risk group. • PSAD 0.08-0.15 ng/ml/ml, and f/t PSA ratio 0.15-0.24 in an intermediate-risk group and high-risk group. • PSAD>0.15 ng/ml/ml and f/t PSA ratio <15 in high-risk group, Results NPV of negative mpMRI was 92.6% for clinically significant prostate carcinoma (CSPCa). It increased to 97.5% in a low-risk group and decreased to 33.3% for CSPCa in a high-risk group. NPV of negative mpMRI results were so close when combined with PSAD <0.15 ng/ml/ml and f/t PSA>15. Conclusion f/t PSA ratio might also be used to increase the NPV of mpMRI, like PSAD. We advise not to avoid prostate biopsy when PSAD is >0.15 ng/ml/ml and the f/t PSA ratio is <0.15. However, we need randomized controlled studies with more patients to confirm our study. (AU)

Magnetic Resonance Imaging, Clinical, and Biopsy Findings in Suspected Prostate Cancer: A Systematic Review and Meta-Analysis.

Importance: Multiple strategies integrating magnetic resonance imaging (MRI) and clinical data have been proposed to determine the need for a prostate biopsy in men with suspected clinically significant prostate cancer (csPCa) (Gleason score ≥3 + 4). However, inconsistencies across different strategies create challenges for drawing a definitive conclusion. Objective: To determine the optimal prostate biopsy decision-making strategy for avoiding unnecessary biopsies and minimizing the risk of missing csPCa by combining MRI Prostate Imaging Reporting & Data System (PI-RADS) and clinical data. Data Sources: PubMed, Ovid MEDLINE, Embase, Web of Science, and Cochrane Library from inception to July 1, 2022. Study Selection: English-language studies that evaluated men with suspected but not confirmed csPCa who underwent MRI PI-RADS followed by prostate biopsy were included. Each study had proposed a biopsy plan by combining PI-RADS and clinical data. Data Extraction and Synthesis: Studies were independently assessed for eligibility for inclusion. Quality of studies was appraised using the Quality Assessment of Diagnostic Accuracy Studies 2 tool and the Newcastle-Ottawa Scale. Mixed-effects meta-analyses and meta-regression models with multimodel inference were performed. Reporting of this study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline. Main Outcomes and Measures: Independent risk factors of csPCa were determined by performing meta-regression between the rate of csPCa and PI-RADS and clinical parameters. Yields of different biopsy strategies were assessed by performing diagnostic meta-analysis. Results: The analyses included 72 studies comprising 36 366 patients. Univariable meta-regression showed that PI-RADS 4 (ß-coefficient [SE], 7.82 [3.85]; P = .045) and PI-RADS 5 (ß-coefficient [SE], 23.18 [4.46]; P < .001) lesions, but not PI-RADS 3 lesions (ß-coefficient [SE], -4.08 [3.06]; P = .19), were significantly associated with a higher risk of csPCa. When considered jointly in a multivariable model, prostate-specific antigen density (PSAD) was the only clinical variable significantly associated with csPCa (ß-coefficient [SE], 15.50 [5.14]; P < .001) besides PI-RADS 5 (ß-coefficient [SE], 9.19 [3.33]; P < .001). Avoiding biopsy in patients with lesions with PI-RADS category of 3 or less and PSAD less than 0.10 (vs <0.15) ng/mL2 resulted in reducing 30% (vs 48%) of unnecessary biopsies (compared with performing biopsy in all suspected patients), with an estimated sensitivity of 97% (vs 95%) and number needed to harm of 17 (vs 15). Conclusions and Relevance: These findings suggest that in patients with suspected csPCa, patient-tailored prostate biopsy decisions based on PI-RADS and PSAD could prevent unnecessary procedures while maintaining high sensitivity.

Fast and accessible T2 mapping using off-resonance corrected DESPOT2 with application to 3D prostate.

PURPOSE: Most T1 and T2 mapping take long acquisitions or needs specialized sequences not widely accessible on clinical scanners. An available solution is DESPOT1/T2 (Driven equilibrium single pulse observation of T1/T2). DESPOT1/T2 uses Spoiled gradient-echo (SPGR) and balanced Steady-State Free Precession (bSSFP) sequences, offering an accessible and reliable way for 3D accelerated T1/T2 mapping. However, bSSFP is prone to off-resonance artifacts, limiting the application of DESPOT2 in regions with high susceptibility contrasts, like the prostate. Our proposal, DESPO+, employs the full bSSFP and SPGR models with a dictionary-based method to reconstruct 3D T1/T2 maps in the prostate region without off-resonance banding. METHODS: DESPO+ modifies the bSSFP acquisition of the original variable flip angle DESPOT2. DESPO+ uses variable repetition and echo times, employing a dictionary-based method of the full bSSFP and SPGR models to reconstruct T1, T2, and Proton Density (PD) simultaneously. The proposed DESPO+ method underwent testing through simulations, T1/T2 phantoms, and on fourteen healthy subjects. RESULTS: The results reveal a significant reduction in T2 map banding artifacts compared to the original DESPOT2 method. DESPO+ approach reduced T2 errors by up to seven times compared to DESPOT2 in simulations and phantom experiments. We also synthesized in-vivo T1-weighted/T2-weighted images from the acquired maps using a spin-echo model to verify the map's quality when lacking a reference. For in-vivo imaging, the synthesized images closely resemble those from the clinical MRI protocol, reducing scan time by around 50% compared to traditional spin-echo T1-weighted/T2-weighted acquisitions. CONCLUSION: DESPO+ provides an off-resonance insensitive and clinically available solution, enabling high-resolution 3D T1/T2 mapping and synthesized T1-weighted/T2-weighted images for the entire prostate, all achieved within a short scan time of 3.6 min, similar to DESPOT1/T2.

The effectiveness of mapping-targeted biopsies on the index lesion in transperineal prostate biopsies.

PURPOSE: To evaluate the effectiveness of mapping-targeted biopsies (MTB) on the index lesion for the detection of clinically significant prostate cancer (csPCa) in transperineal fusion-image prostate biopsies. MATERIALS AND METHODS: A retrospective analysis was conducted on 309 men with suspected PCa who underwent prostate biopsies at the Creu Blanca reference center in Barcelona, Spain. The Prostate Imaging-Reporting and Data System (PI-RADS v.2.1) of the magnetic resonance images (MRI) were reclassified by an expert radiologist reading of pre-biopsy biparametric MRI used for segmentation of suspected lesions. Transperineal MTB of suspicious lesions and 12-core systematic biopsies were performed using the Artemis™ platform. CsPCa was defined as International Society of Urological Pathology grade group ≥ 2. RESULTS: CsPCa was detected in 192 men (62.1%), with detection rates of 6.3% for PI-RADS 2, 26.8% for PI-RADS 3, 87.3% for PI-RADS 4, and 93.1% for PI-RADS 5. MTB of the index lesion identified 185 csPCa (96.3%). CsPCa was detected solely in systematic biopsies in three cases (1.6%), while an additional four cases (2.1%) were identified only in the second suspected lesion. A predictive model for csPCa detection in MTB of the index lesion was developed, with an AUC of 0.918 (95% CI 0.887-0.950). CONCLUSIONS: This model had the potential to avoid 23.3% of prostate biopsies without missing additional csPCa cases. MTB of the index lesion was highly effective for identifying csPCa in fusion transperineal prostate biopsies. A developed predictive model successfully reduced the need for almost one quarter of biopsies without missing csPCa cases.

TransVFS: A spatio-temporal local-global transformer for vision-based force sensing during ultrasound-guided prostate biopsy.

Robot-assisted prostate biopsy is a new technology to diagnose prostate cancer, but its safety is influenced by the inability of robots to sense the tool-tissue interaction force accurately during biopsy. Recently, vision based force sensing (VFS) provides a potential solution to this issue by utilizing image sequences to infer the interaction force. However, the existing mainstream VFS methods cannot realize the accurate force sensing due to the adoption of convolutional or recurrent neural network to learn deformation from the optical images and some of these methods are not efficient especially when the recurrent convolutional operations are involved. This paper has presented a Transformer based VFS (TransVFS) method by leveraging ultrasound volume sequences acquired during prostate biopsy. The TransVFS method uses a spatio-temporal local-global Transformer to capture the local image details and the global dependency simultaneously to learn prostate deformations for force estimation. Distinctively, our method explores both the spatial and temporal attention mechanisms for image feature learning, thereby addressing the influence of the low ultrasound image resolution and the unclear prostate boundary on the accurate force estimation. Meanwhile, the two efficient local-global attention modules are introduced to reduce 4D spatio-temporal computation burden by utilizing the factorized spatio-temporal processing strategy, thereby facilitating the fast force estimation. Experiments on prostate phantom and beagle dogs show that our method significantly outperforms existing VFS methods and other spatio-temporal Transformer models. The TransVFS method surpasses the most competitive compared method ResNet3dGRU by providing the mean absolute errors of force estimation, i.e., 70.4 ± 60.0 millinewton (mN) vs 123.7 ± 95.6 mN, on the transabdominal ultrasound dataset of dogs.

The Transatlantic Recommendations for Prostate Gland Evaluation with Magnetic Resonance Imaging After Focal Therapy (TARGET): A Systematic Review and International Consensus Recommendations.

BACKGROUND AND OBJECTIVE: Magnetic resonance imaging (MRI) can detect recurrences after focal therapy for prostate cancer but there is no robust guidance regarding its use. Our objective was to produce consensus recommendations on MRI acquisition, interpretation, and reporting after focal therapy. METHODS: A systematic review was performed in July 2022 to develop consensus statements. A two-round consensus exercise was then performed, with a consensus meeting in January 2023, during which 329 statements were scored by 23 panellists from Europe and North America spanning urology, radiology, and pathology with experience across eight focal therapy modalities. Using RAND Corporation/University of California-Los Angeles methodology, the Transatlantic Recommendations for Prostate Gland Evaluation with MRI after Focal Therapy (TARGET) were based on consensus for statements scored with agreement or disagreement. KEY FINDINGS AND LIMITATIONS: In total, 73 studies were included in the review. All 20 studies (100%) reporting suspicious imaging features cited focal contrast enhancement as suspicious for cancer recurrence. Of 31 studies reporting MRI assessment criteria, the Prostate Imaging-Reporting and Data System (PI-RADS) score was the scheme used most often (20 studies; 65%), followed by a 5-point Likert score (six studies; 19%). For the consensus exercise, consensus for statements scored with agreement or disagreement increased from 227 of 295 statements (76.9%) in round one to 270 of 329 statements (82.1%) in round two. Key recommendations include performing routine MRI at 12 mo using a multiparametric protocol compliant with PI-RADS version 2.1 standards. PI-RADS category scores for assessing recurrence within the ablation zone should be avoided. An alternative 5-point scoring system is presented that includes a major dynamic contrast enhancement (DCE) sequence and joint minor diffusion-weighted imaging and T2-weighted sequences. For the DCE sequence, focal nodular strong early enhancement was the most suspicious imaging finding. A structured minimum reporting data set and minimum reporting standards for studies detailing MRI data after focal therapy are presented. CONCLUSIONS AND CLINICAL IMPLICATIONS: The TARGET consensus recommendations may improve MRI acquisition, interpretation, and reporting after focal therapy for prostate cancer and provide minimum standards for study reporting. PATIENT SUMMARY: Magnetic resonance imaging (MRI) scans can detect recurrent of prostate cancer after focal treatments, but there is a lack of guidance on MRI use for this purpose. We report new expert recommendations that may improve practice.

Diagnostic accuracy of qualitative and quantitative magnetic resonance imaging-guided contrast-enhanced ultrasound (MRI-guided CEUS) for the detection of prostate cancer: a prospective and multicenter study.

PURPOSE: To evaluate the diagnostic value of MRI-guided contrast-enhanced ultrasound (CEUS) for prostate cancer (PCa) diagnosis, and characteristics of PCa in qualitative and quantitative CEUS. MATERIAL AND METHODS: This prospective and multicenter study included 250 patients (133 in the training cohort, 57 in the validation cohort and 60 in the test cohort) who underwent MRI, MRI-guided CEUS and prostate biopsy between March 2021 and February 2023. MRI interpretation, qualitative and quantitative CEUS analysis were conducted. Multitree extreme gradient boosting (XGBoost) machine learning-based models were applied to select the eight most important quantitative parameters. Univariate and multivariate logistic regression models were constructed to select independent predictors of PCa. Diagnostic value was determined for MRI, qualitative and quantitative CEUS using the area under receiver operating characteristic curve (AUC). RESULTS: The performance of quantitative CEUS was superior to that of the qualitative CEUS and MRI in predicting PCa. The AUC was 0.779 (95%CI 0.70-0.849), 0.756 (95%CI 0.638-0.874) and 0.759 (95%CI 0.638-0.879) of qualitative CEUS, and 0.885 (95%CI 0.831-0.940), 0.802 (95%CI 0.684-0.919) and 0.824 (95%CI 0.713-0.936) of quantitative CEUS in training, validation and test cohort, respectively. Compared with quantitative CEUS, MRI achieved less well performance for AUC 0.811 (95%CI 0.741-0.882, p = 0.099), 0.748 (95%CI 0.628-0.868, p = 0.539) and 0.737 (95%CI 0.602-0.873, p = 0.029), respectively. Moreover, the highest specificity of 80.6% was obtained by quantitative CEUS. CONCLUSION: We developed a reliable method of MRI-guided CEUS that demonstrated enhanced performance compared to MRI. The qualitative and quantitative CEUS characteristics will contribute to improved diagnosis of PCa.

RAPHIA: A deep learning pipeline for the registration of MRI and whole-mount histopathology images of the prostate.

Image registration can map the ground truth extent of prostate cancer from histopathology images onto MRI, facilitating the development of machine learning methods for early prostate cancer detection. Here, we present RAdiology PatHology Image Alignment (RAPHIA), an end-to-end pipeline for efficient and accurate registration of MRI and histopathology images. RAPHIA automates several time-consuming manual steps in existing approaches including prostate segmentation, estimation of the rotation angle and horizontal flipping in histopathology images, and estimation of MRI-histopathology slice correspondences. By utilizing deep learning registration networks, RAPHIA substantially reduces computational time. Furthermore, RAPHIA obviates the need for a multimodal image similarity metric by transferring histopathology image representations to MRI image representations and vice versa. With the assistance of RAPHIA, novice users achieved expert-level performance, and their mean error in estimating histopathology rotation angle was reduced by 51% (12 degrees vs 8 degrees), their mean accuracy of estimating histopathology flipping was increased by 5% (95.3% vs 100%), and their mean error in estimating MRI-histopathology slice correspondences was reduced by 45% (1.12 slices vs 0.62 slices). When compared to a recent conventional registration approach and a deep learning registration approach, RAPHIA achieved better mapping of histopathology cancer labels, with an improved mean Dice coefficient of cancer regions outlined on MRI and the deformed histopathology (0.44 vs 0.48 vs 0.50), and a reduced mean per-case processing time (51 vs 11 vs 4.5 min). The improved performance by RAPHIA allows efficient processing of large datasets for the development of machine learning models for prostate cancer detection on MRI. Our code is publicly available at: https://github.com/pimed/RAPHIA.

Performance of standard systematic biopsy versus MRI/TRUS fusion biopsy using the Navigo® system in contemporary cohort.

INTRODUCTION: The introduction of multi parameter magnetic resonance imaging (mpMRI) of the prostate in combination with MRI/TRUS fusion and systematic biopsy resulted in improved detection of prostate cancer. The aim of the current study was to document the performance of MRI/TRUS fusion biopsy of the prostate using the Navigo™ software in a contemporary cohort of patients from nonreferral centers. MATERIAL AND METHODS: We performed a two centers prospective data collection (2014-2020) for men with clinically suspected Pca and patients on active surveillance for low-risk Pca that were referred for TRUS biopsy after performing mpMRI of the prostate with a visible lesion. The primary outcome was detection of clinically significant cancer (csPca) defined as ISUP grade group ≥2. Patients were stratified according to biopsy technique and PI-RADS category. RESULTS: The study group included 236 patients of whom 129 (54.9%) were diagnosed with Pca and 82 (34.7%) with csPca (GG ≥ 2) on combined biopsy. The overall detection of csPca was 31% for targeted vs. 25.4% for systematic biopsy with an absolute difference of 5.6% in favor of the fusion technique. No significant difference between the two techniques was observed for detection of benign prostate or GG1 disease. The improved performance of the targeted approach was noted only in patients with PI-RADS 4 and 5 lesions. Of the patients with csPca 10 (12%) were diagnosed only by the systematic biopsy while 20 (24%) were detected only in the fusion biopsy. Systematic biopsy of prostate lobe without MRI lesion detected only 2 cases (∼1%) with high grade disease. CONCLUSIONS: Detection of csPca by mpMRI/TRUS fusion biopsy using the 3D Navigo™ system is feasible. The targeted approach outperforms the systematic one, however the later technique also detects high risk disease and should be included in the biopsy procedure. The overall detection rate (34.9%) of clinically significant prostate cancer by both targeted and systematic sampling is relatively low.

Multispecies comparative prostate anatomy by imaging: Implications for experimental models of prostatic disease.

BACKGROUND: There is an increasing interest in using preclinical models for development and assessment of medical devices and imaging techniques for prostatic disease care. Still, a comprehensive assessment of the prostate's radiological anatomy in primary preclinical models such as dogs, rabbits, and mice utilizing human anatomy as a reference point remains necessary with no optimal model for each purpose being clearly defined in the literature. Therefore, this study compares the anatomical characteristics of different animal models to the human prostatic gland from the imaging perspective. METHODS: We imaged five Beagle laboratory dogs, five New Zealand White rabbits, and five mice, all sexually mature males, under Institutional Animal Care and Use Committee (IACUC) approval. Ultrasonography (US) was performed using the Vevo® F2 for mice (57 MHz probe). Rabbits and dogs were imaged using the Siemens® Acuson S3000 (17 MHz probe) and endocavitary (8 MHz) probes, respectively. Magnetic resonance imaging (MRI) was also conducted with a 7T scanner in mice and 3T scanner in rabbits and dogs. RESULTS: Canine transrectal US emerged as the optimal method for US imaging, depicting a morphologically similar gland to humans but lacking echoic zonal differentiation. MRI findings in canines indicated a homogeneously structured gland similar to the human peripheral zone on T2-weighted images (T2W) and apparent diffusion coefficient (ADC). In rabbits, US imaging faced challenges due to the pubic symphysis, whereas MRI effectively visualized all structures with the prostate presenting a similar aspect to the human peripheral gland on T2W and ADC maps. Murine prostate assessment revealed poor visualization of the prostate glands in ultrasound due to its small size, while 7T MRI delineated the distinct prostates and its lobes, with the lateral and dorsal prostate resembling the peripheral zone and the anterior prostate the central zone of the human gland. CONCLUSION: Dogs stand out as superior models for advanced preclinical studies in prostatic disease research. However, mice present as a good model for early stage studies and rabbits are a cost-effective alternative and serve as valuable tools in specific research domains when canine research is not feasible.

Different diagnostic strategies combining prostate health index and magnetic resonance imaging for predicting prostate cancer: A multicentre study.

OBJECTIVE: To explore how prostate health index (PHI) and multiparametric magnetic resonance imaging (mpMRI) should be used in concert to improve diagnostic capacity for clinically significant prostate cancers (CsCaP) in patients with prostate-specific antigen (PSA) between 4 and 20 ng/ml. METHODS: About 426 patients fulfilling the inclusion criteria were included in this study. Univariable and multivariable logistic analyses were performed to analyze the association between the clinical indicators and CaP/CsCaP. We used the Delong test to compare the differences in the area under the curve (AUC) values of four models for CaP and CsCaP. Decision curve analysis (DCA) and calibration plots were used to assess predictive performance. We compared clinical outcomes of different diagnostic strategies constructed using different combinations of the models by the chi-square test and the McNemar test. RESULTS: The AUC of PHI-MRI (a risk prediction model based on PHI and mpMRI) was 0.859, which was significantly higher than those of PHI (AUC = 0.792, P < 0.001) and mpMRI (AUC = 0.797, P < 0.001). PHI-MRI had a higher net benefit on DCA for predicting CaP and CsCaP in comparison to PHI and mpMRI. Adding the PHI-MRI in diagnostic strategies for CsCaP, such as use PHI-MRI alone or sequential use of PHI followed by PHI-MRI, could reduce the number of biopsies by approximately 20% compared to use PHI followed by mpMRI (256 vs 316, 257 vs 316, respectively). CONCLUSIONS: The PHI-MRI model was superior to PHI and MRI alone. It may reduce the number of biopsies and ensure the detection rate of CsCaP under an appropriate sensitivity at the cost of an increased number of MRI scans.

DiagSet: a dataset for prostate cancer histopathological image classification.

Cancer diseases constitute one of the most significant societal challenges. In this paper, we introduce a novel histopathological dataset for prostate cancer detection. The proposed dataset, consisting of over 2.6 million tissue patches extracted from 430 fully annotated scans, 4675 scans with assigned binary diagnoses, and 46 scans with diagnoses independently provided by a group of histopathologists can be found at https://github.com/michalkoziarski/DiagSet . Furthermore, we propose a machine learning framework for detection of cancerous tissue regions and prediction of scan-level diagnosis, utilizing thresholding to abstain from the decision in uncertain cases. The proposed approach, composed of ensembles of deep neural networks operating on the histopathological scans at different scales, achieves 94.6% accuracy in patch-level recognition and is compared in a scan-level diagnosis with 9 human histopathologists showing high statistical agreement.

Algorithms for classification of sequences and segmentation of prostate gland: an external validation study.

OBJECTIVES: The aim of the study was to externally validate two AI models for the classification of prostate mpMRI sequences and segmentation of the prostate gland on T2WI. MATERIALS AND METHODS: MpMRI data from 719 patients were retrospectively collected from two hospitals, utilizing nine MR scanners from four different vendors, over the period from February 2018 to May 2022. Med3D deep learning pretrained architecture was used to perform image classification,UNet-3D was used to segment the prostate gland. The images were classified into one of nine image types by the mode. The segmentation model was validated using T2WI images. The accuracy of the segmentation was evaluated by measuring the DSC, VS,AHD.Finally,efficacy of the models was compared for different MR field strengths and sequences. RESULTS: 20,551 image groups were obtained from 719 MR studies. The classification model accuracy is 99%, with a kappa of 0.932. The precision, recall, and F1 values for the nine image types had statistically significant differences, respectively (all P < 0.001). The accuracy for scanners 1.436 T, 1.5 T, and 3.0 T was 87%, 86%, and 98%, respectively (P < 0.001). For segmentation model, the median DSC was 0.942 to 0.955, the median VS was 0.974 to 0.982, and the median AHD was 5.55 to 6.49 mm,respectively.These values also had statistically significant differences for the three different magnetic field strengths (all P < 0.001). CONCLUSION: The AI models for mpMRI image classification and prostate segmentation demonstrated good performance during external validation, which could enhance efficiency in prostate volume measurement and cancer detection with mpMRI. CLINICAL RELEVANCE STATEMENT: These models can greatly improve the work efficiency in cancer detection, measurement of prostate volume and guided biopsies.

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

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