Asunto(s)

RESUMEN

Histotripsy is a noninvasive focused ultrasound therapy that mechanically fractionates tissue to create well-defined lesions. In a previous clinical pilot trial to treat benign prostatic hyperplasia (BPH), histotripsy did not result in consistent objective improvements in symptoms, potentially because of the fibrotic and mechanically tough nature of this tissue. In this study, we aimed to identify the dosage required to homogenize BPH tissue by different histotripsy modalities, including boiling histotripsy (BH) and cavitation histotripsy (CH). A method for histotripsy lesion quantification via entropy (HLQE) analysis was developed and utilized to quantify lesion area of the respective treatments. These data were correlated to changes in mechanical stiffness measured by ultrasound shear-wave elastography before and after treatment with each parameter set and dose. Time points corresponding to histologically observed complete lesions were qualitatively evaluated and quantitatively measured. For the BH treatment, complete lesions occurred with > = 30 s treatment time, with a corresponding maximum reduction in stiffness of -90.9 ± 7.2(s.d.)%. High pulse repetition frequency (PRF) CH achieved a similar reduction to that of BH at 288 s (-91.6 ± 6.0(s.d.)%), and low-PRF CH achieved a (-82.1 ± 5.1(s.d.)%) reduction in stiffness at dose > = 144 s. Receiver operating characteristic curve analysis showed that a > ~ 75% reduction in stiffness positively correlated with complete lesions observed histologically, and can provide an alternative metric to track treatment progression.

Asunto(s)

RESUMEN

BACKGROUND: Prostate tuberculosis (TB) is a rare and often underdiagnosed condition due to its nonspecific symptoms and imaging features, which can mimic malignancies on 18F-fluorodeoxyglucose positron emission tomography (PET) scans. This resemblance poses a challenge in differentiating TB from prostate cancer, especially in patients with preexisting tumors such as diffuse large B-cell lymphoma. The purpose of this study is to highlight the importance of considering TB in the differential diagnosis of patients with atypical imaging findings, even in the presence of known malignancies. CASE: We present a case of a 60-year-old man with diffuse large B-cell lymphoma who was initially misdiagnosed with a prostate tumor based on 18F-fluorodeoxyglucose PET/computed tomography scans. The subsequent ultrasound-guided prostate biopsy confirmed the presence of prostate TB, not malignancy. CONCLUSIONS: This case report underscores the critical role of considering TB as a potential diagnosis in patients with hematological tumors and atypical imaging results. It serves as a reminder for clinicians to exercise caution when interpreting PET/computed tomography scans and to incorporate TB into their differential diagnoses, thereby avoiding misdiagnosis and inappropriate treatment.

Asunto(s)

RESUMEN

PURPOSE: To investigate the relationship between prostatic urethral angle (PUA) and the development of surgical capsule calculi (SCC) within the prostate, and to examine the presence and impact of intravesical prostatic protrusion (IPP). MATERIALS AND METHODS: A retrospective analysis was conducted on 90 patients who underwent radical prostatectomy, with preoperative assessments using both transrectal ultrasound of the prostate (TRUS) and magnetic resonance imaging. Patients were divided into groups with and without SCC and further categorized into type 1 and type 2 stones based on the location and severity of the calculi. Statistical analysis included chi-square and independent sample t-tests, with p<0.05 considered significant. RESULTS: Of the patients, 82.2% were diagnosed with SCC. No significant difference in PUA was found between patients with and without SCC. However, a notable disparity in IPP presence was observed, suggesting an inverse correlation with SCC development. Additionally, no significant differences were identified when comparing the two types of SCC based on PUA and IPP measurements. CONCLUSIONS: The presence of IPP exhibited an inverse relationship with SCC, suggesting diminished urine flow pressure over the prostatic urethra may reduce the likelihood of SCC formation. However, no direct association between PUA and the presence or severity of SCC was identified. These findings highlight the complexity of factors contributing to prostatic calculi development and the potential role of IPP in this context.

Asunto(s)

RESUMEN

The purpose of this study is to evaluate whether the periprostatic adipose tissue thickness (PPATT) is an independent prognostic factor for prostate cancer patients after laparoscopic radical prostatectomy (LRP). This retrospective cohort study included consecutive prostate cancer patients who underwent LRP treatment at Wuhan Union Hospital from June 2, 2016, to September 7, 2023. PPATT was defined as the thickness of periprostatic fat and was obtained by measuring the shortest vertical distance from the pubic symphysis to the prostate on the midsagittal T2-weighted MR images. Subcutaneous adipose tissue thickness (SATT) was obtained by measuring the shortest vertical distance from the pubic symphysis to the skin at the same slice with PPATT. The primary outcome of the study was biochemical recurrence (BCR), and the secondary outcome was overall survival (OS). Multivariable Cox regression analysis was used to identify independent prognostic factors for prostate cancer survival and prognosis. Based on the optimal cutoff value, 162 patients were divided into a low PPATT/SATT group (n = 82) and a high PPATT/SATT group (n = 80). During the entire follow-up period (median 23.5 months), 26 patients in the high PPATT/SATT group experienced BCR (32.5%), compared to 18 in the low PPATT/SATT group (22.0%). Kaplan-Meier curve analysis indicated that the interval to BCR was significantly shorter in the high PPATT/SATT group (P = 0.037). Multivariable Cox regression analysis revealed that an increase in the PPATT/SATT ratio was associated with BCR (hazard ratio: 1.90, 95% CI, 1.03-3.51; P = 0.040). The PPATT/SATT ratio is a significant independent risk factor for BCR after LRP for prostate cancer patients.

Asunto(s)

RESUMEN

INTRODUCTION: Most men diagnosed with very-low and low-risk prostate cancer are candidates for active surveillance; however, there is still a misclassification risk. We examined whether PI-RADS category 4 or 5 combined with ISUP 1 on prostate biopsy predicts upgrading and/or adverse pathology at radical prostatectomy. MATERIALS AND METHODS: A total of 127 patients had ISUP 1 cancer on biopsy after multiparametric MRI (mpMRI) and then underwent radical prostatectomy. We then evaluated them for ISUP upgrading and/or adverse pathology on radical prostatectomy. RESULTS: Eight-nine patients (70%) were diagnosed with PI-RADS 4 or 5 lesions. ISUP upgrading was significantly higher among patients with PI-RADS 4-5 lesions (84%) compared to patients with equivocal or non-suspicious mpMRI findings (26%, p < 0.001). Both PI-RADS 4-5 lesions (OR 24.3, 95% CI 7.3, 80.5, p < 0.001) and stage T2 on DRE (OR 5.9, 95% CI 1.2, 29.4, p = 0.03) were independent predictors of upgrading on multivariate logistic regression analysis. Men with PI-RADS 4-5 lesions also had significantly more extra-prostatic extension (51% vs. 3%, p < 0.001) and positive surgical margins (16% vs. 3%. p = 0.03). The only independent predictor of adverse pathology was PI-RADS 4-5 (OR 21.7, 95% CI 4.8, 99, p < 0.001). CONCLUSION: PI-RADS 4 or 5 lesions on mpMRI were strong independent predictors of upgrading and adverse pathology. Incorporating mpMRI findings when selecting patients for active surveillance must be further evaluated in future studies.

Asunto(s)

RESUMEN

Three-dimensional (3D) freehand ultrasound (US) is a widely used imaging modality that allows non-invasive imaging of medical anatomy without radiation exposure. Surface reconstruction of US volume is vital to acquire the accurate anatomical structures needed for modeling, registration, and visualization. However, traditional methods cannot produce a high-quality surface due to image noise. Despite improvements in smoothness, continuity, and resolution from deep learning approaches, research on surface reconstruction in freehand 3D US is still limited. This study introduces FUNSR, a self-supervised neural implicit surface reconstruction method to learn signed distance functions (SDFs) from US volumes. In particular, FUNSR iteratively learns the SDFs by moving the 3D queries sampled around volumetric point clouds to approximate the surface, guided by two novel geometric constraints: sign consistency constraint and on-surface constraint with adversarial learning. Our approach has been thoroughly evaluated across four datasets to demonstrate its adaptability to various anatomical structures, including a hip phantom dataset, two vascular datasets and one publicly available prostate dataset. We also show that smooth and continuous representations greatly enhance the visual appearance of US data. Furthermore, we highlight the potential of our method to improve segmentation performance, and its robustness to noise distribution and motion perturbation.

Asunto(s)

RESUMEN

MRI-guided targeted biopsy (MRGB) was recommended as part of biopsy paradigm of prostate cancers by current guidelines. This study aimed to analyze the diagnostic efficacy of MRGB and systemic biopsy (SB), and to compare diagnostic capabilities within subgroups of MRGB: MRI-cognitive biopsy (MRCB) and MRI-fusion biopsy (MRFB). We retrospectively enrolled patients who underwent MRGB for suspicious malignant lesion(s) identified on MRI in a single tertiary center, sample size was 74 patients. An mpMRI was performed prior to biopsy and reviewed by an experienced radiologist specialized in prostate cancer. Per-person results of MRGB and each concomitant SB were analyzed as independent biopsies for its positive biopsy rate and positive core percentage. Per-lesion results of MRFB and MRCB were compared for the detection rate. Variables of interest were analyzed with t-test, chi-squared test, and logistic regression analysis. Statistical analyses were performed with IBM Statistical Product and Service Solutions (SPSS), Version 23 (IBM, Armonk, New York). Total of 74 patients fulfilled the inclusion criteria and were enrolled. MRFB had higher PCa detection rate comparing to both MRCB and SB (56.1%, 30.3%, and 33.9% respectively, p value = 0.036); clinically significant prostate cancer (csPCa) detection rate was also significantly higher in MRFB group (43.9%, 24.2%, and 16.9% in each group respectively, p value = 0.011). In per-lesion analysis, MRCB and MRFB had no significant difference in PCa and csPCa detection rate (41.0% vs. 26.2% and 29.5% vs. 16.7% respectively, p value = 0.090 and 0.103). In the lesion ≦ 1.3 cm group, MRFB could achieve higher PCa detection rate, comparing to MRCB (36.4% vs. 14.3%, p value = 0.047); there were also higher positive rates for PCa and csPCa per biopsied cores (22.1% vs. 6.8% and 15.6% vs. 2.7%, p value = 0.029 and 0.028, respectively). Further logistic regression of multi-variate analysis in subgroup of lesion ≦ 1.3 cm revealed that PIRADS score and biopsy method were significant predictors of positive biopsy result for PCa (p value = 0.045 and 0.026, respectively) and for csPCa (p value = 0.043 and 0.025, respectively). In patients receiving trans-perineal prostate biopsy, MRFB had higher cancer detection rate than MRCB and SB. In per lesion comparison, MRFB and MRCB had similar diagnostic accuracy. However, in lesions with diameter less than 1.3 cm, MRFB can provided better diagnose value for PCa and csPCa than MRCB.

Asunto(s)

RESUMEN

The diagnosis of early prostate cancer depends on the accurate segmentation of prostate regions in magnetic resonance imaging (MRI). However, this segmentation task is challenging due to the particularities of prostate MR images themselves and the limitations of existing methods. To address these issues, we propose a U-shaped encoder-decoder network MM-UNet based on Mamba and CNN for prostate segmentation in MR images. Specifically, we first proposed an adaptive feature fusion module based on channel attention guidance to achieve effective fusion between adjacent hierarchical features and suppress the interference of background noise. Secondly, we propose a global context-aware module based on Mamba, which has strong long-range modeling capabilities and linear complexity, to capture global context information in images. Finally, we propose a multi-scale anisotropic convolution module based on the principle of parallel multi-scale anisotropic convolution blocks and 3D convolution decomposition. Experimental results on two public prostate MR image segmentation datasets demonstrate that the proposed method outperforms competing models in terms of prostate segmentation performance and achieves state-of-the-art performance. In future work, we intend to enhance the model's robustness and extend its applicability to additional medical image segmentation tasks.

Asunto(s)

RESUMEN

Background Multiparametric MRI can help identify clinically significant prostate cancer (csPCa) (Gleason score ≥7) but is limited by reader experience and interobserver variability. In contrast, deep learning (DL) produces deterministic outputs. Purpose To develop a DL model to predict the presence of csPCa by using patient-level labels without information about tumor location and to compare its performance with that of radiologists. Materials and Methods Data from patients without known csPCa who underwent MRI from January 2017 to December 2019 at one of multiple sites of a single academic institution were retrospectively reviewed. A convolutional neural network was trained to predict csPCa from T2-weighted images, diffusion-weighted images, apparent diffusion coefficient maps, and T1-weighted contrast-enhanced images. The reference standard was pathologic diagnosis. Radiologist performance was evaluated as follows: Radiology reports were used for the internal test set, and four radiologists' PI-RADS ratings were used for the external (ProstateX) test set. The performance was compared using areas under the receiver operating characteristic curves (AUCs) and the DeLong test. Gradient-weighted class activation maps (Grad-CAMs) were used to show tumor localization. Results Among 5735 examinations in 5215 patients (mean age, 66 years ± 8 [SD]; all male), 1514 examinations (1454 patients) showed csPCa. In the internal test set (400 examinations), the AUC was 0.89 and 0.89 for the DL classifier and radiologists, respectively (P = .88). In the external test set (204 examinations), the AUC was 0.86 and 0.84 for the DL classifier and radiologists, respectively (P = .68). DL classifier plus radiologists had an AUC of 0.89 (P < .001). Grad-CAMs demonstrated activation over the csPCa lesion in 35 of 38 and 56 of 58 true-positive examinations in internal and external test sets, respectively. Conclusion The performance of a DL model was not different from that of radiologists in the detection of csPCa at MRI, and Grad-CAMs localized the tumor. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Johnson and Chandarana in this issue.

Asunto(s)

RESUMEN

Background Intravenous prostate-specific membrane antigen (PSMA)-targeted radioligand therapy improves survival in men with metastatic castration-resistant prostate cancer. Yet, the impact of selective prostatic arterial administration on primary tumor uptake is unclear. Purpose To compare gallium 68 (68Ga)-PSMA-11 uptake using dynamic PET/CT in prostatic tumoral volumes of interest (VOIs) during intravenous and selective prostatic arterial infusions for individuals with untreated, high-risk prostate cancer. Materials and Methods In this prospective, intraindividual comparative study conducted at an academic medical center, five men aged 58, 61, 64, 66, and 68 years with treatment-naive prostate cancer were enrolled between January 2022 and February 2023 and underwent two dynamic 68Ga-PSMA-11 PET/CT examinations 1 week apart. During the first examination, the radiotracer was administered intravenously. During the second administration, the radiotracer was delivered into either the right or left prostatic artery through an angiographically placed microcatheter. The primary outcome was maximum standardized uptake value (SUVmax) in prostatic tumoral VOIs. The secondary outcomes included mean SUV (SUVmean) in prostatic tumoral VOIs and area under the SUVmean curves (AUC). Longitudinal mixed-effects models were used to compare dynamic SUVmax and SUVmean time-activity curves (TACs), and paired t tests were used for the remaining data. Results The mean SUVmax within tumoral VOIs was 14 (range, 3-43) for venous sessions and 938 (range, 460-1436) for arterial sessions (P = .008). The SUVmean within VOIs was greater during arterial sessions (P < .001) overall and 46-fold and 19-fold greater at peak uptake and final time points, respectively. The mean AUC was greater on arterial TACs than on venous TACs at 14600 SUV × min (range, 8353-20025 SUV × min) and 240 SUV × min (range, 69-622 SUV × min), respectively (P = .002). Conclusion Selective prostatic arterial infusion resulted in greater 68Ga-PSMA-11 tumoral SUV than intravenous infusion. Further study of local-regional, intra-arterial delivery of a PSMA-targeted theranostic agent is warranted in high-risk prostate cancer. ClinicalTrials.gov identifier: NCT04976257 © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Civelek in this issue.

Asunto(s)

RESUMEN

BACKGROUND: MRI fusion prostate biopsy has improved the detection of clinically significant prostate cancer (CSC). Continued refinements in predicting the pre-biopsy probability of CSC are essential for optimal patient counseling. We investigated potential factors related to improved cancer detection rates (CDR) of CSC in patients with PI-RADS ≥ 3 lesions. METHODS: The pathology of 980 index lesions in 980 patients sampled by transrectal mpMRI-targeted prostate biopsy across four medical centers between 2017-2020 was reviewed. PI-RADS lesion distribution included 291 PI-RADS-5, 374 PI-RADS-4, and 315 PI-RADS-3. We compared CDR of index PI-RADS ≥ 3 lesions based on location (TZ) vs. (PZ), PSA density (PSAD), and history of prior negative conventional transrectal ultrasound-guided biopsy (TRUS). RESULTS: Mean age, PSA, prostate volume, and level of prior negative TRUS biopsy were 66 years (43-90), 7.82 ng/dL (5.6-11.2), 54 cm3 (12-173), and 456/980 (46.5%), respectively. Higher PSAD, no prior history of negative TRUS biopsy, and PZ lesions were associated with higher CDR. Stratified CDR highlighted significant variance across subgroups. CDR for a PI-RADS-5 score, PZ lesion with PSAD ≥ 0.15, and prior negative biopsy was 77%. Conversely, the CDR rate for a PI-RADS-4 score, TZ lesion with PSAD < 0.15, and prior negative biopsy was significantly lower at 14%. CONCLUSIONS: For index PI-RADS ≥ 3 lesions, CDR varied significantly based on location, prior history of negative TRUS biopsy, and PSAD. Such considerations are critical when counseling on the merits and potential yield of prostate needle biopsy.

Asunto(s)

RESUMEN

BACKGROUND: Magnetic  resonance imaging (MRI) followed by targeted biopsy (TBx) is utilized for prostate cancer (PCa) detection. However, the value of adding systematic biopsies (SBx) to targeted biopsy procedures (combined biopsy; CBx) in men with suspicious MRI findings has not been determined. METHODS: We analysed biopsy outcomes in 429 men with MRI lesions in the prospective multicenter STHLM3MRI pilot study, planned for prostate biopsy. Participants underwent 1.5T biparametric MRI without contrast enhancement, reported according to the PI-RADS v2, and with TBx plus SBx if the MRI lesion score was ≥ 3. The endpoints were clinically nonsignificant (nsPCa) and clinically significant PCa (csPCa), defined as ISUP grade groups 1 and ≥ 2, respectively. RESULTS: The median age was 65 years (59-70), and the median PSA 6.0 ng/ml (4.1-9.0). The detection rates of csPCa when using TBx or SBx combined were 18%, 46%, and 85% in men with PIRADS scores of 3 (n = 195), 4 (n = 121), and 5 (n = 113), respectively. This combined strategy detected csPCa in more men than TBx alone (43.6% vs 39.2%, p < 0.02), with similar detection of nsPCa (19.3% vs 17.7%, p = 0.2). In men with equivocal lesions (PI-RADS 3), the detection rates for csPCa were similar for the combined strategy and for TBx alone (17.9% and 15.4%, p = 0.06). However, there was an increase in the detection of nsPCa when using the combined strategy (21.0% vs 15.4%, p < 0.02). Men with equivocal lesions and a PSA density < 0.1 ng/ml2 or a Stockholm 3 test < 0.11 had a low risk of harboring csPCa. CONCLUSIONS: Supplementing targeted with systematic biopsies enhances clinically significant cancer detection. However, in men with equivocal lesions, this combination has potential for detecting nonsignificant disease. A subgroup of men with equivocal MRI findings may be identified as having a low risk for significant cancer and spared unnecessary biopsies.

Asunto(s)

RESUMEN

BACKGROUND: We aimed to determine if preoperative prostate volume-enucleated weight concordance predicts short-term anatomical endoscopic enucleation of the prostate (AEEP) outcomes using the REAP international database. METHODS: 649 patients with data on both preoperative ultrasound-derived prostate volume and enucleated specimen weight were analyzed. Linear regression was used to investigate the effect of volume-weight concordance on postoperative outcomes. Model residuals were used to divide the cohort into 3 centiles: (1) less-than-expected enucleated specimen weight; (2) appropriate concordance between prostate volume and specimen weight; (3) more-than-expected specimen weight. Outcomes were also analyzed with only enucleated weight as a predictor (comparing ≤ 80 g and > 80 g). RESULTS: There was a trend towards more-than-expected enucleated specimen weight with increased age (p = 0.006). There was an increasing trend of operation time (p = 0.012) and enucleation time (p = 0.015) as specimen weight increased, and a decreasing trend of postoperative acute urinary retention (p = 0.005). Laser type, enucleation method, and early apical release were similar. In correlation analysis, greater-than-expected prostate weight was associated with greater Qmax improvement at 3 months. Prostate weight alone did not appear to be a significant predictor of outcomes. CONCLUSIONS: If enucleated specimen weight is more than expected according to preoperative ultrasound volume measurement, greater Qmax improvement and less postoperative acute urinary retention is expected. Although precision may be limited by ultrasound approximation and inexact specimen weight measurements, these shortcomings are similar in real-world clinical practice. Overall, preoperative prostate volume and actual enucleated specimen weight should be interpreted in the context of each other to predict clinical outcomes.

Asunto(s)

RESUMEN

BACKGROUND: Transrectal ultrasound-guided prostate biopsy (TRUS-Bx) is the gold standard diagnostic method for prostate cancer. In people with low health literacy, accurate and early diagnosis rates decrease, making it difficult to maintain health and compliance with treatment. In our study, we investigated how health literacy and sociocultural parameters affected compliance and awareness in patients with suspected prostate cancer, for whom TRUS-Bx was planned. METHODS: In the study, 98 male patients aged 50-80 years, recommended for TRUS-Bx, were included in our study. The data including age, prostate-specific antigen, prostate volume, digital rectal examination findings, education leveland area of residence of the patients included in the study were recorded. Health Literacy Survey-Turkey- Questionnaire 47 and Turkish Health Literacy Scale-32 forms were completed by the patients who agreed to participate in the study, and their scores were recorded. Patients scheduled for TRUS-Bx were divided into two groups: those who attended their appointments and underwent the biopsy, and those who did not attend their scheduled appointments. The effect of health literacy and other parameters on the TRUS-Bx requirement was examined between the two groups. Furthermore, 52 patients who underwent TRUS-Bx were divided into two groups as malignancy (malignant) detected and not-detected (benign) patients according to the pathology results, and the parameters were analyzed separately for these groups. RESULTS: The education level of the patients who underwent the TRUS-Bx procedure was found to be statistically higher (p = 0.026). Health Literacy Survey-Turkey- Questionnaire 47 and Turkish Health Literacy Scale-32 scores were statistically significantly higher in the TRUS-Bx group (p = 0.001, p < 0.001, respectively). In the logistic regression analysis, education level, Health Literacy Survey-Turkey- Questionnaire 47 and Turkish Health Literacy Scale-32 were found to be important predictors for awareness of the requirement for TRUS-Bx. CONCLUSION: The study's findings indicate that patients with higher health literacy and education levels were more likely to receive an early diagnosis and promptly proceed with the recommended TRUS-Bx after visiting a urologist.

Asunto(s)

RESUMEN

Micro-ultrasound has recently been introduced as a low-cost alternative to multi-parametric MRI for imaging prostate cancer. Early clinical studies have demonstrated promising results; however, robust validation via comparison with whole-mount pathology has yet to be achieved. Due to micro-ultrasound probe design and tissue deformation during scanning, it is difficult to accurately correlate micro-ultrasound imaging planes with ground truth whole-mount pathology slides. In this study, we developed a multi-step methodology to co-register micro-ultrasound and MRI to whole-mount pathology. The three-step process had a registration error of 3.90 ± 0.11 mm and consists of: (1) micro-ultrasound image reconstruction, (2) 3D landmark registration of micro-ultrasound to MRI, and (3) 2D capsule registration of MRI to whole-mount pathology. This process was then used in a preliminary reader study to compare the diagnostic accuracy of micro-ultrasound and MRI in 15 patients who underwent radical prostatectomy for prostate cancer. Micro-ultrasound was found to have equivalent performance to retrospective MRI review for index lesion detection (91.7% vs. 80%), while demonstrating an increased detection of tumor extent (52.5% vs. 36.7%) with similar false positive regions-of-interest (38.3% vs. 40.8%). Prospective MRI review had reduced detection of index lesions (73.3%) and tumor extent (18.9%) but improved false positive regions-of-interest (22.7%) relative to micro-ultrasound and retrospective MRI. Further evaluation is needed with a larger sample size.

Asunto(s)

Asunto(s)

Asunto(s)

RESUMEN

AIM: The aim of this study was to determine whether biparametric magnetic resonance imaging (MRI) is effective in the diagnosis of clinically significant prostate cancer in prostate peripheral zone Prostate Imaging Reporting and Data System (PIRADS) 3 lesions without the use of dynamic contrast enhancement. MATERIALS AND METHODS: Patients who underwent biparametric MRI over a 12-month period from January 2022 to December 2022 and were diagnosed with PIRADS 3 lesion in the peripheral zone were included in the study. No patient received dynamic contrast enhancement. Histological analysis was done after performing local anesthetic transperineal biopsy to determine detection rate of clinically significant prostate cancer. Prostate-specific antigen density (PSAD) and biopsy complication rates were also reviewed. RESULTS: Sixty-one out of 688 MRIs (8.8%) performed over the study period had a PIRADS 3 lesion in the peripheral zone where contrast is supposed to add value. Fifty-eight of the 61 went ahead to biopsy, and csPCa (Gleason score: ≥3 + 4, with a max core length of ≥6 mm and above) was diagnosed in 17%. Among those diagnosed with csPCa, 80% had a PSAD of >0.15 ng/ml/cc. No postbiopsy complications were reported. CONCLUSION: Biparametric MRI without contrast offers a reliable alternative to multiparametric MRI with minimum or neglible impact on clinically significant prostate cancer (csPCa) diagnosis in peripheral zone PIRADS 3 lesions, especially when used in conjunction with other factors such as PSAD. There is potential to address health economics and patient burden in prostate cancer investigation.

Asunto(s)

RESUMEN

Objective.Automatic segmentation of prostatic zones from MRI can improve clinical diagnosis of prostate cancer as lesions in the peripheral zone (PZ) and central gland (CG) exhibit different characteristics. Existing approaches are limited in their accuracy in localizing the edges of PZ and CG. The proposed boundary-aware semantic clustering network (BASC-Net) improves segmentation performance by learning features in the vicinity of the prostate zonal boundaries, instead of only focusing on manually segmented boundaries.Approach.BASC-Net consists of two major components: the semantic clustering attention (SCA) module and the boundary-aware contrastive (BAC) loss. The SCA module implements a self-attention mechanism that extracts feature bases representing essential features of the inner body and boundary subregions and constructs attention maps highlighting each subregion. SCA is the first self-attention algorithm that utilizes ground truth masks to supervise the feature basis construction process. The features extracted from the inner body and boundary subregions of the same zone were integrated by BAC loss, which promotes the similarity of features extracted in the two subregions of the same zone. The BAC loss further promotes the difference between features extracted from different zones.Main results.BASC-Net was evaluated on the NCI-ISBI 2013 Challenge and Prostate158 datasets. An inter-dataset evaluation was conducted to evaluate the generalizability of the proposed method. BASC-Net outperformed nine state-of-the-art methods in all three experimental settings, attaining Dice similarity coefficients of 79.9% and 88.6% for PZ and CG, respectively, in the NCI-ISBI dataset, 80.5% and 89.2% for PZ and CG, respectively, in Prostate158 dataset, and 73.2% and 87.4% for PZ and CG, respectively, in the inter-dataset evaluation.Significance.As prostate lesions in PZ and CG have different characteristics, the zonal boundaries segmented by BASC-Net will facilitate prostate lesion detection.

Asunto(s)