Radiomic Machine-Learning Analysis of Multiparametric Magnetic Resonance Imaging in the Diagnosis of Clinically Significant Prostate Cancer: New Combination of Textural and Clinical Features

Can a nomogram predict apical prostate cancer pathology upgrade from fusion biopsy to final pathology? A multicenter study

BACKGROUND

This study evaluates the efficacy of a nomogram for predicting the pathology upgrade of apical prostate cancer (PCa).

METHODS

A total of 754 eligible patients were diagnosed with apical PCa through combined systematic and magnetic resonance imaging (MRI)-targeted prostate biopsy followed by radical prostatectomy (RP) were retrospectively identified from two hospitals (training: 754, internal validation: 182, internal-external validation: 148). A nomogram for the identification of apical tumors in high-risk pathology upgrades through comparing the results of biopsy and RP was established incorporating statistically significant risk factors based on univariable and multivariable logistic regression. The nomogram's performance was assessed via the receiver operating characteristic (ROC) curve, calibration plots, and decision curve analysis (DCA).

RESULTS

Univariable and multivariable analysis identified age, targeted biopsy, number of targeted cores, TNM stage, and the prostate imaging-reporting and data system score as significant predictors of apical tumor pathological progression. Our nomogram, based on these variables, demonstrated ROC curves for pathology upgrade with values of 0.883 (95% CI, 0.847-0.929), 0.865 (95% CI, 0.790-0.945), and 0.840 (95% CI, 0.742-0.904) for the training, internal validation and internal-external validation cohorts respectively. Calibration curves showed good consistency between the predicted and actual outcomes. The validation groups also showed great generalizability with the calibration curves. DCA results also demonstrated excellent performance for our nomogram with positive benefit across a threshold probability range of 0-0.9 for the training and internal validation group, and 0-0.6 for the internal-external validation group.

CONCLUSION

The nomogram, integrating clinical, radiological, and pathological data, effectively predicts the risk of pathology upgrade in apical PCa tumors. It holds significant potential to guide clinicians in optimizing the surgical management of these patients.

The Added Value of MRI-Based Targeted Biopsy in Biopsy-Naïve Patients: A Propensity-Score Matched Comparison

BACKGROUND

Multiparametric Magnetic Resonance Imaging (mpMRI)-based targeted biopsy has shown to be beneficial in detecting Clinically Significant Prostate Cancer (csPCa) and avoiding diagnosis of Non-csPCa (ncsPCa); however, its role in the treatment of biopsy-naïve patients is still under discussion.

METHODS

After identifying predictors for the diagnosis of csPCa via Multivariate Logistic Regression Analysis (MLRA), a propensity-score (1:1 nearest neighbor) matched comparison was performed between a Systematic-Only Biopsy (SOB) cohort and a mpMRI-based Combined (systematic + targeted) Biopsy (CB) cohort from two tertiary urologic centers (SOB: Department of Urology, University General Hospital of Heraklion, University of Crete, School of Medicine, Heraklion, Crete, Greece; CB: LKH Hall in Tirol, Austria). Only biopsy-naïve patients were included in the study. The study period for the included patients was from February 2018 to July 2023 for the SOB group and from July 2017 to June 2023 for the CB group. The primary outcome was the diagnosis of csPCa (≥ISUP 2); secondary outcomes were overall cancer detection, the added value of targeted biopsy in csPCa detection, and the reduction in ncsPCa diagnosis with CB compared to SOB. To estimate the Average Treatment effect of the Treated groups (ATT), cluster-robust standard errors were used to perform g-computation in the matched sample. p-values < 0.05 with a two-sided 95% confidence interval were considered statistically significant.

RESULTS

Matching achieved well-balanced groups (each n = 140 for CB and SOB). In the CB group, 65/140 (46.4%) patients were diagnosed with csPCa compared to 44/140 (31.4%) in the SOB group (RR 1.48, 95%-CI: 1.09-2.0, p = 0.01). In the CB group, 4.3% (6/140) and 1.4% (2/140) of csPCa cases were detected with targeted-only and systematic-only biopsy cores, respectively. In the CB group, 22/140 (15.7%) patients were diagnosed with ncsPCa compared to 33/140 (23.6%) in the SOB group (RR = 0.67, 95% CI: 0.41-1.08, p = 0.1). When comparing SOB to CB (ATT), the marginal OR was 0.56 (95% CI: 0.38-0.82, p = 0.003) for the diagnosis of csPCa and 0.75 (95% CI: 0.47-1.05, p = 0.085) for the diagnosis of overall cancer (≥ISUP 1).

CONCLUSION

The CB approach was superior to the SOB approach in detecting csPCa, while no additional detection of ncsPCa was seen. Our results support the application of mpMRI for biopsy-naïve patients with suspicions of prostate cancer.

AI-powered radiomics: revolutionizing detection of urologic malignancies

PURPOSE OF REVIEW

This review aims to highlight the integration of artificial intelligence-powered radiomics in urologic oncology, focusing on the diagnostic and prognostic advancements in the realm of managing prostate, kidney, and bladder cancers.

RECENT FINDINGS

As artificial intelligence continues to shape the medical imaging landscape, its integration into the field of urologic oncology has led to impressive results. For prostate cancer diagnostics, machine learning has shown promise in refining clinically-significant lesion detection, with some success in deciphering ambiguous lesions on multiparametric MRI. For kidney cancer, radiomics has emerged as a valuable tool for better distinguishing between benign and malignant renal masses and predicting tumor behavior from CT or MRI scans. Meanwhile, in the arena of bladder cancer, there is a burgeoning emphasis on prediction of muscle invasive cancer and forecasting disease trajectory. However, many studies showing promise in these areas face challenges due to limited sample sizes and the need for broader external validation.

SUMMARY

Radiomics integrated with artificial intelligence offers a pioneering approach to urologic oncology, ushering in an era of enhanced diagnostic precision and reduced invasiveness, guiding patient-tailored treatment plans. Researchers must embrace broader, multicentered endeavors to harness the full potential of this field.

Laparoscopic versus Ultrasound-Guided Transversus Abdominis Plane Block for Postoperative Analgesia Management after Radical Prostatectomy: Results from a Single Center Study

(1) Background: Regional anesthesia, achieved through nerve blocks, has gained widespread acceptance as an effective pain management approach. This research aimed to evaluate the efficacy of laparoscopic (LAP) transversus abdominis plane (TAP) block in patients undergoing laparoscopic radical prostatectomy. (2) Methods: From January 2023 to July 2023, 60 consecutive patients undergoing minimally invasive radical prostatectomy were selected. Patients were split into two groups receiving ultrasound-guided (US) or laparoscopic-guided TAP block. The primary outcome was a pain score expressed by a 0-10 visual analog scale (VAS) during the first 72 h after surgery. (3) Results: Both LAP-TAP and US-TAP block groups were associated with lower pain scores postoperatively. No statistically significant differences were observed between the two groups in surgery time, blood loss, time to ambulation, length of stay, and pain after surgery (all p > 0.2). In the LAP-TAP block group, the overall operating room time was significantly shorter than in the US-TAP block group (140 vs. 152 min, p = 0.04). (4) Conclusions: The laparoscopic approach, compared to the US-TAP block, was equally safe and not inferior in reducing analgesic drug use postoperatively. Moreover, the intraoperative LAP-TAP block seems to be a time-sparing procedure that could be recommended when patient-controlled analgesia cannot be delivered.

T2-Weighted MRI Radiomic Features Predict Prostate Cancer Presence and Eventual Biochemical Recurrence

Prostate cancer (PCa) is the most diagnosed non-cutaneous cancer in men. Despite therapies such as radical prostatectomy, which is considered curative, distant metastases may form, resulting in biochemical recurrence (BCR). This study used radiomic features calculated from multi-parametric magnetic resonance imaging (MP-MRI) to evaluate their ability to predict BCR and PCa presence. Data from a total of 279 patients, of which 46 experienced BCR, undergoing MP-MRI prior to surgery were assessed for this study. After surgery, the prostate was sectioned using patient-specific 3D-printed slicing jigs modeled using the T2-weighted imaging (T2WI). Sectioned tissue was stained, digitized, and annotated by a GU-fellowship trained pathologist for cancer presence. Digitized slides and annotations were co-registered to the T2WI and radiomic features were calculated across the whole prostate and cancerous lesions. A tree regression model was fitted to assess the ability of radiomic features to predict BCR, and a tree classification model was fitted with the same radiomic features to classify regions of cancer. We found that 10 radiomic features predicted eventual BCR with an AUC of 0.97 and classified cancer at an accuracy of 89.9%. This study showcases the application of a radiomic feature-based tool to screen for the presence of prostate cancer and assess patient prognosis, as determined by biochemical recurrence.

The Molecular Biology of Prostate Cancer Stem Cells: From the Past to the Future

Prostate cancer (PCa) continues to rank as the second leading cause of cancer-related mortality in western countries, despite the golden treatment using androgen deprivation therapy (ADT) or anti-androgen therapy. With decades of research, scientists have gradually realized that the existence of prostate cancer stem cells (PCSCs) successfully explains tumor recurrence, metastasis and therapeutic failure of PCa. Theoretically, eradication of this small population may improve the efficacy of current therapeutic approaches and prolong PCa survival. However, several characteristics of PCSCs make their diminishment extremely challenging: inherent resistance to anti-androgen and chemotherapy treatment, over-activation of the survival pathway, adaptation to tumor micro-environments, escape from immune attack and being easier to metastasize. For this end, a better understanding of PCSC biology at the molecular level will definitely inspire us to develop PCSC targeted approaches. In this review, we comprehensively summarize signaling pathways responsible for homeostatic regulation of PCSCs and discuss how to eliminate these fractional cells in clinical practice. Overall, this study deeply pinpoints PCSC biology at the molecular level and provides us some research perspectives.