Search

Objectives: Radical prostatectomy (RP) is a common intervention in patients with localized prostate cancer (PCa), with nerve-sparing RP recommended to reduce adverse effects on patient quality of life. Accurate pre-operative detection of extraprostatic extension (EPE) remains challenging, often leading to the application of suboptimal treatment. The aim of this study was to enhance pre-operative EPE detection through multimodal data integration using explainable machine learning (ML)., Methods: Patients with newly diagnosed PCa who underwent [ 68 Ga]Ga-PSMA-11 PET/MRI and subsequent RP were recruited retrospectively from two time ranges for training, cross-validation, and independent validation. The presence of EPE was measured from post-surgical histopathology and predicted using ML and pre-operative parameters, including PET/MRI-derived features, blood-based markers, histology-derived parameters, and demographic parameters. ML models were subsequently compared with conventional PET/MRI-based image readings., Results: The study involved 107 patients, 59 (55%) of whom were affected by EPE according to postoperative findings for the initial training and cross-validation. The ML models demonstrated superior diagnostic performance over conventional PET/MRI image readings, with the explainable boosting machine model achieving an AUC of 0.88 (95% CI 0.87-0.89) during cross-validation and an AUC of 0.88 (95% CI 0.75-0.97) during independent validation. The ML approach integrating invasive features demonstrated better predictive capabilities for EPE compared to visual clinical read-outs (Cross-validation AUC 0.88 versus 0.71, p = 0.02)., Conclusion: ML based on routinely acquired clinical data can significantly improve the pre-operative detection of EPE in PCa patients, potentially enabling more accurate clinical staging and decision-making, thereby improving patient outcomes., Critical Relevance Statement: This study demonstrates that integrating multimodal data with machine learning significantly improves the pre-operative detection of extraprostatic extension in prostate cancer patients, outperforming conventional imaging methods and potentially leading to more accurate clinical staging and better treatment decisions., Key Points: Extraprostatic extension is an important indicator guiding treatment approaches. Current assessment of extraprostatic extension is difficult and lacks accuracy. Machine learning improves detection of extraprostatic extension using PSMA-PET/MRI and histopathology., Competing Interests: Declarations. Ethics approval and consent to participate: This study was approved by the institutional review board with ethics ID EK 1985/2014 at the General Hospital of Vienna and was performed in line with the principles of the Declaration of Helsinki. Informed Consent was obtained from all patients participating in the study. Consent for publication: Not applicable. Competing interests: M. Hacker has received lecture fees from Siemens Healthineers and GE Healthcare. M. Hacker has received consulting fees from Evomics. P.C. has received lecture fees from Siemens Healthineers and is the upcoming Editor-in-Chief of Insights into Imaging. As such, they did not participate in the selection nor review processes for this article. The remaining authors have nothing to disclose., (© 2024. The Author(s).)

This paper summarises key themes and discussions from the 4th international workshop dedicated to the advancement of the technical, scientific and clinical applications of combined positron emission tomography (PET)/magnetic resonance imaging (MRI) systems that was held in Tübingen, Germany, from February 23 to 27, 2015. Specifically, we summarise the three days of invited presentations from active researchers in this and associated fields augmented by round table discussions and dialogue boards with specific topics. These include the use of PET/MRI in cardiovascular disease, paediatrics, oncology, neurology and multi-parametric imaging, the latter of which was suggested as a key promoting factor for the wider adoption of integrated PET/MRI. Discussions throughout the workshop and a poll taken on the final day demonstrated that attendees felt more strongly that PET/MRI has further advanced in both technical versatility and acceptance by clinical and research-driven users from the status quo of last year. Still, with only minimal evidence of progress made in exploiting the true complementary nature of the PET and MRI-based information, PET/MRI is still yet to achieve its potential. In that regard, the conclusion of last year's meeting "the real work has just started" still holds true.

Purpose: The aim of this study is to non-invasively assess early, irradiation-induced normal tissue alterations via metabolic imaging with 3'-deoxy-3'-[(18) F]fluorothymidine ([(18) F]FLT)., Procedures: Twenty-nine male C57BL/6 mice were investigated by [(18) F]FLT positron emission tomography for 7 days after total body irradiation (1, 4, and 8 Gy) versus 'sham' irradiation (0 Gy). Target/background ratios were determined. The imaging results were validated by histology and immunohistochemistry (Thymidine kinase 1, Ki-67)., Results: [(18) F]FLT demonstrated a dose-dependent intestinal accumulation post irradiation. Mean target/background ratio (±standard error) 0 Gy: 1.4 (0.2), 1 Gy: 1.7 (0.1), 4 Gy: 3.1 (0.3), 8 Gy: 4.2 (0.6). Receiver operating characteristic analysis (area under the curve, p value): 0 vs. 1 Gy: 0.81, 0.049; 0 vs. 4 Gy: 1.0, 0.0016; and 0 vs. 8 Gy: 1.0, 0.0020. Immunohistochemistry confirmed the results., Conclusions: [(18) F]FLT seems to provide dose-dependent information on radiation-induced proliferation in the bowel. This opens the perspective for monitoring therapy-related side-effects as well as assessing, e.g., radiation accident victims.

This workshop was held a year after the initial positron emission tomography/magnetic resonance (PET/MR) workshop in Tübingen, which was recently reported in this journal. The discussions at the 2013 workshop, however, differed substantially from those of the initial workshop, attesting to the progress of combined PET/MR as an innovative imaging modality. Discussions were focused on the search for truly novel, unique clinical and research applications as well as technical issues such as reliable and accurate approaches for attenuation and scatter correction of PET emission data. The workshop provided hands-on experience with PET and MR imaging. In addition, structured and moderated open discussion sessions, including six dialogue boards and two roundtable discussions, provided input from current and future PET/MR imaging users. This summary provides a snapshot of the current achievements and challenges for PET/MR.