Defining the optimal target-to-background ratio to identify positive lymph nodes in prostate cancer patients undergoing robot-assisted [99mTc]Tc-PSMA radioguided surgery: updated results and ad interim analyses of a prospective phase II study.

INTRODUCTION: Prostate-specific membrane antigen radioguided surgery (PSMA-RGS) might identify lymph node invasion (LNI) in prostate cancer (PCa) patients undergoing extended pelvic lymph node dissection (ePLND). The optimal target-to-background (TtB) ratio to define RGS positivity is still unknown. MATERIALS & METHODS: Ad interim analyses which focused on 30 patients with available pathological information were conducted. All patients underwent preoperative PSMA positron emission tomography (PET). 99m-Technetium-PSMA imaging and surgery ([99mTc]Tc-PSMA-I&S) was administered the day before surgery. In vivo measurements were conducted using an intraoperative gamma probe. Performance characteristics and implications associated with different TtB ratios were assessed. RESULTS: Overall, 9 (30%) patients had LNI, with 22 (13%) and 80 (11%) positive regions and lymph nodes, respectively. PSMA-RGS showed uptakes in 12 (40%) vs. 7 (23%) vs. 6 (20%) patients for a TtB ratio ≥ 2 vs. ≥ 3 vs. ≥ 4. At a per-region level, sensitivity, specificity and accuracy for a TtB ratio ≥ 2 vs. ≥ 3 vs. ≥ 4 were 72%, 88% and 87% vs. 54%, 98% and 92% vs. 36%, 99% and 91%. Performing ePLND only in patients with suspicious spots at PSMA PET (n = 7) would have spared 77% ePLNDs at the cost of missing 13% (n = 3) pN1 patients. A TtB ratio ≥ 2 at RGS identified 8 (24%) suspicious areas not detected by PSMA PET, of these 5 (63%) harbored LNI, with one pN1 patient (11%) that would have been missed by PSMA PET. Adoption of a TtB ratio ≥ 2 vs. ≥ 3 vs. ≥ 4, would have allowed to spare 18 (60%) vs. 23 (77%) vs. 24 (80%) ePLNDs missing 2 (11%) vs. 3 (13%) vs. 4 (17%) pN1 patients. CONCLUSIONS: PSMA-RGS using a TtB ratio ≥ 2 to identify suspicious nodes, could allow to spare > 50% ePLNDs and would identify additional pN1 patients compared to PSMA PET and higher TtB ratios.

Advancements in Neuroendocrine Neoplasms: Imaging and Future Frontiers.

Neuroendocrine neoplasms (NENs) are a diverse group of tumors with varying clinical behaviors. Their incidence has risen due to increased awareness, improved diagnostics, and aging populations. The 2019 World Health Organization classification emphasizes integrating radiology and histopathology to characterize NENs and create personalized treatment plans. Imaging methods like CT, MRI, and PET/CT are crucial for detection, staging, treatment planning, and monitoring, but each of them poses different interpretative challenges and none are immune to pitfalls. Treatment options include surgery, targeted therapies, and chemotherapy, based on the tumor type, stage, and patient-specific factors. This review aims to provide insights into the latest developments and challenges in NEN imaging, diagnosis, and management.

Preoperative assessment of lymph nodal metastases with [68Ga]Ga-DOTATOC PET radiomics for improved surgical planning in well-differentiated pancreatic neuroendocrine tumours.

PURPOSE: Accurate identification of lymph node (LN) metastases is pivotal for surgical planning of pancreatic neuroendocrine tumours (PanNETs); however, current imaging techniques have sub-optimal diagnostic sensitivity. Aim of this study is to investigate whether [68Ga]Ga-DOTATOC PET radiomics might improve the identification of LN metastases in patients with non-functioning PanNET (NF-PanNET) referred to surgical intervention. METHODS: Seventy-two patients who performed preoperative [68Ga]Ga-DOTATOC PET between December 2017 and March 2022 for NF-PanNET. [68Ga]Ga-DOTATOC PET qualitative assessment of LN metastases was measured using diagnostic balanced accuracy (bACC), sensitivity (SN), specificity (SP), positive and negative predictive values (PPV, NPV). SUVmax, SUVmean, Somatostatin receptor density (SRD), total lesion SRD (TLSRD) and IBSI-compliant radiomic features (RFs) were obtained from the primary tumours. To predict LN involvement, these parameters were engineered, selected and used to train different machine learning models. Models were validated using tenfold repeated cross-validation and control models were developed. Models' bACC, SN, SP, PPV and NPV were collected and compared (Kruskal-Wallis, Mann-Whitney). RESULTS: LN metastases were detected in 29/72 patients at histology. [68Ga]Ga-DOTATOC PET qualitative examination of LN involvement provided bACC = 60%, SN = 24%, SP = 95%, PPV = 78% and NPV = 65%. The best-performing radiomic model provided a bACC = 70%, SN = 77%, SP = 61%, PPV = 60% and NPV = 83% (outperforming the control model, p < 0.05*). CONCLUSION: In this study, [68Ga]Ga-DOTATOC PET radiomics allowed to increase diagnostic sensitivity in detecting LN metastases from 24 to 77% in NF-PanNET patients candidate to surgery. Especially in case of micrometastatic involvement, this approach might assist clinicians in a better patients' stratification.

Use of 18F-fluoro-2-deoxy-d-glucose (18F-FDG) PET/CT for lymph node assessment before radical cystectomy in bladder cancer patients.

OBJECTIVE: To assess the diagnostic performance of 18F-fluoro-2-deoxy-d-glucose (18F-FDG) positron emission tomograpy (PET)/computed tomography (CT) in nodal staging before radical cystectomy (RC) and pelvic lymph node dissection (PLND) for bladder cancer (BCa). MATERIALS AND METHODS: This analysis was based on a cohort of 199 BCa patients undergoing RC and bilateral PLND between 2015 and 2022. Neoadjuvant chemotherapy (NAC) or immunotherapy (NAI) was administered after oncological evaluation. All patients received preoperative 18F-FDG PET/CT to assess extravesical disease. Point estimates for true negative, false negative, false positive, true positive, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of conventional imaging and PET/CT were calculated. Subgroup analysis in patients receiving neoadjuvant treatment was performed. RESULTS: At preoperative evaluation, 30 patients (15.1%) had 48 suspicious nodal spots on 18F-FDG PET/CT. At RC and bilateral PLND, a total of 4871 lymph nodes (LNs) were removed with 237 node metastases corresponding to 126 different regions. Pathological node metastases were found in 17/30 (57%) vs 39/169 patients (23%) with suspicious vs negative preoperative 18F-FDG PET/CT, respectively (sensitivity = 0.30, specificity = 0.91, PPV = 0.57, NPV = 0.77, accuracy = 0.74). On per-region analysis including 1367 nodal regions, LN involvement was found in 19/48 (39%) vs 105/1319 (8%) suspicious vs negative regions at PET/CT, respectively (sensitivity = 0.15, specificity = 0.98, PPV = 0.40, NPV = 0.92, ACC = 0.90). Similar results were observed for patients receiving NAC (n = 44, 32.1%) and NAI (n = 93, 67.9% [per-patient: sensitivity = 0.36, specificity = 0.91, PPV = 0.59, NPV = 0.80, accuracy = 0.77; per-region: sensitivity = 0.12, specificity = 0.98, PPV = 0.32, NPV = 0.93, ACC = 0.91]). Study limitations include its retrospective design and limited patient numbers. CONCLUSIONS: In eight out of 10 patients with negative preoperative 18F-FDG PET/CT, pN0 disease was confirmed at final pathology. No differences were found based on NAC vs NAI treatment. These findings suggest that 18F-FDG PET/CT could play a role in the preoperative evaluation of nodal metastases in BCa patients, although its cost-effectiveness is uncertain.

Which Patients with Prostate Cancer and Lymph Node Uptake at Preoperative Prostate-specific Membrane Antigen Positron Emission Tomography/Computerized Tomography Scan Are at a Higher Risk of Prostate-specific Antigen Persistence After Radical Prostatectomy? Identifying Indicators of Systemic Disease by Integrating Clinical, Magnetic Resonance Imaging, and Functional Imaging Parameters.

BACKGROUND: The role of local therapies including radical prostatectomy (RP) in prostate cancer (PCa) patients with clinical lymphadenopathies on prostate-specific membrane antigen (PSMA) positron emission tomography/computerized tomography (PET/CT) has scarcely been explored. Limited data are available to identify men who would benefit from RP; on the contrary, those more likely to benefit already have systemic disease. OBJECTIVE: We aimed to assess the predictors of prostate-specific antigen (PSA) persistence in surgically managed PCa patients with lymphadenopathies on a PSMA PET/CT scan by integrating clinical, magnetic resonance imaging (MRI), and PSMA PET/CT parameters. DESIGN, SETTING, AND PARTICIPANTS: We identified 519 patients treated with RP and extended lymph node dissection, and who received preoperative PSMA PET between 2017 and 2022 in nine referral centers. Among them, we selected 88 patients with nodal uptake at preoperative PSMA PET (miTxN1M0). OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The outcome was PSA persistence, defined as a PSA value of ≥0.1 ng/ml at the first measurement after surgery. Multivariable logistic regression models tested the predictors of PSA persistence. Covariates consisted of biopsy International Society of Urological Pathology (ISUP) grade group, clinical stage at MRI, and number of positive spots at a PET/CT scan. A regression tree analysis stratified patients into risk groups based on preoperative characteristics. RESULTS AND LIMITATIONS: Overall, lymph node invasion (LNI) was detected in 63 patients (72%) and 32 (36%) experienced PSA persistence after RP. At multivariable analyses, having more than two lymph nodal positive findings at PSMA PET, seminal vesicle invasion (SVI) at MRI, and ISUP grade group >3 at biopsy were independent predictors of PSA persistence (all p < 0.05). At the regression tree analysis, patients were stratified in four risk groups according to biopsy ISUP grade, number of positive findings at PET/CT, and clinical stage at MRI. The model depicted good discrimination at internal validation (area under the curve 78%). CONCLUSIONS: One out of three miN1M0 patients showed PSA persistence after surgery. Patients with ISUP grade 2-3, as well as patients with organ-confined disease at MRI and a single or two positive nodal findings at PET are those in whom RP may achieve the best oncological outcomes in the context of a multimodal approach. Conversely, patients with a high ISUP grade and extracapsular extension or SVI or more than two spots at PSMA PET should be considered as potentially affected by systemic disease upfront. PATIENT SUMMARY: Our novel and straightforward risk classification integrates currently available preoperative risk tools and should, therefore, assist physician in preoperative counseling of men candidates for radical treatment for prostate cancer with positive lymph node uptake at prostate-specific membrane antigen positron emission tomography.

Diagnostic accuracy of fully hybrid [68Ga]Ga-PSMA-11 PET/MRI and [68Ga]Ga-RM2 PET/MRI in patients with biochemically recurrent prostate cancer: a prospective single-center phase II clinical trial.

PURPOSE: To compare the diagnostic accuracy and detection rates of PET/MRI with [68Ga]Ga-PSMA-11 and [68Ga]Ga-M2 in patients with biochemical recurrence of prostate cancer (PCa). METHODS: Sixty patients were enrolled in this prospective single-center phase II clinical trial from June 2020 to October 2022. Forty-four/60 completed all study examinations and were available at follow-up (median: 22.8 months, range: 6-31.5 months). Two nuclear medicine physicians analyzed PET images and two radiologists interpreted MRI; images were then re-examined to produce an integrated PET/MRI report for both [68Ga]Ga-PSMA-11 and [68Ga]Ga-RM2 examinations. A composite reference standard including histological specimens, response to treatment, and conventional imaging gathered during follow-up was used to validate imaging findings. Detection rates, accuracy, sensitivity, specificity, positive, and negative predictive value were assessed. McNemar's test was used to compare sensitivity and specificity on a per-patient base and detection rate on a per-region base. Prostate bed, locoregional lymph nodes, non-skeletal distant metastases, and bone metastases were considered. p-value significance was defined below the 0.05 level after correction for multiple testing. RESULTS: Patients' median age was 69.8 years (interquartile range (IQR): 61.8-75.1) and median PSA level at time of imaging was 0.53 ng/mL (IQR: 0.33-2.04). During follow-up, evidence of recurrence was observed in 31/44 patients. Combining MRI with [68Ga]Ga-PSMA-11 PET and [68Ga]Ga-RM2 PET resulted in sensitivity = 100% and 93.5% and specificity of 69.2% and 69.2%, respectively. When considering the individual imaging modalities, [68Ga]Ga-RM2 PET showed lower sensitivity compared to [68Ga]Ga-PSMA-11 PET and MRI (61.3% vs 83.9% and 87.1%, p = 0.046 and 0.043, respectively), while specificity was comparable among the imaging modalities (100% vs 84.6% and 69.2%, p = 0.479 and 0.134, respectively). CONCLUSION: This study brings further evidence on the utility of fully hybrid PET/MRI for disease characterization in patients with biochemically recurrent PCa. Imaging with [68Ga]Ga-PSMA-11 PET showed high sensitivity, while the utility of [68Ga]Ga-RM2 PET in absence of a simultaneous whole-body/multiparametric MRI remains to be determined.

Systematic Review and Metanalysis on the Role of Prostate-Specific Membrane Antigen Positron Emission Tomography/Magnetic Resonance Imaging for Intraprostatic Tumour Assessment.

The present systematic review and meta-analysis are focused on the diagnostic accuracy of PSMA PET/MRI in primary prostate cancer assessment. A literature search was conducted on the PubMed database using the terms "PSMA" AND "prostate cancer" or "prostate" AND "PET/MRI" or "PET MRI" or "PET-MRI" or "PET-MR" AND "primary" or "staging." Ten articles were eligible for analysis after applying the exclusion criteria. PET/MRI showed better diagnostic accuracy in detecting primary PCa compared to multiparametric (mp) MRI and PET alone. The pooled sensitivity and specificity of 68Ga-PSMA PET/MRI at the per-patient level were 0.976 (CI: 0.943-0.991) and 0.739 (CI: 0.437-0.912); respectively. PSMA PET/MRI has good sensitivity in detecting primary PCa, especially in patients with PIRADS 3 PCa.

Predictors of PSMA PET Positivity: Analysis in a Selected Cohort of Biochemical Recurrence Prostate Cancer Patients after Radical Prostatectomy.

Localized prostate cancer (PCa) can be treated with radical prostatectomy (RP). Up to 30% of patients undergoing this procedure experience biochemical recurrence (BCR), namely the rise in serum prostate-specific antigen (PSA) levels during the post-surgical follow-up, requiring further treatments and with the risk of severe disease progression. Currently, the most accurate imaging technique to confirm, detect, and locate disease relapses in BCR patients is prostate-specific membrane antigen (PSMA)-targeted PET, as recommended by international clinical guidelines. The aim of the study was to investigate potential clinical and pathological predictors of PSMA PET positivity, validated by clinical and instrumental follow-up or histopathological data. In this study, a selected cohort of BCR patients after RP and no other PCa-related therapy who underwent either PSMA PET/CT or PSMA PET/MRI has been analysed. Among the considered predictors, both pathological staging after RP equal or higher than pT3a and higher PSA levels at the time of the scan were significantly correlated with PSMA PET positivity on multivariate logistic regression analysis. As expected, PSMA PET confirmed its role as an accurate imaging technique in the setting of BCR in PCa. These findings may inform appropriate and tailored patient selection and scan timing to optimize and fully exploit this powerful diagnostic tool.

The potential role of osteoporosis in unspecific [18F]PSMA-1007 bone uptake.

AIM: Unspecific bone uptake is one of the main limitations of PET imaging with some PSMA-targeting radiopharmaceuticals, especially with [18F]PSMA-1007. We explored the potential association between osteoporosis and the occurrence of unspecific [18F]PSMA-1007 bone uptake investigating markers which might correlate with bone mineral density. MATERIALS AND METHODS: We retrospectively analyzed treatment-naïve patients with a confirmed diagnosis of prostate adenocarcinoma who underwent staging [18F]PSMA-1007 positron emission tomography (PET). Qualitative image analysis was performed independently by three experienced nuclear medicine physicians. Patients were divided in two groups according to the presence/absence of unspecific bone uptake. Clinical information, blood count parameters (assessed within 3 months to the PET scan), body mass index (BMI), and bone density as estimated by computed tomography were collected. The Kruskal-Wallis and t-test were used to compare parameters. RESULTS: We analyzed 77 patients: 29 of them (38%) had unspecific bone uptake at [18F]PSMA-1007 PET, most commonly in the pelvic bones (69%) and ribs (62%). We did not find any significant difference in clinical parameters in the two groups. In patients with unspecific bone uptake, white blood cell, and neutrophil counts were significantly higher; in the same group, we observed lower values of BMI and bone density, although not statistically different. CONCLUSIONS: We observed unspecific bone uptake on [18F]PSMA-1007 PET in more than 1/3 of patients. In this exploratory analysis, we found a significant correlation between blood count parameters and unspecific [18F]PSMA-1007 bone uptake. We may speculate that [18F]PSMA-1007 unspecific bone uptake could be associated with osteoporosis. This hypothesis needs to be further investigated in larger populations and exploring more specific markers of osteoporosis.

[68Ga]Ga-PSMA and [68Ga]Ga-RM2 PET/MRI vs. Histopathological Images in Prostate Cancer: A New Workflow for Spatial Co-Registration.

This study proposed a new workflow for co-registering prostate PET images from a dual-tracer PET/MRI study with histopathological images of resected prostate specimens. The method aims to establish an accurate correspondence between PET/MRI findings and histology, facilitating a deeper understanding of PET tracer distribution and enabling advanced analyses like radiomics. To achieve this, images derived by three patients who underwent both [68Ga]Ga-PSMA and [68Ga]Ga-RM2 PET/MRI before radical prostatectomy were selected. After surgery, in the resected fresh specimens, fiducial markers visible on both histology and MR images were inserted. An ex vivo MRI of the prostate served as an intermediate step for co-registration between histological specimens and in vivo MRI examinations. The co-registration workflow involved five steps, ensuring alignment between histopathological images and PET/MRI data. The target registration error (TRE) was calculated to assess the precision of the co-registration. Furthermore, the DICE score was computed between the dominant intraprostatic tumor lesions delineated by the pathologist and the nuclear medicine physician. The TRE for the co-registration of histopathology and in vivo images was 1.59 mm, while the DICE score related to the site of increased intraprostatic uptake on [68Ga]Ga-PSMA and [68Ga]Ga-RM2 PET images was 0.54 and 0.75, respectively. This work shows an accurate co-registration method for histopathological and in vivo PET/MRI prostate examinations that allows the quantitative assessment of dual-tracer PET/MRI diagnostic accuracy at a millimetric scale. This approach may unveil radiotracer uptake mechanisms and identify new PET/MRI biomarkers, thus establishing the basis for precision medicine and future analyses, such as radiomics.

Identification of the Optimal Candidates for Nodal Staging with Extended Pelvic Lymph Node Dissection Among Prostate Cancer Patients Who Underwent Preoperative Prostate-specific Membrane Antigen Positron Emission Tomography. External Validation of the Memorial Sloan Kettering Cancer Center and Briganti Nomograms and Development of a Novel Tool.

BACKGROUND: Although the therapeutic role of extended pelvic lymph node dissection (ePLND) in patients with prostate cancer (PCa) is still under debate, this procedure is recommended for staging purposes in selected cases. Nomograms for predicting lymph node invasion (LNI) do not account for prostate-specific membrane antigen (PSMA) positron emission tomography (PET) imaging, which is characterized by a high negative predictive value for nodal metastases. OBJECTIVE: To externally validate models predicting LNI in patients with miN0M0 PCa at PSMA PET and to develop a novel tool in this setting. DESIGN, SETTING, AND PARTICIPANTS: Overall, 458 patients with miN0M0 disease undergoing radical prostatectomy (RP) and ePLND at 12 centers between 2017 and 2022 were identified. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSES: Available tools were externally validated using calibration plots, the area under the receiver operating characteristic curve (AUC), and decision curve analyses to assess calibration, discrimination, and the net benefit. A novel coefficient-based model was developed, internally validated, and compared with available tools. RESULTS AND LIMITATIONS: Overall, 53 patients (12%) had LNI. The AUC was 69% for the Briganti 2012, 64% for the Briganti 2017, 73% for the Briganti 2019, and 66% for the Memorial Sloan Kettering Cancer Center nomogram. Multiparametric magnetic resonance imaging stage, biopsy grade group 5, the diameter of the index lesion, and the percentage of positive cores at systematic biopsy were independent predictors of LNI (all p ≤ 0.04). Internal cross-validation confirmed a coefficient-based model with AUC of 78%, better calibration, and a higher net benefit in comparison to the other nomograms assessed. Use of a 5% cutoff would have spared 47% ePLND procedures (vs 13% for the Briganti 2019 nomogram) at the cost of missing only 2.1% LNI cases . The lack of central review of imaging and pathology represents the main limitation. CONCLUSIONS: Tools for predicting LNI are associated with suboptimal performance for men with miN0M0 PCa. We propose a novel model for predicting LNI that outperforms available tools in this population. PATIENT SUMMARY: Tools currently used to predict lymph node invasion (LNI) in prostate cancer are not optimal for men with negative node findings on PET (positron emission tomography) scans, leading to a high number of unnecessary extended pelvic lymph node dissection (ePLND) procedures. A novel tool should be used in clinical practice to identify candidates for ePLND to reduce the risk of unnecessary procedures without missing LNI cases.

Somatostatin receptor activity assessed by 68Ga-DOTATOC PET can preoperatively predict DAXX/ATRX loss of expression in well-differentiated pancreatic neuroendocrine tumors.

PURPOSE: To evaluate the role of 68Ga-DOTATOC PET parameters in predicting DAXX/ATRX loss of expression in patients with Pancreatic neuroendocrine tumors (PanNET) candidate to surgery. METHODS: This retrospective study included 72 consecutive patients with PanNET (January 2018-March 2022) who underwent to 68Ga-DOTATOC PET for preoperative staging. Image analysis: qualitative assessment and extraction of SUVmax, SUV mean, somatostatin receptor density (SRD), and total lesion somatostatin receptor density (TLSRD) from primary PanNET. Radiological diameter and biopsy information (grade, Ki67) were collected. Loss of expression (LoE) of DAXX/ATRX was assessed by immunohistochemistry on surgical specimen. Student t-test, univariate and multivariate logistic regression and ROC curves have been used to investigate the predictive value of PET parameters on DAXX/ATRX LoE. RESULTS: Forty-two/72 patients had a G1, 28/72 a G2, and 2/72 a G3 PanNET. Seven/72 patients had DAXX LoE, 10/72 ATRX LoE, and 2/72 DAXX/ATRX LoE. SRD and TLSRD could predict DAXX LoE (p = 0.002, p = 0.018, respectively). By evaluating SRD in combination with radiological diameter, only SRD maintained statistical significance (multivariate logistic regression: p = 0.020, OR = 1.05), providing the best prediction (AUC-ROC = 79.01%; cut-off = 46.96; sensitivity = 77.78%; specificity = 88.89%). In the sub-analysis performed on 55 patients with biopsy availability, SRD demonstrated its role in providing useful and additional information (multivariate logistic regression: SRD p = 0.007; grade p = 0.040). CONCLUSION: SRD has a predictive role on DAXX LoE in PanNETs, with higher probability of LoE at increasing SRD values. SRD provides complementary/additional information to grade assessed on biopsy material, and the combined use of these approaches might support patients' management by preoperatively identifying subjects with more aggressive diseases.

External validation of a convolutional neural network for the automatic segmentation of intraprostatic tumor lesions on 68Ga-PSMA PET images.

Introduction: State of the art artificial intelligence (AI) models have the potential to become a "one-stop shop" to improve diagnosis and prognosis in several oncological settings. The external validation of AI models on independent cohorts is essential to evaluate their generalization ability, hence their potential utility in clinical practice. In this study we tested on a large, separate cohort a recently proposed state-of-the-art convolutional neural network for the automatic segmentation of intraprostatic cancer lesions on PSMA PET images. Methods: Eighty-five biopsy proven prostate cancer patients who underwent 68Ga PSMA PET for staging purposes were enrolled in this study. Images were acquired with either fully hybrid PET/MRI (N = 46) or PET/CT (N = 39); all participants showed at least one intraprostatic pathological finding on PET images that was independently segmented by two Nuclear Medicine physicians. The trained model was available at https://gitlab.com/dejankostyszyn/prostate-gtv-segmentation and data processing has been done in agreement with the reference work. Results: When compared to the manual contouring, the AI model yielded a median dice score = 0.74, therefore showing a moderately good performance. Results were robust to the modality used to acquire images (PET/CT or PET/MRI) and to the ground truth labels (no significant difference between the model's performance when compared to reader 1 or reader 2 manual contouring). Discussion: In conclusion, this AI model could be used to automatically segment intraprostatic cancer lesions for research purposes, as instance to define the volume of interest for radiomics or deep learning analysis. However, more robust performance is needed for the generation of AI-based decision support technologies to be proposed in clinical practice.

Role of [68Ga]Ga-PSMA-11 PET radiomics to predict post-surgical ISUP grade in primary prostate cancer.

PURPOSE: The aim of this study is to investigate the role of [68Ga]Ga-PSMA-11 PET radiomics for the prediction of post-surgical International Society of Urological Pathology (PSISUP) grade in primary prostate cancer (PCa). METHODS: This retrospective study included 47 PCa patients who underwent [68Ga]Ga-PSMA-11 PET at IRCCS San Raffaele Scientific Institute before radical prostatectomy. The whole prostate was manually contoured on PET images and 103 image biomarker standardization initiative (IBSI)-compliant radiomic features (RFs) were extracted. Features were then selected using the minimum redundancy maximum relevance algorithm and a combination of the 4 most relevant RFs was used to train 12 radiomics machine learning models for the prediction of PSISUP grade: ISUP ≥ 4 vs ISUP < 4. Machine learning models were validated by means of fivefold repeated cross-validation, and two control models were generated to assess that our findings were not surrogates of spurious associations. Balanced accuracy (bACC) was collected for all generated models and compared with Kruskal-Wallis and Mann-Whitney tests. Sensitivity, specificity, and positive and negative predictive values were also reported to provide a complete overview of models' performance. The predictions of the best performing model were compared against ISUP grade at biopsy. RESULTS: ISUP grade at biopsy was upgraded in 9/47 patients after prostatectomy, resulting in a bACC = 85.9%, SN = 71.9%, SP = 100%, PPV = 100%, and NPV = 62.5%, while the best-performing radiomic model yielded a bACC = 87.6%, SN = 88.6%, SP = 86.7%, PPV = 94%, and NPV = 82.5%. All radiomic models trained with at least 2 RFs (GLSZM-Zone Entropy and Shape-Least Axis Length) outperformed the control models. Conversely, no significant differences were found for radiomic models trained with 2 or more RFs (Mann-Whitney p > 0.05). CONCLUSION: These findings support the role of [68Ga]Ga-PSMA-11 PET radiomics for the accurate and non-invasive prediction of PSISUP grade.

External validation of an 18F-FDG-PET radiomic model predicting survival after radiotherapy for oropharyngeal cancer.

PURPOSE/OBJECTIVE: The purpose of the study is to externally validate published 18F-FDG-PET radiomic models for outcome prediction in patients with oropharyngeal cancer treated with chemoradiotherapy. MATERIAL/METHODS: Outcome data and pre-radiotherapy PET images of 100 oropharyngeal cancer patients (stage IV:78) treated with concomitant chemotherapy to 66-69 Gy/30 fr were available. Tumors were segmented using a previously validated semi-automatic method; 450 radiomic features (RF) were extracted according to IBSI (Image Biomarker Standardization Initiative) guidelines. Only one model for cancer-specific survival (CSS) prediction was suitable to be independently tested, according to our criteria. This model, in addition to HPV status, SUVmean and SUVmax, included two independent meta-factors (Fi), resulting from combining selected RF clusters. In a subgroup of 66 patients with complete HPV information, the global risk score R was computed considering the original coefficients and was tested by Cox regression as predictive of CSS. Independently, only the radiomic risk score RF derived from Fi was tested on the same subgroup to learn about the radiomics contribution to the model. The metabolic tumor volume (MTV) was also tested as a single predictor and its prediction performances were compared to the global and radiomic models. Finally, the validation of MTV and the radiomic score RF were also tested on the entire dataset. RESULTS: Regarding the analysis of the subgroup with HPV information, with a median follow-up of 41.6 months, seven patients died due to cancer. R was confirmed to be associated to CSS (p value = 0.05) with a C-index equal 0.75 (95% CI=0.62-0.85). The best cut-off value (equal to 0.15) showed high ability in patient stratification (p=0.01, HR=7.4, 95% CI=1.6-11.4). The 5-year CSS for R were 97% (95% CI: 93-100%) vs 74% (56-92%) for low- and high-risk groups, respectively. RF and MTV alone were also significantly associated to CSS for the subgroup with an almost identical C-index. According to best cut-off value (RF>0.12 and MTV>15.5cc), the 5-year CSS were 96% (95% CI: 89-100%) vs 65% (36-94%) and 97% (95% CI: 88-100%) vs 77% (58-93%) for RF and MTV, respectively. Results regarding RF and MTV were confirmed in the overall group. CONCLUSION: A previously published PET radiomic model for CSS prediction was independently validated. Performances of the model were similar to the ones of using only the MTV, without improvement of prediction accuracy.

Role of Machine Learning (ML)-Based Classification Using Conventional 18F-FDG PET Parameters in Predicting Postsurgical Features of Endometrial Cancer Aggressiveness.

PURPOSE: to investigate the preoperative role of ML-based classification using conventional 18F-FDG PET parameters and clinical data in predicting features of EC aggressiveness. METHODS: retrospective study, including 123 EC patients who underwent 18F-FDG PET (2009-2021) for preoperative staging. Maximum standardized uptake value (SUVmax), SUVmean, metabolic tumour volume (MTV), and total lesion glycolysis (TLG) were computed on the primary tumour. Age and BMI were collected. Histotype, myometrial invasion (MI), risk group, lymph-nodal involvement (LN), and p53 expression were retrieved from histology. The population was split into a train and a validation set (80-20%). The train set was used to select relevant parameters (Mann-Whitney U test; ROC analysis) and implement ML models, while the validation set was used to test prediction abilities. RESULTS: on the validation set, the best accuracies obtained with individual parameters and ML were: 61% (TLG) and 87% (ML) for MI; 71% (SUVmax) and 79% (ML) for risk groups; 72% (TLG) and 83% (ML) for LN; 45% (SUVmax; SUVmean) and 73% (ML) for p53 expression. CONCLUSIONS: ML-based classification using conventional 18F-FDG PET parameters and clinical data demonstrated ability to characterize the investigated features of EC aggressiveness, providing a non-invasive way to support preoperative stratification of EC patients.

Decoding the Heterogeneity of Malignant Gliomas by PET and MRI for Spatial Habitat Analysis of Hypoxia, Perfusion, and Diffusion Imaging: A Preliminary Study.

Background: Tumor heterogeneity poses major clinical challenges in high-grade gliomas (HGGs). Quantitative radiomic analysis with spatial tumor habitat clustering represents an innovative, non-invasive approach to represent and quantify tumor microenvironment heterogeneity. To date, habitat imaging has been applied mainly on conventional magnetic resonance imaging (MRI), although virtually extendible to any imaging modality, including advanced MRI techniques such as perfusion and diffusion MRI as well as positron emission tomography (PET) imaging. Objectives: This study aims to evaluate an innovative PET and MRI approach for assessing hypoxia, perfusion, and tissue diffusion in HGGs and derive a combined map for clustering of intra-tumor heterogeneity. Materials and Methods: Seventeen patients harboring HGGs underwent a pre-operative acquisition of MR perfusion (PWI), Diffusion (dMRI) and 18F-labeled fluoroazomycinarabinoside (18F-FAZA) PET imaging to evaluate tumor vascularization, cellularity, and hypoxia, respectively. Tumor volumes were segmented on fluid-attenuated inversion recovery (FLAIR) and T1 post-contrast images, and voxel-wise clustering of each quantitative imaging map identified eight combined PET and physiologic MRI habitats. Habitats' spatial distribution, quantitative features and histopathological characteristics were analyzed. Results: A highly reproducible distribution pattern of the clusters was observed among different cases, particularly with respect to morphological landmarks as the necrotic core, contrast-enhancing vital tumor, and peritumoral infiltration and edema, providing valuable supplementary information to conventional imaging. A preliminary analysis, performed on stereotactic bioptic samples where exact intracranial coordinates were available, identified a reliable correlation between the expected microenvironment of the different spatial habitats and the actual histopathological features. A trend toward a higher representation of the most aggressive clusters in WHO (World Health Organization) grade IV compared to WHO III was observed. Conclusion: Preliminary findings demonstrated high reproducibility of the PET and MRI hypoxia, perfusion, and tissue diffusion spatial habitat maps and correlation with disease-specific histopathological features.

A Single-center Prospective Observational Study Investigating the Accuracy of Preoperative Diagnostic Procedures in the Assessment of Lymph Node Metastases in Nonfunctioning Pancreatic Neuroendocrine Tumors.

OBJECTIVE: To determine the accuracy of preoperative imaging, including contrast-enhanced computed tomography (CE-CT), endoscopic ultrasound (EUS), and 68 Gallium-DOTATOC positron emission tomography ( 68 Ga-DOTATOC PET), in identifying nodal metastases (N+) in sporadic nonfunctioning pancreatic neuroendocrine tumors (NF-PanNETs). BACKGROUND: An accurate preoperative identification of N+ in NF-PanNETs is critical for surgical planning. The accuracy of different imaging techniques in detecting lymph node (LN) metastases in NF-PanNETs has been poorly investigated. METHODS: All consecutive patients undergoing surgery for sporadic NF-PanNETs (2018-2021) were enrolled in a prospective study (DETECTYON; NCT03918759). The accuracy of preoperative imaging techniques in detecting N+ was assessed through sensitivity, specificity positive and negative predictive values. RESULTS: Overall, 100 patients with NF-PanNETs underwent CE-CT, EUS, and 68 Ga-DOTATOC PET before pancreatic resection. LN metastases were found in 42 cases (42%). Sensitivity, specificity, positive predictive value, and negative predictive value of different imaging techniques were 26%, 95%, 79%, 64% for CE-CT, 19%, 98%, 89%, 63% for EUS, and 12%, 95%, 63%, 60% for 68 Ga-DOTATOC PET, respectively. Radiologic tumor size >4 cm and the presence of radiologic N+ at ≥1 imaging were independent predictors of N+ at pathology. The identification of N+ at ≥1 imaging technique was associated with a higher number of positive LNs compared with negative imaging (4 vs 2) ( P =0.012). CONCLUSIONS: CE-CT, EUS, and 68 Ga-DOTATOC PET are poorly sensitive in predicting nodal status in NF-PanNETs despite a high specificity.