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.

Metabolic Parameters as Biomarkers of Response to Immunotherapy and Prognosis in Non-Small Cell Lung Cancer (NSCLC): A Real World Experience.

Immune-checkpoint inhibitors (ICIs) have been proven to have great efficacy in non-small cell lung cancer (NSCLC) as single agents or in combination therapy, being capable to induce deep and durable remission. However, severe adverse events may occur and about 40% of patients do not benefit from the treatment. Predictive factors of response to ICIs are needed in order to customize treatment. The aim of this study is to evaluate the correlation between quantitative positron emission tomography (PET) parameters defined before starting ICI therapy and responses to treatment and patient outcome. We retrospectively analyzed 92 NSCLC patients treated with nivolumab, pembrolizumab or atezolizumab. Basal PET/computed tomography (CT) scan parameters (whole-body metabolic tumor volume-wMTV, total lesion glycolysis-wTLG, higher standardized uptake volume maximum and mean-SUVmax and SUVmean) were calculated for each patient and correlated with outcomes. Patients who achieved disease control (complete response + partial response + stable disease) had significantly lower MTV median values than patients who had not (progressive disease) (77 vs. 160.2, p = 0.039). Furthermore, patients with MTV and TLG values lower than the median values had improved OS compared to patients with higher MTV and TLG (p = 0.03 and 0.05, respectively). No relation was found between the other parameters and outcome. In conclusion, baseline metabolic tumor burden, measured with MTV, might be an independent predictor of treatment response to ICI and a prognostic biomarker in NSCLC patients.

CD4+CD25+CD127hi cell frequency predicts disease progression in type 1 diabetes.

Transient partial remission, a period of low insulin requirement experienced by most patients soon after diagnosis, has been associated with mechanisms of immune regulation. A better understanding of such natural mechanisms of immune regulation might identify new targets for immunotherapies that reverse type 1 diabetes (T1D). In this study, using Cox model multivariate analysis, we validated our previous findings that patients with the highest frequency of CD4+CD25+CD127hi (127-hi) cells at diagnosis experience the longest partial remission, and we showed that the 127-hi cell population is a mix of Th1- and Th2-type cells, with a significant bias toward antiinflammatory Th2-type cells. In addition, we extended these findings to show that patients with the highest frequency of 127-hi cells at diagnosis were significantly more likely to maintain ß cell function. Moreover, in patients treated with alefacept in the T1DAL clinical trial, the probability of responding favorably to the antiinflammatory drug was significantly higher in those with a higher frequency of 127-hi cells at diagnosis than those with a lower 127-hi cell frequency. These data are consistent with the hypothesis that 127-hi cells maintain an antiinflammatory environment that is permissive for partial remission, ß cell survival, and response to antiinflammatory immunotherapy.

Combining positron emission tomography/computed tomography, radiomics, and sentinel lymph node mapping for nodal staging of endometrial cancer patients.

OBJECTIVE: To evaluate the combination of positron emission tomography/computed tomography (PET/CT) and sentinel lymph node (SLN) biopsy in women with apparent early-stage endometrial carcinoma. The correlation between radiomics features extracted from PET images of the primary tumor and the presence of nodal metastases was also analyzed. METHODS: From November 2006 to March 2019, 167 patients with endometrial cancer were included. All women underwent PET/CT and surgical staging: 60/167 underwent systematic lymphadenectomy (Group 1) while, more recently, 107/167 underwent SLN biopsy (Group 2) with technetium-99m +blue dye or indocyanine green. Histology was used as standard reference. PET endometrial lesions were segmented (n=98); 167 radiomics features were computed inside tumor contours using standard Image Biomarker Standardization Initiative (IBSI) methods. Radiomics features associated with lymph node metastases were identified (Mann-Whitney test) in the training group (A); receiver operating characteristic (ROC) curves, area under the curve (AUC) values were computed and optimal cut-off (Youden index) were assessed in the test group (B). RESULTS: In Group 1, eight patients had nodal metastases (13%): seven correctly ridentified by PET/CT true-positive with one false-negative case. In Group 2, 27 patients (25%) had nodal metastases: 13 true-positive and 14 false-negative. Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of PET/CT for pelvic nodal metastases were 87%, 94%, 93%, 70%, and 98% in Group 1 and 48%, 97%, 85%, 87%, and 85% in Group 2, respectively. On radiomics analysis a significant association was found between the presence of lymph node metastases and 64 features. Volume-density, a measurement of shape irregularity, was the most predictive feature (p=0001, AUC=0,77, cut-off 0.35). When testing cut-off in Group B to discriminate metastatic tumors, PET false-negative findings were reduced from 14 to 8 (-43%). CONCLUSIONS: PET/CT demonstrated high specificity in detecting nodal metastases. SLN and histologic ultrastaging increased false-negative PET/CT findings, reducing the sensitivity of the technique. PET radiomics features of the primary tumor seem promising for predicting the presence of nodal metastases not detected by visual analysis.