Purpose Attenuation correction and scatter compensation (AC/SC) are two main steps toward quantitative PET imaging, which remain challenging in PET-only and PET/MRI systems. These can be effectively tackled via deep learning (DL) methods. However, trustworthy, and generalizable DL models commonly require well-curated, heterogeneous, and large datasets from multiple clinical centers. At the same time, owing to legal/ethical issues and privacy concerns, forming a large collective, centralized dataset poses significant challenges. In this work, we aimed to develop a DL-based model in a multicenter setting without direct sharing of data using federated learning (FL) for AC/SC of PET images. Methods Non-attenuation/scatter corrected and CT-based attenuation/scatter corrected (CT-ASC) 18F-FDG PET images of 300 patients were enrolled in this study. The dataset consisted of 6 different centers, each with 50 patients, with scanner, image acquisition, and reconstruction protocols varying across the centers. CT-based ASC PET images served as the standard reference. All images were reviewed to include high-quality and artifact-free PET images. Both corrected and uncorrected PET images were converted to standardized uptake values (SUVs). We used a modified nested U-Net utilizing residual U-block in a U-shape architecture. We evaluated two FL models, namely sequential (FL-SQ) and parallel (FL-PL) and compared their performance with the baseline centralized (CZ) learning model wherein the data were pooled to one server, as well as center-based (CB) models where for each center the model was built and evaluated separately. Data from each center were divided to contribute to training (30 patients), validation (10 patients), and test sets (10 patients). Final evaluations and reports were performed on 60 patients (10 patients from each center). Results In terms of percent SUV absolute relative error (ARE%), both FL-SQ (CI:12.21–14.81%) and FL-PL (CI:11.82–13.84%) models demonstrated excellent agreement with the centralized framework (CI:10.32–12.00%), while FL-based algorithms improved model performance by over 11% compared to CB training strategy (CI: 22.34–26.10%). Furthermore, the Mann–Whitney test between different strategies revealed no significant differences between CZ and FL-based algorithms (p-value > 0.05) in center-categorized mode. At the same time, a significant difference was observed between the different training approaches on the overall dataset (p-value < 0.05). In addition, voxel-wise comparison, with respect to reference CT-ASC, exhibited similar performance for images predicted by CZ (R2 = 0.94), FL-SQ (R2 = 0.93), and FL-PL (R2 = 0.92), while CB model achieved a far lower coefficient of determination (R2 = 0.74). Despite the strong correlations between CZ and FL-based methods compared to reference CT-ASC, a slight underestimation of predicted voxel values was observed. Conclusion Deep learning-based models provide promising results toward quantitative PET image reconstruction. Specifically, we developed two FL models and compared their performance with center-based and centralized models. The proposed FL-based models achieved higher performance compared to center-based models, comparable with centralized models. Our work provided strong empirical evidence that the FL framework can fully benefit from the generalizability and robustness of DL models used for AC/SC in PET, while obviating the need for the direct sharing of datasets between clinical imaging centers.

Pathology diagnostics relies on the assessment of morphology by trained experts, which remains subjective and qualitative. Here we developed a framework for large-scale histomorphometry (FLASH) performing deep learning-based semantic segmentation and subsequent large-scale extraction of interpretable, quantitative, morphometric features in non-tumour kidney histology. We use two internal and three external, multi-centre cohorts to analyse over 1000 kidney biopsies and nephrectomies. By associating morphometric features with clinical parameters, we confirm previous concepts and reveal unexpected relations. We show that the extracted features are independent predictors of long-term clinical outcomes in IgA-nephropathy. We introduce single-structure morphometric analysis by applying techniques from single-cell transcriptomics, identifying distinct glomerular populations and morphometric phenotypes along a trajectory of disease progression. Our study provides a concept for Next-generation Morphometry (NGM), enabling comprehensive quantitative pathology data mining, i.e., pathomics.

Background: Stroke is reported as a consequence of SARS-CoV-2 infection. However, there is a lack of regarding comprehensive stroke phenotype and characteristics Methods: We conducted a multinational observational study on features of consecutive acute ischemic stroke (AIS), intracranial hemorrhage (ICH), and cerebral venous or sinus thrombosis (CVST) among SARS-CoV-2 infected patients. We further investigated the association of demographics, clinical data, geographical regions, and countrie's health expenditure among AIS patients with the risk of large vessel occlusion (LVO), stroke severity as measured by National Institute of Health stroke scale (NIHSS), and stroke subtype as measured by the TOAST criteria. Additionally, we applied unsupervised machine learning algorithms to uncover possible similarities among stroke patients. Results: Among the 136 tertiary centers of 32 countries who participated in this study, 71 centers from 17 countries had at least one eligible stroke patient. Out of 432 patients included, 323(74.8%) had AIS, 91(21.1%) ICH, and 18(4.2%) CVST. Among 23 patients with subarachnoid hemorrhage, 16(69.5%) had no evidence of aneurysm. A total of 183(42.4%) patients were women, 104(24.1%) patients were younger than 55 years, and 105(24.4%) patients had no identifiable vascular risk factors. Among 380 patients who had known interval onset of the SARS-CoV-2 and stroke, 144(37.8%) presented to the hospital with chief complaints of stroke-related symptoms, with asymptomatic or undiagnosed SARS-CoV-2 infection. Among AIS patients 44.5% had LVO; 10% had small artery occlusion according to the TOAST criteria. We observed a lower median NIHSS (8[3-17], versus 11[5-17]; p=0.02) and higher rate of mechanical thrombectomy (12.4% versus 2%; p<0.001) in countries with middle to high-health expenditure when compared to countries with lower health expenditure. The unsupervised machine learning identified 4 subgroups, with a relatively large group with no or limited comorbidities. Conclusions: We observed a relatively high number of young, and asymptomatic SARS-CoV-2 infections among stroke patients. Traditional vascular risk factors were absent among a relatively large cohort of patients. Among hospitalized patients, the stroke severity was lower and rate of mechanical thrombectomy was higher among countries with middle to high-health expenditure.