The standard non-invasive imaging technique used to assess the severity and extent of Coronary Artery Disease (CAD) is Coronary Computed Tomography Angiography (CCTA). However, manual grading of each patient's CCTA according to the CAD-Reporting and Data System (CAD-RADS) scoring is time-consuming and operator-dependent, especially in borderline cases. This work proposes a fully automated, and visually explainable, deep learning pipeline to be used as a decision support system for the CAD screening procedure. The pipeline performs two classification tasks: firstly, identifying patients who require further clinical investigations and secondly, classifying patients into subgroups based on the degree of stenosis, according to commonly used CAD-RADS thresholds. The pipeline pre-processes multiplanar projections of the coronary arteries, extracted from the original CCTAs, and classifies them using a fine-tuned Multi-Axis Vision Transformer architecture. With the aim of emulating the current clinical practice, the model is trained to assign a per-patient score by stacking the bi-dimensional longitudinal cross-sections of the three main coronary arteries along channel dimension. Furthermore, it generates visually interpretable maps to assess the reliability of the predictions. When run on a database of 1873 three-channel images of 253 patients collected at the Monzino Cardiology Center in Milan, the pipeline obtained an AUC of 0.87 and 0.93 for the two classification tasks, respectively. According to our knowledge, this is the first model trained to assign CAD-RADS scores learning solely from patient scores and not requiring finer imaging annotation steps that are not part of the clinical routine.

The biological pathways involved in lesion formation after an acute ischemic stroke (AIS) are poorly understood. Despite successful reperfusion treatment, up to two thirds of patients with large vessel occlusion remain functionally dependent. Imaging characteristics extracted from DWI and T2-FLAIR follow-up MR sequences could aid in providing a better understanding of the lesion constituents. We built a fully automated pipeline based on a tree ensemble machine learning model to predict poor long-term functional outcome in patients from the MR CLEAN-NO IV trial. Several feature sets were compared, considering only imaging, only clinical, or both types of features. Nested cross-validation with grid search and a feature selection procedure based on SHapley Additive exPlanations (SHAP) was used to train and validate the models. Considering features from both imaging modalities in combination with clinical characteristics led to the best prognostic model (AUC = 0.85, 95%CI [0.81, 0.89]). Moreover, SHAP values showed that imaging features from both sequences have a relevant impact on the final classification, with texture heterogeneity being the most predictive imaging biomarker. This study suggests the prognostic value of both DWI and T2-FLAIR follow-up sequences for AIS patients. If combined with clinical characteristics, they could lead to better understanding of lesion pathophysiology and improved long-term functional outcome prediction.

The present study aimed to identify clusters of cognitive profiles as well as to explore the effects of these clusters on demographic/individual characteristics and on improvements after a computer-based cognitive training (CCT) in early cognitive impairment. Fifty-seven subjects underwent to an adaptive CCT for 3 weeks (4 individual face-to-face sessions/week of 45 min) and were evaluated at baseline (T0), post-intervention (T1), and after 6 (T2) and 12 (T3) months. Clusters of cognitive profiles were explored with k-means analysis. The analysis revealed two clusters, which were composed by 27 and 30 patients characterized by lower (Cluster 1) and higher (Cluster 2) cognitive functioning. At T1, cognitive performance improved in both groups, but Cluster 1 gained more benefits in global cognitive functioning than Cluster 2. However, at T3, Cluster 2 remained stable in its clinical condition, whereas Cluster 1 showed a pronounced worsening. In conclusion, Cluster 1 profile was associated with a more marked but also short-lasting responsiveness to CCT, whereas patients fitting with Cluster 2 characteristics seemed to obtain more CCT benefits in terms of stability or even delay of cognitive/functional decline. These findings may have relevant implications in informing the timing and modality of delivery of CCT.

This study aims to investigate the correlation between intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) parameters in magnetic resonance imaging (MRI) and programmed death-ligand 1 (PD-L1) expression in non-small cell lung cancer (NSCLC). Twenty-one patients diagnosed with stage III NSCLC from April 2021 to April 2022 were included. The tumors were distinguished into two groups: no PD-L1 expression (<1%), and positive PD-L1 expression (≥1%). Conventional MRI and IVIM-DWI sequences were acquired with a 1.5-T system. Both fixed-size ROIs and freehand segmentations of the tumors were evaluated, and the data were analyzed through a software using four different algorithms. The diffusion (D), pseudodiffusion (D*), and perfusion fraction (pf) were obtained. The correlation between IVIM parameters and PD-L1 expression was studied with Pearson correlation coefficient. The Wilcoxon–Mann–Whitney test was used to study IVIM parameter distributions in the two groups. Twelve patients (57%) had PD-L1 ≥1%, and 9 (43%) <1%. There was a statistically significant correlation between D* values and PD-L1 expression in images analyzed with algorithm 0, for fixed-size ROIs (189.2 ± 65.709 µm²/s × 10⁴ in no PD-L1 expression vs. 122.0 ± 31.306 µm²/s × 10⁴ in positive PD-L1 expression, p = 0.008). The values obtained with algorithms 1, 2, and 3 were not significantly different between the groups. The IVIM-DWI MRI parameter D* can reflect PD-L1 expression in NSCLC.

Background/Objectives: Cervical dystonia (CD) is a condition characterized by involuntary activity of cervical muscles, which is often accompanied by various non-motor symptoms. Recent studies indicate impaired saccadic eye movements in CD. Local administration of botulinum toxin type A (BoNT/A), which causes temporary paralysis of the injected muscle, is the first-line treatment of focal dystonia, including CD. To our knowledge, concurrent observation of the effect of BoNT/A on smooth eye movements, voluntary saccades, memory-guided saccades, and antisaccades in CD has not yet been explored. The aim of this study was to assess the effect of BoNT/A on eye movements and non-motor symptoms in patients with CD, which, when altered, could imply a central effect of BoNT/A. Methods: Thirty patients with CD performed smooth pursuit, prosaccadic expression, memory-guided saccades, and antisaccade tasks; eye movements were recorded by an eye tracker. Motor and non-motor symptoms, including depression, anxiety, pain, disability, and cognitive changes prior to and after BoNT/A administration, were also evaluated. Results: The number of correct onward counts (p < 0.001), overall correct memory-guided saccades count (p = 0.005), motor symptoms (p = 0.001), and non-motor symptoms, i.e., anxiety (p = 0.04), depression (p = 0.02), and cognition (p < 0.001) markedly improved after BoNT/A administration. Conclusions: Memory-guided saccades, depression, and anxiety improve after BoNT/A in CD.