Objective. This study aims to design and implement the first deep learning (DL) model to classify subjects in the prodromic states of Alzheimer’s disease (AD) based on resting-state electroencephalographic (EEG) signals. Approach. EEG recordings of 17 healthy controls (HCs), 56 subjective cognitive decline (SCD) and 45 mild cognitive impairment (MCI) subjects were acquired at resting state. After preprocessing, we selected sections corresponding to eyes-closed condition. Five different datasets were created by extracting delta, theta, alpha, beta and delta-to-theta frequency bands using bandpass filters. To classify SCD vs MCI and HC vs SCD vs MCI, we propose a framework based on the transformer architecture, which uses multi-head attention to focus on the most relevant parts of the input signals. We trained and validated the model on each dataset with a leave-one-subject-out cross-validation approach, splitting the signals into 10 s epochs. Subjects were assigned to the same class as the majority of their epochs. Classification performances of the transformer were assessed for both epochs and subjects and compared with other DL models. Main results. Results showed that the delta dataset allowed our model to achieve the best performances for the discrimination of SCD and MCI, reaching an Area Under the ROC Curve (AUC) of 0.807, while the highest results for the HC vs SCD vs MCI classification were obtained on alpha and theta with a micro-AUC higher than 0.74. Significance. We demonstrated that DL approaches can support the adoption of non-invasive and economic techniques as EEG to stratify patients in the clinical population at risk for AD. This result was achieved since the attention mechanism was able to learn temporal dependencies of the signal, focusing on the most discriminative patterns, achieving state-of-the-art results by using a deep model of reduced complexity. Our results were consistent with clinical evidence that changes in brain activity are progressive when considering early stages of AD.

The accurate segmentation and identification of vertebrae presents the foundations for spine analysis including fractures, malfunctions and other visual insights. The large-scale vertebrae segmentation challenge (VerSe), organized as a competition at the Medical Image Computing and Computer Assisted Intervention (MICCAI), is aimed at vertebrae segmentation and labeling. In this paper, we propose a framework that addresses the tasks of vertebrae segmentation and identification by exploiting both deep learning and classical machine learning methodologies. The proposed solution comprises two phases: a binary fully automated segmentation of the whole spine, which exploits a 3D convolutional neural network, and a semi-automated procedure that allows locating vertebrae centroids using traditional machine learning algorithms. Unlike other approaches, the proposed method comes with the added advantage of no requirement for single vertebrae-level annotations to be trained. A dataset of 214 CT scans has been extracted from VerSe’20 challenge data, for training, validating and testing the proposed approach. In addition, to evaluate the robustness of the segmentation and labeling algorithms, 12 CT scans from subjects affected by severe, moderate and mild scoliosis have been collected from a local medical clinic. On the designated test set from Verse’20 data, the binary spine segmentation stage allowed to obtain a binary Dice coefficient of 89.17%, whilst the vertebrae identification one reached an average multi-class Dice coefficient of 90.09%. In order to ensure the reproducibility of the algorithms hereby developed, the code has been made publicly available.

The identification of EEG biomarkers to discriminate Subjective Cognitive Decline (SCD) from Mild Cognitive Impairment (MCI) conditions is a complex task which requires great clinical effort and expertise. We exploit the self-attention component of the Transformer architecture to obtain physiological explanations of the model's decisions in the discrimination of 56 SCD and 45 MCI patients using resting-state EEG. Specifically, an interpretability workflow leveraging attention scores and time-frequency analysis of EEG epochs through Continuous Wavelet Transform is proposed. In the classification framework, models are trained and validated with 5-fold cross-validation and evaluated on a test set obtained by selecting 20% of the total subjects. Ablation studies and hyperparameter tuning tests are conducted to identify the optimal model configuration. Results show that the best performing model, which achieves acceptable results both on epochs’ and patients’ classification, is capable of finding specific EEG patterns that highlight changes in the brain activity between the two conditions. We demonstrate the potential of attention weights as tools to guide experts in understanding which disease-relevant EEG features could be discriminative of SCD and MCI.

The study of visuomotor adaptation (VMA) capabilities has been encompassed in various experimental protocols aimed at investigating human motor control strategies and/or cognitive functions. VMA-oriented frameworks can have clinical applications, primarily in the investigation and assessment of neuromotor impairments caused by conditions such as Parkinson’s disease or post-stroke, which affect the lives of tens of thousands of people worldwide. Therefore, they can enhance the understanding of the specific mechanisms of such neuromotor disorders, thus being a potential biomarker for recovery, with the aim of being integrated with conventional rehabilitative programs. Virtual Reality (VR) can be entailed in a framework targeting VMA since it allows the development of visual perturbations in a more customizable and realistic way. Moreover, as has been demonstrated in previous works, a serious game (SG) can further increase engagement thanks to the use of full-body embodied avatars. Most studies implementing VMA frameworks have focused on upper limb tasks and have utilized a cursor as visual feedback for the user. Hence, there is a paucity in the literature about VMA-oriented frameworks targeting locomotion tasks. In this article, the authors present the design, development, and testing of an SG-based framework that addresses VMA in a locomotion activity by controlling a full-body moving avatar in a custom VR environment. This workflow includes a set of metrics to quantitatively assess the participants’ performance. Thirteen healthy children were recruited to evaluate the framework. Several quantitative comparisons and analyses were run to validate the different types of introduced visuomotor perturbations and to evaluate the ability of the proposed metrics to describe the difficulty caused by such perturbations. During the experimental sessions, it emerged that the system is safe, easy to use, and practical in a clinical setting. Despite the limited sample size, which represents the main limitation of the study and can be compensated for with future recruitment, the authors claim the potential of this framework as a useful instrument for quantitatively assessing either motor or cognitive impairments. The proposed feature-based approach gives several objective parameters as additional biomarkers that can integrate the conventional clinical scores. Future studies might investigate the relation between the proposed biomarkers and the clinical scores for specific disorders such as Parkinson’s disease and cerebral palsy.

Robot-assisted radical prostatectomy (RARP) has become the most prevalent treatment for patients with organ-confined prostate cancer. Despite superior outcomes, suboptimal vesicourethral anastomosis (VUA) may lead to serious complications, including urinary leakage, prolonged catheterization, and extended hospitalization. A precise localization of both the surgical needle and the surrounding vesical and urethral tissues to coadapt is needed for fine-grained assessment of this task. Nonetheless, the identification of anatomical structures from endoscopic videos is difficult due to tissue distortions, changes in brightness, and instrument interferences. In this paper, we propose and compare two Deep Learning (DL) pipelines for the automatic segmentation of the mucosal layers and the suturing needle in real RARP videos by exploiting different architectures and training strategies. To train the models, we introduce a novel, annotated dataset collected from four VUA procedures. Experimental results show that the nnU-Net 2D model achieved the highest class-specific metrics, with a Dice Score of 0.663 for the mucosa class and 0.866 for the needle class, outperforming both transformer-based and baseline convolutional approaches on external validation video sequences. This work paves the way for computer-assisted tools that can objectively evaluate surgical performance during the critical phase of suturing tasks.

Accurate segmentation of key tumor subregions in adult gliomas from Magnetic Resonance Imaging (MRI) is of critical importance for brain tumor diagnosis, treatment planning, and prognosis. However, this task remains poorly investigated and highly challenging due to the considerable variability in shape and appearance of these areas across patients. This study proposes a novel Deep Learning architecture leveraging modality-specific encoding and attention-based refinement for the segmentation of glioma subregions, including peritumoral edema (ED), necrotic core (NCR), and enhancing tissue (ET). The model is trained and validated on the Brain Tumor Segmentation (BraTS) 2023 challenge dataset and benchmarked against a state-of-the-art transformer-based approach. Our architecture achieves promising results, with Dice scores of 0.78, 0.86, and 0.88 for NCR, ED, and ET, respectively, outperforming SegFormer3D while maintaining comparable model complexity. To ensure a comprehensive evaluation, performance was also assessed on standard composite tumor regions, i.e., tumor core (TC) and whole tumor (WT). The statistically significant improvements obtained on all regions highlight the effectiveness of integrating complementary modality-specific information and applying channel-wise feature recalibration in the proposed model.