Touch-free guided hand gesture recognition for human-robot interactions plays an increasingly significant role in teleoperated surgical robot systems. Indeed, despite depth cameras provide more practical information accuracy enhancement, the instability and computational burden of data represent a tricky problem. In this letter, we propose novel multi-sensor system teleoperation. A fusion model is designed performing interference presence occlusions. multilayer Recurrent Neural Network (RNN)...

Recent advances in image acquisition and processing techniques, along with the success of novel deep learning architectures, have given opportunity to develop innovative algorithms capable provide a better characterization neurological related diseases. In this work, we introduce neural network based approach classify Multiple Sclerosis (MS) patients into four clinical profiles. Starting from their structural connectivity information, obtained by diffusion tensor imaging represented as...

The coronavirus disease 19 (COVID-19) pandemic is having a dramatic impact on society and healthcare systems. In this complex scenario, lung computerized tomography (CT) may play an important prognostic role. However, datasets released so far present limitations that hamper the development of tools for quantitative analysis. paper, we open-source CT dataset comprising information 50 COVID-19-positive patients. volumes are provided along with (i) automatic threshold-based annotation obtained...

Primary Central Nervous System Lymphoma (PCNSL) is an aggressive neoplasm with a poor prognosis. Although therapeutic progresses have significantly improved Overall Survival (OS), number of patients do not respond to HD-MTX-based chemotherapy (15-25%) or experience relapse (25-50%) after initial response. The reasons underlying this response therapy are unknown. Thus, there urgent need develop predictive models for PCNSL. In study, we investigated whether radiomics features can improve...

The detection of the Optic Disc (OD) is an significant step in retinal fundus images analysis, it allows to extract relevant information that proved be useful for prevention several pathologies, such as glaucoma, hypertension, diabetes and other cardiovascular diseases, which manifest their effects retina. In this work we present a supervised method automatically detecting position digital images, goal has been achieved by means proper reuse previous knowledge from pre-trained Convolutional...

Purpose: The main goal of this study is to investigate the discrimination power Grey Matter (GM) thickness connectome data between Multiple Sclerosis (MS) clinical profiles using statistical and Machine Learning (ML) methods. Materials Methods: A dataset composed 90 MS patients acquired at clinic Lyon Neurological Hospital was used for analysis. Four were considered, corresponding Clinical Isolated Syndrome (CIS), Relapsing-Remitting (RRMS), Secondary Progressive (SPMS), Primary (PPMS). Each...

An abstract is not available for this content so a preview has been provided. Please use the Get access link above information on how to content.

Abstract Lesion segmentation in medical images is difficult yet crucial for proper diagnosis and treatment. Identifying lesions costly time-consuming requires highly specialized knowledge. For this reason, supervised semi-supervised learning techniques have been developed. Nevertheless, the lack of annotated data, which common imaging, an issue; context, interesting approaches can use unsupervised to accurately distinguish between healthy tissues lesions, training network without using...

Prediction of disability progression in multiple sclerosis patients is a critical component their management. In particular, one challenge to identify and characterize patient profile who may benefit efficient treatments. However, it not yet clear whether particular relation exists between the brain structure status.This work aims at producing fully automatic model for expanded status score estimation, given structural connectivity representation patient. The task addressed by first...

Abstract Purpose Ureteroscopy is an efficient endoscopic minimally invasive technique for the diagnosis and treatment of upper tract urothelial carcinoma. During ureteroscopy, automatic segmentation hollow lumen primary importance, since it indicates path that endoscope should follow. In order to obtain accurate lumen, this paper presents method based on convolutional neural networks (CNNs). Methods The proposed ensemble 4 parallel CNNs simultaneously process single multi-frame information....

Background: Multiple sclerosis (MS) is an autoimmune inflammatory disease of the central nervous system characterized by demyelination and neurodegeneration processes. It leads to different clinical courses degrees disability that need be anticipated neurologist for personalized therapy. Recently, machine learning (ML) techniques have reached a high level performance in brain diagnosis and/or prognosis, but decision process trained ML typically nontransparent. Using structural connectivity...

Advanced developments in the medical field have gradually increased public demand for surgical skill evaluation. However, this assessment always depends on direct observation of experienced surgeons, which is time-consuming and variable. The introduction robot-assisted surgery provides a new possibility evaluation paradigm. This paper aims at evaluating surgeon performance automatically with novel metrics based different data.Urologists ([Formula: see text]) from hospital were requested to...

The development of the Robot-Assisted Minimally Invasive Surgery (RAMIS) imposes an increasing demand for surgical training platforms, especially low-cost simulation-based through creation new open-source modules. For this goal, a da Vinci Surgical robot simulator based on Unity Physics Engine is developed. integrated with Research Kit (dVRK), kinematic models and multiple sensors. Robot Operating System (ROS) interface embedded better integration ROS software components. can provide...

Abstract Purpose Primary central nervous system lymphoma (PCNSL) is a rare, aggressive form of extranodal non-Hodgkin lymphoma. To predict the overall survival (OS) in advance utmost importance as it has potential to aid clinical decision-making. Though radiomics-based machine learning (ML) demonstrated promising performance PCNSL, demands large amounts manual feature extraction efforts from magnetic resonance images beforehand. deep (DL) overcomes this limitation. Methods In paper, we...

Lower reward responsiveness has been associated with fatigue in multiple sclerosis (MS). However, association of MS-related damage to the mesocorticolimbic pathway (superolateral medial forebrain bundle [slMFB]) not assessed. We investigated and depression slMFB MS patients stratified based on longitudinal patterns.Patient stratification: 1. Sustained Fatigue (SF): latest two Modified Impact Scale (MFIS) ≥ 38 (n = 26); 2. Reversible (RF): MFIS < 38, at least one previous 25); 3. Never...

Ureteroscopy is becoming the first surgical treatment option for majority of urinary affections. This procedure performed using an endoscope which provides surgeon with visual information necessary to navigate inside tract. Having in mind development assistance systems, that could enhance performance surgeon, task lumen segmentation a fundamental part since this reference marks path should follow. something has not been analyzed ureteroscopy data before. However, presents several challenges...

Zero-shot anomaly detection (ZSAD) offers potential for identifying anomalies in medical imaging without task-specific training. In this paper, we evaluate CLIP-based models, originally developed industrial tasks, on brain tumor using the BraTS-MET dataset. Our analysis examines their ability to detect medical-specific with no or minimal supervision, addressing challenges posed by limited data annotation. While these models show promise transferring general knowledge performance falls short...