Search

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., (Creative Commons Attribution license.)

Background: The automatic segmentation of kidneys in medical images is not a trivial task when the subjects undergoing the medical examination are affected by Autosomal Dominant Polycystic Kidney Disease (ADPKD). Several works dealing with the segmentation of Computed Tomography images from pathological subjects were proposed, showing high invasiveness of the examination or requiring interaction by the user for performing the segmentation of the images. In this work, we propose a fully-automated approach for the segmentation of Magnetic Resonance images, both reducing the invasiveness of the acquisition device and not requiring any interaction by the users for the segmentation of the images., Methods: Two different approaches are proposed based on Deep Learning architectures using Convolutional Neural Networks (CNN) for the semantic segmentation of images, without needing to extract any hand-crafted features. In details, the first approach performs the automatic segmentation of images without any procedure for pre-processing the input. Conversely, the second approach performs a two-steps classification strategy: a first CNN automatically detects Regions Of Interest (ROIs); a subsequent classifier performs the semantic segmentation on the ROIs previously extracted., Results: Results show that even though the detection of ROIs shows an overall high number of false positives, the subsequent semantic segmentation on the extracted ROIs allows achieving high performance in terms of mean Accuracy. However, the segmentation of the entire images input to the network remains the most accurate and reliable approach showing better performance than the previous approach., Conclusion: The obtained results show that both the investigated approaches are reliable for the semantic segmentation of polycystic kidneys since both the strategies reach an Accuracy higher than 85%. Also, both the investigated methodologies show performances comparable and consistent with other approaches found in literature working on images from different sources, reducing both the invasiveness of the analyses and the interaction needed by the users for performing the segmentation task.

In the last 10 years, the demand for robot-based depalletization systems has constantly increased due to the growth of sectors such as logistics, storage, and supply chains. Since the scenarios are becoming more and more unstructured, characterized by unknown pallet layouts and stock-keeping unit shapes, the classical depalletization systems based on the knowledge of predefined positions within the pallet frame are going to be substituted by innovative and robust solutions based on 2D/3D vision and Deep Learning (DL) methods. In particular, the Convolutional Neural Networks (CNNs) are deep networks that have proven to be effective in processing 2D/3D images, for example in the automatic object detection task, and robust to the possible variability among the data. However, deep neural networks need a big amount of data to be trained. In this context, whenever deep networks are involved in object detection for supporting depalletization systems, the dataset collection represents one of the main bottlenecks during the commissioning phase. The present work aims at comparing different training strategies to customize an object detection model aiming at minimizing the number of images required for model fitting, while ensuring reliable and robust performances. Different approaches based on a CNN for object detection are proposed, evaluated, and compared in terms of the F1-score. The study was conducted considering different starting conditions in terms of the neural network's weights, the datasets, and the training set sizes. The proposed approaches were evaluated on the detection of different kinds of paper boxes placed on an industrial pallet. The outcome of the work validates that the best strategy is based on fine-tuning of a CNN-based model already trained on the detection of paper boxes, with a median F1-score greater than 85.0 % . [ABSTRACT FROM AUTHOR]

Nuclei identification is a fundamental task in many areas of biomedical image analysis related to computational pathology applications. Nowadays, deep learning is the primary approach by which to segment the nuclei, but accuracy is closely linked to the amount of histological ground truth data for training. In addition, it is known that most of the hematoxylin and eosin (H&E)-stained microscopy nuclei images contain complex and irregular visual characteristics. Moreover, conventional semantic segmentation architectures grounded on convolutional neural networks (CNNs) are unable to recognize distinct overlapping and clustered nuclei. To overcome these problems, we present an innovative method based on gradient-weighted class activation mapping (Grad-CAM) saliency maps for image segmentation. The proposed solution is comprised of two steps. The first is the semantic segmentation obtained by the use of a CNN; then, the detection step is based on the calculation of local maxima of the Grad-CAM analysis evaluated on the nucleus class, allowing us to determine the positions of the nuclei centroids. This approach, which we denote as NDG-CAM, has performance in line with state-of-the-art methods, especially in isolating the different nuclei instances, and can be generalized for different organs and tissues. Experimental results demonstrated a precision of 0.833, recall of 0.815 and a Dice coefficient of 0.824 on the publicly available validation set. When used in combined mode with instance segmentation architectures such as Mask R-CNN, the method manages to surpass state-of-the-art approaches, with precision of 0.838, recall of 0.934 and a Dice coefficient of 0.884. Furthermore, performance on the external, locally collected validation set, with a Dice coefficient of 0.914 for the combined model, shows the generalization capability of the implemented pipeline, which has the ability to detect nuclei not only related to tumor or normal epithelium but also to other cytotypes. [ABSTRACT FROM AUTHOR]

In prostate cancer, fusion biopsy, which couples magnetic resonance imaging (MRI) with transrectal ultrasound (TRUS), poses the basis for targeted biopsy by allowing the comparison of information coming from both imaging modalities at the same time. Compared with the standard clinical procedure, it provides a less invasive option for the patients and increases the likelihood of sampling cancerous tissue regions for the subsequent pathology analyses. As a prerequisite to image fusion, segmentation must be achieved from both MRI and TRUS domains. The automatic contour delineation of the prostate gland from TRUS images is a challenging task due to several factors including unclear boundaries, speckle noise, and the variety of prostate anatomical shapes. Automatic methodologies, such as those based on deep learning, require a huge quantity of training data to achieve satisfactory results. In this paper, the authors propose a novel optimization formulation to find the best superellipse, a deformable model that can accurately represent the prostate shape. The advantage of the proposed approach is that it does not require extensive annotations, and can be used independently of the specific transducer employed during prostate biopsies. Moreover, in order to show the clinical applicability of the method, this study also presents a module for the automatic segmentation of the prostate gland from MRI, exploiting the nnU-Net framework. Lastly, segmented contours from both imaging domains are fused with a customized registration algorithm in order to create a tool that can help the physician to perform a targeted prostate biopsy by interacting with the graphical user interface. [ABSTRACT FROM AUTHOR]

The non-destructive testing methods offer great benefit in detecting and classifying the weld defects. Among these, infrared (IR) thermography stands out in the inspection, characterization, and analysis of the defects from the camera image sequences, particularly with the recent advent of deep learning. However, in IR, the defect classification becomes a cumbersome task because of the exposure to the inconsistent and unbalanced heat source, which requires additional supervision. In light of this, authors present a fully automated system capable of detecting defective welds according to the electrical resistance properties in the inline mode. The welding process is captured by an IR camera that generates a video sequence. A set of features extracted by such video feeds supervised machine learning and deep learning algorithms in order to build an industrial diagnostic framework for weld defect detection. The experimental study validates the aptitude of a customized convolutional neural network architecture to classify the malfunctioning weld joints with mean accuracy of 99% and median f1 score of 73% across five-fold cross validation on our locally acquired real world dataset. The outcome encourages the integration of thermographic-based quality control frameworks in all applications where fast and accurate recognition and safety assurance are crucial industrial requirements across the production line. [ABSTRACT FROM AUTHOR]

Computer-aided diagnosis (CAD) systems can help radiologists in numerous medical tasks including classification and staging of the various diseases. The 3D tomosynthesis imaging technique adds value to the CAD systems in diagnosis and classification of the breast lesions. Several convolutional neural network (CNN) architectures have been proposed to classify the lesion shapes to the respective classes using a similar imaging method. However, not only is the black box nature of these CNN models questionable in the healthcare domain, but so is the morphological-based cancer classification, concerning the clinicians. As a result, this study proposes both a mathematically and visually explainable deep-learning-driven multiclass shape-based classification framework for the tomosynthesis breast lesion images. In this study, authors exploit eight pretrained CNN architectures for the classification task on the previously extracted regions of interests images containing the lesions. Additionally, the study also unleashes the black box nature of the deep learning models using two well-known perceptive explainable artificial intelligence (XAI) algorithms including Grad-CAM and LIME. Moreover, two mathematical-structure-based interpretability techniques, i.e., t-SNE and UMAP, are employed to investigate the pretrained models' behavior towards multiclass feature clustering. The experimental results of the classification task validate the applicability of the proposed framework by yielding the mean area under the curve of 98.2%. The explanability study validates the applicability of all employed methods, mainly emphasizing the pros and cons of both Grad-CAM and LIME methods that can provide useful insights towards explainable CAD systems. [ABSTRACT FROM AUTHOR]

Smart industrial workstations for the training and evaluation of workers are an innovative approach to face the problems of manufacturing quality assessment and fast training. However, such products do not implement algorithms that are able to accurately track the pose of a hand tool that might also be partially occluded by the operator's hands. In the best case, the already proposed systems roughly track the position of the operator's hand center assuming that a certain task has been performed if the hand center position is close enough to a specified area. The problem of the pose estimation of 3D objects, including the hand tool, is an open and debated problem. The methods that lead to high accuracies are time consuming and require a 3D model of the object to detect, which is why they cannot be adopted for a real-time training system. The rise in deep learning has stimulated the search for better-performing vision-based solutions. Nevertheless, the problem of hand tool pose estimation for assembly and training procedures appears to not have been extensively investigated. In this study, four different vision-based methods based, respectively, on ArUco markers, OpenPose, Azure Kinect Body Tracking and the YOLO network have been proposed in order to estimate the position of a specific point of interest of the tool that has to be tracked in real-time during an assembly or maintenance procedure. The proposed approaches have been tested on a real scenario with four users handling a power drill simulating three different conditions during an assembly procedure. The performance of the methods has been evaluated and compared with the HTC Vive tracking system as a benchmark. Then, the advantages and drawbacks in terms of the accuracy and invasiveness of the method have been discussed. The authors can state that OpenPose is the most robust proposal arising from the study. The authors will investigate the OpenPose performance in more depth in further studies. The framework appears to be very interesting regarding its integration into a smart workstation for quality assessment and training. [ABSTRACT FROM AUTHOR]

Pedestrian detection and tracking have become an important field in the computer vision research area. This growing interest, started in the last decades, might be explained by the multitude of potential applications that could use the results of this research field, e.g. robotics, entertainment, surveillance, care for the elderly and disabled, and content-based indexing. In this survey paper, vision-based pedestrian detection systems are analysed based on their field of application, acquisition technology, computer vision techniques and classification strategies. Three main application fields have been individuated and discussed: video surveillance, human-machine interaction and analysis. Due to the large variety of acquisition technologies, this paper discusses both the differences between 2D and 3D vision systems, and indoor and outdoor systems. The authors reserved a dedicated section for the analysis of the Deep Learning methodologies, including the Convolutional Neural Networks in pedestrian detection and tracking, considering their recent exploding adoption for such a kind systems. Finally, focusing on the classification point of view, different Machine Learning techniques have been analysed, basing the discussion on the classification performances on different benchmark datasets. The reported results highlight the importance of testing pedestrian detection systems on different datasets to evaluate the robustness of the computed groups of features used as input to classifiers. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic is inevitably changing the world in a dramatic way, and the role of computed tomography (CT) scans can be pivotal for the prognosis of COVID-19 patients. Since the start of the pandemic, great care has been given to the relationship between interstitial pneumonia caused by the infection and the onset of thromboembolic phenomena. In this preliminary study, we collected n = 20 CT scans from the Polyclinic of Bari, all from patients positive with COVID-19, nine of which developed pulmonary thromboembolism (PTE). For eight CT scans, we obtained masks of the lesions caused by the infection, annotated by expert radiologists; whereas for the other four CT scans, we obtained masks of the lungs (including both healthy parenchyma and lesions). We developed a deep learning-based segmentation model that utilizes convolutional neural networks (CNNs) in order to accurately segment the lung and lesions. By considering the images from publicly available datasets, we also realized a training set composed of 32 CT scans and a validation set of 10 CT scans. The results obtained from the segmentation task are promising, allowing to reach a Dice coefficient higher than 97%, posing the basis for analysis concerning the assessment of PTE onset. We characterized the segmented region in order to individuate radiomic features that can be useful for the prognosis of PTE. Out of 919 extracted radiomic features, we found that 109 present different distributions according to the Mann–Whitney U test with corrected p-values less than 0.01. Lastly, nine uncorrelated features were retained that can be exploited to realize a prognostic signature. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Cytological study of the nasal mucosa (also known as rhino-cytology) represents an important diagnostic aid that allows highlighting of the presence of some types of rhinitis through the analysis of cellular features visible under a microscope. Nowadays, the automated detection and classification of cells benefit from the capacity of deep learning techniques in processing digital images of the cytological preparation. Even though the results of such automatic systems need to be validated by a specialized rhino-cytologist, this technology represents a valid support that aims at increasing the accuracy of the analysis while reducing the required time and effort. The quality of the rhino-cytological preparation, which is clearly important for the microscope observation phase, is also fundamental for the automatic classification process. In fact, the slide-preparing technique turns out to be a crucial factor among the multiple ones that may modify the morphological and chromatic characteristics of the cells. This paper aims to investigate the possible differences between direct smear (SM) and cytological centrifugation (CYT) slide-preparation techniques, in order to preserve image quality during the observation and cell classification phases in rhino-cytology. Firstly, a comparative study based on image analysis techniques has been put forward. The extraction of densitometric and morphometric features has made it possible to quantify and describe the spatial distribution of the cells in the field images observed under the microscope. Statistical analysis of the distribution of these features has been used to evaluate the degree of similarity between images acquired from SM and CYT slides. The results prove an important difference in the observation process of the cells prepared with the above-mentioned techniques, with reference to cell density and spatial distribution: the analysis of CYT slides has been more difficult than of the SM ones due to the spatial distribution of the cells, which results in a lower cell density than the SM slides. As a marginal part of this study, a performance assessment of the computer-aided diagnosis (CAD) system called Rhino-cyt has also been carried out on both groups of image slide types. [ABSTRACT FROM AUTHOR]

Deep Learning approaches for automatic segmentation of organs from CT scans and MRI are providing promising results, leading towards a revolution in the radiologists' workflow. Precise delineations of abdominal organs boundaries reveal fundamental for a variety of purposes: surgical planning, volumetric estimation (e.g. Total Kidney Volume – TKV – assessment in Autosomal Dominant Polycystic Kidney Disease – ADPKD), diagnosis and monitoring of pathologies. Fundamental imaging techniques exploited for these tasks are Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), which enable clinicians to perform 3D analyses of all Regions of Interests (ROIs). In the realm of existing methods for segmentation and classification of these zones, Convolutional Neural Networks (CNNs) are emerging as the reference approach. In the last five years an enormous research effort has been done about the possibility of applying CNNs in Medical Imaging, resulting in more than 8000 documents on Scopus and more than 80000 results on Google Scholar. The high accuracy provided by those systems cannot be denied as motivation of all obtained results, though there are still problems to be addressed with. In this survey, major article databases, as Scopus, for instance, were systematically investigated for different kinds of Deep Learning approaches in segmentation of abdominal organs with a particular focus on liver, kidney and spleen. In this work, approaches are accurately classified, both by relevance of each organ (for instance, segmentation of liver has specific properties, if compared to other organs) and by type of computational approach, as well as the architecture of the employed network. For this purpose, a case study of segmentation for each of these organs is presented. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) has been recently employed to build smart systems that perform incredibly well in a wide range of tasks, such as image recognition, machine translation, and self-driving cars. In several fields the considerable improvement in the computing hardware and the increasing need for big data analytics has boosted DL work. In recent years physiological signal processing has strongly benefited from deep learning. In general, there is an exponential increase in the number of studies concerning the processing of electromyographic (EMG) signals using DL methods. This phenomenon is mostly explained by the current limitation of myoelectric controlled prostheses as well as the recent release of large EMG recording datasets, e.g. Ninapro. Such a growing trend has inspired us to seek and review recent papers focusing on processing EMG signals using DL methods. Referring to the Scopus database, a systematic literature search of papers published between January 2014 and March 2019 was carried out, and sixty-five papers were chosen for review after a full text analysis. The bibliometric research revealed that the reviewed papers can be grouped in four main categories according to the final application of the EMG signal analysis: Hand Gesture Classification, Speech and Emotion Classification, Sleep Stage Classification and Other Applications. The review process also confirmed the increasing trend in terms of published papers, the number of papers published in 2018 is indeed four times the amount of papers published the year before. As expected, most of the analyzed papers (≈ 60 %) concern the identification of hand gestures, thus supporting our hypothesis. Finally, it is worth reporting that the convolutional neural network (CNN) is the most used topology among the several involved DL architectures, in fact, the sixty percent approximately of the reviewed articles consider a CNN. [ABSTRACT FROM AUTHOR]