Search

Abstract An increasingly strong connection between artificial intelligence and medicine has enabled the development of predictive models capable of supporting physicians’ decision-making. Artificial intelligence encompasses much more than machine learning, which nevertheless is its most cited and used sub-branch in the last decade. Since most clinical problems can be modeled through machine learning classifiers, it is essential to discuss their main elements. This review aims to give primary educational insights on the most accessible and widely employed classifiers in radiology field, distinguishing between “shallow” learning (i.e., traditional machine learning) algorithms, including support vector machines, random forest and XGBoost, and “deep” learning architectures including convolutional neural networks and vision transformers. In addition, the paper outlines the key steps for classifiers training and highlights the differences between the most common algorithms and architectures. Although the choice of an algorithm depends on the task and dataset dealing with, general guidelines for classifier selection are proposed in relation to task analysis, dataset size, explainability requirements, and available computing resources. Considering the enormous interest in these innovative models and architectures, the problem of machine learning algorithms interpretability is finally discussed, providing a future perspective on trustworthy artificial intelligence. Relevance statement The growing synergy between artificial intelligence and medicine fosters predictive models aiding physicians. Machine learning classifiers, from shallow learning to deep learning, are offering crucial insights for the development of clinical decision support systems in healthcare. Explainability is a key feature of models that leads systems toward integration into clinical practice. Key points • Training a shallow classifier requires extracting disease-related features from region of interests (e.g., radiomics). • Deep classifiers implement automatic feature extraction and classification. • The classifier selection is based on data and computational resources availability, task, and explanation needs. Graphical Abstract

The SARS-CoV-2 virus pandemic had devastating effects on various aspects of life: clinical cases, ranging from mild to severe, can lead to lung failure and to death. Due to the high incidence, data-driven models can support physicians in patient management. The explainability and interpretability of machine-learning models are mandatory in clinical scenarios. In this work, clinical, laboratory and radiomic features were used to train machine-learning models for COVID-19 prognosis prediction. Using Explainable AI algorithms, a multi-level explainable method was proposed taking into account the developer and the involved stakeholder (physician, and patient) perspectives. A total of 1023 radiomic features were extracted from 1589 Chest X-Ray images (CXR), combined with 38 clinical/laboratory features. After the pre-processing and selection phases, 40 CXR radiomic features and 23 clinical/laboratory features were used to train Support Vector Machine and Random Forest classifiers exploring three feature selection strategies. The combination of both radiomic, and clinical/laboratory features enabled higher performance in the resulting models. The intelligibility of the used features allowed us to validate the models’ clinical findings. According to the medical literature, LDH, PaO2 and CRP were the most predictive laboratory features. Instead, ZoneEntropy and HighGrayLevelZoneEmphasis - indicative of the heterogeneity/uniformity of lung texture - were the most discriminating radiomic features. Our best predictive model, exploiting the Random Forest classifier and a signature composed of clinical, laboratory and radiomic features, achieved AUC=0.819, accuracy=0.733, specificity=0.705, and sensitivity=0.761 in the test set. The model, including a multi-level explainability, allows us to make strong clinical assumptions, confirmed by the literature insights.

Migraine is a burdensome neurological disorder that still lacks clear and easily accessible diagnostic biomarkers. Furthermore, a straightforward pathway is hard to find for migraineurs’ management, so the search for response predictors has become urgent. Nowadays, artificial intelligence (AI) has pervaded almost every aspect of our lives, and medicine has not been missed. Its applications are nearly limitless, and the ability to use machine learning approaches has given researchers a chance to give huge amounts of data new insights. When it comes to migraine, AI may play a fundamental role, helping clinicians and patients in many ways. For example, AI-based models can increase diagnostic accuracy, especially for non-headache specialists, and may help in correctly classifying the different groups of patients. Moreover, AI models analysing brain imaging studies reveal promising results in identifying disease biomarkers. Regarding migraine management, AI applications showed value in identifying outcome measures, the best treatment choices, and therapy response prediction. In the present review, the authors introduce the various and most recent clinical applications of AI regarding migraine.

Introduction: The aim of our study was to evaluate the feasibility of texture analysis of epicardial fat (EF) and thoracic subcutaneous fat (TSF) in patients undergoing cardiac CT (CCT). Materials and methods: We compared a consecutive population of 30 patients with BMI ≤25 kg/m2 (Group A, 60.6 ± 13.7 years) with a control population of 30 patients with BMI >25 kg/m2 (Group B, 63.3 ± 11 years). A dedicated computer application for quantification of EF and a texture analysis application for the study of EF and TSF were employed. Results: The volume of EF was higher in group B (mean 116.1 cm3 vs. 86.3 cm3, p = 0.014), despite no differences were found neither in terms of mean density (−69.5 ± 5 HU vs. −68 ± 5 HU, p = 0.28), nor in terms of quartiles distribution (Q1, p = 0.83; Q2, p = 0.22, Q3, p = 0.83, Q4, p = 0.34). The discriminating parameters of the histogram class were mean (p = 0.02), 0,1st (p = 0.001), 10th (p = 0.002), and 50th percentiles (p = 0.02). DifVarnc was the discriminating parameter of the co-occurrence matrix class (p = 0.007).The TSF thickness was 15 ± 6 mm in group A and 19.5 ± 5 mm in group B (p = 0.003). The TSF had a mean density of −97 ± 19 HU in group A and −95.8 ± 19 HU in group B (p = 0.75). The discriminating parameters of texture analysis were 10th (p = 0.03), 50th (p = 0.01), 90th percentiles (p = 0.04), S(0,1)SumAverg (p = 0.02), S(1,-1)SumOfSqs (p = 0.02), S(3,0)Contrast (p = 0.03), S(3,0)SumAverg (p = 0.02), S(4,0)SumAverg (p = 0.04), Horzl_RLNonUni (p = 0.02), and Vertl_LngREmph (p = 0.0005). Conclusions: Texture analysis provides distinctive radiomic parameters of EF and TSF. EF and TSF had different radiomic features as the BMI varies.

The epicardial adipose tissue (EAT) is the visceral fat located between the myocardium and the pericardium. We aimed to perform a longitudinal evaluation of the epicardial adipose tissue using an advanced computer-assisted approach in a population of patients undergoing Cardiac CT (CCT) during statin administration, in relation to their body mass index (BMI). We retrospectively enrolled 95 patients [mean age 62 ± 10 years; 68 males (72%) and 27 females (28%)] undergoing CCT for suspected coronary artery disease during statin administration. CCT was performed at two subsequent time points. At the second CCT, EAT showed a mean density increase (−75.59 ± 7.0 HU vs. −78.18 ± 5.3 HU, p < 0.001) and a volume decrease (130 ± 54.3 cm3 vs.142.79 ± 56.9 cm3, p < 0.001). Concerning coronary artery EAT thickness, a reduction was found at the origin of the right coronary artery (13.26 ± 5.2 mm vs. 14.94 ± 5.8, p = 0.001) and interventricular artery (8.22 ± 3.7 mm vs. 9.13 ± 3.9 mm, p = 0.001). The quartile (Q) attenuation percentage (%) distribution of EAT changed at the second CCT. The EAT % distribution changed by the BMI in Q1 (p = 0.015), Q3 (p = 0.001) and Q4 (p = 0.043) at the second CCT, but the normal-BMI and overweight/obese patients showed a similar response to statin therapy in terms of quartile distribution changes. In conclusion, statins may determine significant changes in EAT quantitative and qualitative characteristics detected by CCT; the BMI influences the EAT composition, but statins determine a similar response in quartile distribution’s variation, irrespective of the BMI.

Melanoma is a malignant cancer type which develops when DNA damage occurs (mainly due to environmental factors such as ultraviolet rays). Often, melanoma results in intense and aggressive cell growth that, if not caught in time, can bring one toward death. Thus, early identification at the initial stage is fundamental to stopping the spread of cancer. In this paper, a ViT-based architecture able to classify melanoma versus non-cancerous lesions is presented. The proposed predictive model is trained and tested on public skin cancer data from the ISIC challenge, and the obtained results are highly promising. Different classifier configurations are considered and analyzed in order to find the most discriminating one. The best one reached an accuracy of 0.948, sensitivity of 0.928, specificity of 0.967, and AUROC of 0.948.

Background: Hereditary transthyretin amyloidosis with polyneuropathy (ATTRv) is an adult-onset multisystemic disease, affecting the peripheral nerves, heart, gastrointestinal tract, eyes, and kidneys. Nowadays, several treatment options are available; thus, avoiding misdiagnosis is crucial to starting therapy in early disease stages. However, clinical diagnosis may be difficult, as the disease may present with unspecific symptoms and signs. We hypothesize that the diagnostic process may benefit from the use of machine learning (ML). Methods: 397 patients referring to neuromuscular clinics in 4 centers from the south of Italy with neuropathy and at least 1 more red flag, as well as undergoing genetic testing for ATTRv, were considered. Then, only probands were considered for analysis. Hence, a cohort of 184 patients, 93 with positive and 91 (age- and sex-matched) with negative genetics, was considered for the classification task. The XGBoost (XGB) algorithm was trained to classify positive and negative TTR mutation patients. The SHAP method was used as an explainable artificial intelligence algorithm to interpret the model findings. Results: diabetes, gender, unexplained weight loss, cardiomyopathy, bilateral carpal tunnel syndrome (CTS), ocular symptoms, autonomic symptoms, ataxia, renal dysfunction, lumbar canal stenosis, and history of autoimmunity were used for the model training. The XGB model showed an accuracy of 0.707 ± 0.101, a sensitivity of 0.712 ± 0.147, a specificity of 0.704 ± 0.150, and an AUC-ROC of 0.752 ± 0.107. Using the SHAP explanation, it was confirmed that unexplained weight loss, gastrointestinal symptoms, and cardiomyopathy showed a significant association with the genetic diagnosis of ATTRv, while bilateral CTS, diabetes, autoimmunity, and ocular and renal involvement were associated with a negative genetic test. Conclusions: Our data show that ML might potentially be a useful instrument to identify patients with neuropathy that should undergo genetic testing for ATTRv. Unexplained weight loss and cardiomyopathy are relevant red flags in ATTRv in the south of Italy. Further studies are needed to confirm these findings.

Abstract The recent developments of information technologies, and the consequent need for access to distributed services and resources, require robust and reliable authentication systems. Biometric systems can guarantee high levels of security and multimodal techniques, which combine two or more biometric traits, warranting constraints that are more stringent during the access phases. This work proposes a novel multimodal biometric system based on iris and retina combination in the spatial domain. The proposed solution follows the alignment and recognition approach commonly adopted in computational linguistics and bioinformatics; in particular, features are extracted separately for iris and retina, and the fusion is obtained relying upon the comparison score via the Levenshtein distance. We evaluated our approach by testing several combinations of publicly available biometric databases, namely one for retina images and three for iris images. To provide comprehensive results, detection error trade‐off‐based metrics, as well as statistical analyses for assessing the authentication performance, were considered. The best achieved False Acceptation Rate and False Rejection Rate indices were and 3.33%, respectively, for the multimodal retina‐iris biometric approach that overall outperformed the unimodal systems. These results draw the potential of the proposed approach as a multimodal authentication framework using multiple static biometric traits.

Background: Deep learning methods have become popular for their high-performance rate in the classification and detection of events in computer vision tasks. Transfer learning paradigm is widely adopted to apply pretrained convolutional neural network (CNN) on medical domains overcoming the problem of the scarcity of public datasets. Some investigations to assess transfer learning knowledge inference abilities in the context of mammogram screening and possible combinations with unsupervised techniques are in progress. Methods: We propose a novel technique for the detection of suspicious regions in mammograms that consist of the combination of two approaches based on scale invariant feature transform (SIFT) keypoints and transfer learning with pretrained CNNs such as PyramidNet and AlexNet fine-tuned on digital mammograms generated by different mammography devices. Preprocessing, feature extraction, and selection steps characterize the SIFT-based method, while the deep learning network validates the candidate suspicious regions detected by the SIFT method. Results: The experiments conducted on both mini-MIAS dataset and our new public dataset Suspicious Region Detection on Mammogram from PP (SuReMaPP) of 384 digital mammograms exhibit high performances compared to several state-of-the-art methods. Our solution reaches 98% of sensitivity and 90% of specificity on SuReMaPP and 94% of sensitivity and 91% of specificity on mini-MIAS. Conclusions: The experimental sessions conducted so far prompt us to further investigate the powerfulness of transfer learning over different CNNs and possible combinations with unsupervised techniques. Transfer learning performances' accuracy may decrease when the training and testing images come out from mammography devices with different properties.

Radiomic analysis allows for the detection of imaging biomarkers supporting decision-making processes in clinical environments, from diagnosis to prognosis. Frequently, the original set of radiomic features is augmented by considering high-level features, such as wavelet transforms. However, several wavelets families (so called kernels) are able to generate different multi-resolution representations of the original image, and which of them produces more salient images is not yet clear. In this study, an in-depth analysis is performed by comparing different wavelet kernels and by evaluating their impact on predictive capabilities of radiomic models. A dataset composed of 1589 chest X-ray images was used for COVID-19 prognosis prediction as a case study. Random forest, support vector machine, and XGBoost were trained (on a subset of 1103 images) after a rigorous feature selection strategy to build-up the predictive models. Next, to evaluate the models generalization capability on unseen data, a test phase was performed (on a subset of 486 images). The experimental findings showed that Bior1.5, Coif1, Haar, and Sym2 kernels guarantee better and similar performance for all three machine learning models considered. Support vector machine and random forest showed comparable performance, and they were better than XGBoost. Additionally, random forest proved to be the most stable model, ensuring an appropriate balance between sensitivity and specificity.

Biometric classification plays a key role in fingerprint characterization, especially in the identification process. In fact, reducing the number of comparisons in biometric recognition systems is essential when dealing with large-scale databases. The classification of fingerprints aims to achieve this target by splitting fingerprints into different categories. The general approach of fingerprint classification requires pre-processing techniques that are usually computationally expensive. Deep Learning is emerging as the leading field that has been successfully applied to many areas, such as image processing. This work shows the performance of pre-trained Convolutional Neural Networks (CNNs), tested on two fingerprint databases—namely, PolyU and NIST—and comparisons to other results presented in the literature in order to establish the type of classification that allows us to obtain the best performance in terms of precision and model efficiency, among approaches under examination, namely: AlexNet, GoogLeNet, and ResNet. We present the first study that extensively compares the most used CNN architectures by classifying the fingerprints into four, five, and eight classes. From the experimental results, the best performance was obtained in the classification of the PolyU database by all the tested CNN architectures due to the higher quality of its samples. To confirm the reliability of our study and the results obtained, a statistical analysis based on the McNemar test was performed.

Structural and metabolic imaging are fundamental for diagnosis, treatment and follow-up in oncology. Beyond the well-established diagnostic imaging applications, ultrasounds are currently emerging in the clinical practice as a noninvasive technology for therapy. Indeed, the sound waves can be used to increase the temperature inside the target solid tumors, leading to apoptosis or necrosis of neoplastic tissues. The Magnetic resonance-guided focused ultrasound surgery (MRgFUS) technology represents a valid application of this ultrasound property, mainly used in oncology and neurology. In this paper; patient safety during MRgFUS treatments was investigated by a series of experiments in a tissue-mimicking phantom and performing ex vivo skin samples, to promptly identify unwanted temperature rises. The acquired MR images, used to evaluate the temperature in the treated areas, were analyzed to compare classical proton resonance frequency (PRF) shift techniques and referenceless thermometry methods to accurately assess the temperature variations. We exploited radial basis function (RBF) neural networks for referenceless thermometry and compared the results against interferometric optical fiber measurements. The experimental measurements were obtained using a set of interferometric optical fibers aimed at quantifying temperature variations directly in the sonication areas. The temperature increases during the treatment were not accurately detected by MRI-based referenceless thermometry methods, and more sensitive measurement systems, such as optical fibers, would be required. In-depth studies about these aspects are needed to monitor temperature and improve safety during MRgFUS treatments.

The embedded systems are increasingly becoming a key technological component of all kinds of complex technical systems and an exhaustive analysis of the state of the art of all current performance with respect to architectures, design methodologies, test and applications could be very interesting. The Advanced Encryption Standard (AES), based on the well-known algorithm Rijndael, is designed to be easily implemented in hardware and software platforms. General purpose computing on graphics processing unit (GPGPU) is an alternative to reconfigurable accelerators based on FPGA devices. This paper presents a direct comparison between FPGA and GPU used as accelerators for the AES cipher. The results achieved on both platforms and their analysis has been compared to several others in order to establish which device is best at playing the role of hardware accelerator by each solution showing interesting considerations in terms of throughput, speedup factor, and resource usage. This analysis suggests that, while hardware design on FPGA remains the natural choice for consumer-product design, GPUs are nowadays the preferable choice for PC based accelerators, especially when the processing routines are highly parallelizable.

Both computational performances and energy efficiency are required for the development of any mobile or embedded information processing system. The Internet of Things (IoT) is the latest evolution of these systems, paving the way for advancements in ubiquitous computing. In a context in which a large amount of data is often analyzed and processed, it is mandatory to adapt node logic and processing capabilities with respect to the available energy resources. This paper investigates under which conditions a partially reconfigurable hardware accelerator can provide energy saving in complex processing tasks. The paper also presents a useful analysis of how the dynamic partial reconfiguration technique can be used to enable energy efficiency in a generic IoT node that exploits a Field Programmable Gate Array (FPGA) device. Furthermore, this work introduces a hardware infrastructure and new energy metrics tailored for the energy efficiency evaluation of the dynamic partial reconfiguration process in embedded FPGA based devices. Exploiting the ability of reconfiguring circuit portions at runtime, the latest generation of FPGAs can be used to foster a better balance between energy consumption and performance. More specifically, the design methodology for the implemented digital signal processing application was adapted for the ZedBoard. To this aim, a case study of a video filtering system is proposed and analyzed by dynamically loading three different hardware filters from the management software running on a Linux-based device. With more details, the presented analytical framework allows for a direct comparison between the energy efficiency of a dynamic partially reconfigurable device and a static non-reconfigurable one. The estimated timing conditions that allow the dynamic partially reconfigurable process to achieve relevant energy efficiency with respect to the corresponding static architecture are also outlined.

Mobile devices are widely replacing the standard personal computers thanks to their small size and userfriendly use. As a consequence, the amount of information, often confidential, exchanged through these devices is raising. This makes them potential targets of malicious network hackers. The use of simple passwords or PIN are not sufficient to provide a suitable security level for those applications requiring high protection levels on data and services. In this paper a biometric authentication system, as a running Android application, has been developed and implemented on a real mobile device. A system test on real users has been also carried out in order to evaluate the human-machine interaction quality, the recognition accuracy of the proposed technique, and the scheduling latency of the operating system and its degree of acceptance. Several measures, such as system usability, users satisfaction, and tolerable speed for identification, have been carried out in order to evaluate the performance of the proposed approach.

Integrated Coastal Zone Management is an emerging research area. The aim is to provide a global view of different and heterogeneous aspects interacting in a geographical area. Decision Support Systems, integrating Computational Intelligence methods, can be successfully used to estimate useful anthropic and environmental indexes. Bayesian Networks have been widely used in the environmental science domain. In this paper a Bayesian model for estimating the Sustainable Coastal Index is presented. The designed Bayesian Network consists of 17 nodes, hierarchically organized in 4 layers. The first layer is initialized with the season and the physiographic region information. In the second layer, the first-order indexes, depending on raw data, of physiographic regions are computed. The third layer estimates the second-order indexes of the analyzed physiographic regions. In the fourth layer, the global Sustainable Coastal Index is inferred. Processed data refers to 13 physiographic regions in the Province of Trapani, western Sicily, Italy. Gathered data describes the environmental information, the agricultural, fisheries, and economical behaviors of the local population and land. The Bayesian Network was trained and tested using a real dataset acquired between 2000 and 2006. The developed system presents interesting results.