Artificial intelligence applications in medical imaging: A review of the medical physics research in Italy

PurposeTo perform a systematic review on the research on the application of artificial intelligence (AI) to imaging published in Italy and identify its fields of application, methods and results.Materials and MethodsA Pubmed search was conducted using terms Artificial Intelligence, Machine Learning, Deep learning, imaging, and Italy as affiliation, excluding reviews and papers outside time interval 2015–2020. In a second phase, participants of the working group AI4MP on Artificial Intelligence of the Italian Association of Physics in Medicine (AIFM) searched for papers on AI in imaging.ResultsThe Pubmed search produced 794 results. 168 studies were selected, of which 122 were from Pubmed search and 46 from the working group. The most used imaging modality was MRI (44%) followed by CT(12%) ad radiography/mammography (11%). The most common clinical indication were neurological diseases (29%) and diagnosis of cancer (25%). Classification was the most common task for AI (57%) followed by segmentation (16%). 65% of studies used machine learning and 35% used deep learning. We observed a rapid increase of research in Italy on artificial intelligence in the last 5 years, peaking at 155% from 2018 to 2019.ConclusionsWe are witnessing an unprecedented interest in AI applied to imaging in Italy, in a diversity of fields and imaging techniques. Further initiatives are needed to build common frameworks and databases, collaborations among different types of institutions, and guidelines for research on AI.     

Artificial intelligence in the diagnosis of COVID-19: challenges and perspectives

Artificial intelligence (AI) is being used to aid in various aspects of the COVID-19 crisis, including epidemiology, molecular research and drug development, medical diagnosis and treatment, and socioeconomics. The association of AI and COVID-19 can accelerate to rapidly diagnose positive patients. To learn the dynamics of a pandemic with relevance to AI, we search the literature using the different academic databases (PubMed, PubMed Central, Scopus, Google Scholar) and preprint servers (bioRxiv, medRxiv, arXiv). In the present review, we address the clinical applications of machine learning and deep learning, including clinical characteristics, electronic medical records, medical images (CT, X-ray, ultrasound images, etc.) in the COVID-19 diagnosis. The current challenges and future perspectives provided in this review can be used to direct an ideal deployment of AI technology in a pandemic.     

Deep learning representations to support COVID-19 diagnosis on CT slices

Introduction: The coronavirus disease 2019 (COVID-19) has become a significant public health problem worldwide. In this context, CT-scan automatic analysis has emerged as a COVID-19 complementary diagnosis tool allowing for radiological finding characterization, patient categorization, and disease follow-up. However, this analysis depends on the radiologist’s expertise, which may result in subjective evaluations.Objective: To explore deep learning representations, trained from thoracic CT-slices, to automatically distinguish COVID-19 disease from control samples.Materials and methods: Two datasets were used: SARS-CoV-2 CT Scan (Set-1) and FOSCAL clinic’s dataset (Set-2). The deep representations took advantage of supervised learning models previously trained on the natural image domain, which were adjusted following a transfer learning scheme. The deep classification was carried out: (a) via an end-to-end deep learning approach and (b) via random forest and support vector machine classifiers by feeding the deep representation embedding vectors into these classifiers.Results: The end-to-end classification achieved an average accuracy of 92.33% (89.70% precision) for Set-1 and 96.99% (96.62% precision) for Set-2. The deep feature embedding with a support vector machine achieved an average accuracy of 91.40% (95.77% precision) and 96.00% (94.74% precision) for Set-1 and Set-2, respectively.Conclusion: Deep representations have achieved outstanding performance in the identification of COVID-19 cases on CT scans demonstrating good characterization of the COVID-19 radiological patterns. These representations could potentially support the COVID-19 diagnosis in clinical settings.     

A Review on Convolutional Neural Networks for Brain Tumor Segmentation: Methods,Datasets, Libraries,and Future Directions

ObjectivesAccurate and reliable segmentation of brain tumors from MRI images helps in planning an enhanced treatment and increases the life expectancy of patients. However, the manual segmentation of brain tumors is subjective and more prone to errors. Nonetheless, the recent advances in convolutional neural network (CNN)-based methods have exhibited outstanding potential in robust segmentation of brain tumors. This article comprehensively investigates recent advances in CNN-based methods for automatic segmentation of brain tumors from MRI images. It examines popular deep learning (DL) libraries/tools for an expeditious and effortless implementation of CNN models. Furthermore, a critical assessment of current DL architectures is delineated along with the scope of improvement.MethodsIn this work, more than 50 scientific papers from 2014-2020 are selected using Google Scholar and PubMed. Also, the leading journals related to our work along with proceedings from major conferences such as MICCAI, MIUA and ECCV are retrieved. This research investigated various annual challenges too related to this work including Multimodal Brain Tumor Segmentation Challenge (MICCAI BRATS) and Ischemic Stroke Lesion Segmentation Challenge (ISLES).ResultAfter a systematic literature search pertinent to the theme, we found that principally there exist three variations of CNN architecture for brain tumor segmentation: single-path and multi-path, fully convolutional, and cascaded CNNs. The respective performances of most automated methods based on CNN are appraised on the BraTS dataset, provided as a part of the MICCAI Multimodal Brain Tumor Segmentation challenge held annually since 2012.ConclusionNotwithstanding the remarkable potential of CNN-based methods, reliable and robust segmentation of brain tumors continues to be an intractable challenge. This is due to the intricate anatomy of the brain, variability in its appearance, and imperfection in image acquisition. Moreover, owing to the small size of MRI datasets, CNN-based methods cannot operate with their full capacity, as demonstrated with large scale datasets, such as ImageNet.     

AI applications to medical images: From machine learning to deep learning

PurposeArtificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context.MethodsA narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections.ResultsWe first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way.ConclusionsBiomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.     

Heart rate variability as a marker of cardiovascular dysautonomia in post-COVID-19 syndrome using artificial intelligence

IntroductionCardiovascular dysautonomia comprising postural orthostatic tachycardia syndrome (POTS) and orthostatic hypotension (OH) is one of the presentations in COVID-19 recovered subjects. We aim to determine the prevalence of cardiovascular dysautonomia in post COVID-19 patients and to evaluate an Artificial Intelligence (AI) model to identify time domain heart rate variability (HRV) measures most suitable for short term ECG in these subjects.MethodsThis observational study enrolled 92 recently COVID-19 recovered subjects who underwent measurement of heart rate and blood pressure response to standing up from supine position and a 12-lead ECG recording for 60 s period during supine paced breathing. Using feature extraction, ECG features including those of HRV (RMSSD and SDNN) were obtained. An AI model was constructed with ShAP AI interpretability to determine time domain HRV features representing post COVID-19 recovered state. In addition, 120 healthy volunteers were enrolled as controls.ResultsCardiovascular dysautonomia was present in 15.21% (OH:13.04%; POTS:2.17%). Patients with OH had significantly lower HRV and higher inflammatory markers. HRV (RMSSD) was significantly lower in post COVID-19 patients compared to healthy controls (13.9 ± 11.8 ms vs 19.9 ± 19.5 ms; P = 0.01) with inverse correlation between HRV and inflammatory markers. Multiple perceptron was best performing AI model with HRV(RMSSD) being the top time domain HRV feature distinguishing between COVID-19 recovered patients and healthy controls.ConclusionPresent study showed that cardiovascular dysautonomia is common in COVID-19 recovered subjects with a significantly lower HRV compared to healthy controls. The AI model was able to distinguish between COVID-19 recovered patients and healthy controls.     

Advances in micro-CT imaging of small animals

PurposeMicron-scale computed tomography (micro-CT) imaging is a ubiquitous, cost-effective, and non-invasive three-dimensional imaging modality. We review recent developments and applications of micro-CT for preclinical research.MethodsBased on a comprehensive review of recent micro-CT literature, we summarize features of state-of-the-art hardware and ongoing challenges and promising research directions in the field.ResultsRepresentative features of commercially available micro-CT scanners and some new applications for both in vivo and ex vivo imaging are described. New advancements include spectral scanning using dual-energy micro-CT based on energy-integrating detectors or a new generation of photon-counting x-ray detectors (PCDs). Beyond two-material discrimination, PCDs enable quantitative differentiation of intrinsic tissues from one or more extrinsic contrast agents. When these extrinsic contrast agents are incorporated into a nanoparticle platform (e.g. liposomes), novel micro-CT imaging applications are possible such as combined therapy and diagnostic imaging in the field of cancer theranostics. Another major area of research in micro-CT is in x-ray phase contrast (XPC) imaging. XPC imaging opens CT to many new imaging applications because phase changes are more sensitive to density variations in soft tissues than standard absorption imaging. We further review the impact of deep learning on micro-CT. We feature several recent works which have successfully applied deep learning to micro-CT data, and we outline several challenges specific to micro-CT.ConclusionsAll of these advancements establish micro-CT imaging at the forefront of preclinical research, able to provide anatomical, functional, and even molecular information while serving as a testbench for translational research.     

Multi-input deep learning approach for Cardiovascular Disease diagnosis using Myocardial Perfusion Imaging and clinical data

PurposeAccurate detection and treatment of Coronary Artery Disease is mainly based on invasive Coronary Angiography, which could be avoided provided that a robust, non-invasive detection methodology emerged. Despite the progress of computational systems, this remains a challenging issue. The present research investigates Machine Learning and Deep Learning methods in competing with the medical experts' diagnostic yield. Although the highly accurate detection of Coronary Artery Disease, even from the experts, is presently implausible, developing Artificial Intelligence models to compete with the human eye and expertise is the first step towards a state-of-the-art Computer-Aided Diagnostic system.MethodsA set of 566 patient samples is analysed. The dataset contains Polar Maps derived from scintigraphic Myocardial Perfusion Imaging studies, clinical data, and Coronary Angiography results. The latter is considered as reference standard. For the classification of the medical images, the InceptionV3 Convolutional Neural Network is employed, while, for the categorical and continuous features, Neural Networks and Random Forest classifier are proposed.ResultsThe research suggests that an optimal strategy competing with the medical expert's accuracy involves a hybrid multi-input network composed of InceptionV3 and a Random Forest. This method matches the expert's accuracy, which is 79.15% in the particular dataset.ConclusionImage classification using deep learning methods can cooperate with clinical data classification methods to enhance the robustness of the predicting model, aiming to compete with the medical expert's ability to identify Coronary Artery Disease subjects, from a large scale patient dataset.     

Using federated data sources and Varian Learning Portal framework to train a neural network model for automatic organ segmentation

PurposeIn this study we trained a deep neural network model for female pelvis organ segmentation using data from several sites without any personal data sharing. The goal was to assess its prediction power compared with the model trained in a centralized manner.MethodsVarian Learning Portal (VLP) is a distributed machine learning (ML) infrastructure enabling privacy-preserving research across hospitals from different regions or countries, within the framework of a trusted consortium. Such a framework is relevant in the case when there is a high level of trust among the participating sites, but there are legal restrictions which do not allow the actual data sharing between them. We trained an organ segmentation model for the female pelvic region using the synchronous data distributed framework provided by the VLP.ResultsThe prediction performance of the model trained using the federated framework offered by VLP was on the same level as the performance of the model trained in a centralized manner where all training data was pulled together in one centre.ConclusionsVLP infrastructure can be used for GPU-based training of a deep neural network for organ segmentation for the female pelvic region. This organ segmentation instance is particularly difficult due to the high variation in the organs’ shape and size. Being able to train the model using data from several clinics can help, for instance, by exposing the model to a larger range of data variations. VLP framework enables such a distributed training approach without sharing protected health information.     

New Insights on Effects of Glucocorticoids in Patients With SARS-CoV-2 Infection

ObjectiveSince January 2020, the highly contagious novel coronavirus SARS-CoV-2 has caused a global pandemic. Severe COVID-19 leads to a massive release of proinflammatory mediators, leading to diffuse damage to the lung parenchyma, and the development of acute respiratory distress syndrome. Treatment with the highly potent glucocorticoid (GC) dexamethasone was found to be effective in reducing mortality in severely affected patients.MethodsTo review the effects of glucocorticoids in the context of COVID-19 we performed a literature search in the PubMed database using the terms COVID-19 and glucocorticoid treatment. We identified 1429 article publications related to COVID-19 and glucocorticoid published from 1.1.2020 to the present including 238 review articles and 36 Randomized Controlled Trials. From these studies, we retrieved 13 Randomized Controlled Trials and 86 review articles that were relevant to our review topics. We focused on the recent literature dealing with glucocorticoid metabolism in critically ill patients and investigating the effects of glucocorticoid therapy on the immune system in COVID-19 patients with severe lung injury.ResultsIn our review, we have discussed the regulation of the hypothalamic-pituitary-adrenal axis in patients with critical illness, selection of a specific GC for critical illness-related GC insufficiency, and recent studies that investigated hypothalamic-pituitary-adrenal dysfunction in patients with COVID-19. We have also addressed the specific activation of the immune system with chronic endogenous glucocorticoid excess, as seen in patients with Cushing syndrome, and, finally, we have discussed immune activation due to coronavirus infection and the possible mechanisms leading to improved outcomes in patients with COVID-19 treated with GCs.ConclusionFor clinical endocrinologists prescribing GCs for their patients, a precise understanding of both the molecular- and cellular-level mechanisms of endogenous and exogenous GCs is imperative, including timing of administration, dosage, duration of treatment, and specific formulations of GCs.     

Therapeutic options of TCM for organ injuries associated with COVID-19 and the underlying mechanism

BackgroundCoronavirus disease-2019 (COVID-19) caused by infection with severe acute respiratory coronavirus-2 (SARS-CoV-2) has been spreading rapidly throughout China and in other countries since the end of 2019. The World Health Organization (WHO) has declared that the epidemic is a public health emergency of international concerns. The timely and appropriate measures for treating COVID-19 in China, which are inseparable from the contribution of traditional Chinese medicine (TCM), have won much praise of the world.PurposeThis review aimed to summarize and discuss the essential role of TCM in protecting tissues from injuries associated with COVID-19, and accordingly to clarify the possible action mechanisms of TCM from the perspectives of anti-inflammatory, antioxidant and anti-apoptotic effects.MethodsElectronic databases such as Pubmed, ResearchGate, Science Direct, Web of Science, medRixv and Wiley were used to search scientific literatures.ResultsThe present review found that traditional Chinese herbs commonly used for the clinical treatment of organ damages caused by COVID-19, such as Scutellaria baicalensis, Salvia miltiorrhizaSalvia miltiorrhiza, and ginseng, could act on multiple signaling pathways involved in inflammation, oxidative stress and apoptosis.ConclusionTCM could protect COVID-19 patients from tissue injuries, a protection that might be, at least partially, attributed to the anti-inflammatory, antioxidant and anti-apoptotic effects of the TCM under investigation. This review provides evidence and support for clinical treatment and novel drug research using TCM.     

Artificial intelligence in the experimental determination and prediction of macromolecular structures

Machine learning methods, in particular convolutional neural networks, have been applied to a variety of problems in cryo-EM and macromolecular crystallographic structure solution. However, they still have only limited acceptance by the community, mainly in areas where they replace repetitive work and allow for easy visual checking, such as particle picking, crystal centering or crystal recognition. With Artificial Intelligence (AI) based protein fold prediction currently revolutionizing the field, it is clear that their scope could be much wider. However, whether we will be able to exploit this potential fully will depend on the manner in which we use machine learning: training data must be well-formulated, methods need to utilize appropriate architectures, and outputs must be critically assessed, which may even require explaining AI decisions.     

Big Data to Knowledge: Application of Machine Learning to Predictive Modeling of Therapeutic Response in Cancer

BackgroundIn recent years, the availability of high throughput technologies, establishment of large molecular patient data repositories, and advancement in computing power and storage have allowed elucidation of complex mechanisms implicated in therapeutic response in cancer patients. The breadth and depth of such data, alongside experimental noise and missing values, requires a sophisticated human-machine interaction that would allow effective learning from complex data and accurate forecasting of future outcomes, ideally embedded in the core of machine learning design.ObjectiveIn this review, we will discuss machine learning techniques utilized for modeling of treatment response in cancer, including Random Forests, support vector machines, neural networks, and linear and logistic regression. We will overview their mathematical foundations and discuss their limitations and alternative approaches in light of their application to therapeutic response modeling in cancer.ConclusionWe hypothesize that the increase in the number of patient profiles and potential temporal monitoring of patient data will define even more complex techniques, such as deep learning and causal analysis, as central players in therapeutic response modeling.     

Artificial intelligent system for multimedia services in smart home environments

Internet of Things (IoT) has introduced new applications and environments. Smart Home provides new ways of communication and service consumption. In addition, Artificial Intelligence (AI) and deep learning have improved different services and tasks by automatizing them. In this field, reinforcement learning (RL) provides an unsupervised way to learn from the environment. In this paper, a new intelligent system based on RL and deep learning is proposed for Smart Home environments to guarantee good levels of QoE, focused on multimedia services. This system is aimed to reduce the impact on user experience when the classifying system achieves a low accuracy. The experiments performed show that the deep learning model proposed achieves better accuracy than the KNN algorithm and that the RL system increases the QoE of the user up to 3.8 on a scale of 10.

     

Glucocorticoid-Induced Hyperglycemia Including Dexamethasone-Associated Hyperglycemia in COVID-19 Infection: A Systematic Review

ObjectiveOptimal glucocorticoid-induced hyperglycemia (GCIH) management is unclear. The COVID-19 pandemic has made this issue more prominent because dexamethasone became the standard of care in patients needing respiratory support. This systematic review aimed to describe the management of GCIH and summarize available management strategies for dexamethasone-associated hyperglycemia in patients with COVID-19.MethodsA systematic review was conducted using the PubMed/MEDLINE, Cochrane Library, Embase, and Web of Science databases with results from 2011 through January 2022. Keywords included synonyms for “steroid-induced diabetes” or “steroid-induced hyperglycemia.” Randomized controlled trials (RCTs) were included for review of GCIH management. All studies focusing on dexamethasone-associated hyperglycemia in COVID-19 were included regardless of study quality.ResultsInitial search for non-COVID GCIH identified 1230 references. After screening and review, 33 articles were included in the non-COVID section of this systematic review. Initial search for COVID-19–related management of dexamethasone-associated hyperglycemia in COVID-19 identified 63 references, whereas 7 of these were included in the COVID-19 section. RCTs of management strategies were scarce, did not use standard definitions for hyperglycemia, evaluated a variety of treatment strategies with varying primary end points, and were generally not found to be effective except for Neutral Protamine Hagedorn insulin added to basal-bolus regimens.ConclusionFew RCTs are available evaluating GCIH management. Further studies are needed to support the formulation of clinical guidelines for GCIH especially given the widespread use of dexamethasone during the COVID-19 pandemic.     

Traditional Chinese herbal medicine at the forefront battle against COVID-19: Clinical experience and scientific basis

BackgroundThroughout the 5000-year history of China, more than 300 epidemics were recorded. Traditional Chinese herbal medicine (TCM) has been used effectively to combat each of these epidemics’ infections, and saved many lives. To date, there are hundreds of herbal TCM formulae developed for the purpose of prevention and treatment during epidemic infections. When COVID-19 ravaged the Wuhan district in China in early January 2020, without a deep understanding about the nature of COVID-19, patients admitted to the TCM Hospital in Wuhan were immediately treated with TCM and reported later with >90% efficacy.ApproachWe conducted conduct a systematic survey of various TCM herbal preparations used in Wuhan and to review their efficacy, according to the published clinical data; and, secondly, to find the most popular herbs used in these preparations and look into the opportunity of future research in the isolation and identification of bioactive natural products for fighting COVID-19.ResultsAlthough bioactive natural products in these herbal preparations may have direct antiviral activities, TCM employed for fighting epidemic infections was primarily based on the TCM theory of restoring the balance of the human immune system, thereby defeating the viral infection indirectly. In addition, certain TCM teachings relevant to the meridian system deserve better attention. For instance, many TCM herbal preparations target the lung meridian, which connects the lung and large intestine. This interconnection between the lung, including the upper respiratory system, and the intestine, may explain why certain TCM formulae showed excellent relief of lung congestion and diarrhea, two characteristics of COVID-19 infection.ConclusionThere is good reason for us to learn from ancient wisdom and accumulated clinical experience, in combination with cutting edge science and technologies, to fight with the devastating COVID-19 pandemic now and emerging new coronaviruses in the future.     

Deep Transfer Learning Based Classification Model for COVID-19 Disease

The COVID-19 infection is increasing at a rapid rate, with the availability of limited number of testing kits. Therefore, the development of COVID-19 testing kits is still an open area of research. Recently, many studies have shown that chest Computed Tomography (CT) images can be used for COVID-19 testing, as chest CT images show a bilateral change in COVID-19 infected patients. However, the classification of COVID-19 patients from chest CT images is not an easy task as predicting the bilateral change is defined as an ill-posed problem. Therefore, in this paper, a deep transfer learning technique is used to classify COVID-19 infected patients. Additionally, a top-2 smooth loss function with cost-sensitive attributes is also utilized to handle noisy and imbalanced COVID-19 dataset kind of problems. Experimental results reveal that the proposed deep transfer learning-based COVID-19 classification model provides efficient results as compared to the other supervised learning models.     

Saliva-based point-of-care testing techniques for COVID-19 detection

Highlights
1. The advantages of COVID-19 detection in saliva were systematically introduced.
2. Saliva-based POCT technologies for the detection of COVID-19 were reviewed.
3. A positive correlation between COVID-19 antibodies in saliva and serum was demonstrated.     

Accumulating Impact of Smoking and Co-morbidities on Severity and Mortality of COVID-19 Infection: A Systematic Review and Meta-analysis

BackgroundHigh prevalence, severity, and formidable morbidity have marked the recent emergence of the novel coronavirus disease (COVID-19) pandemic. The significant association with the pre-existing co-morbid conditions has increased the disease burden of this global health emergency, pushing the patients, healthcare workers and facilities to the verge of complete disruption.MethodsMeta-analysis of pooled data was undertaken to assess the cumulative risk assessment of multiple co-morbid conditions associated with severe COVID-19. PubMed, Scopus, and Google Scholar were searched from January 1^st to June 27^th 2020 to generate a well-ordered, analytical, and critical review. The exercise began with keying in requisite keywords, followed by inclusion and exclusion criteria, data extraction, and quality evaluation. The final statistical meta-analysis of the risk factors of critical/severe and non-critical COVID-19 infection was carried out on Microsoft Excel (Ver. 2013), MedCalc (Ver.19.3), and RevMan software (Ver.5.3).ResultsWe investigated 19 eligible studies, comprising 12037 COVID-19 disease patients, representing the People’s Republic of China (PRC), USA, and Europe. 18.2% (n = 2200) of total patients had critical/severe COVID-19 disease. The pooled analysis showed a significant association of COVID-19 disease severity risk with cardiovascular disease (RR: 3.11, p < 0.001), followed by diabetes (RR: 2.06, p < 0.001), hypertension (RR: 1.54, p < 0.001), and smoking (RR: 1.52, p < 006).ConclusionThe review involved a sample size of 12037 COVID-19 patients across a wide geographical distribution. The reviewed reports have focussed on the association of individual risk assessment of co-morbid conditions with the heightened risk of COVID-19 disease. The present meta-analysis of cumulative risk assessment of co-morbidity from cardiovascular disease, diabetes, hypertension, and smoking signals a novel interpretation of inherent risk factors exacerbating COVID-19 disease severity. Consequently, there exists a definite window of opportunity for increasing survival of COVID-19 patients (with high risk and co-morbid conditions) by timely identification and implementation of appropriately suitable treatment modalities.