•We show how deep learning can be applied for COVID-19 detection from chest X-rays;•The proposed method is aimed to mark as first step a chest X-ray as related to a healthy patient or to a patient ...with pulmonary diseases, the second step is aimed to discriminate between generic pulmonary disease and COVID-19. The last step is aimed to detect the interesting area in the chest X-ray (to provide explainability);•We propose an explainable method aimed to automatically detect the areas of interest in the chest X-ray, symptomatic of the COVID-19 disease.•We obtain an accuracy of 0.99 in COVID-19 detection by evaluating 6,113 chest x-rays, with a time window required for the detection approximately equal to 2.5 seconds.
Background and Objective: Coronavirus disease (COVID-19) is an infectious disease caused by a new virus never identified before in humans. This virus causes respiratory disease (for instance, flu) with symptoms such as cough, fever and, in severe cases, pneumonia. The test to detect the presence of this virus in humans is performed on sputum or blood samples and the outcome is generally available within a few hours or, at most, days. Analysing biomedical imaging the patient shows signs of pneumonia. In this paper, with the aim of providing a fully automatic and faster diagnosis, we propose the adoption of deep learning for COVID-19 detection from X-rays.
Method: In particular, we propose an approach composed by three phases: the first one to detect if in a chest X-ray there is the presence of a pneumonia. The second one to discern between COVID-19 and pneumonia. The last step is aimed to localise the areas in the X-ray symptomatic of the COVID-19 presence.
Results and Conclusion: Experimental analysis on 6,523 chest X-rays belonging to different institutions demonstrated the effectiveness of the proposed approach, with an average time for COVID-19 detection of approximately 2.5 seconds and an average accuracy equal to 0.97.
Aim
Prostate cancer represents the most common cancer afflicting men. It may be asymptomatic at the early stage. In this paper, we propose a methodology aimed to detect the prostate cancer grade by ...computing non-invasive shape-based radiomic features directly from magnetic resonance images.
Materials and methods
We use a freely available dataset composed by coronal magnetic resonance images belonging to 112 patients. We represent magnetic resonance slices in terms of formal model, and we exploit model checking to check whether a set of properties (formulated with the support of pathologists and radiologists) is verified on the formal model. Each property is related to a different cancer grade with the aim to cover all the cancer grade groups.
Results
An average specificity equal to 0.97 and an average sensitivity equal to 1 have been obtained with our methodology.
Conclusion
The experimental analysis demonstrates the effectiveness of radiomics and formal verification for Gleason grade group detection from magnetic resonance.
Prostate cancer is classified into different stages, each stage is related to a different Gleason score. The labeling of a diagnosed prostate cancer is a task usually performed by radiologists. In ...this paper we propose a deep architecture, based on several convolutional layers, aimed to automatically assign the Gleason score to Magnetic Resonance Imaging (MRI) under analysis. We exploit a set of 71 radiomic features belonging to five categories: First Order, Shape, Gray Level Co-occurrence Matrix, Gray Level Run Length Matrix and Gray Level Size Zone Matrix. The radiomic features are gathered directly from segmented MRIs using two free-available dataset for research purpose obtained from different institutions. The results, obtained in terms of accuracy, are promising: they are ranging between 0.96 and 0.98 for Gleason score prediction.
Prostate cancer is a significant public health burden and a major cause of morbidity and mortality among men worldwide. Only in 2018 were reported 1.3 million of new diagnosed patients. Usually an ...invasive trans-perineal biopsy is the way to diagnose prostate cancer grade by prostate tissue removal. In this paper we propose a non invasive method to detect the prostate cancer grade (the so-called Gleason score) by computing radiomic biomarkers from magnetic resonance images. Furthermore, the proposed method predicts whether the cancer is suitable for the surgery treatment basing on the pathologist and surgeon suggestions. We represent patient magnetic resonances in terms of formal models and, through an algorithm designed by authors, we infer a set of properties aimed to predict the Gleason score and the treatment. By exploiting a formal verification environment, the properties are verified on two different real-world data-sets, the first one is composed of 36 patients, while the second one of 26, confirming the effectiveness of the proposed method.
Introduction and objectives
The Prostate Imaging Reporting and Data System (PI-RADS) version 2 emerged as standard in prostate magnetic resonance imaging examination. The Pi-RADS scores are assigned ...by radiologists and indicate the likelihood of a clinically significant cancer. The aim of this paper is to propose a methodology to automatically mark a magnetic resonance imaging with its related PI-RADS.
Materials and methods
We collected a dataset from two different institutions composed by DWI ADC MRI for 91 patients marked by expert radiologists with different PI-RADS score. A formal model is generated starting from a prostate magnetic resonance imaging, and a set of properties related to the different PI-RADS scores are formulated with the help of expert radiologists and pathologists.
Results
Our methodology relies on the adoption of formal methods and radiomic features, and in the experimental analysis, we obtain a specificity and sensitivity equal to 1.Q
Conclusions
The proposed methodology is able to assign the PI-RADS score by analyzing prostate magnetic resonance imaging with a very high accuracy.
Neuroendocrine neoplasms (NENs) are heterogeneous tumours with a common phenotype descended from the diffuse endocrine system. NENs are found nearly anywhere in the body but the most frequent ...location is the gastrointestinal tract. Gastrointestinal neuroendocrine neoplasms (GI-NENs) are rather uncommon, representing around 2% of all gastrointestinal tumours and 20–30% of all primary neoplasms of the small bowel. GI-NENs have various clinical manifestations due to the different substances they can produce; some of these tumours appear to be associated with familial syndromes, such as multiple endocrine neoplasm and neurofibromatosis type 1. The current WHO classification (2019) divides NENs into three major categories: well-differentiated NENs, poorly differentiated NENs, and mixed neuroendocrine-non-neuroendocrine neoplasms. The diagnosis, localization, and staging of GI-NENs include morphology and functional imaging, above all contrast-enhanced computed tomography (CECT), and in the field of nuclear medicine imaging, a key role is played by
68
Ga-labelled-somatostatin analogues (
68
Ga-DOTA-peptides) positron emission tomography/computed tomography (PET/TC). In this review of recent literature, we described the objectives of morphological/functional imaging and potential future possibilities of prognostic imaging in the assessment of GI-NENs.
The coronavirus is caused by the infection of the SARS-CoV-2 virus: it represents a complex and new condition, considering that until the end of December 2019 this virus was totally unknown to the ...international scientific community. The clinical management of patients with the coronavirus disease has undergone an evolution over the months, thanks to the increasing knowledge of the virus, symptoms and efficacy of the various therapies. Currently, however, there is no specific therapy for SARS-CoV-2 virus, know also as Coronavirus disease 19, and treatment is based on the symptoms of the patient taking into account the overall clinical picture. Furthermore, the test to identify whether a patient is affected by the virus is generally performed on sputum and the result is generally available within a few hours or days. Researches previously found that the biomedical imaging analysis is able to show signs of pneumonia. For this reason in this paper, with the aim of providing a fully automatic and faster diagnosis, we design and implement a method adopting deep learning for the novel coronavirus disease detection, starting from computed tomography medical images. The proposed approach is aimed to detect whether a computed tomography medical images is related to an healthy patient, to a patient with a pulmonary disease or to a patient affected with Coronavirus disease 19. In case the patient is marked by the proposed method as affected by the Coronavirus disease 19, the areas symptomatic of the Coronavirus disease 19 infection are automatically highlighted in the computed tomography medical images. We perform an experimental analysis to empirically demonstrate the effectiveness of the proposed approach, by considering medical images belonging from different institutions, with an average time for Coronavirus disease 19 detection of approximately 8.9 s and an accuracy equal to 0.95.
Brain cancer is widely recognised as one of the most aggressive types of tumors. In fact, approximately 70% of patients diagnosed with this malignant cancer do not survive. In this paper, we propose ...a method aimed to detect and localise brain cancer, starting from the analysis of magnetic resonance images. The proposed method exploits deep learning, in particular convolutional neural networks and class activation mapping, in order to provide explainability by highlighting the areas of the medical image related to brain cancer (from the model point of view). We evaluate the proposed method with 3000 magnetic resonances using a free available dataset. The results we obtained are encouraging. We reach an accuracy ranging from 97.83% to 99.67% in brain cancer detection by exploiting four different models: VGG16, ResNet50, Alex_Net, and MobileNet, thus showing the effectiveness of the proposed method.
: To assess the association of RAS mutation status and radiomics-derived data by Contrast Enhanced-Magnetic Resonance Imaging (CE-MRI) in liver metastases.
: 76 patients (36 women and 40 men; 59 ...years of mean age and 36-80 years as range) were included in this retrospective study. Texture metrics and parameters based on lesion morphology were calculated. Per-patient univariate and multivariate analysis were made. Wilcoxon-Mann-Whitney U test, receiver operating characteristic (ROC) analysis, pattern recognition approaches with features selection approaches were considered.
: Significant results were obtained for texture features while morphological parameters had not significant results to classify RAS mutation. The results showed that using a univariate analysis was not possible to discriminate accurately the RAS mutation status. Instead, considering a multivariate analysis and classification approaches, a KNN exclusively with texture parameters as predictors reached the best results (AUC of 0.84 and an accuracy of 76.9% with 90.0% of sensitivity and 67.8% of specificity on training set and an accuracy of 87.5% with 91.7% of sensitivity and 83.3% of specificity on external validation cohort).
: Texture parameters derived by CE-MRI and combined using multivariate analysis and patter recognition approaches could allow stratifying the patients according to RAS mutation status.
Ultrasound is the most disruptive innovation in intensive care life, above all in this time, with a high diagnostic value when applied appropriately. In recent years, point-of-care lung ultrasound ...has gained significant popularity as a diagnostic tool in the acutely dyspnoeic patients. In the era of Sars-CoV-2 outbreak, lung ultrasound seems to be strongly adapting to the follow-up for lung involvement of patients with ascertaining infections, till to be used, in our opinion emblematically, as a screening test in suspected patients at the emergency triage or at home medical visit. In this brief review, we discuss the lung ultrasound dichotomy, certainties and uncertainties, describing its potential role in validated clinical contexts, as a clinical-dependent exam, its limits and pitfalls in a generic and off-label clinical context, as a virtual anatomical-dependent exam, and its effects on the clinical management of patients with COVID-19.