This paper introduces a novel method for flare forecasting, combining prediction accuracy with the ability to identify the most relevant predictive variables. This result is obtained by means of a ...two-step approach: first, a supervised regularization method for regression, namely, LASSO is applied, where a sparsity-enhancing penalty term allows the identification of the significance with which each data feature contributes to the prediction; then, an unsupervised fuzzy clustering technique for classification, namely, Fuzzy C-Means, is applied, where the regression outcome is partitioned through the minimization of a cost function and without focusing on the optimization of a specific skill score. This approach is therefore hybrid, since it combines supervised and unsupervised learning; realizes classification in an automatic, skill-score-independent way; and provides effective prediction performances even in the case of imbalanced data sets. Its prediction power is verified against NOAA Space Weather Prediction Center data, using as a test set, data in the range between 1996 August and 2010 December and as training set, data in the range between 1988 December and 1996 June. To validate the method, we computed several skill scores typically utilized in flare prediction and compared the values provided by the hybrid approach with the ones provided by several standard (non-hybrid) machine learning methods. The results showed that the hybrid approach performs classification better than all other supervised methods and with an effectiveness comparable to the one of clustering methods; but, in addition, it provides a reliable ranking of the weights with which the data properties contribute to the forecast.
Using a computational approach to extract the spinal canal from whole-body PET/CT images, Marini et al. reveal increased glucose consumption in the spinal cord in prospectively recruited patients ...with amyotrophic lateral sclerosis. Simultaneous measurement of brain 18F-Fluorodeoxyglucose uptake reveals a divergent metabolic response in the two structures.
Abstract
We recently reported the potential of Hough transform in delineating spinal cord metabolism by 18F-fluorodeoxyglucose PET/CT scanning in amyotrophic lateral sclerosis. The present study aimed to verify the relationship between spinal cord and brain metabolism in 44 prospectively recruited patients affected by amyotrophic lateral sclerosis submitted to 18F-fluorodeoxyglucose brain and whole-body PET/CT. Patients were studied to highlight the presence of brain hypo- or hypermetabolism with respect to healthy controls, and multiple regression analysis was performed to evaluate the correlation between spinal cord and brain metabolism. Our results confirmed higher 18F-fluorodeoxyglucose uptake in both cervical and dorsal spinal cord in patients with amyotrophic lateral sclerosis with respect to controls. This finding was paralleled by the opposite pattern in the brain cortex that showed a generalized reduction in tracer uptake. This hypometabolism was particularly evident in wide regions of the frontal-dorsolateral cortex while it did not involve the midbrain. Bulbar and spinal disease onset was associated with similar degree of metabolic activation in the spinal cord. However, among spinal onset patients, upper limb presentation was associated with a more pronounced metabolic activation of cervical segment. Obtained data suggest a differential neuro-pathological state or temporal sequence in disease progression.
Candidemia is associated with a heavy burden of morbidity and mortality in hospitalized patients. The availability of blood culture results could require up to 48-72 h after blood draw; thus, early ...treatment decisions are made in the absence of a definite diagnosis.
In this retrospective study, we assessed the performance of different supervised machine learning algorithms for the early differential diagnosis of candidemia and bacteremia in adult patients on a large dataset automatically extracted within the AUTO-CAND project.
Overall, 12,483 episodes of candidemia (1275; 10%) or bacteremia (11,208; 90%) were included in the analysis. A random forest classifier achieved the best diagnostic performance for candidemia, with sensitivity 0.98 and specificity 0.65 on the training set (true skill statistic TSS = 0.63) and sensitivity 0.74 and specificity 0.57 on the test set (TSS = 0.31). Then, the random classifier was trained in the subgroup of patients with available serum β-D-glucan (BDG) and procalcitonin (PCT) values by exploiting the feature ranking learned in the entire dataset. Although no statistically significant differences were observed from the performance measures obtained by employing BDG and PCT alone, the performance measures of the classifier that included the features selected in the entire dataset, plus BDG and PCT, were the highest in most cases.
Random forest classifiers trained on large datasets of automatically extracted data have the potential to improve current diagnostic algorithms for candidemia. However, further development through implementation of automatically extracted clinical features may be necessary to achieve crucial improvements.
Emerging evidence suggests that metformin, a widely used anti-diabetic drug, may be useful in the prevention and treatment of different cancers. In the present study, we demonstrate that metformin ...directly inhibits the enzymatic function of hexokinase (HK) I and II in a cell line of triple-negative breast cancer (MDA-MB-231). The inhibition is selective for these isoforms, as documented by experiments with purified HK I and II as well as with cell lysates. Measurements of
18
F-fluoro-deoxyglycose uptake document that it is dose- and time-dependent and powerful enough to virtually abolish glucose consumption despite unchanged availability of membrane glucose transporters. The profound energetic imbalance activates phosphorylation and is subsequently followed by cell death. More importantly, the "in vivo" relevance of this effect is confirmed by studies of orthotopic xenografts of MDA-MB-231 cells in athymic (nu/nu) mice. Administration of high drug doses after tumor development caused an evident tumor necrosis in a time as short as 48 h. On the other hand, 1 mo metformin treatment markedly reduced cancer glucose consumption and growth. Taken together, our results strongly suggest that HK inhibition contributes to metformin therapeutic and preventive potential in breast cancer.
Operational flare forecasting aims at providing predictions that can be used to make decisions, typically on a daily scale, about the space weather impacts of flare occurrence. This study shows that ...video-based deep learning can be used for operational purposes when the training and validation sets used for network optimization are generated while accounting for the periodicity of the solar cycle. Specifically, this article describes an algorithm that can be applied to build up sets of active regions that are balanced according to the flare class rates associated to a specific cycle phase. These sets are used to train and validate a long-term recurrent convolutional network made of a combination of a convolutional neural network and a long short-term memory network. The reliability of this approach is assessed in the case of two prediction windows containing the solar storms of March 2015, June 2015, and September 2017.
The European Union funded the FLARECAST project, that ran from January 2015 until February 2018. FLARECAST had a research-to-operations (R2O) focus, and accordingly introduced several innovations ...into the discipline of solar flare forecasting. FLARECAST innovations were: first, the treatment of hundreds of physical properties viewed as promising flare predictors on equal footing, extending multiple previous works; second, the use of fourteen (14) different machine learning techniques, also on equal footing, to optimize the immense Big Data parameter space created by these many predictors; third, the establishment of a robust, three-pronged communication effort oriented toward policy makers, space-weather stakeholders and the wider public. FLARECAST pledged to make all its data, codes and infrastructure openly available worldwide. The combined use of 170+ properties (a total of 209 predictors are now available) in multiple machine-learning algorithms, some of which were designed exclusively for the project, gave rise to changing sets of best-performing predictors for the forecasting of different flaring levels, at least for major flares. At the same time, FLARECAST reaffirmed the importance of rigorous training and testing practices to avoid overly optimistic pre-operational prediction performance. In addition, the project has (a) tested new and revisited physically intuitive flare predictors and (b) provided meaningful clues toward the transition from flares to eruptive flares, namely, events associated with coronal mass ejections (CMEs). These leads, along with the FLARECAST data, algorithms and infrastructure, could help facilitate integrated space-weather forecasting efforts that take steps to avoid effort duplication. In spite of being one of the most intensive and systematic flare forecasting efforts to-date, FLARECAST has not managed to convincingly lift the barrier of stochasticity in solar flare occurrence and forecasting: solar flare prediction thus remains inherently probabilistic.
Positron Emission Tomography (PET) imaging with Prostate-Specific Membrane Antigen (PSMA) and Fluorodeoxyglucose (FDG) represent promising biomarkers for risk-stratification of Prostate Cancer (PCa). ...We verified whether the expression of genes encoding for PSMA and enzymes regulating FDG cellular uptake are independent and additive prognosticators in PCa.
mRNA expression of genes involved in glucose metabolism and PSMA regulation obtained from primary PCa specimens were retrieved from open-source databases and analyzed using an integrative bioinformatics approach. Machine Learning (ML) techniques were used to create predictive Progression-Free Survival (PFS) models. Cellular models of primary PCa with different aggressiveness were used to compare 18FF-PSMA-1007 and 18FF-FDG uptake kinetics in vitro. Confocal microscopy, immunofluorescence staining, and quantification analyses were performed to assess the intracellular and cellular membrane PSMA expression.
ML analyses identified a predictive functional network involving four glucose metabolism-related genes: ALDOB, CTH, PARP2, and SLC2A4. By contrast, FOLH1 expression (encoding for PSMA) did not provide any additive predictive value to the model. At a cellular level, the increase in proliferation rate and migratory potential by primary PCa cells was associated with enhanced FDG uptake and decreased PSMA retention (paralleled by the preferential intracellular localization).
The overexpression of a functional network involving four glucose metabolism-related genes identifies a higher risk of disease progression since the earliest phases of PCa, in agreement with the acknowledged prognostic value of FDG PET imaging. By contrast, the prognostic value of PSMA PET imaging is independent of the expression of its encoding gene FOLH1. Instead, it is influenced by the protein docking to the cell membrane, regulating its accessibility to tracer binding.
Multiple Myeloma (MM) is the second most common type of hematological disease and, although it is rare among patients under 40 years of age, its incidence rises in elderly subjects. MM manifestations ...are usually identified through hyperCalcemia, Renal failure, Anaemia, and lytic Bone lesions (CRAB). In particular, the extent of the bone disease is negatively related to a decreased quality of life in patients and, in general, bone disease in MM increases both morbidity and mortality. The detection of lytic bone lesions on imaging, especially computerized tomography (CT) and Magnetic Resonance Imaging (MRI), is becoming crucial from the clinical viewpoint to separate asymptomatic from symptomatic MM patients and the detection of focal lytic lesions in these imaging data is becoming relevant even when no clinical symptoms are present. Therefore, radiology is pivotal in the staging and accurate management of patients with MM even in early phases of the disease. In this review, we describe the opportunities offered by quantitative imaging and radiomics in multiple myeloma. At the present time there is still high variability in the choice between various imaging methods to study MM patients and high variability in image interpretation with suboptimal agreement among readers even in tertiary centers. Therefore, the potential of medical imaging for patients affected by MM is still to be completely unveiled. In the coming years, new insights to study MM with medical imaging will derive from artificial intelligence (AI) and radiomics usage in different bone lesions and from the wide implementations of quantitative methods to report CT and MRI. Eventually, medical imaging data can be integrated with the patient's outcomes with the purpose of finding radiological biomarkers for predicting the prognostic flow and therapeutic response of the disease.
To analyze multimodal three-dimensional medical images, interpolation is required for resampling which—unavoidably—introduces an interpolation error. In this work we describe the interpolation method ...used for imaging and neuroimaging and we characterize the Gibbs effect occurring when using such methods. In the experimental section we consider three segmented three-dimensional images resampled with three different neuroimaging software tools for comparing undersampling and oversampling strategies and to identify where the oversampling error lies. The experimental results indicate that undersampling to the lowest image size is advantageous in terms of mean value per segment errors and that the oversampling error is larger where the gradient is steeper, showing a Gibbs effect.
Radiomics is a promising research field that combines big data analysis (from tissue texture analysis) with clinical questions. We studied the application of CT texture analysis in adrenal ...pheochromocytomas (PCCs) to define the correlation between the extracted features and the secretory pattern, the histopathological data, and the natural history of the disease. A total of 17 patients affected by surgically removed PCCs were retrospectively enrolled. Before surgery, all patients underwent contrast-enhanced CT and complete endocrine evaluation (catecholamine secretion and genetic evaluation). The pheochromocytoma adrenal gland scaled score (PASS) was determined upon histopathological examination. After a resampling of all CT images, the PCCs were delineated using LifeX software in all three phases (unenhanced, arterial, and venous), and 58 texture parameters were extracted for each volume of interest. Using the Mann-Whitney test, the correlations between the hormonal hypersecretion, the malignancy score of the lesion (PASS > 4), and texture parameters were studied. The parameters DISCRETIZED_HUpeak and GLZLM_GLNU in the unenhanced phase and GLZLM_SZE, CONVENTIONAL_HUmean, CONVENTIONAL_HUQ3, DISCRETIZED_HUmean, DISCRETIZED_AUC_CSH, GLRLM_HGRE, and GLZLM_SZHGE in the venous phase were able to differentiate secreting PCCs (
< 0.01), and the parameters GLZLM_GLNU in the unenhanced phase and GLRLM_GLNU and GLRLM_RLNU in the venous differentiated tumors with low and high PASS. CT texture analysis of adrenal PCCs can be a useful tool for the early identification of secreting or malignant tumors.