Use of deep learning in the MRI diagnosis of Chiari malformation type I.

PURPOSE: To train deep learning convolutional neural network (CNN) models for classification of clinically significant Chiari malformation type I (CM1) on MRI to assist clinicians in diagnosis and decision making. METHODS: A retrospective MRI dataset of patients diagnosed with CM1 and healthy individuals with normal brain MRIs from the period January 2010 to May 2020 was used to train ResNet50 and VGG19 CNN models to automatically classify images as CM1 or normal. A total of 101 patients diagnosed with CM1 requiring surgery and 111 patients with normal brain MRIs were included (median age 30 with an interquartile range of 23-43; 81 women with CM1). Isotropic volume transformation, image cropping, skull stripping, and data augmentation were employed to optimize model accuracy. K-fold cross validation was used to calculate sensitivity, specificity, and the area under receiver operating characteristic curve (AUC) for model evaluation. RESULTS: The VGG19 model with data augmentation achieved a sensitivity of 97.1% and a specificity of 97.4% with an AUC of 0.99. The ResNet50 model achieved a sensitivity of 94.0% and a specificity of 94.4% with an AUC of 0.98. CONCLUSIONS: VGG19 and ResNet50 CNN models can be trained to automatically detect clinically significant CM1 on MRI with a high sensitivity and specificity. These models have the potential to be developed into clinical support tools in diagnosing CM1.

Foundations of Multiparametric Brain Tumour Imaging Characterisation Using Machine Learning.

The heterogeneity of brain tumours at the molecular, metabolic and structural levels poses significant challenge for accurate tissue characterisation. Artificial intelligence and radiomics have emerged as valuable tools to analyse quantitative features extracted from medical images which capture the complex microenvironment of brain tumours. In particular, a number of computational tools including machine learning algorithms have been proposed for image preprocessing, tumour segmentation, feature extraction, classification, and prognostic stratifications as well. In this chapter, we explore the fundamentals of multiparametric brain tumour characterisation, as an understanding of the strengths, limitations and applications of these tools allows clinicians to better develop and evaluate models with improved diagnostic and prognostic value in brain tumour patients.

SoftMatch: Comparing Scanpaths Using Combinatorial Spatio-Temporal Sequences with Fractal Curves.

Recent studies matching eye gaze patterns with those of others contain research that is heavily reliant on string editing methods borrowed from early work in bioinformatics. Previous studies have shown string editing methods to be susceptible to false negative results when matching mutated genes or unordered regions of interest in scanpaths. Even as new methods have emerged for matching amino acids using novel combinatorial techniques, scanpath matching is still limited by a traditional collinear approach. This approach reduces the ability to discriminate between free viewing scanpaths of two people looking at the same stimulus due to the heavy weight placed on linearity. To overcome this limitation, we here introduce a new method called SoftMatch to compare pairs of scanpaths. SoftMatch diverges from traditional scanpath matching in two different ways: firstly, by preserving locality using fractal curves to reduce dimensionality from 2D Cartesian (x,y) coordinates into 1D (h) Hilbert distances, and secondly by taking a combinatorial approach to fixation matching using discrete Fréchet distance measurements between segments of scanpath fixation sequences. These matching "sequences of fixations over time" are a loose acronym for SoftMatch. Results indicate high degrees of statistical and substantive significance when scoring matches between scanpaths made during free-form viewing of unfamiliar stimuli. Applications of this method can be used to better understand bottom up perceptual processes extending to scanpath outlier detection, expertise analysis, pathological screening, and salience prediction.

Application of deep learning for automatic segmentation of brain tumors on magnetic resonance imaging: a heuristic approach in the clinical scenario.

PURPOSE: Accurate brain tumor segmentation on magnetic resonance imaging (MRI) has wide-ranging applications such as radiosurgery planning. Advances in artificial intelligence, especially deep learning (DL), allow development of automatic segmentation that overcome the labor-intensive and operator-dependent manual segmentation. We aimed to evaluate the accuracy of the top-performing DL model from the 2018 Brain Tumor Segmentation (BraTS) challenge, the impact of missing MRI sequences, and whether a model trained on gliomas can accurately segment other brain tumor types. METHODS: We trained the model using Medical Decathlon dataset, applied it to the BraTS 2019 glioma dataset, and developed additional models using individual and multimodal MRI sequences. The Dice score was calculated to assess the model's accuracy compared to ground truth labels by neuroradiologists on BraTS dataset. The model was then applied to a local dataset of 105 brain tumors, performance of which was qualitatively evaluated. RESULTS: The DL model using pre- and post-gadolinium contrast T1 and T2 FLAIR sequences performed best, with a Dice score 0.878 for whole tumor, 0.732 tumor core, and 0.699 active tumor. Lack of T1 or T2 sequences did not significantly degrade performance, but FLAIR and T1C were important contributors. All segmentations performed by the model in the local dataset, including non-glioma cases, were considered accurate by a pool of specialists. CONCLUSION: The DL model could use available MRI sequences to optimize glioma segmentation and adopt transfer learning to segment non-glioma tumors, thereby serving as a useful tool to improve treatment planning and personalized surveillance of patients.

Radiomics in gliomas: clinical implications of computational modeling and fractal-based analysis.

Radiomics is an emerging field that involves extraction and quantification of features from medical images. These data can be mined through computational analysis and models to identify predictive image biomarkers that characterize intra-tumoral dynamics throughout the course of treatment. This is particularly difficult in gliomas, where heterogeneity has been well established at a molecular level as well as visually in conventional imaging. Thus, acquiring clinically useful features remains difficult due to temporal variations in tumor dynamics. Identifying surrogate biomarkers through radiomics may provide a non-invasive means of characterizing biologic activities of gliomas. We present an extensive literature review of radiomics-based analysis, with a particular focus on computational modeling, machine learning, and fractal-based analysis in improving differential diagnosis and predicting clinical outcomes. Novel strategies in extracting quantitative features, segmentation methods, and their clinical applications are producing promising results. Moreover, we provide a detailed summary of the morphometric parameters that have so far been proposed as a means of quantifying imaging characteristics of gliomas. Newly emerging radiomic techniques via machine learning and fractal-based analyses holds considerable potential for improving diagnostic and prognostic accuracy of gliomas. Key points• Radiomic features can be mined through computational analysis to produce quantitative imaging biomarkers that characterize intra-tumoral dynamics throughout the course of treatment.• Surrogate image biomarkers identified through radiomics could enable a non-invasive means of characterizing biologic activities of gliomas.• With novel analytic algorithms, quantification of morphological or sub-regional tumor features to predict survival outcomes is producing promising results.• Quantifying intra-tumoral heterogeneity may improve grading and molecular sub-classifications of gliomas.• Computational fractal-based analysis of gliomas allows geometrical evaluation of tumor irregularities and complexity, leading to novel techniques for tumor segmentation, grading, and therapeutic monitoring.

Computer-aided assessment of the extra-cellular matrix during pancreatic carcinogenesis: a pilot study.

BACKGROUND: A hallmark of pancreatic ductal adenocarcinoma is the desmoplastic reaction, but its impact on the tumor behavior remains controversial. Our aim was to introduce a computer -aided method to precisely quantify the amount of pancreatic collagenic extra-cellular matrix, its spatial distribution pattern, and the degradation process. METHODS: A series of normal, inflammatory and neoplastic pancreatic ductal adenocarcinoma formalin-fixed and paraffin-embedded Sirius red stained sections were automatically digitized and analyzed using a computer-aided method. RESULTS: We found a progressive increase of pancreatic collagenic extra-cellular matrix from normal to the inflammatory and pancreatic ductal adenocarcinoma. The two-dimensional fractal dimension showed a significant difference in the collagenic extra-cellular matrix spatial complexity between normal versus inflammatory and pancreatic ductal adenocarcinoma. A significant difference when comparing the number of cycles necessary to degrade the pancreatic collagenic extra-cellular matrix in normal versus inflammatory and pancreatic ductal adenocarcinoma was also found. The difference between inflammatory and pancreatic ductal adenocarcinoma was also significant. Furthermore, the mean velocity of collagenic extra-cellular matrix degradation was found to be faster in inflammatory and pancreatic ductal adenocarcinoma than in normal. CONCLUSION: These findings demonstrate that inflammatory and pancreatic ductal adenocarcinomas are characterized by an increased amount of pancreatic collagenic extra-cellular matrix and by changes in their spatial complexity and degradation. Our study defines new features about the pancreatic collagenic extra-cellular matrix, and represents a basis for further investigations into the clinical behavior of pancreatic ductal adenocarcinoma and the development of therapeutic strategies.

Carbon footprint as an instrument for enhancing food quality: overview of the wine, olive oil and cereals sectors.

The quantification of greenhouse gases (GHG) emissions represents a critical issue for the future development of agro-food produces. Consumers' behaviour could play an important role in requiring environmental performance as an essential element for food quality. Nowadays, the carbon footprint (CFP) is a tool used worldwide by agro-food industries to communicate environmental information. This paper aims to investigate the role that CFP could have in consumers' choices in three significant agro-food sectors in the Mediterranean area: wine, olive oil and cereals. A critical review about the use of CFP was carried out along the supply chain of these three sectors, in order to identify opportunities for enhancing food quality and environmental sustainability and highlighting how environmental information could influence consumers' preferences. The analysis of the state of the art shows a great variability of the results about GHG emissions referred to agricultural and industrial processes. In many cases, the main environmental criticisms are linked to the agricultural phase, but the other phases of the supply chain could also contribute to the increased CFP. However, despite the wide use of CFP by companies as a communication tool to help consumers' choices in agro-food products, some improvements are needed in order to provide clearer and more understandable information. © 2016 Society of Chemical Industry.

Use of Artificial Intelligence in the Prediction of Chiari Malformation Type 1 Recurrence After Posterior Fossa Decompressive Surgery.

Purpose The purpose of this study was to train a deep learning-based method for the prediction of postoperative recurrence of symptoms in Chiari malformation type 1 (CM1) patients undergoing surgery. Studies suggest that certain radiological and clinical features do exist in patients with treatment failure, though these are inconsistent and poorly defined. Methodology This study was a retrospective cohort study of patients who underwent primary surgical intervention for CM1 from January 2010 to May 2020. Only patients who completed pre- and postoperative 12-item short form (SF-12) surveys were included and these were used to classify the recurrence or persistence of symptoms. Forty patients had an improvement in overall symptoms while 17 had recurrence or persistence. After magnetic resonance imaging (MRI) data augmentation, a ResNet50, pre-trained on the ImageNet dataset, was used for feature extraction, and then clustering-constrained attention multiple instance learning (CLAM), a weakly supervised multi-instance learning framework, was trained for prediction of recurrence. Five-fold cross-validation was used for the development of MRI only, clinical features only, and a combined machine learning model. Results This study included 57 patients who underwent CM1 decompression. The recurrence rate was 30%. The combined model incorporating MRI, pre-operative SF-12 physical component scale (PCS), and extent of cerebellar ectopia performed best with an area under the curve (AUC) of 0.71 and an F1 score of 0.74. Conclusion This is the first study to our knowledge to explore the prediction of postoperative recurrence of symptoms in CM1 patients using machine learning methods and represents the first step toward developing a clinically useful prognostication machine learning model. Further studies utilizing a similar deep learning approach with a larger sample size are needed to improve the performance.

Fractals in the Neurosciences: A Translational Geographical Approach.

The chapter presents three new fractal indices (fractal fragmentation index, fractal tentacularity index, and fractal anisotropy index) and normalized Kolmogorov complexity with proven applicability in geographic research, developed by the authors, and the possibility of their future use in neuroscience. The research demonstrates the relevance of fractal analysis in different fields and the basic concepts and principles of fractal geometry being sufficient for the development of models relevant to the studied reality. Also, the research highlighted the need to continue interdisciplinary research based on known fractal indicators, as well as the development of new analysis methods with the translational potential between fields.

A Deep Learning Framework for Skull Stripping in Brain MRI.

Skull-stripping, an important pre-processing step in neuroimage computing, involves the automated removal of non-brain anatomy (such as the skull, eyes, and ears) from brain images to facilitate brain segmentation and analysis. Manual segmentation is still practiced, but it is time-consuming and highly dependent on the expertise of clinicians or image analysts. Prior studies have developed various skull-stripping algorithms that perform well on brains with mild or no structural abnormalities. Nonetheless, they were not able to address the issue for brains with significant morphological changes, such as those caused by brain tumors, particularly when the tumors are located near the skull's border. In such cases, a portion of the normal brain may be stripped, or the reverse may occur during skull stripping. To address this limitation, we propose to use a novel deep learning framework based on nnUNet for skull stripping in brain MRI. Two publicly available datasets were used to evaluate the proposed method, including a normal brain MRI dataset - The Neurofeedback Skull-stripped Repository (NFBS), and a brain tumor MRI dataset - The Cancer Genome Atlas (TCGA). The method proposed in the study performed better than six other current methods, namely BSE, ROBEX, UNet, SC-UNet, MV-UNet, and 3D U-Net. The proposed method achieved an average Dice coefficient of 0.9960, a sensitivity of 0.9999, and a specificity of 0.9996 on the NFBS dataset, and an average Dice coefficient of 0.9296, a sensitivity of 0.9288, a specificity of 0.9866 and an accuracy of 0.9762 on the TCGA brain tumor dataset.

Artificial Intelligence-Assisted Classification of Gliomas Using Whole Slide Images.

CONTEXT.­: Glioma is the most common primary brain tumor in adults. The diagnosis and grading of different pathological subtypes of glioma is essential in treatment planning and prognosis. OBJECTIVE.­: To propose a deep learning-based approach for the automated classification of glioma histopathology images. Two classification methods, the ensemble method based on 2 binary classifiers and the multiclass method using a single multiclass classifier, were implemented to classify glioma images into astrocytoma, oligodendroglioma, and glioblastoma, according to the 5th edition of the World Health Organization classification of central nervous system tumors, published in 2021. DESIGN.­: We tested 2 different deep neural network architectures (VGG19 and ResNet50) and extensively validated the proposed approach based on The Cancer Genome Atlas data set (n = 700). We also studied the effects of stain normalization and data augmentation on the glioma classification task. RESULTS.­: With the binary classifiers, our model could distinguish astrocytoma and oligodendroglioma (combined) from glioblastoma with an accuracy of 0.917 (area under the curve [AUC] = 0.976) and astrocytoma from oligodendroglioma (accuracy = 0.821, AUC = 0.865). The multiclass method (accuracy = 0.861, AUC = 0.961) outperformed the ensemble method (accuracy = 0.847, AUC = 0.933) with the best performance displayed by the ResNet50 architecture. CONCLUSIONS.­: With the high performance of our model (>80%), the proposed method can assist pathologists and physicians to support examination and differential diagnosis of glioma histopathology images, with the aim to expedite personalized medical care.

The E3 Ubiquitin Ligase SCF Cyclin F Promotes Sequestosome-1/p62 Insolubility and Foci Formation and is Dysregulated in ALS and FTD Pathogenesis.

Amyotrophic lateral sclerosis (ALS)- and frontotemporal dementia (FTD)-linked mutations in CCNF have been shown to cause dysregulation to protein homeostasis. CCNF encodes for cyclin F, which is part of the cyclin F-E3 ligase complex SCFcyclinF known to ubiquitylate substrates for proteasomal degradation. In this study, we identified a function of cyclin F to regulate substrate solubility and show how cyclin F mechanistically underlies ALS and FTD disease pathogenesis. We demonstrated that ALS and FTD-associated protein sequestosome-1/p62 (p62) was a canonical substrate of cyclin F which was ubiquitylated by the SCFcyclinF complex. We found that SCFcyclin F ubiquitylated p62 at lysine(K)281, and that K281 regulated the propensity of p62 to aggregate. Further, cyclin F expression promoted the aggregation of p62 into the insoluble fraction, which corresponded to an increased number of p62 foci. Notably, ALS and FTD-linked mutant cyclin F p.S621G aberrantly ubiquitylated p62, dysregulated p62 solubility in neuronal-like cells, patient-derived fibroblasts and induced pluripotent stem cells and dysregulated p62 foci formation. Consistently, motor neurons from patient spinal cord tissue exhibited increased p62 ubiquitylation. We suggest that the p.S621G mutation impairs the functions of cyclin F to promote p62 foci formation and shift p62 into the insoluble fraction, which may be associated to aberrant mutant cyclin F-mediated ubiquitylation of p62. Given that p62 dysregulation is common across the ALS and FTD spectrum, our study provides insights into p62 regulation and demonstrates that ALS and FTD-linked cyclin F mutant p.S621G can drive p62 pathogenesis associated with ALS and FTD.

Developing an eLearning tool formalizing in YAWL the guidelines used in a transfusion medicine service.

The blood transfusion is a complex activity subject to a high risk of eventually fatal errors. The development and application of computer-based systems could help reducing the error rate, playing a fundamental role in the improvement of the quality of care. This poster presents an under development eLearning tool formalizing the guidelines of the transfusion process. This system, implemented in YAWL (Yet Another Workflow Language), will be used to train the personnel in order to improve the efficiency of care and to reduce errors.

It Seems Italian, Doesn't It? An Exploratory Analysis of English and Spanish Consumers about Italian Appearance Food Products.

The Italian export of agri-food products has been increasingly threatened by the unfair use of misleading Italian symbols (such as the national flag or the green-white-red colors) by non-Italian producers. This research paper investigated what English and Spanish consumers know about "Made in Italy" food, and their attitude towards Italian appearance food products. Primary data were collected in Spain and England, and a probit model was used to identify the determinants of consumers' vulnerability to misleading Italian symbols. We found that merely having Italian symbols on the package might lead almost half of the consumers in the sample to consider food as Made in Italy, regardless of the actual origin. This result confirms the severity of the problem. The econometric model provides suggestions for public actions to mitigate the issue.

Purchases of Fruit and Vegetables for at Home Consumption During COVID-19 in the UK: Trends and Determinants.

This paper addresses the issue of fruit and vegetable purchases in the UK during the COVID-19 pandemic. The study is motivated by the importance of fruit and vegetables for human nutrition, health and reduction of population obesity, especially in the UK where per capita consumption is still below recommended levels. A rich panel dataset was used reporting actual shopping places and quarterly expenditure for at-home consumption of fruit and vegetable purchases of 12,492 households in years 2019 and 2020. The unique dataset allowed us to compare expenditure for fruit and vegetables before and after the COVID-19 outbreak and to identify the main drivers of changes in purchases. Regression analysis found that expenditure increased ~3% less than what expected given the overall increase in the numbers of at-home meals during lockdown. Also, Online shopping was found to be an alternative source for fruit and vegetables purchase during the pandemic. However, the expenditure for processed products grew more than the one for fresh products, resulting in a reduction of the relative share of the latter and possible deterioration of the diet quality.

Spherical coordinates transformation pre-processing in Deep Convolution Neural Networks for brain tumor segmentation in MRI.

Magnetic Resonance Imaging (MRI) is used in everyday clinical practice to assess brain tumors. Deep Convolutional Neural Networks (DCNN) have recently shown very promising results in brain tumor segmentation tasks; however, DCNN models fail the task when applied to volumes that are different from the training dataset. One of the reasons is due to the lack of data standardization to adjust for different models and MR machines. In this work, a 3D spherical coordinates transform during the pre-processing phase has been hypothesized to improve DCNN models' accuracy and to allow more generalizable results even when the model is trained on small and heterogeneous datasets and translated into different domains. Indeed, the spherical coordinate system avoids several standardization issues since it works independently of resolution and imaging settings. The model trained on spherical transform pre-processed inputs resulted in superior performance over the Cartesian-input trained model on predicting gliomas' segmentation on Tumor Core and Enhancing Tumor classes, achieving a further improvement in accuracy by merging the two models together. The proposed model is not resolution-dependent, thus improving segmentation accuracy and theoretically solving some transfer learning problems related to the domain shifting, at least in terms of image resolution in the datasets.

Purchases of Meats and Fish in Great Britain During the COVID-19 Lockdown Period.

The purpose of this paper is to provide an analysis of the purchases of meat and fish in Great Britain during the lockdown period using time series constructed from a unique scanner panel dataset available since 2013 and which is based on information about 30 thousand households. The time series available for the analysis represent the purchases (expenditure and quantities) of all consumers and by income groups were used to compute price and quantity indices all the meats together and for each meat (i.e., beef, lamb, pork, poultry, and other meats) and fish. The changes in expenditure were decomposed into changes in prices, quantities purchased and changes in quality purchased (trading up/down in quality) i.e., whether cheaper meat or fish were purchased. A further extension of the analysis was produced by considering the evolution of calories, saturated fats and sodium per purchased quantity for meat and fish during the period of study. The results indicate that although the shares of quantities remained relatively constant, the calories, saturated fats and sodium from the purchased quantities showed an increasing trend, indicating that most of the incomes groups were lowering the nutritional quality of their meat and fish purchases. This is clearly shown by the fact "other meats" represents on average 39 percent of the calories contributed by meat and fish, 49 per cent of the saturated fats and about 68 of the total sodium in meat and fish during the lockdown period. This result highlights the need to emphasize healthy messages related to the purchases of meat.

Generative Adversarial Networks in Digital Pathology and Histopathological Image Processing: A Review.

Digital pathology is gaining prominence among the researchers with developments in advanced imaging modalities and new technologies. Generative adversarial networks (GANs) are a recent development in the field of artificial intelligence and since their inception, have boosted considerable interest in digital pathology. GANs and their extensions have opened several ways to tackle many challenging histopathological image processing problems such as color normalization, virtual staining, ink removal, image enhancement, automatic feature extraction, segmentation of nuclei, domain adaptation and data augmentation. This paper reviews recent advances in histopathological image processing using GANs with special emphasis on the future perspectives related to the use of such a technique. The papers included in this review were retrieved by conducting a keyword search on Google Scholar and manually selecting the papers on the subject of H&E stained digital pathology images for histopathological image processing. In the first part, we describe recent literature that use GANs in various image preprocessing tasks such as stain normalization, virtual staining, image enhancement, ink removal, and data augmentation. In the second part, we describe literature that use GANs for image analysis, such as nuclei detection, segmentation, and feature extraction. This review illustrates the role of GANs in digital pathology with the objective to trigger new research on the application of generative models in future research in digital pathology informatics.

Assessment of eye-tracking scanpath outliers using fractal geometry.

Outlier scanpaths identification is a crucial preliminary step in designing visual software, digital media analysis, radiology training and clustering participants in eye-tracking experiments. However, the task is challenging due to the visual irregularity of the scanpath shapes and the difficulty in dimensionality reduction due to geometric complexity. Conventional approaches have used heat maps to exclude scanpaths that lack a similarity pattern. However, the typically-used packages, such as ScanMatch and MultiMatch often generate discordant results when outlier identification is done empirically. This paper introduces a novel outlier evaluation approach by integrating the fractal dimension (FD), capturing the geometrical complexity of patterns, as an additional parameter with the heat map. This additional parameter is used to evaluate the degree of influence of a scanpath within a dataset. More specifically, the 2D Cartesian coordinates of a scanpath are fitted to a space filling 1D fractal curve to characterise its temporal FD. The FDs of the scanpaths are then compared to match their geometric complexity to one another. The findings indicate that the FD can be a beneficial additional parameter when evaluating the candidacy of poorly matching scanpaths as outliers and performs better at identifying unusual scanpaths than using other methods, including scanpath matching, Jaccard, or bounding box methods alone.

Psychological pressure and changes in food consumption: the effect of COVID-19 crisis.

In this paper, we investigate the short-term and long-term effects of the COVID-19 emergency on consumers' decision of changing dietary habit. We used a certified dataset reporting information about 456 Italian consumers during the lockdown in the first wave of the pandemic emergency (April 2020). The survey collected data about changes in food purchases, respondents' mood during the lockdown, conspiracist beliefs, exposure to the virus, and planned food purchasing behavior after the lockdown. We used the data to construct measures of the psychological pressure exerted by the COVID-19 emergency on consumers. We use an endogenous selection regression model to assess the impact of psychological pressure on the decision of changing food purchased. The analysis identified two opposite approaches to change in food purchasing decisions: impulsive approach and reflective approach. The former is associated with a higher probability of changing food purchase but a lower probability to keep the changes in the long run than the latter. Our results suggest that COVID-19 psychological pressure was associated with impulsive approach to buy food. Consequently, food-purchasing behavior is expected to revert to pre-COVID 19 habits when the emergency is over.