Effect of substrate mismatch, orientation, and flexibility on heterogeneous ice nucleation

Heterogeneous nucleation is the main path to ice formation on Earth. The ice nucleating ability of a certain substrate is mainly determined by both molecular interactions and the structural mismatch between the ice and the substrate lattices. We focus on the latter factor using molecular simulations of the mW model. Quantifying the effect of structural mismatch alone is challenging due to its coupling with molecular interactions. To disentangle both the factors, we use a substrate composed of water molecules in such a way that any variation on the nucleation temperature can be exclusively ascribed to the structural mismatch. We find that a 1% increase in structural mismatch leads to a decrease of ∼4 K in the nucleation temperature. We also analyze the effect of orientation of the substrate with respect to the liquid. The three main ice orientations (basal, primary prism, and secondary prism) have a similar ice nucleating ability. We finally assess the effect of lattice flexibility by comparing substrates where molecules are immobile to others where a certain freedom to fluctuate around the lattice positions is allowed. Interestingly, we find that the latter type of substrate is more efficient in nucleating ice because it can adapt its structure to that of ice.

Nonlinear Weighting Ensemble Learning Model to Diagnose Parkinson's Disease Using Multimodal Data

Parkinson's Disease (PD) is the second most prevalent neurodegenerative disorder among adults. Although its triggers are still not clear, they may be due to a combination of different types of biomarkers measured through medical imaging, metabolomics, proteomics or genetics, among others. In this context, we have proposed a Computer-Aided Diagnosis (CAD) system that combines structural and functional imaging data from subjects in Parkinson's Progression Markers Initiative dataset by means of an Ensemble Learning methodology trained to identify and penalize input sources with low classification rates and/or high-variability. This proposal improves results published in recent years and provides an accurate solution not only from the point of view of image preprocessing (including a comparison between different intensity preservation techniques), but also in terms of dimensionality reduction methods (Isomap). In addition, we have also introduced a bagging classification schema for scenarios with unbalanced data. As shown by our results, the CAD proposal is able to detect PD with [Formula: see text] of balanced accuracy, and opens up the possibility of combining any number of input data sources relevant for PD.

Enhancing Multimodal Patterns in Neuroimaging by Siamese Neural Networks with Self-Attention Mechanism

The combination of different sources of information is currently one of the most relevant aspects in the diagnostic process of several diseases. In the field of neurological disorders, different imaging modalities providing structural and functional information are frequently available. Those modalities are usually analyzed separately, although a joint of the features extracted from both sources can improve the classification performance of Computer-Aided Diagnosis (CAD) tools. Previous studies have computed independent models from each individual modality and combined them in a subsequent stage, which is not an optimum solution. In this work, we propose a method based on the principles of siamese neural networks to fuse information from Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET). This framework quantifies the similarities between both modalities and relates them with the diagnostic label during the training process. The resulting latent space at the output of this network is then entered into an attention module in order to evaluate the relevance of each brain region at different stages of the development of Alzheimer's disease. The excellent results obtained and the high flexibility of the method proposed allow fusing more than two modalities, leading to a scalable methodology that can be used in a wide range of contexts.

Using Explainable Artificial Intelligence in the Clock Drawing Test to Reveal the Cognitive Impairment Pattern

The prevalence of dementia is currently increasing worldwide. This syndrome produces a deterioration in cognitive function that cannot be reverted. However, an early diagnosis can be crucial for slowing its progress. The Clock Drawing Test (CDT) is a widely used paper-and-pencil test for cognitive assessment in which an individual has to manually draw a clock on a paper. There are a lot of scoring systems for this test and most of them depend on the subjective assessment of the expert. This study proposes a computer-aided diagnosis (CAD) system based on artificial intelligence (AI) methods to analyze the CDT and obtain an automatic diagnosis of cognitive impairment (CI). This system employs a preprocessing pipeline in which the clock is detected, centered and binarized to decrease the computational burden. Then, the resulting image is fed into a Convolutional Neural Network (CNN) to identify the informative patterns within the CDT drawings that are relevant for the assessment of the patient's cognitive status. Performance is evaluated in a real context where patients with CI and controls have been classified by clinical experts in a balanced sample size of [Formula: see text] drawings. The proposed method provides an accuracy of [Formula: see text] in the binary case-control classification task, with an AUC of [Formula: see text]. These results are indeed relevant considering the use of the classic version of the CDT. The large size of the sample suggests that the method proposed has a high reliability to be used in clinical contexts and demonstrates the suitability of CAD systems in the CDT assessment process. Explainable artificial intelligence (XAI) methods are applied to identify the most relevant regions during classification. Finding these patterns is extremely helpful to understand the brain damage caused by CI. A validation method using resubstitution with upper bound correction in a machine learning approach is also discussed.

POS1051 TO WHAT EXTENT ARE BASELINE CHARACTERISTICS IN BIOLOGIC-EXPERIENCED PATIENTS WITH PSORIATIC ARTHRITIS ASSOCIATED WITH ACHIEVEMENT OF MINIMAL DISEASE ACTIVITY AT WEEK 24 OF GUSELKUMAB TREATMENT: A POST HOC ANALYSIS OF THE PHASE IIIb COSMOS CLINICAL TRIAL

Background

Guselkumab (GUS) is a human monoclonal antibody targeting the interleukin-23p19-subunit. It has demonstrated efficacy at Week 24 in the Phase IIIb COSMOS clinical trial of patients with active psoriatic arthritis (PsA) and inadequate response or intolerance to one or two tumour necrosis factor inhibitors (TNFis).1

Objectives

The aim of this post hoc analysis was to identify predictors of minimal disease activity (MDA) with GUS at Week 24 in patients with active PsA and inadequate response or intolerance to one or two TNFis.

Methods

A multiple logistic regression analysis was performed to identify potential predictors of MDA with GUS at Week 24 in TNFi-refractory patients with PsA. Odds ratios, 95% confidence intervals and p-values were calculated. Baseline characteristics assessed as predictors included age, sex, body mass index (BMI), C-reactive protein (CRP), other medication use and disease duration. Clinical features included tender and swollen joint counts (TJC/SJC), affected joint location, dactylitis, enthesitis, spondylitis, Psoriasis Area and Severity Index (PASI) score and psoriasis (PsO) localisation (Figure 1). Missing data for MDA at Week 24 were imputed as non-response; missing baseline values were imputed for two patients.

Figure 1.

Odds ratios and 95% CIs for potential predictors of minimal disease activity response to guselkumab 100 mg every 8 weeks at Week 24 in patients with PsA and an inadequate response or intolerance to one or two prior TNF inhibitors.

BMI, body mass index; CI, confidence interval; CRP, C-reactive protein; csDMARD, conventional systemic disease-modifying anti-rheumatic drug; HAQ-DI, Health Assessment Questionnaire - Disability Index; MDA, minimal disease activity; PASI, Psoriasis Area and Severity Index; PsA, psoriatic arthritis; PsO, psoriasis; TNF, tumour necrosis factor.

N=187 for all clinical features and baseline characteristics. Negative predictors are indicated by bold text and positive predictors by italicisation (p<0.05).

Results

Of the 187 patients in this study, 54.6% were women and the mean disease duration was 8.3 years. The patients had a mean TJC 0–68 of 21.0, a mean SJC 0–66 of 10.3, a mean PASI score of 11.6 and a mean BMI of 28.9. Furthermore, 67.9% had enthesitis and 35.8% had dactylitis at baseline. One prior TNFi had been received by 88.2% of patients, and two received by 11.8%. At Week 24, 17.1% of patients (32/187) achieved MDA. Wrist involvement (p=0.031) and scalp PsO (p=0.049) were positive predictors of MDA. Women were significantly less likely to achieve MDA (p=0.036) than men; other negative predictors included involvement of shoulder or small joints of the hand, and hand/foot PsO (all p<0.05). Age, BMI, CRP, TJC/SJC, HAQ-DI, PASI, spondylitis, enthesitis, dactylitis, other medication use and number of prior TNFis were not predictive of MDA (Figure 1).

Conclusion

Baseline characteristics and clinical features may be positively (wrist involvement, scalp PsO) or negatively (female sex, involvement of shoulder or small joints of the hand, hand/foot PsO) associated with achieving MDA with GUS at Week 24 in a TNFi-refractory population. Though the low patient number limits the generalisability of this analysis, assessment of Week 48 data may further elucidate potential predictors of MDA after longer-term treatment.

References

[1]Coates C et al. Ann Rheum Dis 2021; 0: 1–11.

Disclosure of Interests

William Tillett Speakers bureau:, Consultant of:, Grant/research support from: William Tillett has received research grants and consulting or speaker fees from AbbVie, Amgen, Celgene, Eli Lilly, Janssen, MSD, Novartis, Pfizer and UCB., Sarah Ohrndorf Speakers bureau: Sarah Ohrndorf has received speaker fees or travel expense reimbursements from AbbVie, BMS, Janssen, Novartis and Pfizer., Julio Ramírez Speakers bureau:, Consultant of: Julio Ramírez has received consulting or speaker fees from AbbVie, Amgen, Eli Lilly, Janssen, Novartis and UCB., Marlies Neuhold Shareholder of: Johnson & Johnson., Employee of: Janssen, Robert Wapenaar Shareholder of: Johnson & Johnson., Employee of: Janssen, Elke Theander Shareholder of: Johnson & Johnson., Employee of: Janssen, Christine CONTRE Shareholder of: Johnson & Johnson., Employee of: Janssen, Mohamed Sharaf Shareholder of: Johnson & Johnson., Employee of: Janssen, May Shawi Shareholder of: Johnson & Johnson., Employee of: Janssen, Marijn Vis Speakers bureau:, Consultant of:, Grant/research support from: Marijn Vis has received research grants and consulting or speaker fees from AbbVie, Amgen, Eli Lilly, Janssen, Novartis, Pfizer, UCB and the Dutch Arthritis Foundation.

Quantifying Differences Between Affine and Nonlinear Spatial Normalization of FP-CIT Spect Images

Spatial normalization helps us to compare quantitatively two or more input brain scans. Although using an affine normalization approach preserves the anatomical structures, the neuroimaging field is more common to find works that make use of nonlinear transformations. The main reason is that they facilitate a voxel-wise comparison, not only when studying functional images but also when comparing MRI scans given that they fit better to a reference template. However, the amount of bias introduced by the nonlinear transformations can potentially alter the final outcome of a diagnosis especially when studying functional scans for neurological disorders like Parkinson's Disease. In this context, we have tried to quantify the bias introduced by the affine and the nonlinear spatial registration of FP-CIT SPECT volumes of healthy control subjects and patients with PD. For that purpose, we calculated the deformation fields of each participant and applied these deformation fields to a 3D-grid. As the space between the edges of small cubes comprising the grid change, we can quantify which parts from the brain have been enlarged, compressed or just remain the same. When the nonlinear approach is applied, scans from PD patients show a region near their striatum very similar in shape to that of healthy subjects. This artificially increases the interclass separation between patients with PD and healthy subjects as the local intensity is decreased in the latter region, and leads machine learning systems to biased results due to the artificial information introduced by these deformations.

Tiled Sparse Coding in Eigenspaces for Image Classification

The automation in the diagnosis of medical images is currently a challenging task. The use of Computer Aided Diagnosis (CAD) systems can be a powerful tool for clinicians, especially in situations when hospitals are overflowed. These tools are usually based on artificial intelligence (AI), a field that has been recently revolutionized by deep learning approaches. blackThese alternatives usually obtain a large performance based on complex solutions, leading to a high computational cost and the need of having large databases. In this work, we propose a classification framework based on sparse coding. Images are blackfirst partitioned into different tiles, and a dictionary is built after applying PCA to these tiles. The original signals are then transformed as a linear combination of the elements of the dictionary. blackThen, they are reconstructed by iteratively deactivating the elements associated with each component. Classification is finally performed employing as features the subsequent reconstruction errors. Performance is evaluated in a real context where distinguishing between four different pathologies: control versus bacterial pneumonia versus viral pneumonia versus COVID-19. blackOur system differentiates between pneumonia patients and controls with an accuracy of 97.74%, whereas in the 4-class context the accuracy is 86.73%. The excellent results and the pioneering use of sparse coding in this scenario evidence that our proposal can assist clinicians when their workload is high.

Homogeneous nucleation of NaCl in supersaturated solutions

The seeding method is an approximate approach to investigate nucleation that combines molecular dynamics simulations with classical nucleation theory. Recently, this technique has been successfully implemented in a broad range of nucleation studies. However, its accuracy is subject to the arbitrary choice of the order parameter threshold used to distinguish liquid-like from solid-like molecules. We revisit here the crystallization of NaCl from a supersaturated brine solution and show that consistency between seeding and rigorous methods, like Forward Flux Sampling (from previous work) or spontaneous crystallization (from this work), is achieved by following a mislabelling criterion to select such threshold (i.e. equaling the fraction of the mislabelled particles in the bulk parent and nucleating phases). This work supports the use of seeding to obtain fast and reasonably accurate nucleation rate estimates and the mislabelling criterion as one giving the relevant cluster size for classical nucleation theory in crystallization studies.

Photodynamic therapy of cutaneous T-cell lymphoma cell lines mediated by 5-aminolevulinic acid and derivatives

The delta-amino acid 5-aminolevulinic acid (ALA), is the precursor of the endogenous photosensitiser Protoporphyrin IX (PpIX), and is currently approved for Photodynamic Therapy (PDT) of certain superficial cancers. However, ALA-PDT is not very effective in diseases in which T-cells play a significant role. Cutaneous T-cell lymphomas (CTCL) is a group of non-Hodgkin malignant diseases, which includes mycosis fungoides (MF) and Sézary syndrome (SS). In previous work, we have designed new ALA esters synthesised by three-component Passerini reactions, and some of them showed higher performance as compared to ALA. This work aimed to determine the efficacy as pro-photosensitisers of five new ALA esters of 2-hydroxy-N-arylacetamides (1f, 1 g, 1 h, 1i and 1 k) of higher lipophilicity than ALA in Myla cells of MF and HuT-78 cells of SS. We have also tested its effectiveness against ALA and the already marketed ALA methyl ester (Me-ALA) and ALA hexyl ester (He-ALA). Both cell Myla and SS cells were effectively and equally photoinactivated by ALA-PDT. Besides, the concentration of ALA required to induce half the maximal porphyrin synthesis was 209 μM for Myla and 169 μM for HuT-78 cells. As a criterion of efficacy, we calculated the concentration of the ALA derivatives necessary to induce half the plateau porphyrin values obtained from ALA. These values were achieved at concentrations 4 and 12 times lower compared to ALA, according to the derivative used. For He-ALA, concentrations were 24 to 25 times lower than required for ALA for inducing comparable porphyrin synthesis in both CTCL cells. The light doses for inducing 50% of cell death (LD50) for He-ALA, 1f, 1 g, 1 h and 1i were around 18 and 25 J/cm² for Myla and HuT-78 cells respectively, after exposure to 0.05 mM concentrations of the compounds. On the other hand, the LD50s for the compound 1 k were 40 and 57 J/cm² for Myla and HuT-78, respectively. In contrast, 0.05 mM of ALA and Me-ALA did not provoke photokilling since the concentration employed was far below the porphyrin saturation point for these compounds. Our results suggest the potential use of ALA derivatives for topical application in PDT treatment of MF and extracorporeal PDT for the depletion of activated T-cells in SS.

Identification of the Patterns Produced in the Offensive Sequences That End in a Goal in European Futsal

Victory is the ultimate aim in high performance sports; when it comes to team sports, the goal is the key that allows players to achieve that victory. This is the case with futsal which, due to its internal structure as well as the speed in the development of its game, makes the achievement of a goal not an isolated event, but rather more than one goal must be scored to achieve victory. The aim of the present study is to analyze the construction of offensive sequences that have resulted in goal-scoring in the two main European futsal leagues, the Spanish and the Italian, as well as to identify the patterns relating to offensive actions that have ended with a goal being scored. Observational methodology was used to develop the research and an ad hoc observation instrument (OAF-I) was developed for this purpose. The data was analyzed using inferential statistics as well as sequential analysis of delays in a diachronic analysis to identify the patterns of offensive actions. The results obtained enable recognition of a league’s idiosyncrasy patterns in goal-scoring in each of the leagues studied. The results obtained will allow experts to have a better understanding of how goals are scored and how to establish more specific training tasks, in both attack and defense.

Aerobic capacity as a protective factor for hypertension in Bogota’s soccer players

Background

In Colombia between 1998-2011 the 23.5% of deaths that were reported were from CardioVascular Disease (CVD), 12.4% were caused by hypertensive disease; well now physical activity has been reported as a protective factor for CVD and Hypertension (HT), those people who perform high levels of physical activity have a relative decrease in developing HT by 19%, however what happens when this physical activity takes place with a duration greater than 4 hours a day, with moderate and high intensities, becoming a sports practice, the same benefits or opposite effects would be had, so the objective of the study was to determine the relationship between aerobic capacity and blood pressure in soccer players in the city of Bogotá.

Methods

Quantitative cross-sectional research; blood pressure of 64 players and the aerobic capacity was assessed using the Legger test (VO2 Max).

Results

It was evidenced that 4.6% of the players have hypotension, 50.8% normotension, 30.8% prehypertension and 12.3% stage I hypertension; As regards for VO2 max, 7.7% had an excellent capacity, 73.8% good and 12.3% favorable, there was no relationship between the variables.

Conclusions

Soccer players, although they have good levels of VO2 max, they do not present a decrease in blood pressure data, being mostly within a normal range.

Key messages

Although physical activity is a protective factor for HT. Soccer training does not show a decrease in blood pressure, possibly could be a risk factor for HT and CVD.

FRI0042 DISCREPANCIES BETWEEN RAPID3 AND DAS28 IN RHEUMATOID ARTHRITIS PATIENTS IN REMISSION OR LOW DISEASE ACTIVITY RECEIVING TNF INHIBITORS: WHAT IS THE ROLE OF THE INFLAMMATION BIOMARKERS?

Background:

Patients and Rheumatologist often differ in their perception of RA disease activity. Remission or low disease activity should be the treatment target in RA, patients should be included in treatment decisions.

Objectives:

To identify factors influencing patient’s self-reported disease activity by RAPID3 test.

Methods:

47 RA patients in remission or low disease activity by DAS28ESR (DAS28ESR ≤ 3.2) receiving TNFi (etanercept, adalimumab and infliximab) stratified their disease activity by RAPID3, then two patients’ groups were defined:target group(RAPID3 with remission 0-3 or low disease activity 3.1-6),non-target group(RAPID3 with moderate 6.1-12 or high disease activity >12). Demographic data, disease duration, autoantibody status, radiological data, concomitant csDMARD therapy was collected. Laboratory measurements included CRP, ESR, calprotectin serum levels, TNFi trough serum levels, and antidrug antibodies (enzyme-linked immunosorbent assay (ELISA) test kit (Calprolab™ Calpro AS, Oslo, Norway, and Promonitor®, Progenika SA, Spain, respectively) according to the manufacturers’ protocol. Pearson´s correlations coefficients were used to identify variables correlating with RAPID3 score. Mixed-effects analyses of covariance (ANCOVAs) models were used to identify factors influencing RAPID3 score.

Results:

Patients in “target group”have shown a significant lower TJC, pain by VAS 0-10mm, and calprotectin serum levels, but higher TNFi serum trough levels in comparison to “non-target group”. When patients were classified according to RAPID 3 categories, patients in “remission” have shown lower calprotectin serum levels than those classified as in “high disease activity” (0.94 (4.88-0.14) vs. 4.57 (7.97-1.25),p=0.001, respectively). Accordingly, when classified according to pain by VAS 0-10mm, patients with low levels of pain had lower calprotectin serum levels vs. those with severe pain (1.43 (6.33-10.14) vs. 5.16 (8.80-1.25),p=0.009, respectively). When distributed according to PGA (1=very good, 2=good, 3=regular, 4=bad, 5=very bad) patients in “very good” group had lower mean of calprotectin serum levels than those in “very bad” group (0.94 (4.88-0.14) vs. 4.57 (7.97-1.25),p=0.001, respectively). PGA and Pain VAS have shown a strong correlation with RAPID 3 (R20.978, and 0.834,p=0.001, respectively), while calprotectin and TNFi serum trough levels showed a moderate correlation (R20.311, and 0.372,p=0.005, respectively). The multivariate adjusted analysis showed a significant association between Pain and RAPID3 (p<0.001) according to the different covariates (age, gender, anti-CCP positivity, time in remission, SJC, TJC, DAS28ESR). In addition, calprotectin and TNFi trough serum levels were associated with RAPID 3 (p<0.005). Backward selection of variables did not substantially modify the association between RAPID 3 and pain, calprotectin and TNFi trough serum levels.

Conclusion:

61.7% of RA patients undergoing TNFi classified as in remission or low disease activity by DAS28ESR, self-reported their disease activity as moderate or high by RAPID3. The most significant factor influencing patient’s perception of disease activity is pain (pain VAS and TJC). However, inflammation markers (calprotectin, TNFi serum trough levels) remain statistically significant after fully adjustment by different confounders. Thus, therapies improving these three domains will have a larger impact in patient´s perception of disease activity.

References:

[1]Studenic P, et al. Arthritis Rheum. 2012;64:2814-23.

Disclosure of Interests:

Jose Inciarte-Mundo Employee of: Eli Lilly, Speakers bureau: Abbvie, Eli Lilly, BMS, Roche and Pfizer, Rosa Morlà Speakers bureau: Abbvie, Eli Lilly, BMS, Roche and Pfizer, Beatriz Frade-Sosa: None declared, Julio Ramírez Speakers bureau: Abbvie, Eli Lilly, BMS, Roche, Novartis and Pfizer, Raul Castellanos-Moreira Speakers bureau: Lilly, MSD, Sanofi, UCB, Virginia Ruiz Speakers bureau: Lilly, Pfizer, Juan de Dios Cañete: None declared, José Gomez Puerta Speakers bureau: Abbvie, Eli Lilly, BMS, Roche and Pfizer, Raimón Sanmartí Speakers bureau: Abbvie, Eli Lilly, BMS, Roche and Pfizer

Autosomal Dominantly Inherited Alzheimer Disease: Analysis of genetic subgroups by Machine Learning

Despite subjects with Dominantly-Inherited Alzheimer's Disease (DIAD) represent less than 1% of all Alzheimer's Disease (AD) cases, the Dominantly Inherited Alzheimer Network (DIAN) initiative constitutes a strong impact in the understanding of AD disease course with special emphasis on the presyptomatic disease phase. Until now, the 3 genes involved in DIAD pathogenesis (PSEN1, PSEN2 and APP) have been commonly merged into one group (Mutation Carriers, MC) and studied using conventional statistical analysis. Comparisons between groups using null-hypothesis testing or longitudinal regression procedures, such as the linear-mixed-effects models, have been assessed in the extant literature. Within this context, the work presented here performs a comparison between different groups of subjects by considering the 3 genes, either jointly or separately, and using tools based on Machine Learning (ML). This involves a feature selection step which makes use of ANOVA followed by Principal Component Analysis (PCA) to determine which features would be realiable for further comparison purposes. Then, the selected predictors are classified using a Support-Vector-Machine (SVM) in a nested k-Fold cross-validation resulting in maximum classification rates of 72-74% using PiB PET features, specially when comparing asymptomatic Non-Carriers (NC) subjects with asymptomatic PSEN1 Mutation-Carriers (PSEN1-MC). Results obtained from these experiments led to the idea that PSEN1-MC might be considered as a mixture of two different subgroups including: a first group whose patterns were very close to NC subjects, and a second group much more different in terms of imaging patterns. Thus, using a k-Means clustering algorithm it was determined both subgroups and a new classification scenario was conducted to validate this process. The comparison between each subgroup vs. NC subjects resulted in classification rates around 80% underscoring the importance of considering DIAN as an heterogeneous entity.

Usefulness of Dual-Point Amyloid PET Scans in Appropriate Use Criteria: A Multicenter Study

BACKGROUND

Biomarkers of neurodegeneration play a major role in the diagnosis of Alzheimer's disease (AD). Information on both amyloid-β accumulation, e.g., from amyloid positron emission tomography (PET), and downstream neuronal injury, e.g., from 18F-fluorodeoxyglucose (FDG) PET, would ideally be obtained in a single procedure.

OBJECTIVE

On the basis that the parallelism between brain perfusion and glucose metabolism is well documented, the objective of this work is to evaluate whether brain perfusion estimated in a dual-point protocol of 18F-florbetaben (FBB) PET can be a surrogate of FDG PET in appropriate use criteria (AUC) for amyloid PET.

METHODS

This study included 47 patients fulfilling international AUC for amyloid PET. FDG PET, early FBB (pFBB) PET (0-10 min post injection), and standard FBB (sFBB) PET (90-110 min post injection) scans were acquired. Results of clinical subjective reports and of quantitative region of interest (ROI)-based analyses were compared between procedures using statistical techniques such as Pearson's correlation coefficients and t-tests.

RESULTS

pFBB and FDG visual reports on the 47 patients showed good agreement (k  >  0.74); ROI quantitative analysis indicated that both data modalities are highly correlated; and the t-test analysis does not reject the null hypothesis that data from pFBB and FDG examinations comes from independent random samples from normal distributions with equal means and variances.

CONCLUSIONS

A good agreement was found between pFBB and FDG data as obtained by subjective visual and quantitative analyses. Dual-point FBB PET scans could offer complementary information (similar to that from FDG PET and FBB PET) in a single procedure, considering pFBB as a surrogate of FDG.

Alzheimer's Disease Computer-Aided Diagnosis: Histogram-Based Analysis of Regional MRI Volumes for Feature Selection and Classification

This paper proposes a novel fully automatic computer-aided diagnosis (CAD) system for the early detection of Alzheimer's disease (AD) based on supervised machine learning methods. The novelty of the approach, which is based on histogram analysis, is twofold: 1) a feature extraction process that aims to detect differences in brain regions of interest (ROIs) relevant for the recognition of subjects with AD and 2) an original greedy algorithm that predicts the severity of the effects of AD on these regions. This algorithm takes account of the progressive nature of AD that affects the brain structure with different levels of severity, i.e., the loss of gray matter in AD is found first in memory-related areas of the brain such as the hippocampus. Moreover, the proposed feature extraction process generates a reduced set of attributes which allows the use of general-purpose classification machine learning algorithms. In particular, the proposed feature extraction approach assesses the ROI image separability between classes in order to identify the ones with greater discriminant power. These regions will have the highest influence in the classification decision at the final stage. Several experiments were carried out on segmented magnetic resonance images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) in order to show the benefits of the overall method. The proposed CAD system achieved competitive classification results in a highly efficient and straightforward way.

Atlas-Based Classification Algorithms for Identification of Informative Brain Regions in fMRI Data

Multi-voxel pattern analysis (MVPA) has been successfully applied to neuroimaging data due to its larger sensitivity compared to univariate traditional techniques. Searchlight is the most widely employed approach to assign functional value to different regions of the brain. However, its performance depends on the size of the sphere, which can overestimate the region of activation when a large sphere size is employed. In the current study, we examined the validity of two different alternatives to Searchlight: an atlas-based local averaging method (ABLA, Schrouff et al. Neuroinformatics 16, 117-143, 2013a) and a Multi-Kernel Learning (MKL, Rakotomamonjy et al. Journal of Machine Learning 9, 2491-2521, 2008) approach, in a scenario where the goal is to find the informative brain regions that support certain mental operations. These methods employ weights to measure the informativeness of a brain region and highly reduce the large computational cost that Searchlight entails. We evaluated their performance in two different scenarios where the differential BOLD activation between experimental conditions was large vs. small, and employed nine different atlases to assess the influence of diverse brain parcellations. Results show that both methods were able to localize informative regions when differences between conditions were large, demonstrating a large sensitivity and stability in the identification of regions across atlases. Moreover, the sign of the weights reported by these methods provided the directionality of univariate approaches. However, when differences were small, only ABLA localized informative regions. Thus, our results show that atlas-based methods are useful alternatives to Searchlight, but that the nature of the classification to perform should be taken into account when choosing the specific method to implement.

A Machine Learning Approach to Reveal the NeuroPhenotypes of Autisms

Although much research has been undertaken, the spatial patterns, developmental course, and sexual dimorphism of brain structure associated with autism remains enigmatic. One of the difficulties in investigating differences between the sexes in autism is the small sample sizes of available imaging datasets with mixed sex. Thus, the majority of the investigations have involved male samples, with females somewhat overlooked. This paper deploys machine learning on partial least squares feature extraction to reveal differences in regional brain structure between individuals with autism and typically developing participants. A four-class classification problem (sex and condition) is specified, with theoretical restrictions based on the evaluation of a novel upper bound in the resubstitution estimate. These conditions were imposed on the classifier complexity and feature space dimension to assure generalizable results from the training set to test samples. Accuracies above [Formula: see text] on gray and white matter tissues estimated from voxel-based morphometry (VBM) features are obtained in a sample of equal-sized high-functioning male and female adults with and without autism ([Formula: see text], [Formula: see text]/group). The proposed learning machine revealed how autism is modulated by biological sex using a low-dimensional feature space extracted from VBM. In addition, a spatial overlap analysis on reference maps partially corroborated predictions of the “extreme male brain” theory of autism, in sexual dimorphic areas.

Parkinson's Disease Detection Using Isosurfaces-Based Features and Convolutional Neural Networks

Computer aided diagnosis systems based on brain imaging are an important tool to assist in the diagnosis of Parkinson's disease, whose ultimate goal is the detection by automatic recognizing of patterns that characterize the disease. In recent times Convolutional Neural Networks (CNN) have proved to be amazingly useful for that task. The drawback, however, is that 3D brain images contain a huge amount of information that leads to complex CNN architectures. When these architectures become too complex, classification performances often degrades because the limitations of the training algorithm and overfitting. Thus, this paper proposes the use of isosurfaces as a way to reduce such amount of data while keeping the most relevant information. These isosurfaces are then used to implement a classification system which uses two of the most well-known CNN architectures, LeNet and AlexNet, to classify DaTScan images with an average accuracy of 95.1% and AUC = 97%, obtaining comparable (slightly better) values to those obtained for most of the recently proposed systems. It can be concluded therefore that the computation of isosurfaces reduces the complexity of the inputs significantly, resulting in high classification accuracies with reduced computational burden.

Assisted Diagnosis of Parkinsonism Based on the Striatal Morphology

Parkinsonism is a clinical syndrome characterized by the progressive loss of striatal dopamine. Its diagnosis is usually corroborated by neuroimaging data such as DaTSCAN neuroimages that allow visualizing the possible dopamine deficiency. During the last decade, a number of computer systems have been proposed to automatically analyze DaTSCAN neuroimages, eliminating the subjectivity inherent to the visual examination of the data. In this work, we propose a computer system based on machine learning to separate Parkinsonian patients and control subjects using the size and shape of the striatal region, modeled from DaTSCAN data. First, an algorithm based on adaptative thresholding is used to parcel the striatum. This region is then divided into two according to the brain hemisphere division and characterized with 152 measures, extracted from the volume and its three possible 2-dimensional projections. Afterwards, the Bhattacharyya distance is used to discard the least discriminative measures and, finally, the neuroimage category is estimated by means of a Support Vector Machine classifier. This method was evaluated using a dataset with 189 DaTSCAN neuroimages, obtaining an accuracy rate over 94%. This rate outperforms those obtained by previous approaches that use the intensity of each striatal voxel as a feature.

Empirical Functional PCA for 3D Image Feature Extraction Through Fractal Sampling

Medical image classification is currently a challenging task that can be used to aid the diagnosis of different brain diseases. Thus, exploratory and discriminative analysis techniques aiming to obtain representative features from the images play a decisive role in the design of effective Computer Aided Diagnosis (CAD) systems, which is especially important in the early diagnosis of dementia. In this work, we present a technique that allows using specific time series analysis techniques with 3D images. This is achieved by sampling the image using a fractal-based method which preserves the spatial relationship among voxels. In addition, a method called Empirical functional PCA (EfPCA) is presented, which combines Empirical Mode Decomposition (EMD) with functional PCA to express an image in the space spanned by a basis of empirical functions, instead of using components computed by a predefined basis as in Fourier or Wavelet analysis. The devised technique has been used to classify images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Parkinson Progression Markers Initiative (PPMI), achieving accuracies up to 93% and 92% differential diagnosis tasks (AD versus controls and PD versus Controls, respectively). The results obtained validate the method, proving that the information retrieved by our methodology is significantly linked to the diseases.

Using deep neural networks along with dimensionality reduction techniques to assist the diagnosis of neurodegenerative disorders

The analysis of neuroimaging data is frequently used to assist the diagnosis of neurodegenerative disorders such as Alzheimer's disease (AD) or Parkinson's disease (PD) and has become a routine procedure in the clinical practice. During the past decade, the pattern recognition community has proposed a number of machine learning-based systems that automatically analyse neuroimaging data in order to improve the diagnosis. However, the high dimensionality of the data is still a challenge and there is room for improvement. The development of novel classification frameworks as TensorFlow, recently released as open source by Google Inc., represents an opportunity to continue evolving these systems. In this work, we demonstrate several computer-aided diagnosis (CAD) systems based on Deep Neural Networks that improve the diagnosis for AD and PD and outperform those based on classical classifiers. In order to address the small sample size problem we evaluate two dimensionality reduction algorithms based on Principal Component Analysis and Non-Negative Matrix Factorization (NNMF), respectively. The performance of developed CAD systems is assessed using 4 datasets with neuroimaging data of different modalities.

Influence of activation pattern estimates and statistical significance tests in fMRI decoding analysis

The use of Multi-Voxel Pattern Analysis (MVPA) has increased considerably in recent functional magnetic resonance imaging (fMRI) studies. A crucial step consists in the choice of a method for the estimation of responses. However, a systematic comparison of the different estimation alternatives and their adequacy to predominant experimental design is missing. In the current study we compared three pattern estimation methods: Least-Squares Unitary (LSU), based on run-wise estimation, Least-Squares All (LSA) and Least-Squares Separate (LSS), which rely on trial-wise estimation. We compared the efficiency of these methods in an experiment where sustained activity needed to be isolated from zero-duration events as well as in a block-design approach and in a event-related design. We evaluated the sensitivity of the t-test in comparison with two non-parametric methods based on permutation testing: one proposed in Stelzer et al. (2013), equivalent to performing a permutation in each voxel separately and the Threshold-Free Cluster Enhancement. LSS resulted the most accurate approach to address the large overlap of signal among close events in the event-related designs. We found a larger sensitivity of Stelzer's method in all settings, especially in the event-related designs, where voxels close to surpass the statistical threshold with the other approaches were now marked as informative regions. Our results provide evidence that LSS is the most accurate approach for unmixing events with different duration and large overlap of signal. This is consistent with previous studies showing that LSS handles large collinearity better than other methods. Moreover, Stelzer's potentiates this better estimation with its large sensitivity.

Robust Ensemble Classification Methodology for I123-Ioflupane SPECT Images and Multiple Heterogeneous Biomarkers in the Diagnosis of Parkinson's Disease

In last years, several approaches to develop an effective Computer-Aided-Diagnosis (CAD) system for Parkinson's Disease (PD) have been proposed. Most of these methods have focused almost exclusively on brain images through the use of Machine-Learning algorithms suitable to characterize structural or functional patterns. Those patterns provide enough information about the status and/or the progression at intermediate and advanced stages of Parkinson's Disease. Nevertheless this information could be insufficient at early stages of the pathology. The Parkinson's Progression Markers Initiative (PPMI) database includes neurological images along with multiple biomedical tests. This information opens up the possibility of comparing different biomarker classification results. As data come from heterogeneous sources, it is expected that we could include some of these biomarkers in order to obtain new information about the pathology. Based on that idea, this work presents an Ensemble Classification model with Performance Weighting. This proposal has been tested comparing Healthy Control subjects (HC) vs. patients with PD (considering both PD and SWEDD labeled subjects as the same class). This model combines several Support-Vector-Machine (SVM) with linear kernel classifiers for different biomedical group of tests—including CerebroSpinal Fluid (CSF), RNA, and Serum tests—and pre-processed neuroimages features (Voxels-As-Features and a list of defined Morphological Features) from PPMI database subjects. The proposed methodology makes use of all data sources and selects the most discriminant features (mainly from neuroimages). Using this performance-weighted ensemble classification model, classification results up to 96% were obtained.

Convolutional Neural Networks for Neuroimaging in Parkinson's Disease: Is Preprocessing Needed?

Spatial and intensity normalizations are nowadays a prerequisite for neuroimaging analysis. Influenced by voxel-wise and other univariate comparisons, where these corrections are key, they are commonly applied to any type of analysis and imaging modalities. Nuclear imaging modalities such as PET-FDG or FP-CIT SPECT, a common modality used in Parkinson's disease diagnosis, are especially dependent on intensity normalization. However, these steps are computationally expensive and furthermore, they may introduce deformations in the images, altering the information contained in them. Convolutional neural networks (CNNs), for their part, introduce position invariance to pattern recognition, and have been proven to classify objects regardless of their orientation, size, angle, etc. Therefore, a question arises: how well can CNNs account for spatial and intensity differences when analyzing nuclear brain imaging? Are spatial and intensity normalizations still needed? To answer this question, we have trained four different CNN models based on well-established architectures, using or not different spatial and intensity normalization preprocessings. The results show that a sufficiently complex model such as our three-dimensional version of the ALEXNET can effectively account for spatial differences, achieving a diagnosis accuracy of 94.1% with an area under the ROC curve of 0.984. The visualization of the differences via saliency maps shows that these models are correctly finding patterns that match those found in the literature, without the need of applying any complex spatial normalization procedure. However, the intensity normalization - and its type - is revealed as very influential in the results and accuracy of the trained model, and therefore must be well accounted.

Using CT Data to Improve the Quantitative Analysis of 18F-FBB PET Neuroimages

¹⁸F-FBB PET is a neuroimaging modality that is been increasingly used to assess brain amyloid deposits in potential patients with Alzheimer's disease (AD). In this work, we analyze the usefulness of these data to distinguish between AD and non-AD patients. A dataset with ¹⁸F-FBB PET brain images from 94 subjects diagnosed with AD and other disorders was evaluated by means of multiple analyses based on t-test, ANOVA, Fisher Discriminant Analysis and Support Vector Machine (SVM) classification. In addition, we propose to calculate amyloid standardized uptake values (SUVs) using only gray-matter voxels, which can be estimated using Computed Tomography (CT) images. This approach allows assessing potential brain amyloid deposits along with the gray matter loss and takes advantage of the structural information provided by most of the scanners used for PET examination, which allow simultaneous PET and CT data acquisition. The results obtained in this work suggest that SUVs calculated according to the proposed method allow AD and non-AD subjects to be more accurately differentiated than using SUVs calculated with standard approaches.

Ensemble of random forests One vs. Rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares

BACKGROUND

Alzheimer's disease (AD) is the most common cause of dementia in the elderly and affects approximately 30 million individuals worldwide. Mild cognitive impairment (MCI) is very frequently a prodromal phase of AD, and existing studies have suggested that people with MCI tend to progress to AD at a rate of about 10-15% per year. However, the ability of clinicians and machine learning systems to predict AD based on MRI biomarkers at an early stage is still a challenging problem that can have a great impact in improving treatments.

METHOD

The proposed system, developed by the SiPBA-UGR team for this challenge, is based on feature standardization, ANOVA feature selection, partial least squares feature dimension reduction and an ensemble of One vs. Rest random forest classifiers. With the aim of improving its performance when discriminating healthy controls (HC) from MCI, a second binary classification level was introduced that reconsiders the HC and MCI predictions of the first level.

RESULTS

The system was trained and evaluated on an ADNI datasets that consist of T1-weighted MRI morphological measurements from HC, stable MCI, converter MCI and AD subjects. The proposed system yields a 56.25% classification score on the test subset which consists of 160 real subjects.

COMPARISON WITH EXISTING METHOD(S)

The classifier yielded the best performance when compared to: (i) One vs. One (OvO), One vs. Rest (OvR) and error correcting output codes (ECOC) as strategies for reducing the multiclass classification task to multiple binary classification problems, (ii) support vector machines, gradient boosting classifier and random forest as base binary classifiers, and (iii) bagging ensemble learning.

CONCLUSIONS

A robust method has been proposed for the international challenge on MCI prediction based on MRI data. The system yielded the second best performance during the competition with an accuracy rate of 56.25% when evaluated on the real subjects of the test set.

A Heavy Tailed Expectation Maximization Hidden Markov Random Field Model with Applications to Segmentation of MRI

A wide range of segmentation approaches assumes that intensity histograms extracted from magnetic resonance images (MRI) have a distribution for each brain tissue that can be modeled by a Gaussian distribution or a mixture of them. Nevertheless, intensity histograms of White Matter and Gray Matter are not symmetric and they exhibit heavy tails. In this work, we present a hidden Markov random field model with expectation maximization (EM-HMRF) modeling the components using the α-stable distribution. The proposed model is a generalization of the widely used EM-HMRF algorithm with Gaussian distributions. We test the α-stable EM-HMRF model in synthetic data and brain MRI data. The proposed methodology presents two main advantages: Firstly, it is more robust to outliers. Secondly, we obtain similar results than using Gaussian when the Gaussian assumption holds. This approach is able to model the spatial dependence between neighboring voxels in tomographic brain MRI.

Functional Brain Imaging Synthesis Based on Image Decomposition and Kernel Modeling: Application to Neurodegenerative Diseases

The rise of neuroimaging in research and clinical practice, together with the development of new machine learning techniques has strongly encouraged the Computer Aided Diagnosis (CAD) of different diseases and disorders. However, these algorithms are often tested in proprietary datasets to which the access is limited and, therefore, a direct comparison between CAD procedures is not possible. Furthermore, the sample size is often small for developing accurate machine learning methods. Multi-center initiatives are currently a very useful, although limited, tool in the recruitment of large populations and standardization of CAD evaluation. Conversely, we propose a brain image synthesis procedure intended to generate a new image set that share characteristics with an original one. Our system focuses on nuclear imaging modalities such as PET or SPECT brain images. We analyze the dataset by applying PCA to the original dataset, and then model the distribution of samples in the projected eigenbrain space using a Probability Density Function (PDF) estimator. Once the model has been built, we can generate new coordinates on the eigenbrain space belonging to the same class, which can be then projected back to the image space. The system has been evaluated on different functional neuroimaging datasets assessing the: resemblance of the synthetic images with the original ones, the differences between them, their generalization ability and the independence of the synthetic dataset with respect to the original. The synthetic images maintain the differences between groups found at the original dataset, with no significant differences when comparing them to real-world samples. Furthermore, they featured a similar performance and generalization capability to that of the original dataset. These results prove that these images are suitable for standardizing the evaluation of CAD pipelines, and providing data augmentation in machine learning systems -e.g. in deep learning-, or even to train future professionals at medical school.

Preprocessing of 18F-DMFP-PET Data Based on Hidden Markov Random Fields and the Gaussian Distribution

¹⁸F-DMFP-PET is an emerging neuroimaging modality used to diagnose Parkinson's disease (PD) that allows us to examine postsynaptic dopamine D_2/3 receptors. Like other neuroimaging modalities used for PD diagnosis, most of the total intensity of ¹⁸F-DMFP-PET images is concentrated in the striatum. However, other regions can also be useful for diagnostic purposes. An appropriate delimitation of the regions of interest contained in ¹⁸F-DMFP-PET data is crucial to improve the automatic diagnosis of PD. In this manuscript we propose a novel methodology to preprocess ¹⁸F-DMFP-PET data that improves the accuracy of computer aided diagnosis systems for PD. First, the data were segmented using an algorithm based on Hidden Markov Random Field. As a result, each neuroimage was divided into 4 maps according to the intensity and the neighborhood of the voxels. The maps were then individually normalized so that the shape of their histograms could be modeled by a Gaussian distribution with equal parameters for all the neuroimages. This approach was evaluated using a dataset with neuroimaging data from 87 parkinsonian patients. After these preprocessing steps, a Support Vector Machine classifier was used to separate idiopathic and non-idiopathic PD. Data preprocessed by the proposed method provided higher accuracy results than the ones preprocessed with previous approaches.

Comparison of Effectiveness and Sensitivity Using Two In-Office Bleaching Protocols for a 6% Hydrogen Peroxide Gel in a Randomized Clinical Trial

Objective:

The aim of this blinded and randomized clinical trial was to compare two application protocols (one 36-minute application vs three 12-minute applications). We then assessed the effectiveness of the bleaching and any increase in sensitivity that was induced by bleaching via a split-mouth design.

Methods and Materials:

Thirty patients were treated. One group had a half arch of teeth treated with a traditional application protocol (group A: 3 × 12 minutes for two sessions). The other received an abbreviated protocol (group B: 1 × 36 minutes over two sessions). Two sessions were appointed with a two-day interval between them. The tooth color was registered at each session, as well as one week and one month after completing the treatment via a spectrophotometer. This measured L*, a*, and b*. This was also evaluated subjectively using the VITA classical A1-D4 guide and VITA Bleachedguide 3D-MASTER. Tooth sensitivity was registered according to the visual analogue scale (VAS) scale. Tooth color variation and sensitivity were compared between groups.

Results:

Both treatments changed tooth color vs baseline. The ΔE* = 5.71 ± 2.62 in group A, and ΔE* = 4.93 ± 2.09 in group B one month after completing the bleaching (p=0.20). No statistical differences were seen via subjective evaluations. There were no differences in tooth sensitivity between the groups. The absolute risk of sensitivity reported for both groups was 6.25% (p=0.298). The intensity by VAS was mild (p=1.00).

Conclusions:

We used hydrogen peroxide (6%) that was light activated with a hybrid LED/laser and two different protocols (one 36-minute application vs three 12-minute applications each for two sessions). These approaches were equally effective. There were no differences in absolute risk of sensitivity; both groups reported mild sensitivity.

Multivariate Analysis of 18F-DMFP PET Data to Assist the Diagnosis of Parkinsonism

An early and differential diagnosis of parkinsonian syndromes still remains a challenge mainly due to the similarity of their symptoms during the onset of the disease. Recently, ¹⁸F-Desmethoxyfallypride (DMFP) has been suggested to increase the diagnostic precision as it is an effective radioligand that allows us to analyze post-synaptic dopamine D_2/3 receptors. Nevertheless, the analysis of these data is still poorly covered and its use limited. In order to address this challenge, this paper shows a novel model to automatically distinguish idiopathic parkinsonism from non-idiopathic variants using DMFP data. The proposed method is based on a multiple kernel support vector machine and uses the linear version of this classifier to identify some regions of interest: the olfactory bulb, thalamus, and supplementary motor area. We evaluated the proposed model for both, the binary separation of idiopathic and non-idiopathic parkinsonism and the multigroup separation of parkinsonian variants. These systems achieved accuracy rates higher than 70%, outperforming DaTSCAN neuroimages for this purpose. In addition, a system that combined DaTSCAN and DMFP data was assessed.