Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging.

BACKGROUND AND OBJECTIVES: Dyslexia is a disorder of neurological origin which affects the learning of those who suffer from it, mainly children, and causes difficulty in reading and writing. When undiagnosed, dyslexia leads to intimidation and frustration of the affected children and also of their family circles. In case no early intervention is given, children may reach high school with serious achievement gaps. Hence, early detection and intervention services for dyslexic students are highly important and recommended in order to support children in developing a positive self-esteem and reaching their maximum academic capacities. This paper presents a new approach for automatic recognition of children with dyslexia using functional magnetic resonance Imaging. METHODS: Our proposed system is composed of a sequence of preprocessing steps to retrieve the brain activation areas during three different reading tasks. Conversion to Nifti volumes, adjustment of head motion, normalization and smoothing transformations were performed on the fMRI scans in order to bring all the subject brains into one single model which will enable voxels comparison between each subject. Subsequently, using Statistical Parametric Maps (SPMs), a total of 165 3D volumes containing brain activation of 55 children were created. The classification of these volumes was handled using three parallel 3D Convolutional Neural Network (3D CNN), each corresponding to a brain activation during one reading task, and concatenated in the last two dense layers, forming a single architecture devoted to performing optimized detection of dyslexic brain activation. Additionally, we used 4-fold cross validation method in order to assess the generalizability of our model and control overfitting. RESULTS: Our approach has achieved an overall average classification accuracy of 72.73%, sensitivity of 75%, specificity of 71.43%, precision of 60% and an F1-score of 67% in dyslexia detection. CONCLUSIONS: The proposed system has demonstrated that the recognition of dyslexic children is feasible using deep learning and functional magnetic resonance Imaging when performing phonological and orthographic reading tasks.

Health-related quality of life and multimorbidity in community-dwelling telecare-assisted elders in the Basque Country.

INTRODUCTION: Multimorbidity is more common in the elderly population and negatively affects health-related quality of life (QoL). The aims of the study were to report the QoL of users of the Basque telecare public service (BTPS) and to establish its relationship with multimorbidity. METHODS: The EuroQol questionnaire was administered to 1125 users of the service. Their sociodemographic and healthcare characteristics were obtained from BTPS databases and the Basque healthcare service. Multiple regression analysis was performed on the overall questionnaire index to determine the effect of chronic diseases and sociodemographic. Moreover, the effects of the different diseases on specific dimensions of the test were explored by logistic regression. RESULTS: Of the users interviewed, 82% were women, 88% ≥75 years and 66% lived alone. The average of chronic pathologies was higher among men (5.3 vs. 4.6), for the lower age range and among those not living alone (P<0.001). For QoL, men and people aged over 84 obtained better scores (0.64 and 0.61, respectively). Worse QoL was associated with being a woman, multimorbidity, and living with one or more people. The existence of multimorbidity meant impaired QoL of 2.6 points for each additional disease over the overall score (P<0.001). CONCLUSIONS: This study reveals that for the population covered by BTPS the impact of chronic pathologies, multimorbidity and their social context affects QoL very diversely. These diverse social and healthcare needs of community-dwelling elders allow the development and implementation of personalised services, such as telecare that facilitate them to remain at home.

Reading networks in children with dyslexia compared to children with ocular motility disturbances revealed by fMRI.

Key PointsDyslexia is a neurological disorder with a genetic origin, but the underlying biological and cognitive causes are still being investigated.This study compares the brain activation pattern while reading in Spanish, a semitransparent language, in three groups of children: typically developing readers, dyslexic readers and readers with functional monocular vision.Based on our results Dyslexia would be a neurological disorder not related to vision impairments and would require a multidisciplinary treatment based on improving phonological awareness and language development. Developmental dyslexia is a neurological disorder the underlying biological and cognitive causes of which are still being investigated, a key point, because the findings will determine the best therapeutic approach to use. Using functional magnetic resonance imaging, we studied the brain activation pattern while reading in the language-related cortical areas from the two reading routes, phonological and orthographic, and the strength of their association with reading scores in 66 Spanish-speaking children aged 9-12 years divided into three groups: typically developing readers (controls), dyslexic readers and readers with monocular vision due to ocular motility disorders but with normal reading development, to assess whether (or not) the neuronal network for reading in children with dyslexia has similarities with that in children with impaired binocular vision due to ocular motility disorders. We found that Spanish-speaking children with dyslexia have a brain circuit for reading that differs from that in children with monocular vision. Individuals with dyslexia tend to hypoactivate some of the language-related areas in the left hemisphere engaged by the phonological route, especially the visual word form area and left Wernicke's area, and try to compensate this deficit by activating language-related areas related to the orthographic route, such as the anterior part of the visual word form area and the posterior part of both middle temporal gyri. That is, they seem to compensate for impairment in the phonological route through orthographic routes of both hemispheres. Our results suggest that ocular motility disturbances do not play a causal role in dyslexia. Dyslexia seems to be a neurological disorder that is unrelated to vision impairments and requires early recognition and multidisciplinary treatment, based on improving phonological awareness and language development, to achieve the best possible outcome.

Study of the intra-arterial distribution of Fe3O4 nanoparticles in a model of colorectal neoplasm induced in rat liver by MRI and spectrometry.

PURPOSE: To evaluate, in an experimental model, the reliability of MRI for determining whether a higher iron concentration was obtained in tumor tissue than in normal liver parenchyma after intra-arterial administration of Fe3O4 lipophilic nanoparticles. MATERIALS AND METHODS: WAG/RijCrl rats were inoculated in the left hepatic lobe with 25,000 syngeneic CC-531 colon adenocarcinoma cells, after which they were randomized into two groups: control (CG) and infused (IG). After confirming tumor induction, the IG rats received intra-arterial suspensions of Fe3O4 nanoparticles (2.6 mg) in Lipiodol® (0.15 mL). To calculate the iron concentration, [Fe], in the tumor and liver tissues of both groups of rats, measurements of signal intensity from the tumors, healthy liver tissue, and paravertebral muscles were made on a 1.5T MRI system in gradient-echo DP* and T2*-weighted sequences. In addition, samples were collected to quantify the [Fe] by inductively coupled plasma-mass spectrometry (ICP-MS), as well as for histological analysis. Statistical analysis was performed with non-parametric tests, and Bland-Altman plots were produced; P values <0.05 were considered significant. RESULTS: In the CG rats (n = 23), the mean [Fe] values estimated by MRI and ICP-MS were 13.2 µmol·g⁻¹ and 5.9 µmol·g⁻¹, respectively, in the tumors, and 19.0 µmol ·g⁻¹ and 11.7 µmol·g⁻¹, respectively, in the hepatic tissue. In the IG rats (n = 19), the values obtained by MRI and ICP-MS were 148.9 µmol·g⁻¹ and 9.4 µmol · g⁻¹, respectively, in the tumors, and 115.3 µmol·g⁻¹ and 11.6 µmol·g⁻¹, respectively, in the healthy liver tissue. The IG results revealed a clear disagreement between MRI and ICP-MS. In the comparative analysis between the groups regarding the [Fe] values obtained by ICP-MS, significant differences were found for the tumor samples (P < 0.001), but not for the hepatic tissue (P = 0.92). Under microscopy, scattered intravascular deposits of nanoparticles were observed, especially in the tumors. CONCLUSION: ICP-MS demonstrated significant uptake of exogenous iron in tumor tissue. MRI was useful for quantifying the [Fe] in the different tissues in the CG animals, but not in the IG animals. Although the irregular distribution of nanoparticles caused an important bias in the measurements obtained by MRI, the relative increase in iron content inside the tumor was suggested.

Overall breast density in MR mammography: diagnostic and therapeutic implications in breast cancer.

The objective of this study was to assess the efficacy of MR mammography (MRM) in evaluating breast cancer extent in women with fatty or dense breasts, and its contribution to the therapeutic approach. The authors reviewed 97 carcinomas detected in 93 women (both symptomatic and from screening) that were classified in two groups according to breast density pattern. Mammography, ultrasound (US), and MRM were performed to evaluate size, extension of the in situ component, presence of multifocal/multicentric disease, and contralateral involvement. Results obtained on mammography plus US were balanced against MRM, considering pathologic analysis as the gold standard. For fatty breasts (n=47), exact measurement was found on mammography plus US and on MRM alone in 70%, underestimation on mammography plus US 23.5% and on MRM 11% (P=0.005). For dense breasts (n=50), exact measurement was found on mammography plus US in 40% and on MRM alone 68%, underestimation on mammography plus US 52% and on MRM 10% (P=0.005). Overall, good correlation (R>0.71) was found between pathologic and clinical size with all imaging methods; nevertheless, when evaluating multifocal/multicentric disease, a poor correlation was observed between histologic assessment and mammography plus US (R=0.52), but it was excellent with regard to MRM (R=0.99). In fatty breasts, the combination of mammography and US allows for a precise assessment of tumoral extension. However, these results show that in dense breasts, MRM is superior to mammography plus US, suggesting that its systematic use in this group of patients is justifiable.