A New Statistical Framework for Corpus Callosum Sub-Region Characterization Based on LBP Texture in Patients With Parkinsonian Disorders: A Pilot Study

Progressive Supranuclear Palsy in India: Past, Present, and Future

Progressive supranuclear palsy (PSP) has emerged as a key area of interest among researchers worldwide, including those in India, who have actively studied the disorder over the past several decades. This review meticulously explores the extensive range of Indian research on PSP up to the present and offers insights into both current initiatives and potential future directions for managing PSP within the region. Historical research contributions have spanned 80 publications from 1974 to 2023, encompassing diverse themes from clinical phenotyping and historical analysis to isolated investigative studies and therapeutic trials. Traditionally, these studies have been conducted in single centers or specific departments, involving a broad range of recruitment numbers. The most frequently encountered phenotype among these studies is PSP-Richardson's syndrome, with patients typically presenting at an average age of 64 years, alongside various other subtypes. Recently, there has been a significant shift toward more collaborative research models, moving from isolated, center-based studies to expansive, multicentric, and pan India projects. A prime example of this new approach is the PAn India Registry for PSP (PAIR-PSP) project, which represents a comprehensive effort to uniformly examine the demographic, clinical, and genetic facets of PSP across India. Looking ahead, there is a critical need for focused research on unraveling genetic insights, identifying risk factors, and developing effective treatment interventions and preventive models. Given its vast population, India's role in advancing our understanding of PSP and other tauopathies could be pivotal, and this work reflects the work on PSP in India till now.

An Adaptive Weighted Attention-Enhanced Deep Convolutional Neural Network for Classification of MRI images of Parkinson's Disease

BACKGROUND

Parkinson's disease (PD) is the second prevalent neurological diseases with a significant growth rate in incidence. Convolutional neural networks using structural magnetic resonance images (sMRI) are widely used for PD classification. However, the areas of change in the patient's MRI images are small and unfixed. Thus, capturing the features of the areas accurately where the lesions changed became a problem.

METHOD

We propose a deep learning framework that combines multi-scale attention guidance and multi-branch feature processing modules to diagnose PD by learning sMRI T2 slice features. In this scheme, firstly, to achieve effective feature transfer and gradient descent, a deep convolutional neural network framework based on dense block is designed. Next, an Adaptive Weighted Attention algorithm is proposed, whose pursers is to extract multi branch and even diverse features. Finally, Dropout layer and SoftMax layer are added to the network structure to obtain good classification results and rich and diverse feature information. The Dropout layer is used to reduce the number of intermediate features to increase the orthogonality between features of each layer. The activation function SoftMax increases the flexibility of the neural network by increasing the degree of fitting to the training set and converting linear to nonlinear.

RESULTS

The best performance of the proposed method an accuracy of 92%, a sensitivity of 94%, specificity of 90% and a F1 score of 95% respectively for identifying PD and HC.

CONCLUSION

Experiments show that the proposed method can successfully distinguish PD and NC. Good classification results were obtained in PD diagnosis classification task and compared with advanced research methods.

Segmental Alterations of the Corpus Callosum in Progressive Supranuclear Palsy: A Multiparametric Magnetic Resonance Imaging Study

Background: The regional distribution of the widespread cerebral morphological alterations in progressive supranuclear palsy (PSP) is considered to include segmental parts of the corpus callosum (CC). Objective: The study was designed to investigate the regional white matter (WM) of the CC by T1 weighted magnetic resonance imaging (T1w MRI) data combined with diffusion tensor imaging (DTI) data in PSP patients, differentiated in the variants Richardson syndrome and PSP-parkinsonism, and to compare them with Parkinson's Disease (PD) patients and healthy controls, in order to identify macro- and micro-structural alterations in vivo. Methods: MRI-based WM mapping was used to perform an operator-independent segmentation for the different CC segments in 66 PSP patients vs. 66 PD patients vs. 44 matched healthy controls. The segmentation was followed by both planimetric and texture analysis of the separated CC areas for the comparison of the three groups. Results were complemented by a DTI-based tract-of-interest analysis of the associated callosal tracts. Results: Significant alterations of the parameters entropy and homogeneity compared to controls were observed for PSP as well as for PD for the CC areas I, II, and III. The inhomogeneity in area II in the PSP cohort was the highest and differed significantly from PD. A combined score was defined as a potential marker for the different types of neurodegenerative parkinsonism; receiver operating characteristics (ROC) curves were calculated with areas under the curve values of 0.86 for PSP vs. controls, 0.72 for PD vs. controls, and 0.69 for PSP vs. PD, respectively. Conclusion: The multiparametric MRI texture and DTI analysis demonstrated extensive alterations of the frontal CC in neurodegenerative parkinsonism, whereas regional CC atrophy cannot be regarded as a constant neuroimaging feature of PSP. Specifically, the comparison PSP vs. PD revealed significant alterations in callosal area II. The combination of the texture and the DTI parameters might contribute as a neuroimaging marker for the assessment of the CC in PSP, including the differentiation vs. PD.