Hippocampus segmentation and classification for dementia analysis using pre-trained neural network models

The diagnostic and clinical overlap of early mild cognitive impairment (EMCI), mild cognitive impairment (MCI), late mild cognitive impairment (LMCI) and Alzheimer disease (AD) is a vital oncological issue in dementia disorder. This study is designed to examine Whole brain (WB), grey matter (GM) and Hippocampus (HC) morphological variation and identify the prominent biomarkers in MR brain images of demented subjects to understand the severity progression. Curve evolution based on shape constraint is carried out to segment the complex brain structure such as HC and GM. Pre-trained models are used to observe the severity variation in these regions. This work is evaluated on ADNI database. The outcome of the proposed work shows that curve evolution method could segment HC and GM regions with better correlation. Pre-trained models are able to show significant severity difference among WB, GM and HC regions for the considered classes. Further, prominent variation is observed between AD vs. EMCI, AD vs. MCI and AD vs. LMCI in the whole brain, GM and HC. It is concluded that AlexNet model for HC region result in better classification for AD vs. EMCI, AD vs. MCI and AD vs. LMCI with an accuracy of 93, 78.3 and 91% respectively.

A weighted region-based level set method for image segmentation with intensity inhomogeneity

Image segmentation is a fundamental task in image processing and is still a challenging problem when processing images with high noise, low resolution and intensity inhomogeneity. In this paper, a weighted region-based level set method, which is based on the techniques of local statistical theory, level set theory and curve evolution, is proposed. Specifically, a new weighted pressure force function (WPF) is first presented to flexibly drive the closed contour to shrink or expand outside and inside of the object. Second, a faster and smoother regularization term is added to ensure the stability of the curve evolution and that there is no need for initialization in curve evolution. Third, the WPF is integrated into the region-based level set framework to accelerate the speed of the curve evolution and improve the accuracy of image segmentation. Experimental results on medical and natural images demonstrate that the proposed segmentation model is more efficient and robust to noise than other state-of-the-art models.

The impact of immediate in-brace 3D corrections on curve evolution after two years of treatment: preliminary results

For the brace treatment of adolescent idiopathic scoliosis (AIS), in-brace correction and brace-wear compliance are well-documented parameters associated with a greater chance of treatment success. However, the number of studies on the impact of sagittal and transverse correction on curve evolution in the context of bracing is limited. The objective of this work was to evaluate how immediate inbrace correction in the three anatomical planes is related to long-term curve evolution after two years of bracing. We performed a retrospective analysis on 94 AIS patients followed for a minimum of two years. We analyzed correlations between in-brace correction and two-year out-of-brace evolution for Cobb and apical axial rotations (ARs) in the medial thoracic and thoraco-lumbar/lumbar regions (MT & TL/L). We also studied the association between the braces’ kyphosing and lordosing effect and the evolution of thoracic kyphosis (TK) and lumbar lordosis (LL) after two years. Finally, we separated the patients into three groups based on their curve progression results after two years (corrected, stable and progressed) and compared the 3D in-brace corrections and compliance for each group. Coefficients were statistically significant for all correlations. They were weak for Cobb angles (MT: -0.242; TL/L: -0.275), low for ARs (MT: -0.423; TL/L: -0.417) and moderate for sagittal curves (TK: 0.549; LL: 0.482). In-brace coronal correction was significantly higher in corrected vs stable patients (p=0.004) while compliance was significantly higher in stable vs progressed patients (p=0.026). This study highlights the importance of initial in-brace correction in all three planes for successful treatment outcomes.

Rapidly Declining Hostless Type Ia Supernova KSP-OT-201509b from the KMTNet Supernova Program: Transitional Nature and Constraint on 56Ni Distribution and Progenitor Type

We report the early discovery and multicolor (BVI) high-cadence light-curve analyses of the rapidly declining sub-Chandrasekhar Type Ia supernova KSP-OT-201509b (= AT 2015cx) from the KMTNet Supernova Program. The Phillips and color stretch parameters of KSP-OT-201509b are ΔM B,15 ≃ 1.62 mag and s BV ≃ 0.54, respectively, at an inferred redshift of 0.072. These, together with other measured parameters (such as the strength of the secondary I-band peak, colors, and luminosity), identify the source to be a rapidly declining Type Ia of a transitional nature that is closer to Branch-normal than 91bg-like. Its early light-curve evolution and bolometric luminosity are consistent with those of homologously expanding ejecta powered by radioactive decay and a Type Ia SN explosion with 0.32 ± 0.01 M ⊙ of synthesized 56Ni mass, 0.84 ± 0.12 M ⊙ of ejecta mass, and (0.61 ± 0.14) × 1051 erg of ejecta kinetic energy. While its B − V and V − I colors evolve largely synchronously with the changes in the I-band light curve, as found in other supernovae, we also find the presence of an early redward evolution in V − I prior to −10 days since peak. The bolometric light curve of the source is compatible with a stratified 56Ni distribution extended to shallow layers of the exploding progenitor. Comparisons between the observed light curves and those predicted from ejecta–companion interactions clearly disfavor Roche lobe–filling companion stars at large separation distances, thus supporting a double-degenerate scenario for its origin. The lack of any apparent host galaxy in our deep stack images reaching a sensitivity limit of ∼28 mag arcsec−2 makes KSP-OT-201509b a hostless Type Ia supernova and offers new insights into supernova host galaxy environments.

An Improved Level Set Algorithm Based on Prior Information for Left Ventricular MRI Segmentation

This paper proposes a new level set algorithm for left ventricular segmentation based on prior information. First, the improved U-Net network is used for coarse segmentation to obtain pixel-level prior position information. Then, the segmentation result is used as the initial contour of level set for fine segmentation. In the process of curve evolution, based on the shape of the left ventricle, we improve the energy function of the level set and add shape constraints to solve the “burr” and “sag” problems during curve evolution. The proposed algorithm was successfully evaluated on the MICCAI 2009: the mean dice score of the epicardium and endocardium are 92.95% and 94.43%. It is proved that the improved level set algorithm obtains better segmentation results than the original algorithm.