No abstract

Background: The purpose of this article is to provide a new evaluation tool based on skeleton maps to assess the tumoral and non-tumoral regions of the 2D MRI in PD-weighted (proton density) and T2w (T2-weighted type) brain images. Methods: The proposed method investigated inter-hemisphere brain tissue similarity using a mask in the right hemisphere and its mirror reflection in the left one. At the hemisphere level and for each ROI (region of interest), a morphological skeleton algorithm was used to efficiently investigate the similarity between hemispheres. Two datasets with 88 T2w and PD images belonging to healthy patients and patients diagnosed with glioma were investigated: D1 contains the original raw images affected by Rician noise and D2 consists of the same images pre-processed for noise removal. Results: The investigation was based on structural similarity assessment by using the Structural Similarity Index (SSIM) and a modified Jaccard metrics. A novel S-Jaccard (Skeleton Jaccard) metric was proposed. Cluster accuracy was estimated based on the Silhouette method (SV). The Silhouette coefficient (SC) indicates the quality of the clustering process for the SSIM and S-Jaccard. To assess the overall classification accuracy an ROC curve implementation was carried out. Conclusions: Consistent results were obtained for healthy patients and for PD images of glioma. We demonstrated that the S-Jaccard metric based on skeletal similarity is an efficient tool for an inter-hemisphere brain similarity evaluation. The accuracy of the proposed skeletonization method was smaller for the original images affected by Rician noise (AUC = 0.883 (T2w) and 0.904 (PD)) but increased for denoised images (AUC = 0.951 (T2w) and 0.969 (PD)).

The brain is highly susceptible to metastases from lung cancer. The segmentation and detection of brain metastases are the main goals for the management of patients with brain metastases and a MRI technique that uses the image signal contrast between tissues rather than their absolute signal intensities is a recommended approach. This paper proposes a specific quantification method for the most relevant first and second-order features computed for brain images acquired as T2-weighted and PD (proton density). T2-w sequences are useful for detecting high-signal tumor infiltration whilst PD (proton density) sequences performed a fat suppression being an intermediate sequence between T1-w and T2-w and share common features of both. Based on the firstorder histogram (the gray-level distribution of the image) and on texture-related information provided by the cooccurrence matrix, features like skewness, kurtosis or entropy, and energy were computed in terms of their discriminatory power for a better clinical investigation of MRI images. Our analysis provides for a smaller number of relevant and distinguishable features and the computational task is at a reasonable level.

No abstract

This paper aims to provide a sound estimation of the true value and proportion of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) of the brain DTI images for a proper 3D volume reconstruction. During the pre-processing stage, two nonlinear filters are operated, i.e. bilateral and anisotropic diffusion. The segmentation of each brain tissue is performed using the k-means clustering algorithm. To minimize filters bias and for obtaining the best reproducible results, a statistical analysis has been performed. Thus, the skewness and kurtosis statistics features were computed for each segmented brain tissue and filter. The fuzzy k-means method allows for clustering analysis and the Bland-Altman analysis investigates the agreement between two filtering techniques of the same statistics feature and brain tissue. Then the 3D reconstruction method is presented using ImageJ and the image stacks for raw and processed data. We conclude that anisotropic diffusion filter offers the best results and 3D reconstruction of brain tissues is feasible.