Development of a Support Vector Machine - Based Image Analysis System for Focal Liver Lesions Classification in Magnetic Resonance Images

This work aimed to investigate whether automated classifiers belonging to feature-based and deep learning may approach brain metastases segmentation successfully. Support Vector Machine and V-Net Convolutional Neural Network are selected as representatives of the two approaches. In the experiments, we consider several configurations of the two methods to segment brain metastases on contrast-enhanced T1-weighted magnetic resonance images. Performances were evaluated and compared under critical conditions imposed by the clinical radiotherapy domain, using in-house dataset and public dataset created for the Multimodal Brain Tumour Image Segmentation (BraTS) challenge. Our results showed that the feature-based and the deep network approaches are promising for the segmentation of Magnetic Resonance Imaging (MRI) brain metastases achieving both an acceptable level of performance. Experimental results also highlight different behaviour between the two methods. Support vector machine (SVM) improves performance with a smaller training set, but it is unable to manage a high level of heterogeneity in the data and requires post-processing refinement stages. The V-Net model shows good performances when trained on multiple heterogeneous cases but requires data augmentations and transfer learning procedures to optimise its behaviour. The paper illustrates a software package implementing an integrated set of procedures for active support in segmenting brain metastases within the radiotherapy workflow.

Download Full-text

Gray Matter Volume and Functional Connectivity in Hypochondriasis: A Magnetic Resonance Imaging and Support Vector Machine Analysis

Frontiers in Human Neuroscience ◽

10.3389/fnhum.2020.596157 ◽

2020 ◽

Vol 14 ◽

Author(s):

Zhe Shen ◽

Liang Yu ◽

Zhiyong Zhao ◽

Kangyu Jin ◽

Fen Pan ◽

...

Keyword(s):

Support Vector Machine ◽

Magnetic Resonance ◽

Functional Connectivity ◽

Gray Matter ◽

Gray Matter Volume ◽

Magnetic Resonance Images ◽

Support Vector ◽

Imaging Data ◽

Matter Volume ◽

Medial Frontal Gyrus

Objective: Patients with hypochondriasis hold unexplainable beliefs and a fear of having a lethal disease, with poor compliances and treatment response to psychotropic drugs. Although several studies have demonstrated that patients with hypochondriasis demonstrate abnormalities in brain structure and function, gray matter volume (GMV) and functional connectivity (FC) in hypochondriasis still remain unclear.Methods: The present study collected T1-weighted and resting-state functional magnetic resonance images from 21 hypochondriasis patients and 22 well-matched healthy controls (HCs). We first analyzed the difference in the GMV between the two groups. We then used the regions showing a difference in GMV between two groups as seeds to perform functional connectivity (FC) analysis. Finally, a support vector machine (SVM) was applied to the imaging data to distinguish hypochondriasis patients from HCs.Results: Compared with the HCs, the hypochondriasis group showed decreased GMV in the left precuneus, and increased GMV in the left medial frontal gyrus. FC analyses revealed decreased FC between the left medial frontal gyrus and cuneus, and between the left precuneus and cuneus. A combination of both GMV and FC in the left precuneus, medial frontal gyrus, and cuneus was able to discriminate the hypochondriasis patients from HCs with a sensitivity of 0.98, specificity of 0.93, and accuracy of 0.95.Conclusion: Our study suggests that smaller left precuneus volumes and decreased FC between the left precuneus and cuneus seem to play an important role of hypochondriasis. Future studies are needed to confirm whether this finding is generalizable to patients with hypochondriasis.

Download Full-text