Segmentation by Thresholding on Medical Imaging – A Survey

Abstract

Medical imaging is one of the important topics in research field. It is the visualization of body parts, tissues, or organs, for use in clinical diagnosis, treatment and disease monitoring. Imaging techniques encompass the fields of radiology, nuclear medicine and optical imaging and image-guided intervention. MRI gives the conservative treatment that does not require incision into the body or the removal of tissue of imaging the cervical spine Magnetic Resonance Imaging (MRI) is a medical imaging technology that uses radio waves and a magnetic field to create detailed images of organs and tissues. The impact of the medical image in various fields are constantly growing. Magnetic Resonance Imaging, is an advanced, state-of-the-art radiology method that produces very clear images of the human body without the use of X-rays. MRI has proven to be highly effective in diagnosing a number of conditions by showing the difference between normal and diseased soft tissues of the body. MRI a powerful diagnostic tool in the assessment of both anatomical deformity and tissue pathology. MRI has tremendous potential in the diagnosis of both intraspinal and osteo-articular disease of the cervical spine. MRI gives extremely clear, detailed images of soft-tissue structures that other imaging techniques cannot achieve. MRI has much greater soft tissue contrast than Computed Tomography, making it useful in neurological, musculoskeletal, cardiovascular, and gynecological imaging. This paper presents the survey of various thresholding techniques used in medical imaging.

Cellular 3D-reconstruction and analysis in the human cerebral cortex using automatic serial sections

“…A thickness of 800 and 900 nm provided sufficient axial spatial resolution to detect and reconstruct pyramidal cells. The UNetDense architecture was applied to detect the pyramidal cells in our images, as threshold-based segmentation techniques typically yield poor output in medical image analysis for low-contrast images, unexplained noise, blurred boundaries, and different light condition 49 , 50 . The variation between brains made it challenging to create a model that suited all three brains since flaws occurred mainly along the edges of the images, and where the contrast was low due to less staining absorption.…”

Aspects of Statistical Analysis of Spatial Point Patterns

“…The UNetDense architecture was applied to detect the pyramidal cells in our images, as threshold-based segmentation techniques typically yield poor output in medical image analysis for low-contrast images, unexplained noise, blurred boundaries, and different light condition (Tsai, 2007, Malarvizhi, 2017. The variation between brains made it challenging to create a model that suited all three brains since flaws occurred mainly along the edges of the images, and where the contrast was low due to less staining absorption.…”