An automated segmentation method for three-dimensional carotid ultrasound images

BACKGROUND: There is a great demand for the extraction of organ models from three-dimensional (3D) medical images in clinical medicine diagnosis and treatment. OBJECTIVE: We aimed to aid doctors in seeing the real shape of human organs more clearly and vividly. METHODS: The method uses the minimum eigenvectors of Laplacian matrix to automatically calculate a group of basic matting components that can properly define the volume image. These matting components can then be used to build foreground images with the help of a few user marks. RESULTS: We propose a direct 3D model segmentation method for volume images. This is a process of extracting foreground objects from volume images and estimating the opacity of the voxels covered by the objects. CONCLUSIONS: The results of segmentation experiments on different parts of human body prove the applicability of this method.

Download Full-text

Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning

Sensors ◽

10.3390/s21061952 ◽

2021 ◽

Vol 21 (6) ◽

pp. 1952

Author(s):

May Phu Paing ◽

Supan Tungjitkusolmun ◽

Toan Huy Bui ◽

Sarinporn Visitsattapongse ◽

Chuchart Pintavirooj

Keyword(s):

Deep Learning ◽

Brain Infarction ◽

Three Dimensional ◽

Dice Similarity Coefficient ◽

Automated Segmentation ◽

Variational Mode Decomposition ◽

Brain Scans ◽

Automated Method ◽

Mode Decomposition ◽

Segmentation Task

Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1-weighted brain scans. As a key novelty, the proposed method combines variational mode decomposition and deep learning-based segmentation to take advantages of both methods and provide better results. There are three main technical contributions in this paper. First, variational mode decomposition is applied as a pre-processing to discriminate the infarct lesions from unwanted non-infarct tissues. Second, overlapped patches strategy is proposed to reduce the workload of the deep-learning-based segmentation task. Finally, a three-dimensional U-Net model is developed to perform patch-wise segmentation of infarct lesions. A total of 239 brain scans from a public dataset is utilized to develop and evaluate the proposed method. Empirical results reveal that the proposed automated segmentation can provide promising performances with an average dice similarity coefficient (DSC) of 0.6684, intersection over union (IoU) of 0.5022, and average symmetric surface distance (ASSD) of 0.3932, respectively.

Download Full-text

Semi-automated segmentation of the prostate gland boundary in ultrasound images using a machine learning approach

10.1117/12.770965 ◽

2008 ◽

Cited By ~ 11

Author(s):

Kristians Diaz ◽

Benjamin Castaneda

Keyword(s):

Machine Learning ◽

Prostate Gland ◽

Learning Approach ◽

Ultrasound Images ◽

Automated Segmentation ◽

Machine Learning Approach

Download Full-text

Prefrontal and hippocampal atrophy using 7-tesla magnetic resonance imaging in patients with Parkinson’s disease

Acta Radiologica Open ◽

10.1177/2058460120988097 ◽

2021 ◽

Vol 10 (2) ◽

pp. 205846012098809

Author(s):

Byeong H Oh ◽

Hyeong C Moon ◽

Aryun Kim ◽

Hyeon J Kim ◽

Chae J Cheong ◽

...

Keyword(s):

Magnetic Resonance Imaging ◽

Parkinson’S Disease ◽

Parkinson's Disease ◽

Magnetic Resonance ◽

7 Tesla ◽

Cortical Atrophy ◽

Automated Segmentation ◽

Healthy Controls ◽

Segmentation Method ◽

Resonance Imaging

Background The pathology of Parkinson’s disease leads to morphological changes in brain structure. Currently, the progressive changes in gray matter volume that occur with time and are specific to patients with Parkinson’s disease, compared to healthy controls, remain unclear. High-tesla magnetic resonance imaging might be useful in differentiating neurological disorders by brain cortical changes. Purpose We aimed to investigate patterns in gray matter changes in patients with Parkinson’s disease by using an automated segmentation method with 7-tesla magnetic resonance imaging. Material and Methods High-resolution T1-weighted 7 tesla magnetic resonance imaging volumes of 24 hemispheres were acquired from 12 Parkinson’s disease patients and 12 age- and sex-matched healthy controls with median ages of 64.5 (range, 41–82) years and 60.5 (range, 25–74) years, respectively. Subgroup analysis was performed according to whether axial motor symptoms were present in the Parkinson’s disease patients. Cortical volume, cortical thickness, and subcortical volume were measured using a high-resolution image processing technique based on the Desikan-Killiany-Tourville atlas and an automated segmentation method (FreeSurfer version 6.0). Results After cortical reconstruction, in 7 tesla magnetic resonance imaging volume segmental analysis, compared with the healthy controls, the Parkinson’s disease patients showed global cortical atrophy, mostly in the prefrontal area (rostral middle frontal, superior frontal, inferior parietal lobule, medial orbitofrontal, rostral anterior cingulate area), and subcortical volume atrophy in limbic/paralimbic areas (fusiform, hippocampus, amygdala). Conclusion We first demonstrated that 7 tesla magnetic resonance imaging detects structural abnormalities in Parkinson’s disease patients compared to healthy controls using an automated segmentation method. Compared with the healthy controls, the Parkinson’s disease patients showed global prefrontal cortical atrophy and hippocampal area atrophy.

Download Full-text

Robotic motion compensation for bone movement, using ultrasound images

Industrial Robot the international journal of robotics research and application ◽

10.1108/ir-12-2014-0435 ◽

2015 ◽

Vol 42 (5) ◽

pp. 466-474 ◽

Cited By ~ 4

Author(s):

P.M.B. Torres ◽

P. J. S. Gonçalves ◽

J.M.M. Martins

Keyword(s):

Motion Compensation ◽

Optical Measurement ◽

Three Dimensional ◽

Point Clouds ◽

Robotic System ◽

Ultrasound Images ◽

Bone Drilling ◽

Content Type ◽

3D Point Clouds ◽

Robotic Motion

Purpose – The purpose of this paper is to present a robotic motion compensation system, using ultrasound images, to assist orthopedic surgery. The robotic system can compensate for femur movements during bone drilling procedures. Although it may have other applications, the system was thought to be used in hip resurfacing (HR) prosthesis surgery to implant the initial guide tool. The system requires no fiducial markers implanted in the patient, by using only non-invasive ultrasound images. Design/methodology/approach – The femur location in the operating room is obtained by processing ultrasound (USA) and computer tomography (CT) images, obtained, respectively, in the intra-operative and pre-operative scenarios. During surgery, the bone position and orientation is obtained by registration of USA and CT three-dimensional (3D) point clouds, using an optical measurement system and also passive markers attached to the USA probe and to the drill. The system description, image processing, calibration procedures and results with simulated and real experiments are presented and described to illustrate the system in operation. Findings – The robotic system can compensate for femur movements, during bone drilling procedures. In most experiments, the update was always validated, with errors of 2 mm/4°. Originality/value – The navigation system is based entirely on the information extracted from images obtained from CT pre-operatively and USA intra-operatively. Contrary to current surgical systems, it does not use any type of implant in the bone to track the femur movements.

Download Full-text