• The Journal of Korea Robotics Society
• /
• v.15 no.4
• /
• pp.316-322
• /
• 2020

Endoscopic spine surgery is an advanced surgical technique for spinal surgery since it minimizes skin incision, muscle damage, and blood loss compared to open surgery. It requires, however, accurate positioning of an endoscope to avoid spinal nerves and to locate the endoscope near the target disk. Before the insertion of the endoscope, a guide needle is inserted to guide it. Also, the result of the surgery highly depends on the surgeons' experience and the patients' CT or MRI images. Thus, for the training, a number of haptic simulators for spinal needle insertion have been developed. But, still, it is difficult to be used in the medical field practically because previous studies require manual segmentation of vertebrae from CT images, and interaction force between the needle and soft tissue has not been considered carefully. This paper proposes AI-based automatic vertebrae CT-image segmentation and haptic rendering method using the proposed need-tissue interaction model. For the segmentation, U-net structure was implemented and the accuracy was 93% in pixel and 88% in IoU. The needle-tissue interaction model including puncture force and friction force was implemented for haptic rendering in the proposed spinal needle insertion simulator.

• Journal of Biomedical Engineering Research
• /
• v.44 no.5
• /
• pp.354-361
• /
• 2023

Most of spinal diseases are diagnosed based on the subjective judgment of a specialist, so numerous studies have been conducted to find objectivity by automating the diagnosis process using deep learning. In this paper, we propose a method that combines segmentation and feature extraction, which are frequently used techniques for diagnosing spinal diseases. Four models, U-Net, U-Net++, DeepLabv3+, and M-Net were trained and compared using 1000 X-ray images, and key-points were derived using Douglas-Peucker algorithms. For evaluation, Dice Similarity Coefficient(DSC), Intersection over Union(IoU), precision, recall, and area under precision-recall curve evaluation metrics were used and U-Net++ showed the best performance in all metrics with an average DSC of 0.9724. For the average Euclidean distance between estimated key-points and ground truth, U-Net was the best, followed by U-Net++. However the difference in average distance was about 0.1 pixels, which is not significant. The results suggest that it is possible to extract key-points based on segmentation and that it can be used to accurately diagnose various spinal diseases, including spondylolisthesis, with consistent criteria.

• Journal of Biomedical Engineering Research
• /
• v.44 no.2
• /
• pp.139-146
• /
• 2023

Osteoporosis is a disease in which the risk of bone fractures increases due to a decrease in bone density caused by aging. Osteoporosis is diagnosed by measuring bone density in the total hip, femoral neck, and lumbar spine. To accurately measure bone density in the lumbar spine, the vertebral region must be segmented from the lumbar X-ray image. Deep learning-based automatic spinal segmentation methods can provide fast and precise information about the vertebral region. In this study, we used 695 lumbar spine images as training and test datasets for a deep learning segmentation model. We proposed a lumbar automatic segmentation model, CM-Net, which combines the center point of the spine and the modified U-Net network. As a result, the average Dice Similarity Coefficient(DSC) was 0.974, precision was 0.916, recall was 0.906, accuracy was 0.998, and Area under the Precision-Recall Curve (AUPRC) was 0.912. This study demonstrates a high-performance automatic segmentation model for lumbar X-ray images, which overcomes noise such as spinal fractures and implants. Furthermore, we can perform accurate measurement of bone density on lumbar X-ray images using an automatic segmentation methodology for the spine, which can prevent the risk of compression fractures at an early stage and improve the accuracy and efficiency of osteoporosis diagnosis.

• Korean Journal of Computational Design and Engineering
• /
• v.17 no.6
• /
• pp.436-442
• /
• 2012

Traumatic loading during car accidents or sports activities can lead to cervical spinal cord injury. Experiments in spinal cord injury research are mainly carried out on rabbit or rat. Finite element models that include the rat cervical spinal cord and adjacent soft tissues should be developed for efficient studies of mechanisms of spinal cord injury. Images of a rat were obtained from high resolution MRI scanner. Polygonal surfaces were extracted structure by structure from the MRI data using the ITK-SNAP volume segmentation software. These surfaces were converted to Non-uniform Rational B-spline surfaces by the INUS Rapidform rapid prototyping software. Rapidform was also used to generate a thin shell surface model for the dura mater which sheathes the spinal cord. Altair's Hypermesh pre-processor was used to generate finite element meshes for each structure. These processes in this study can be utilized in modeling of other biomedical tissues and can be one of examples for reverse engineering on biomechanics.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 1999.11a
• /
• pp.162-163
• /
• 1999

• Journal of the Korean Society of Radiology
• /
• v.16 no.7
• /
• pp.879-887
• /
• 2022

In this study, we tried to confirm whether the mechanical sequential elevation method of the body pressure measuring bed actually induces segmental motion for each part of the spine. To this end, a lateral X-ray examination was performed, and it was confirmed that the sequential pressure device induces a step-wise segmentation of the spine by mechanically lifting each part of the spine vertically. Then, pain, walking ability, and depression scale were measured and analyzed in subjects who were aware of back pain. VAS(p<0.05) and ODI(p<0.05) for 10 days tended to decrease in average after bed use. In the gait ability test(p<0.05), as the number of times of bed use increased, the moving time in the test decreased and the moving distance increased. In addition, GSDDF(p<0.05) decreased after bed use. As a result, it was confirmed that the spinal segmentation caused by the heat and acupressure provided by the bed affected gait and depression as well as pain relief.

• Radiation Oncology Journal
• /
• v.37 no.2
• /
• pp.134-142
• /
• 2019

Purpose: The aim is to study the dependence of deformable based auto-segmentation of head and neck organs-at-risks (OAR) on anatomy matching for a single atlas based system and generate an acceptable set of contours. Methods: A sample of ten patients in neutral neck position and three atlas sets consisting of ten patients each in different head and neck positions were utilized to generate three scenarios representing poor, average and perfect anatomy matching respectively and auto-segmentation was carried out for each scenario. Brainstem, larynx, mandible, cervical oesophagus, oral cavity, pharyngeal muscles, parotids, spinal cord, and trachea were the structures selected for the study. Automatic and oncologist reference contours were compared using the dice similarity index (DSI), Hausdroff distance and variation in the centre of mass (COM). Results: The mean DSI scores for brainstem was good irrespective of the anatomy matching scenarios. The scores for mandible, oral cavity, larynx, parotids, spinal cord, and trachea were unacceptable with poor matching but improved with enhanced bony matching whereas cervical oesophagus and pharyngeal muscles had less than acceptable scores for even perfect matching scenario. HD value and variation in COM decreased with better matching for all the structures. Conclusion: Improved anatomy matching resulted in better segmentation. At least a similar setup can help generate an acceptable set of automatic contours in systems employing single atlas method. Automatic contours from average matching scenario were acceptable for most structures. Importance should be given to head and neck position during atlas generation for a single atlas based system.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.12
• /
• pp.102-107
• /
• 2009

As technology gets developed, medical equipments are also modernized and leading-edge systems, such as PACS become popular. Many scientists noticed importance of medical image processing technology. Technique of region segmentation is the first step of digital medical image processing. Segmentation technique helps doctors to find out abnormal symptoms early, such as tumors, edema, and necrotic tissue, and helps to diagnoses correctly. Segmentation of white matter, gray matter and CSF of a brain image is very crucial part. However, the segmentation is not easy due to ambiguous boundaries and inhomogeneous physical characteristics. The rate of incorrect segmentation is high because of these difficulties. Fuzzy-based segmentation algorithms are robust to even ambiguous boundaries. In this paper a modified Fuzzy-based segmentation algorithm is proposed to handle the noise of MR scanners. A proposed algorithm requires minimal computations of mean and variance of neighbor pixels to adjust a new neighbor list. With the addition of minimal compuation, the modified FCM(mFCM) lowers the rate of incorrect clustering below 30% approximately compared the traditional FCM.

• Korean Journal of Radiology
• /
• v.19 no.6
• /
• pp.1140-1146
• /
• 2018

Objective: To compare the spinal enumeration methods that establish the first lumbar vertebra in patients with spinal variants. Materials and Methods: Of the 1446 consecutive patients who had undergone computed tomography of the spine from March 2012 to July 2016, 100 patients (62 men, 38 women; mean age, 47.9 years; age range, 19-88 years) with spinal variants were included. Two radiologists (readers 1 and 2) established the first lumbar vertebra through morphologic analysis of the thoracolumbar junction, and labeled the vertebra by counting in a cranial-to-caudal manner. Inter-observer agreement was established. Additionally, reader 1 detected the 20th vertebra under the assumption that there are 12 thoracic vertebra, and then classified it as a thoracic vertebra, lumbar vertebra, or thoracolumbar transitional vertebra (TLTV), on the basis of morphologic analysis. Results: The first lumbar vertebra, as established by morphologic analysis, was labeled by each reader as the 21st segment in 65.0% of the patients, as the 20th segment in 31.0%, and as the 19th segment in 4.0%. Inter-observer agreement between the two readers in determining the first lumbar vertebra, based on morphologic analysis, was nearly perfect (${\kappa}$ value: 1.00). The 20th vertebra was morphologically classified as a TLTV in 60.0% of the patients, as the first lumbar segment in 31.0%, as the second lumbar segment in 4.0%, and as a thoracic segment in 5.0%. Conclusion: The establishment of the first lumbar vertebra using morphologic characteristics of the thoracolumbar junction in patients with spinal variants was consistent with the morphologic traits of vertebral segmentation.

• Korean Journal of Radiology
• /
• v.25 no.4
• /
• pp.363-373
• /
• 2024

Objective: To develop and evaluate a deep learning model for automated segmentation and detection of bone metastasis on spinal MRI. Materials and Methods: We included whole spine MRI scans of adult patients with bone metastasis: 662 MRI series from 302 patients (63.5 ± 11.5 years; male:female, 151:151) from three study centers obtained between January 2015 and August 2021 for training and internal testing (random split into 536 and 126 series, respectively) and 49 MRI series from 20 patients (65.9 ± 11.5 years; male:female, 11:9) from another center obtained between January 2018 and August 2020 for external testing. Three sagittal MRI sequences, including non-contrast T1-weighted image (T1), contrast-enhanced T1-weighted Dixon fat-only image (FO), and contrast-enhanced fat-suppressed T1-weighted image (CE), were used. Seven models trained using the 2D and 3D U-Nets were developed with different combinations (T1, FO, CE, T1 + FO, T1 + CE, FO + CE, and T1 + FO + CE). The segmentation performance was evaluated using Dice coefficient, pixel-wise recall, and pixel-wise precision. The detection performance was analyzed using per-lesion sensitivity and a free-response receiver operating characteristic curve. The performance of the model was compared with that of five radiologists using the external test set. Results: The 2D U-Net T1 + CE model exhibited superior segmentation performance in the external test compared to the other models, with a Dice coefficient of 0.699 and pixel-wise recall of 0.653. The T1 + CE model achieved per-lesion sensitivities of 0.828 (497/600) and 0.857 (150/175) for metastases in the internal and external tests, respectively. The radiologists demonstrated a mean per-lesion sensitivity of 0.746 and a mean per-lesion positive predictive value of 0.701 in the external test. Conclusion: The deep learning models proposed for automated segmentation and detection of bone metastases on spinal MRI demonstrated high diagnostic performance.