• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.85-92
• /
• 2023

Deep learning applications are increasingly being leveraged for disease detection tasks in medical imaging modalities such as X-ray, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI). Most data-centric deep learning challenges necessitate the use of supervised learning methodologies to attain high accuracy and to facilitate performance evaluation through comparison with the ground truth. Supervised learning mandates a substantial amount of image and label sets, however, procuring an adequate volume of medical imaging data for training is a formidable task. Various data augmentation strategies can mitigate the underfitting issue inherent in supervised learning-based models that are trained on limited medical image and label sets. This research investigates the enhancement of a deep learning-based rib fracture segmentation model and the efficacy of data augmentation techniques such as left-right flipping, rotation, and scaling. Augmented dataset with L/R flipping and rotations(30°, 60°) increased model performance, however, dataset with rotation(90°) and ⨯0.5 rescaling decreased model performance. This indicates the usage of appropriate data augmentation methods depending on datasets and tasks.

• Composites Research
• /
• v.36 no.6
• /
• pp.395-401
• /
• 2023

In this study, finite element modeling of unidirectional composite materials of the computed tomography (CT) was conducted using a supervised learning-based segmentation technique. Firstly, Micro-CT scan was performed to obtain the raw volume of unidirectional composite materials, providing microstructure information. From the CT volume images, actual microstructure of the cross-section of unidirectional composite materials was extracted by the labeling process. Then, a U-net deep learning model was trained with a small number of raw images as inputs and their labeled images as outputs to generate a segmentation model. Subsequently, most of remaining images were input to the trained U-net deep learning model to segment all raw volume for identifying complex microstructure, which was used for the generation of finite element model. Finally, the fiber volume fraction of the finite element model was compared with that of experimentally measured volume to validate the appropriateness of the proposed method.

• Proceedings of the KSMRM Conference
• /
• 2003.10a
• /
• pp.78-78
• /
• 2003

목적： 이전에는 손쉽게 구할 수 있는 표준데이터를 가지고 visual human body model을 형성하였다. 주로 팬텀이나, 외국인의 데이터를 가지고 만든 것이기 때문에 우리가 실제 실험에 쓰려면 큰 차이가 있었다. 그래서 본 연구에서는 실제 우리나라 사람 중 동일 인물의 MR와 CT 이미지를 가지고 인체 모델을 만들고자 하였다. 그러기 위해서 먼저 인체의 MR, CT영상에 대한 특징을 분석해야 했고, 이것을 바탕으로 영상 분할(Image Segmentation)을 하였다. 인체 부위에 따라 영상 분할 방법도 그 차이가 있음을 알 수 있었다.

• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.25-34
• /
• 2022

Brain computed tomography (CT) is useful for brain lesion diagnosis, such as brain hemorrhage, due to non-invasive methodology, 3-dimensional image provision, low radiation dose. However, there has been numerous misdiagnosis owing to a lack of radiologist and heavy workload. Recently, object detection technologies based on artificial intelligence have been developed in order to overcome the limitations of traditional diagnosis. In this study, the applicability of a deep learning-based YOLOv5s model was evaluated for brain hemorrhage detection using brain CT images. Also, the effect of hyperparameters in the trained YOLOv5s model was analyzed. The YOLOv5s model consisted of backbone, neck and output modules. The trained model was able to detect a region of brain hemorrhage and provide the information of the region. The YOLOv5s model was trained with various activation functions, optimizer functions, loss functions and epochs, and the performance of the trained model was evaluated in terms of brain hemorrhage detection accuracy and training time. The results showed that the trained YOLOv5s model is able to provide a bounding box for a region of brain hemorrhage and the accuracy of the corresponding box. The performance of the YOLOv5s model was improved by using the mish activation function, the stochastic gradient descent (SGD) optimizer function and the completed intersection over union (CIoU) loss function. Also, the accuracy and training time of the YOLOv5s model increased with the number of epochs. Therefore, the YOLOv5s model is suitable for brain hemorrhage detection using brain CT images, and the performance of the model can be maximized by using appropriate hyperparameters.

• Journal of the Korean Society of Radiology
• /
• v.14 no.3
• /
• pp.211-220
• /
• 2020

High-quality computed tomography (CT) images enable precise lesion detection and accurate diagnosis. A lot of studies have been performed to improve CT image quality while reducing radiation dose. Recently, deep learning-based techniques for improving CT image quality have been developed and show superior performance compared to conventional techniques. In this study, a super-resolution convolutional neural network (SRCNN) model was used to improve the spatial resolution of CT images, and image quality according to the hyperparameters, which determine the performance of the SRCNN model, was evaluated in order to verify the effect of hyperparameters on the SRCNN model. Profile, structural similarity (SSIM), peak signal-to-noise ratio (PSNR), and full-width at half-maximum (FWHM) were measured to evaluate the performance of the SRCNN model. The results showed that the performance of the SRCNN model was improved with an increase of the numbers of epochs and training sets, and the learning rate needed to be optimized for obtaining acceptable image quality. Therefore, the SRCNN model with optimal hyperparameters is able to improve CT image quality.

• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.369-374
• /
• 2022

Purpose: Focused ultrasound is an emerging technology for treating the brain locally in a noninvasive manner. In this study, we have investigated the influence of skull properties on simulating transcranial pressure field. Methods: A 3D computational model of transcranial focused ultrasound was constructed using female and male CT data to solve for intracranial pressure. For heterogeneous model, the acoustic properties were calculated from CT Hounsfield units based on a porosity. The homogeneous model assigned constant acoustic properties for the single-layered skull. Results: A computational model was validated against empirical data. The homogeneous models were then compared with the heterogeneous model, resulted in 10.87% and 7.19% differences in peak pressure for female and male models respectively. For the focal volume, homogeneous model demonstrated more than 94% overlap compared with the heterogeneous model. Conclusion: Homogeneous model can be constructed using MR images that are commonly used for the segmentation of the skull. We propose the possibility of the homogeneous model for the simulating transcranial pressure field owing to comparable focal volume between homogeneous model and heterogeneous model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.611-614
• /
• 2023

갈비뼈 병변 진단 과정은 방사선 전문의가 CT 스캐너를 통해 생성된 2 차원 CT 이미지들을 해석하며 진행된다. 병변의 위치를 파악하고 정확한 진단을 내리기 위해 수백장의 2차원 CT 이미지들이 세밀하게 검토되며 갈비뼈를 분류한다. 본 연구는 이런 노동 집약적 작업의 문제점을 개선시키기 위해 Biaxial Rib Segmentation(BARS)을 제안한다. BARS 는 흉부 CT 볼륨의 관상면과 수평면으로 구성된 2 차원 이미지들을 U-Net 모델에 학습한다. 모델이 산출한 세그멘테이션 마스크들의 조합은 서로 다른 평면의 공간 정보를 보완하며 3 차원 갈비뼈 볼륨을 재건한다. BARS 의 성능은 DSC, Recall, Precision 지표를 사용해 평가하며, DSC 90.29%, Recall 89.74%, Precision 90.72%를 보인다. 향후에는 이를 기반으로 순차적 갈비뼈 레이블링 연구를 진행할 계획이다.

• Korean Journal of Computational Design and Engineering
• /
• v.15 no.3
• /
• pp.234-242
• /
• 2010

3D CAD technology has been extended to a medical area including dental clinic beyond industrial design. The 2D images obtained by CT(Computerized Tomography) and MRI(Magnetic Resonance Imaging) are not intuitive, and thus the volume rendering technique, which transforms 2D data into 3D anatomic information, has been in practical use. This paper has focused on a method and its implementation for forming 3D geometric surface model from laminated CT images of the pubis. The implemented system could support a dental clinic to observe and examine the status of a patient's pubis before implant surgery. The supplement of 3D implant model would help dental surgeons settle operation plans more safely and confidently. It also would be utilized with teaching materials for a practice and training.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.150-153
• /
• 2002

The use of the finite element method for biomechanical analysis is increasing rapidly in recent years. Since biomechanical models are usually in very complex shapes, it takes a lot of time and efforts to build reasonable finite element models. In this paper, a new tetrahedral meshing algorithm from the series of 2-D computed tomography(CT) images has been proposed. In this scheme, the planar sections of three-dimensional objects and the side surfaces between two planar sections are triangulated first, and then an advancing front algorithm is employed to construct tetrahedral elements by using basic operators. A sample finite element model for thoracic vertebra is presented.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.55 no.6
• /
• pp.221-226
• /
• 2006

The current flowing though a power line is measured by a current transformer (CT). Since a CT is a kind of transformer, saturation of magnetic flux in the core may occur when a large primary current flows. This saturation makes the secondary current of a CT distorted and causes problems in the protection point of view. Because of the current distortion, a protection relay cannot collect the correct information showing how the primary power system changed. Consequently, the current distortion may cause the mal-operation or operation time delay of protective relay. In this paper, an algorithm based on AR model and LSQ is proposed to compensate the saturated CT secondary currents. Various test results indicate that the proposed algorithm can accurately compensate a severely distorted secondary current and is not affected by remanence.