• BMB Reports
• /
• v.55 no.3
• /
• pp.113-124
• /
• 2022

Single-cell RNA sequencing (scRNA-seq) has greatly advanced our understanding of cellular heterogeneity by profiling individual cell transcriptomes. However, cell dissociation from the tissue structure causes a loss of spatial information, which hinders the identification of intercellular communication networks and global transcriptional patterns present in the tissue architecture. To overcome this limitation, novel transcriptomic platforms that preserve spatial information have been actively developed. Significant achievements in imaging technologies have enabled in situ targeted transcriptomic profiling in single cells at single-molecule resolution. In addition, technologies based on mRNA capture followed by sequencing have made possible profiling of the genome-wide transcriptome at the 55-100 ㎛ resolution. Unfortunately, neither imaging-based technology nor capture-based method elucidates a complete picture of the spatial transcriptome in a tissue. Therefore, addressing specific biological questions requires balancing experimental throughput and spatial resolution, mandating the efforts to develop computational algorithms that are pivotal to circumvent technology-specific limitations. In this review, we focus on the current state-of-the-art spatially resolved transcriptomic technologies, describe their applications in a variety of biological domains, and explore recent discoveries demonstrating their enormous potential in biomedical research. We further highlight novel integrative computational methodologies with other data modalities that provide a framework to derive biological insight into heterogeneous and complex tissue organization.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.670-684
• /
• 2024

3D Cross-Modal Retrieval (3DCMR) is a task that retrieves 3D objects regardless of modalities, such as images, meshes, and point clouds. One of the most prominent methods used for 3DCMR is the Cross-Modal Center Loss Function (CLF) which applies the conventional center loss strategy for 3D cross-modal search and retrieval. Since CLF is based on center loss, the center features in CLF are also susceptible to subtle changes in hyperparameters and external inferences. For instance, performance degradation is observed when the batch size is too small. Furthermore, the Mean Squared Error (MSE) used in CLF is unable to adapt to changes in batch size and is vulnerable to data variations that occur during actual inference due to the use of simple Euclidean distance between multi-modal features. To address the problems that arise from small batch training, we propose a Noisy Center Loss (NCL) method to estimate the optimal center features. In addition, we apply the simple Siamese representation learning method (SimSiam) during optimal center feature estimation to compare projected features, making the proposed method robust to changes in batch size and variations in data. As a result, the proposed approach demonstrates improved performance in ModelNet40 dataset compared to the conventional methods.

• Archives of Plastic Surgery
• /
• v.34 no.2
• /
• pp.265-268
• /
• 2007

Purpose: Superficial temporal artery(STA) aneurysms are very rare and mostly occur as pseudoaneurysms secondary to trauma. Clinical diagnosis of STA pseudoaneurysm is based on a history of trauma or surgery to frontotemporal region, which presents with pulsatile mass. To confirm diagnosis, many imaging strategies can be used such as digital subtraction angiography, sonography, CT and MRI. But, these imaging modalities are invasive or inaccurate or expensive. Thus, we used 3D CT angiography to confirm STA aneurysm and to get accurate information. Methods: We have experienced two cases of pulsatile mass on the temporal area, suspected as STA pseudoaneurysms. On the basis of clinical information, we performed 3D CT angiography to get more accurate information about this pulsatile mass and to confirm diagnosis. On the basis of information from 3D CT angiography, we performed operation. Results: The lesions were diagnosed as pseudoaneurysm of superficial temporal artery by 3D CT angiography, and surgically resected safely without any complication on the basis of information from 3D CT angiography. 3D CT angiography was excellent diagnostic method for detecting STA pseudoaneurysms, and effectively showed many information about pseudoanerysms such as relationship between the aneurysms and surrounding structures, and its size. Conclusion: We could effectively diagnose and treat on the basis of information from 3D CT angiography. We present our cases with a brief review of the literature related to STA traumatic pseudoaneurysms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5179-5196
• /
• 2019

To explore an effective non-invasion medical imaging diagnostics approach for hepatocellular carcinoma (HCC), we propose a method based on adopting the multiple technologies with the multi-parametric data fusion, transfer learning, and multi-scale deep feature extraction. Firstly, to make full use of complementary and enhancing the contribution of different modalities viz. multi-parametric MRI images in the lesion diagnosis, we propose a data-level fusion strategy. Secondly, based on the fusion data as the input, the multi-scale residual neural network with SPP (Spatial Pyramid Pooling) is utilized for the discriminative feature representation learning. Thirdly, to mitigate the impact of the lack of training samples, we do the pre-training of the proposed multi-scale residual neural network model on the natural image dataset and the fine-tuning with the chosen multi-parametric MRI images as complementary data. The comparative experiment results on the dataset from the clinical cases show that our proposed approach by employing the multiple strategies achieves the highest accuracy of 0.847±0.023 in the classification problem on the HCC differentiation. In the problem of discriminating the HCC lesion from the non-tumor area, we achieve a good performance with accuracy, sensitivity, specificity and AUC (area under the ROC curve) being 0.981±0.002, 0.981±0.002, 0.991±0.007 and 0.999±0.0008, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4290-4309
• /
• 2020

In recent years, advancements in machine learning capabilities have allowed it to see widespread adoption for tasks such as object detection, image classification, and anomaly detection. However, despite their promise, a limitation lies in the fact that a network's performance quality is based on the data which it receives. A well-trained network will still have poor performance if the subsequent data supplied to it contains artifacts, out of focus regions, or other visual distortions. Under normal circumstances, images of the same scene captured from differing points of focus, angles, or modalities must be separately analysed by the network, despite possibly containing overlapping information such as in the case of images of the same scene captured from different angles, or irrelevant information such as images captured from infrared sensors which can capture thermal information well but not topographical details. This factor can potentially add significantly to the computational time and resources required to utilize the network without providing any additional benefit. In this study, we plan to explore using image fusion techniques to assemble multiple images of the same scene into a single image that retains the most salient key features of the individual source images while discarding overlapping or irrelevant data that does not provide any benefit to the network. Utilizing this image fusion step before inputting a dataset into the network, the number of images would be significantly reduced with the potential to improve the classification performance accuracy by enhancing images while discarding irrelevant and overlapping regions.

• Korean Journal of Digital Imaging in Medicine
• /
• v.5 no.1
• /
• pp.32-44
• /
• 2002

The role of radiology department has been greatly increased in the past few years as the technology in the medical imaging devices improved and the introduction of PACS (Picture Archiving and Communications System) to the conventional film-based diagnostic structure is a truly remarkable factor to the medical history. In addition, the value of using digital information in medical imaging is highly expected to grow as the technology over the computer and the network improves. However, the current medical practice, using PACS is somewhat limited compared to the film-based conventional one due to a poor image quality. The image quality is the most important and inevitable factor in the PACS environment and it is one of the most necessary steps to more wide practice of digital imaging. The existing image quality control tools are limited in controlling images produced from the medical modalities, because they cannot display the real image changing status. Thus, the image quality is distorted and the ability to diagnosis becomes hindered compared to the one of the film-based practice. In addition, the workflow of the radiologist greatly increases; as every doctor has to perform his or her own image quality control every time they view images produced from the medical modalities. To resolve these kinds of problems and enhance current medical practice under the PACS environment, we have developed a program to display a better image quality by using the ROI optical density of the existing gray level values. When the LUT is used properly, small detailed regions, which cannot be seen by using the existing image quality controls are easily displayed and thus, greatly improves digital medical practice. The purpose of this study is to provide an easier medical practice to physicians, by applying the technology of converting the H-D curves of the analog film screen to the digital imaging technology and to preset image quality control values to each exposed body part, modality and group of physicians for a better and easier medical practice. We have asked to 5 well known professional physicians to compare image quality of the same set of exam by using the two different methods: existing image quality control and the LUT technology. As the result, the LUT technology was enormously favored over the existing image quality control method. All the physicians have pointed out the far more superiority of the LUT over the existing image quality control method and highly praised its ability to display small detailed regions, which cannot be displayed by existing image quality control tools. Two physicians expressed the necessity of presetting the LUT values for each exposed body part. Overall, the LUT technology yielded a great interest among the physicians and highly praised for its ability to overcome currently embedded problems of PACS. We strongly believe that the LUT technology can enhance the current medical practice and open a new beginning in the future medical imaging.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.49-58
• /
• 2022

The purpose of this study is to find out how on-line counseling modalities (phone, video, and video counseling using digital mask) differ from face-to-face counseling in terms of clients' perception of working alliance, depth and smoothness of each session, satisfaction, and their qualitative counseling experience. 40 university students participated in the experiment, divided into 4 groups, received 3 personal counseling sessions per person. The quantitative data revealed no significant difference among the four counseling groups in working alliance. Also, the "depth" of the session was similar in the four groups, but phone and video with mask counseling group who did not expose their faces showed higher "smoothness" in the first and second sessions than face-to-face counseling group, indicating that anonymity was helping the clients' inhibition overcome. Through the post-interview data, subtle differences in experience of each counseling method were identified by the participants. The results are expected to provide primary information for developing and implementing various online counseling modalities in the future.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.4
• /
• pp.389-394
• /
• 2006

Inaccurate localization exposes a robot to many dangerous conditions. It could make a robot be moved to wrong direction or damaged by collision with surrounding obstacles. There are numerous approaches to self-localization, and there are different modalities as well (vision, laser range finders, ultrasonic sonars). Since sensor information is generally uncertain and contains noise, there are many researches to reduce the noise. But, the correctness is limited because most researches are based on statistical approach. The goal of our research is to measure more exact robot location by matching between built VRML 3D model and real vision image. To determine the position of mobile robot, landmark-localization technique has been applied. Landmarks are any detectable structure in the physical environment. Some use vertical lines, others use specially designed markers, In this paper, specially designed markers are used as landmarks. Given known focal length and a single image of three landmarks it is possible to compute the angular separation between the lines of sight of the landmarks. The image-processing and neural network pattern matching techniques are employed to recognize landmarks placed in a robot working environment. After self-localization, the 2D scene of the vision is overlaid with the VRML scene.

• Journal of Korean Academy of Nursing
• /
• v.11 no.2
• /
• pp.9-21
• /
• 1981

The purpose of this study was to observe and describe the maternal attachment behavior during the mother's first interactions with her newborn and define the factors contributing to differences in maternal attachment behavior. Observations of the mother's first interaction with her newborn can offer valuable information about the mother-infant relationship, and it provides an opportunity for planning individulized care for them. Data was collected from Sep. 1, 1950 to Oct.30, 1980 at Ewha Womans University Hospital. Maternal attachment behaviors of healthy full-term infants were observed and recorded on the .maternal attachment tool and analysed by the use of means, standard deviations and ANEVA test. The following trends of maternal behaviors were observed: 1. Identifying behaviors was the predominant mode and all of the mothers inspects baby's body features. 2. Modalities of interaction, that is, touching was initiated on the babies extremities and heads (57.3%) rather than the trunks (8.7%) and mothers touched their infants with their fingertips (58.2%) more than palm touching (14.6%) 3. Care-taking activities performed by the mother were negligible at the first interaction. 4. Parity of mother, sex of infant, age of mother, planned pregnancy, length of visits by mother to infant appeared to have significant influence on the maternal attachment behaviors.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.122-128
• /
• 2009

In this paper, we present a design and an evaluation of a hand-held ball based haptic interface, named "TouchBall." Using a trackball mechanism, the device provides flexibility in terms of directional degrees of freedom. It also has an advantage of a direct transfer of force feedback through frictional touch (with high sensitivity), thus requiring only relatively small amount of inertia. This leads to a compact hand-held design appropriate for mobile and 3D interactive applications. The device is evaluated for the detection thresholds for directions of the force feedback and the perceived amount of directional force. The refined directionality information should combine with other modalities with less sensory conflict, enriching the user experience for a given application.