المؤلفون: Al-Battal, Abdullah F., Duong, Soan T. M., Tang, Van Ha, Tran, Quang Duc, Truong, Steven Q. H., Phan, Chien, Nguyen, Truong Q., An, Cheolhong

مصطلحات موضوعية: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition

الوصف: Multi-phase computed tomography (CT) scans use contrast agents to highlight different anatomical structures within the body to improve the probability of identifying and detecting anatomical structures of interest and abnormalities such as liver lesions. Yet, detecting these lesions remains a challenging task as these lesions vary significantly in their size, shape, texture, and contrast with respect to surrounding tissue. Therefore, radiologists need to have an extensive experience to be able to identify and detect these lesions. Segmentation-based neural networks can assist radiologists with this task. Current state-of-the-art lesion segmentation networks use the encoder-decoder design paradigm based on the UNet architecture where the multi-phase CT scan volume is fed to the network as a multi-channel input. Although this approach utilizes information from all the phases and outperform single-phase segmentation networks, we demonstrate that their performance is not optimal and can be further improved by incorporating the learning from models trained on each single-phase individually. Our approach comprises three stages. The first stage identifies the regions within the liver where there might be lesions at three different scales (4, 8, and 16 mm). The second stage includes the main segmentation model trained using all the phases as well as a segmentation model trained on each of the phases individually. The third stage uses the multi-phase CT volumes together with the predictions from each of the segmentation models to generate the final segmentation map. Overall, our approach improves relative liver lesion segmentation performance by 1.6% while reducing performance variability across subjects by 8% when compared to the current state-of-the-art models.

الوصول الحر: http://arxiv.org/abs/2404.11152Test

المؤلفون: Kalaw, Fritz Gerald P, Cavichini, Melina, Zhang, Junkang, Wen, Bo, Lin, Andrew C, Heinke, Anna, Nguyen, Truong, An, Cheolhong, Bartsch, Dirk-Uwe G, Cheng, Lingyun, Freeman, William R

المصدر: Eye. 38(6)

مصطلحات موضوعية: Biomedical and Clinical Sciences, Ophthalmology and Optometry, Clinical Research, Bioengineering, Retinal Vessels, Retina, Humans, Algorithms, Artificial Intelligence, Neural Networks, Computer, Clinical Sciences, Immunology, Opthalmology and Optometry, Ophthalmology & Optometry, Ophthalmology and optometry

الوصف: PurposeThis study aimed to compare a new Artificial Intelligence (AI) method to conventional mathematical warping in accurately overlaying peripheral retinal vessels from two different imaging devices: confocal scanning laser ophthalmoscope (cSLO) wide-field images and SLO ultra-wide field images.MethodsImages were captured using the Heidelberg Spectralis 55-degree field-of-view and Optos ultra-wide field. The conventional mathematical warping was performed using Random Sample Consensus-Sample and Consensus sets (RANSAC-SC). This was compared to an AI alignment algorithm based on a one-way forward registration procedure consisting of full Convolutional Neural Networks (CNNs) with Outlier Rejection (OR CNN), as well as an iterative 3D camera pose optimization process (OR CNN + Distortion Correction [DC]). Images were provided in a checkerboard pattern, and peripheral vessels were graded in four quadrants based on alignment to the adjacent box.ResultsA total of 660 boxes were analysed from 55 eyes. Dice scores were compared between the three methods (RANSAC-SC/OR CNN/OR CNN + DC): 0.3341/0.4665/4784 for fold 1-2 and 0.3315/0.4494/4596 for fold 2-1 in composite images. The images composed using the OR CNN + DC have a median rating of 4 (out of 5) versus 2 using RANSAC-SC. The odds of getting a higher grading level are 4.8 times higher using our OR CNN + DC than RANSAC-SC (p

وصف الملف: application/pdf

الوصول الحر: https://escholarship.org/uc/item/24d0952hTest

المؤلفون: Kim, Byeonghwi, Kim, Jinyeon, Kim, Yuyeong, Min, Cheolhong, Choi, Jonghyun

مصطلحات موضوعية: Computer Science - Robotics, Computer Science - Artificial Intelligence

الوصف: Accomplishing household tasks requires to plan step-by-step actions considering the consequences of previous actions. However, the state-of-the-art embodied agents often make mistakes in navigating the environment and interacting with proper objects due to imperfect learning by imitating experts or algorithmic planners without such knowledge. To improve both visual navigation and object interaction, we propose to consider the consequence of taken actions by CAPEAM (Context-Aware Planning and Environment-Aware Memory) that incorporates semantic context (e.g., appropriate objects to interact with) in a sequence of actions, and the changed spatial arrangement and states of interacted objects (e.g., location that the object has been moved to) in inferring the subsequent actions. We empirically show that the agent with the proposed CAPEAM achieves state-of-the-art performance in various metrics using a challenging interactive instruction following benchmark in both seen and unseen environments by large margins (up to +10.70% in unseen env.).
Comment: ICCV 2023 (Project page: https://bhkim94.github.io/projects/CAPEAMTest)

الوصول الحر: http://arxiv.org/abs/2308.07241Test

المؤلفون: Wang, Yiqian, Warter, Alexandra, Cavichini, Melina, Alex, Varsha, Bartsch, Dirk-Uwe G., Freeman, William R., Nguyen, Truong Q., An, Cheolhong

مصطلحات موضوعية: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition

الوصف: Optical Coherence Tomography (OCT) is one of the most important retinal imaging technique. However, involuntary motion artifacts still pose a major challenge in OCT imaging that compromises the quality of downstream analysis, such as retinal layer segmentation and OCT Angiography. We propose deep learning based neural networks to correct axial and coronal motion artifacts in OCT based on a single volumetric scan. The proposed method consists of two fully-convolutional neural networks that predict Z and X dimensional displacement maps sequentially in two stages. The experimental result shows that the proposed method can effectively correct motion artifacts and achieve smaller error than other methods. Specifically, the method can recover the overall curvature of the retina, and can be generalized well to various diseases and resolutions.

الوصول الحر: http://arxiv.org/abs/2305.18361Test

المؤلفون: Yassin, Shaden H, Wang, Yiqian, Freeman, William R, Heinke, Anna, Walker, Evan, Nguyen, Truong, Bartsch, Dirk‐Uwe G, An, Cheolhong, Borooah, Shyamanga

المصدر: Clinical and Experimental Ophthalmology. 51(5)

مصطلحات موضوعية: Biomedical and Clinical Sciences, Ophthalmology and Optometry, Eye Disease and Disorders of Vision, Neurodegenerative, Rare Diseases, Eye, Humans, Artificial Intelligence, Retina, Retinitis Pigmentosa, Tomography, Optical Coherence, Visual Acuity, artificial intelligence, microperimetry, retinitis pigmentosa, spectral domain optical coherence tomography, structure-function, Clinical Sciences, Opthalmology and Optometry, Public Health and Health Services, Ophthalmology & Optometry, Ophthalmology and optometry

الوصف: BackgroundRetinitis pigmentosa (RP) represents a group of progressive, genetically heterogenous blinding diseases. Recently, relationships between measures of retinal function and structure are needed to help identify outcome measures or biomarkers for clinical trials. The ability to align retinal multimodal images, taken on different platforms, will allow better understanding of this relationship. We investigate the efficacy of artificial intelligence (AI) in overlaying different multimodal retinal images in RP patients.MethodsWe overlayed infrared images from microperimetry on near-infra-red images from scanning laser ophthalmoscope and spectral domain optical coherence tomography in RP patients using manual alignment and AI. The AI adopted a two-step framework and was trained on a separate dataset. Manual alignment was performed using in-house software that allowed labelling of six key points located at vessel bifurcations. Manual overlay was considered successful if the distance between same key points on the overlayed images was ≤1/2°.ResultsFifty-seven eyes of 32 patients were included in the analysis. AI was significantly more accurate and successful in aligning images compared to manual alignment as confirmed by linear mixed-effects modelling (p

وصف الملف: application/pdf

الوصول الحر: https://escholarship.org/uc/item/9fk6q61wTest

المؤلفون: Wang, Yiqian, Galang, Carlo, Freeman, William, Nguyen, Truong, An, Cheolhong

مصطلحات موضوعية: Optical coherence tomography, deep learning, image segmentation, motion correction, retinal imaging

الوصف: Optical Coherence Tomography (OCT) is a widely used non-invasive high resolution 3D imaging technique for biological tissues and plays an important role in ophthalmology. OCT retinal layer segmentation is a fundamental image processing step for OCT-Angiography projection, and disease analysis. A major problem in retinal imaging is the motion artifacts introduced by involuntary eye movements. In this paper, we propose neural networks that jointly correct eye motion and retinal layer segmentation utilizing 3D OCT information, so that the segmentation among neighboring B-scans would be consistent. The experimental results show both visual and quantitative improvements by combining motion correction and 3D OCT layer segmentation comparing to conventional and deep-learning based 2D OCT layer segmentation.

وصف الملف: application/pdf

الوصول الحر: https://escholarship.org/uc/item/0379r5c1Test

المؤلفون: An, Cheolhong.

المصدر: Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses

الوصف: Thesis (Ph. D.)--University of California, San Diego, 2008.
Title from first page of PDF file (viewed November 19, 2008). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 100-105).

الإتاحة: http://wwwlib.umi.com/cr/ucsd/fullcit?p3330376Test

المؤلفون: Zhang, Zunming, Tang, Rui, Chen, Xinyu, Waller, Lauren, Kau, Alston, Fung, Anthony A, Gutierrez, Bien, An, Cheolhong, Cho, Sung Hwan, Shi, Lingyan, Lo, Yu-Hwa

المصدر: Proceedings of the National Academy of Sciences of the United States of America. 119(8)

مصطلحات موضوعية: Cancer, Bioengineering, 1.1 Normal biological development and functioning, Underpinning research, Generic health relevance, Flow Cytometry, High-Throughput Screening Assays, Humans, Image Processing, Computer-Assisted, Imaging, Three-Dimensional, Software, single cell, high throughput, 3D imaging flow cytometer, disease diagnosis, spatial biology

الوصف: We develop a high-throughput technique to relate positions of individual cells to their three-dimensional (3D) imaging features with single-cell resolution. The technique is particularly suitable for nonadherent cells where existing spatial biology methodologies relating cell properties to their positions in a solid tissue do not apply. Our design consists of two parts, as follows: recording 3D cell images at high throughput (500 to 1,000 cells/s) using a custom 3D imaging flow cytometer (3D-IFC) and dispensing cells in a first-in-first-out (FIFO) manner using a robotic cell placement platform (CPP). To prevent errors due to violations of the FIFO principle, we invented a method that uses marker beads and DNA sequencing software to detect errors. Experiments with human cancer cell lines demonstrate the feasibility of mapping 3D side scattering and fluorescent images, as well as two-dimensional (2D) transmission images of cells to their locations on the membrane filter for around 100,000 cells in less than 10 min. While the current work uses our specially designed 3D imaging flow cytometer to produce 3D cell images, our methodology can support other imaging modalities. The technology and method form a bridge between single-cell image analysis and single-cell molecular analysis.

وصف الملف: application/pdf

الوصول الحر: https://escholarship.org/uc/item/3xr9s5c9Test

المؤلفون: Zhang, Junkang, Wang, Yiqian, Dai, Ji, Cavichini, Melina, Bartsch, Dirk-Uwe G, Freeman, William R, Nguyen, Truong Q, An, Cheolhong

مصطلحات موضوعية: Machine Learning, Information and Computing Sciences, Computer Vision and Multimedia Computation, Bioengineering, Biomedical Imaging, Networking and Information Technology R&D (NITRD), Machine Learning and Artificial Intelligence, Neurosciences, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Neural Networks, Computer, Retina, Image segmentation, Training, Convolutional neural networks, Transformers, Pipelines, Feature extraction, Image registration, retinal images, multi-modal, coarse-to-fine, convolutional neural networks, Artificial Intelligence and Image Processing, Electrical and Electronic Engineering, Cognitive Sciences, Artificial Intelligence & Image Processing, Computer vision and multimedia computation, Graphics, augmented reality and games

الوصف: Multi-modal retinal image registration plays an important role in the ophthalmological diagnosis process. The conventional methods lack robustness in aligning multi-modal images of various imaging qualities. Deep-learning methods have not been widely developed for this task, especially for the coarse-to-fine registration pipeline. To handle this task, we propose a two-step method based on deep convolutional networks, including a coarse alignment step and a fine alignment step. In the coarse alignment step, a global registration matrix is estimated by three sequentially connected networks for vessel segmentation, feature detection and description, and outlier rejection, respectively. In the fine alignment step, a deformable registration network is set up to find pixel-wise correspondence between a target image and a coarsely aligned image from the previous step to further improve the alignment accuracy. Particularly, an unsupervised learning framework is proposed to handle the difficulties of inconsistent modalities and lack of labeled training data for the fine alignment step. The proposed framework first changes multi-modal images into a same modality through modality transformers, and then adopts photometric consistency loss and smoothness loss to train the deformable registration network. The experimental results show that the proposed method achieves state-of-the-art results in Dice metrics and is more robust in challenging cases.

وصف الملف: application/pdf

الوصول الحر: https://escholarship.org/uc/item/5sk137x8Test
https://escholarship.org/content/qt5sk137x8/qt5sk137x8.pdfTest

المؤلفون: Yong‐Jin Park, Yun Goo Ro, Young‐Eun Shin, Cheolhong Park, Sangyun Na, Yoojin Chang, Hyunhyub Ko

المصدر: Advanced Science, Vol 10, Iss 36, Pp n/a-n/a (2023)

مصطلحات موضوعية: artificial synaptic devices, human‐machine interface, transistors, triboelectric nanogenerators, Science

الوصف: Abstract In the domains of wearable electronics, robotics, and the Internet of Things, there is a demand for devices with low power consumption and the capability of multiplex sensing, memory, and learning. Triboelectric nanogenerators (TENGs) offer remarkable versatility in this regard, particularly when integrated with synaptic transistors that mimic biological synapses. However, conventional TENGs, generating only two spikes per cycle, have limitations when used in synaptic devices requiring repetitive high‐frequency gating signals to perform various synaptic plasticity functions. Herein, a multi‐layered micropatterned TENG (M‐TENG) consisting of a polydimethylsiloxane (PDMS) film and a composite film that includes 1H,1H,2H,2H‐perfluorooctyltrichlorosilane/BaTiO3/PDMS are proposed. The M‐TENG generates multiple spikes from a single touch by utilizing separate triboelectric charges at the multiple friction layers, along with a contact/separation delay achieved by distinct spacers between layers. This configuration allows the maximum triboelectric output charge of M‐TENG to reach up to 7.52 nC, compared to 3.69 nC for a single‐layered TENG. Furthermore, by integrating M‐TENGs with an organic electrochemical transistor, the spike number multiplication property of M‐TENGs is leveraged to demonstrate an artificial synaptic device with low energy consumption. As a proof‐of‐concept application, a robotic hand is operated through continuous memory training under repeated stimulations, successfully emulating long‐term plasticity.

وصف الملف: electronic resource

العلاقة: https://doaj.org/toc/2198-3844Test

الوصول الحر: https://doaj.org/article/1289804645ae4eb8bf15d30fa1850cfbTest