Education & Certifications


  • B.S., Stanford University, Biomedical Computation, Honors (2021)

All Publications


  • Conceptual Framework and Documentation Standards of Cystoscopic Media Content for Artificial Intelligence. Journal of biomedical informatics Eminaga, O., Jiyong Lee, T., Ge, J., Shkolyar, E., Laurie, M., Long, J., Graham Hockman, L., Liao, J. C. 2023: 104369

    Abstract

    The clinical documentation of cystoscopy includes visual and textual materials. However, the secondary use of visual cystoscopic data for educational and research purposes remains limited due to inefficient data management in routine clinical practice.A conceptual framework was designed to document cystoscopy in a standardized manner with three major sections: data management, annotation management, and utilization management. A Swiss-cheese model was proposed for quality control and root cause analyses. We defined the infrastructure required to implement the framework with respect to FAIR (findable, accessible, interoperable, reusable) principles. We applied two scenarios exemplifying data sharing for research and educational projects to ensure compliance with FAIR principles.The framework was successfully implemented while following FAIR principles. The cystoscopy atlas produced from the framework could be presented in an educational web portal; a total of 68 full-length qualitative videos and corresponding annotation data were sharable for artificial intelligence projects covering frame classification and segmentation problems at case, lesion, and frame levels.Our study shows that the proposed framework facilitates the storage of visual documentation in a standardized manner and enables FAIR data for education and artificial intelligence research.

    View details for DOI 10.1016/j.jbi.2023.104369

    View details for PubMedID 37088456

  • PlexusNet: A neural network architectural concept for medical image classification. Computers in biology and medicine Eminaga, O., Abbas, M., Shen, J., Laurie, M., Brooks, J. D., Liao, J. C., Rubin, D. L. 2023; 154: 106594

    Abstract

    State-of-the-art (SOTA) convolutional neural network models have been widely adapted in medical imaging and applied to address different clinical problems. However, the complexity and scale of such models may not be justified in medical imaging and subject to the available resource budget. Further increasing the number of representative feature maps for the classification task decreases the model explainability. The current data normalization practice is fixed prior to model development and discounting the specification of the data domain. Acknowledging these issues, the current work proposed a new scalable model family called PlexusNet; the block architecture and model scaling by the network's depth, width, and branch regulate PlexusNet's architecture. The efficient computation costs outlined the dimensions of PlexusNet scaling and design. PlexusNet includes a new learnable data normalization algorithm for better data generalization. We applied a simple yet effective neural architecture search to design PlexusNet tailored to five clinical classification problems that achieve a performance noninferior to the SOTA models ResNet-18 and EfficientNet B0/1. It also does so with lower parameter capacity and representative feature maps in ten-fold ranges than the smallest SOTA models with comparable performance. The visualization of representative features revealed distinguishable clusters associated with categories based on latent features generated by PlexusNet. The package and source code are at https://github.com/oeminaga/PlexusNet.git.

    View details for DOI 10.1016/j.compbiomed.2023.106594

    View details for PubMedID 36753979

  • An Efficient Framework for Video Documentation of Bladder Lesions for Cystoscopy: A Proof-of-Concept Study. Journal of medical systems Eminaga, O., Ge, T. J., Shkolyar, E., Laurie, M. A., Lee, T. J., Hockman, L., Jia, X., Xing, L., Liao, J. C. 2022; 46 (11): 73

    Abstract

    Processing full-length cystoscopy videos is challenging for documentation and research purposes. We therefore designed a surgeon-guided framework to extract short video clips with bladder lesions for more efficient content navigation and extraction. Screenshots of bladder lesions were captured during transurethral resection of bladder tumor, then manually labeled according to case identification, date, lesion location, imaging modality, and pathology. The framework used the screenshot to search for and extract a corresponding 10-seconds video clip. Each video clip included a one-second space holder with a QR barcode informing the video content. The success of the framework was measured by the secondary use of these short clips and the reduction of storage volume required for video materials. From 86 cases, the framework successfully generated 249 video clips from 230 screenshots, with 14 erroneous video clips from 8 screenshots excluded. The HIPPA-compliant barcodes provided information of video contents with a 100% data completeness. A web-based educational gallery was curated with various diagnostic categories and annotated frame sequences. Compared with the unedited videos, the informative short video clips reduced the storage volume by 99.5%. In conclusion, our framework expedites the generation of visual contents with surgeon's instruction for cystoscopy and potential incorporation of video data towards applications including clinical documentation, education, and research.

    View details for DOI 10.1007/s10916-022-01862-8

    View details for PubMedID 36190581

  • Spontaneous cell fusions as a mechanism of parasexual recombination in tumour cell populations NATURE ECOLOGY & EVOLUTION Miroshnychenko, D., Baratchart, E., Ferrall-Fairbanks, M. C., Vander Velde, R., Laurie, M. A., Bui, M. M., Tan, A., Altrock, P. M., Basanta, D., Marusyk, A. 2021; 5 (3): 379–91

    Abstract

    The initiation and progression of cancers reflect the underlying process of somatic evolution, in which the diversification of heritable phenotypes provides a substrate for natural selection, resulting in the outgrowth of the most fit subpopulations. Although somatic evolution can tap into multiple sources of diversification, it is assumed to lack access to (para)sexual recombination-a key diversification mechanism throughout all strata of life. On the basis of observations of spontaneous fusions involving cancer cells, the reported genetic instability of polypoid cells and the precedence of fusion-mediated parasexual recombination in fungi, we asked whether cell fusions between genetically distinct cancer cells could produce parasexual recombination. Using differentially labelled tumour cells, we found evidence of low-frequency, spontaneous cell fusions between carcinoma cells in multiple cell line models of breast cancer both in vitro and in vivo. While some hybrids remained polyploid, many displayed partial ploidy reduction, generating diverse progeny with heterogeneous inheritance of parental alleles, indicative of partial recombination. Hybrid cells also displayed elevated levels of phenotypic plasticity, which may further amplify the impact of cell fusions on the diversification of phenotypic traits. Using mathematical modelling, we demonstrated that the observed rates of spontaneous somatic cell fusions may enable populations of tumour cells to amplify clonal heterogeneity, thus facilitating the exploration of larger areas of the adaptive landscape (relative to strictly asexual populations), which may substantially accelerate a tumour's ability to adapt to new selective pressures.

    View details for DOI 10.1038/s41559-020-01367-y

    View details for Web of Science ID 000608672700001

    View details for PubMedID 33462489

  • Optical biopsy of penile cancer with in vivo confocal laser endomicroscopy. Urologic oncology Shkolyar, E. n., Laurie, M. A., Mach, K. E., Trivedi, D. R., Zlatev, D. V., Chang, T. C., Metzner, T. J., Leppert, J. T., Kao, C. S., Liao, J. C. 2019

    Abstract

    Surgical management of penile cancer depends on accurate margin assessment and staging. Advanced optical imaging technologies may improve penile biopsy and organ-sparing treatment. We evaluated the feasibility of confocal laser endomicroscopy for intraoperative assessment of benign and malignant penile tissue.With institutional review board approval, 11 patients were recruited, 9 with suspected penile cancer, and 2 healthy controls. Confocal laser endomicroscopy using a 2.6-mm fiber-optic probe was performed at 1 or 2 procedures on all subjects, for 13 imaging procedures. Fluorescein was administered intravenously approximately 3 minutes prior to imaging for contrast. Video sequences from in vivo (n = 12) and ex vivo (n = 6) imaging were obtained of normal glans, suspicious lesions, and surgical margins. Images were processed, annotated, characterized, and correlated with standard hematoxylin and eosin histopathology.No adverse events related to imaging were reported. Distinguishing features of benign and malignant penile tissue could be identified by confocal laser endomicroscopy. Normal skin had cells of uniform size and shape, with distinct cytoplasmic membranes consistent with squamous epithelium. Malignant lesions were characterized by disorganized, crowded cells of various size and shape, lack of distinct cytoplasmic membranes, and hazy, moth-eaten appearance. The transition from normal to abnormal squamous epithelium could be identified.We report the initial feasibility of intraoperative confocal laser endomicroscopy for penile cancer optical biopsy. Pending further evaluation, confocal laser endomicroscopy could serve as an adjunct or replacement to conventional frozen section pathology for management of penile cancer.

    View details for DOI 10.1016/j.urolonc.2019.08.018

    View details for PubMedID 31537485