Machine learning and computer vision engineer with 15+ years across software engineering, applied research, and data science, including prior VP-Engineering and Principal Data Scientist scope. Currently a Research Data Scientist at ARUP Laboratories, building production computer vision and machine learning for digital pathology — unsupervised pre-training of vision transformers on high-resolution microscopy, multiple-instance learning for whole-slide image classification, and cloud inference systems with monitoring and validation. Applied researcher with three peer-reviewed publications (2025) spanning CNN-based microscopy detection, machine learning in clinical flow cytometry, and clinical validation of a real-time AML detection system. Ships end-to-end: data infrastructure and pipelines, model development, deployment (AWS, Kubernetes, SageMaker), and post-deployment monitoring.
Machine learning and data analytics algorithm development to assist in various research pathology efforts.
Providing software and data expertise to clients in Fintech, Bioinformatics, and other industries.
Team lead role helping to enable data driven product features across a consumer IoT product line.
Mindbody, at the time, required that many core roles train for 3 months in customer support. It provided a great opportunity to get an idea of the product, the customer needs, and build familiarity with the organization. I wish more companies would make things like this part of onboarding.
Mycobacteria, including Mycobacterium tuberculosis (MTB) and non-tuberculosis mycobacteria (NTM), are important causes of infectious disease and cause significant mortality and morbidity globally. Fast detection is extremely important to reduce transmission and mortality associated with these infectious agents. Manual smear microscopy is a cost-effective tool for diagnosing and monitoring of these organisms; however, it is labor-intensive and requires highly-trained personnel. We present the development of an artificial intelligence computer vision process using a deep convolutional neural network to detect acid-fast bacilli (AFB) from Kinyoun acid-fast stained slides. We collected 231 clinical specimens between August 2023 and June 2024. Following acid-fast staining, whole slide images (WSI) were digitized, and AFB organisms were manually annotated. A machine learning computer vision model was trained using 11,411 annotated organisms across 109 WSI. Model predictions were correlated with final culture-confirmed results. The final model estimated AFB density per 1000 x microscope field of view (FOV). Using a density threshold of ≥10−2 AFB/1000xFOV (corresponding to 1 + per Clinical and Laboratory Standards Institute (CLSI) guideline M48) to predict positive culture results, the model correctly classified 68% of validation slides, with a sensitivity of 79% and specificity of 63%. Manual AO compared to final culture read showed sensitivity of 76% and specificity of 96%. Although performance of our model was not sufficient to be clinically implemented in our laboratory, our study provides a framework for AI-based AFB detection and a publicly available data set to support future advancements in automated detection of AFB.
Machine learning or artificial intelligence can be used to effectively analyze flow cytometry data from hematologic malignancies. Here we review three main methods in machine learning: supervised, unsupervised, and weakly supervised learning and how they can be applied to clinical flow cytometry. Additionally, we review the operational, logistical, and regulatory considerations that underlie a clinical implementation of these tools.
Machine-learning (ML) models in flow cytometry have the potential to reduce error rates, increase reproducibility, and boost the efficiency of clinical labs. While numerous ML models for flow cytometry data have been proposed, few studies have described the clinical deployment of such models. Realizing the potential gains of ML models in clinical labs requires not only an accurate model but also infrastructure for automated inference, error detection, analytics and monitoring, and structured data extraction. Here, we describe an ML model for the detection of Acute Myeloid Leukemia (AML), along with the infrastructure supporting clinical implementation. Our infrastructure leverages the resilience and scalability of the cloud for model inference, a Kubernetes-based workflow system that provides model reproducibility and resource management, and a system for extracting structured diagnoses from full-text reports. We also describe our model monitoring and visualization platform, an essential element for ensuring continued model accuracy. Finally, we present a post-deployment analysis of impacts on turn-around time and compare production accuracy to the original validation statistics.