Skip to main content
Hudanyun ShengHS
Looking for a job

Hudanyun Sheng

@hudanyunsheng

Data scientist at Johnson & Johnson building physician-verification pipelines and models to identify likely early adopters for drug launches.

China
Message

At Johnson & Johnson, I built a cost-aware pipeline to extract physician information from hospital schedules in PDFs and images. It uses Camelot, OCR, and vision-language models with quality-based fallback, alongside a Streamlit interface for review and annotation.

I also developed models to identify likely early adopters for drug launches using HCP profiles, HCO attributes, and historical sales of analogous drugs. I engineered features from internal ratings and commercial data, then implemented validation in Kedro.

At UT Southwestern Medical Center, I developed a Mask R-CNN pipeline for segmenting nuclei and classifying six cell types in H&E-stained tissue. By adapting the loss function and training strategy for partially annotated samples, I recovered approximately 20% of the training data; the evaluated pipeline achieved an 82.5% detection rate and 82.0% classification accuracy.

At the Donald Danforth Plant Science Center, I developed leaf segmentation and tracking workflows and contributed Python modules, tests, and documentation to PlantCV. My work spans computer vision and machine learning for biomedical imaging, plant phenotyping, and document understanding.

Experience

Work history, roles, and key accomplishments

Zenni Optical logoZO

Data Scientist, AI/ML Department

Jun 2023 - Jan 2024 (7 months)

Deployed a FastAPI service for extracting optical parameters from prescription images using OCR and rule-based parsing, adapting to Japanese formats. Analyzed OCR failures and built an internal Streamlit tool for validation and error review.

UT Southwestern Medical Center logoUC

Data Scientist

Sep 2021 - May 2023 (1 year 8 months)

Developed a Mask R-CNN pipeline for nuclei segmentation and classification in H&E-stained tissue, recovering 20% of training data with partially annotated samples. Evaluated the weakly supervised pipeline achieving 82.5% detection rate and 82.0% classification accuracy, and co-authored a study in Modern Pathology.

Mask RCNNs
Weak Supervision
Image SegmentationClassificationDockerFlask
Parallel Processing
CyTOF
Multiplex Imaging
Donald Danforth Plant Science Center logoDC

Data Science Researcher

Donald Danforth Plant Science Center

Feb 2020 - Sep 2021 (1 year 7 months)

Developed leaf instance segmentation and time-series tracking workflows to quantify plant growth, automating processing of RGB, thermal, and hyperspectral images. Contributed Python modules, tests, documentation, and community training to PlantCV, an open-source toolkit.

Education

Degrees, certifications, and relevant coursework

University of Florida logoUF

University of Florida

Master of Science, Electrical and Computer Engineering

M.S. in Electrical and Computer Engineering, with thesis on switchgrass genotype classification using hyperspectral imagery.

University of Florida logoUF

University of Florida

Master of Science, Industrial and Systems Engineering

M.S. in Industrial and Systems Engineering.

Tongji University logoTU

Tongji University

Bachelor of Science, Physics

B.S. in Physics.

Tech stack

Software and tools used professionally

Availability

Looking for a job

Location

China

Authorized to work in

Salary expectations

50k+ USD

Interested in hiring Hudanyun?

You can contact Hudanyun and 600K+ other talented remote workers on Himalayas.

Message Hudanyun

People also viewed

View all talent

Get matched with your dream remote job

Sign up now and join over 1,000,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan