Skip to content
View odafeng's full-sized avatar

Block or report odafeng

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
odafeng/README.md

Shih-Feng Huang 黃士峯

Colon & Code
clinical problems → structured data → deployable systems

Surgical Data Scientist | Colorectal Surgeon

Building real-world AI systems for surgical workflows


I build an end-to-end surgical data pipeline that connects:

CT imaging → intraoperative workflow → postoperative outcomes

From raw clinical data to reproducible analysis and deployable systems.

高雄榮總大腸直腸外科主治醫師
專注於將臨床問題轉化為可計算、可重現、可部署的資料科學系統


⚙️ Surgical Data Pipeline (Core System)

CT Imaging → Feature Extraction → Difficulty Modeling ↓ Intraoperative Video / Workflow Analysis ↓ Postoperative Outcomes / PRO / Prediction Models

🧠 Preoperative

  • Automated CT-based pelvimetry
  • Surgical difficulty modeling (FREDRIC framework)

🎥 Intraoperative

  • Learning curve modeling (RA-CUSUM)
  • Video-based workflow analysis

📊 Postoperative

  • Outcome prediction (ML / survival analysis)
  • Digital follow-up & PRO systems

🚀 Featured Systems

🔬 CT Pelvimetry Pipeline

ctpelvimetry
→ Fully automated CT-based pelvimetry
→ Published & validated (IJCARS)
→ Packaged and distributed via PyPI


📈 Learning Curve Intelligence

RiSSA_ML_Learning_Curve
→ ML-based surgical safety profiling
→ Published in Journal of Robotic Surgery


📊 Clinical Outcome Modeling

Stage_III_Colon_EDR
→ Early recurrence prediction
→ Multi-center validation


📱 Surgical Follow-up Platform

Hemorrhoids_PostOp
→ Digital postoperative monitoring system
→ Deployed in IRB-approved clinical study


📚 Selected Publications

Focus: surgical AI, learning curves, and outcome modeling

  • Machine learning–based learning curve analysis — J Robotic Surg. 2026 doi
  • Video-based RA-CUSUM proficiency assessment — Int J Colorectal Dis. 2026 doi
  • Robotic single-stapling vs double-stapling anastomosis — J Robotic Surg. 2025 doi

Full list → ORCID


🧰 Methods & Stack

  • Data Science: pandas, scikit-learn, lifelines, PyTorch
  • Imaging: CT processing, TotalSegmentator, 3D Slicer
  • Causal Inference: overlap weighting, RMST, survival modeling
  • Systems: Next.js, TypeScript, PostgreSQL

🧭 Direction

Building the infrastructure of Surgical Data Science:

  • From clinical intuition → quantitative modeling
  • From retrospective data → real-time systems
  • From isolated studies → reproducible pipelines
  • Next: surgical video analytics — automated phase recognition, workflow decomposition, and AI-assisted intraoperative feedback

Pinned Loading

  1. RiSSA_ML_Learning_Curve RiSSA_ML_Learning_Curve Public

    ML-based risk modeling for learning curve assessment in robotic left-sided colorectal cancer surgery

    Jupyter Notebook 1

  2. Stage_III_Colon_EDR Stage_III_Colon_EDR Public

    Analysis pipeline for developing and externally validating a four-variable pathology-based model to predict early distant recurrence (within 18 months) in stage III colon cancer. The repository con…

    Jupyter Notebook 1

  3. Auto_ISD_Pelvimetry Auto_ISD_Pelvimetry Public

    This repository provides a fully automated CT-based pipeline for interspinous distance (ISD) measurement and mid-pelvic workspace quantification in rectal cancer. Using TotalSegmentator and geometr…

    Python

  4. ctpelvimetry ctpelvimetry Public

    Automated CT pelvimetry and body composition analysis

    Python

  5. Hemorrhoids_PostOp Hemorrhoids_PostOp Public

    Hemorrhoid postoperative symptom monitoring and AI-assisted patient education PWA — React + Supabase + Claude API

    JavaScript

  6. Auto_CT_Pelvimetry Auto_CT_Pelvimetry Public

    Automated CT pelvimetry pipeline for pelvic bony landmark measurement, validated against manual 3D Slicer measurements

    Jupyter Notebook