CellVision

Academic / Computer Vision

A blood-cell analysis platform spanning segmentation, labeling, active learning, correction, and reporting.

Interactive workspace connecting segmentation, labeling, correction, and reporting.

Overview

CellVision combines several steps of blood-cell image analysis in one Streamlit-based workflow.

The problem

Segmentation, labeling, correction, model evaluation, and reporting need to remain connected so human feedback can improve classifier quality.

My contribution

Built the end-to-end workflow, added human-in-the-loop labeling and active learning, and designed result and dashboard views.

System or workflow

  1. 01Segment cells from source images.
  2. 02Label and review extracted samples.
  3. 03Train and refine the classifier with active learning.
  4. 04Correct predictions and inspect final reporting views.

Technical highlights

  1. 01End-to-end workflow from image segmentation to prediction review
  2. 02Human-in-the-loop labeling and active learning
  3. 03Result and dashboard views for model evaluation and cell distribution

Links

Next project13Tour Into the PictureAcademic / Computer Vision

Project image

Interactive demo