A 3D lesion segmentation method on whole-body PET images including automated quality control.
-
Updated
Jun 20, 2024
A 3D lesion segmentation method on whole-body PET images including automated quality control.
This repository is the result of an academic project at Ecole Centrale in Nantes, France, with my classmate @damien-gautier-nantes. The aim of this project was to evaluate the performance of universal segmentation models for segmenting cancerous lesions. The UniverSeg and Segment Anything (SAM) models were tested.
ImageJ macros for preparation of single images from stacks with maximum intensity projections and partially automated selection of slices in focus. CellProfiler Pipeline for yH2AX and 53BP1 counting and mitotic cells segmentation in asynchronous cultures. R scripts for processing of CellProfiler output.
Add a description, image, and links to the maximum-intensity-projections topic page so that developers can more easily learn about it.
To associate your repository with the maximum-intensity-projections topic, visit your repo's landing page and select "manage topics."