Skip to content
/ Transfer_learning_sarcopenia_C3 Public

A machine learning model was trained, on a cohort of head and neck cancer patients, to segment skeletal muscle in the neck at the level of the C3 vertebra. The model was a convolutional neural network and had a Dice score of 0.89 (89% accuracy). A value of skeletal muscle area (SMA) and density (SMD) was found for each patient in a cohort of aro…

0 stars 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

hermionewarr/Transfer_learning_sarcopenia_C3

BranchesTags

Repository files navigation

Transfer_learning_sarcopenia_C3

This is the code for my master's project. 1 is loading and storing the slice of interest from a patients CT scan, segmented with ITK SNAP. 2 is training a pretrained machine learning model to segment skeletal muscle and find a value of SMA from those segments. The pretrained model used is FCN Resnet50. 3 is automatically segmenting patients C3 CT slice, using our retrained model. The file to create bone masks for each pateint is also included.

Published as a poster discussion at ESTRO: https://www.estro.org/Congresses/ESTRO-2021/911/posterdiscussion10-theinterfaceofphysicsandradiobi/3959/automatedsarcopeniaassessmentintheneckandsurvivala

About

A machine learning model was trained, on a cohort of head and neck cancer patients, to segment skeletal muscle in the neck at the level of the C3 vertebra. The model was a convolutional neural network and had a Dice score of 0.89 (89% accuracy). A value of skeletal muscle area (SMA) and density (SMD) was found for each patient in a cohort of aro…

Topics

machine-learning ai healthcare medical-imaging segments neck sarcopenia

Resources

Readme
Activity

Stars

0 stars

Watchers

2 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages