Edit this page

NA-MIC Project Weeks

Back to Projects List

Automatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR

Segmentation

Key Investigators

Project Description

The segmentation of medical and dental images is a fundamental step in automated clinical decision support systems. It supports the entire clinical workflow from diagnosis, therapy planning, intervention, and follow-up. In this paper, we propose a novel tool to accurately process a full-face segmentation in about 5 minutes that would otherwise require an average of 7h of manual work by experienced clinicians. This work focuses on the integration of the state-of-the-art UNEt TRansformers (UNETR) of the Medical Open Network for Artificial Intelligence (MONAI) framework. We trained and tested our models using 618 de-identified Cone-Beam Computed Tomography (CBCT) volumetric images of the head acquired with several parameters from different centers for a generalized clinical application. Our results on a 5-fold cross-validation showed high accuracy and robustness with an Dice up to 0.962 pm 0.02.

Objective

  1. Create only one model for multiple structures.
  2. Create a slicer module for the algorithm
  3. Add new structure to segment
  4. Deploy the AMASSS tool with the updated trained models

Approach and Plan

  1. Get the data merged by the clinicians for the skull.
  2. Use the begening of a slicer module to create a new one for AMASSS.
  3. Use new dataset to train new HD models.

Progress and Next Steps

  1. An algorithm has already been made to run segmentation out of slicer as a docker to implement in the DSCI
  2. We collected data to generate segmentation model using the MONAI librairie
  3. For large field of view :
    • A model has been trained to generate a segmentation of 5 skull structures (mandible, maxilla, cranial base, cervical vertebra and upper airway)
    • An other to segment the skin.
  4. For small field of view :
    • A model for upper and lower root canal has been trained as well as HD mandible and maxilla
    • We still need data to train networks for crown and mandible canal segmentation
  5. To be more user friendly, the development of an AMASSS module for Slicer has been started in march.
  6. The UI of a slicer module was already started befor project week and has now been updated.
  7. We linked the UI with a CLI module to run the prediction/segmentation directly on the user computer through Slicer 5’s python 3.9

  8. The module has been tested locally with clinicians and is ready to be deployed as a Slicer module as a part of the slicer CMF extention ( The code is available at https://github.com/Maxlo24/Slicer_Automatic_Tools )

  9. We colaborated with Slicer Batch Annonymize (Hina Shah, Juan Carolos Prieto) to use AMASSS as a first step to perform defacing of patients scans during the batch anonymisation process. ( Figure 3 Mask for defacing )

Illustrations

1. Different process to perform a CBCT segmentation

prediction

2. Screen of the slicer module during a segmentation

Screen slicer

3. Use of AMASSS to generate mask for a defacing tool

mask for defaceing

Background and References