Edit this page

NA-MIC Project Weeks

Back to Projects List

Multi-stage deep learning segmentation of teeth

Key Investigators

Project Description

Segmenting and identifying the teeth in a mandible or maxilla is a difficult task, especially due to the high number of structures and their similarity. Recent results suggest that multi-stage segmentation may yield more accurate segmentation in these scenarios.

Objective

The idea is to create a simple two-stage approach in MONAILabel where the first stage detects the teeth centre and the second stage accurately segments the teeth themselves.

Approach and Plan

  1. Discuss with Andrés the details about multi-stage segmentation in MONAILabel
  2. Design the changes to be made

Progress and Next Steps

  1. Discussion with Andrés about multi-stage deep learning approach
    • Multistage approach is more robust because the complexity is separated (robustness is the main advantage)
      • Paper (see below) has several models: ROI, Centroid/Skeleton (numbers OR images), Multi-task tooth segmentation, Tooth ID classification, Cascaded bone segmentation
      • Baseline data for centroid model are just the centroids, that can be calculated from the baseline segmentation. Same with the centerline one
      • Implementing generic multi-stage approach in MONAILabel is a bit of a work
        • In MONAI core this is easier to set up
    • Why one model? Having one upper and one lower is OK for us
      • Even lower + upper + bone + implant/tooth separation is a possibility
      • Advantage of one multi-stage model is that we have only one system
      • If we have both upper and lower then we need more data
      • Clinically we’ll only have either upper or lower
    • How do we connect the stages?
      • Centroid/skeleton using numbers (not images) is regression (not segmentation)
      • Concatenate input numbers on the “bottom of the UNet” where we have a huge array of numbers after downsampling
    • MONAI files
      • .pt: model (need to define network first etc.)
      • .ts: torch script that contains preprocessing and the inference too
  2. Proposal
    • Simple multi-stage model implementation using MONAI
    • Initial: ROI definition -> Centroids -> Tooth segmentation
    • Later still possible to add for example tooth identification, centerline, implant segmentation, etc.

Illustrations

There are some promising preliminary results

Good result Good result Good result

but there is room for improvement!

Bad result Bad result

Background and References