[Defense] A Contrastive Learning Approach For Automated Identification Of Anatomical Landmarks In 3D Human Torso Surface Scans
Thursday, November 21, 2024
2:00 pm - 3:30 pm
In
Partial
Fulfillment
of
the
Requirements
for
the
Degree
of
Doctor
of
Philosophy
Sara
Bouhali
will
defend
her
dissertation
A
Contrastive
Learning
Approach
For
Automated
Identification
Of
Anatomical
Landmarks
In
3D
Human
Torso
Surface
Scans
Abstract
The utilization of three-dimensional (3D) imaging is expanding for quantifying breast morphology, particularly for assessing breast symmetry and for longitudinal monitoring of changes in breast appearance during reconstructive surgery. Breast morphometry from 3D photographs has been reported, however, several studies utilize manual identification of anatomical landmarks (fiducials), which is time-consuming and subject to operator bias. Using machine learning (ML) algorithms to automate the identification of fiducials would mitigate operator bias and yield reliable, objective measurements. Here, we propose an ML framework to automate the identification of thirteen anatomical landmarks in 3D photographs of female torsos. An ML framework was developed to detect individual fiducial points using supervised contrastive learning. The framework includes a feature extractor utilizing a convolutional neural network backbone and a multi-layer perceptron to generate and condense a feature map for each image. Specifically, we utilized a feature bank that is updated regularly during training to optimize the representation of fiducial points and filter out background (clutter) points. This framework ensures that features of the same fiducial point are similar to each other but distinct from features of other fiducial points and background clutter. Inference is performed by computing a score map for each fiducial point, where the highest score indicates the predicted point location. Extensive experiments were conducted on a breast reconstruction dataset and a public dataset to rigorously validate the effectiveness of the proposed method. The evaluation employed a qualitative and quantitative analysis to assess various performance aspects of the model. The proposed approach demonstrated competitive performance in comparison to existing techniques for automated fiducial points identification in 3D images. The proposed framework can be integrated into various medical applications, such as the registration of 3D torso images from different clinical visits and the evaluation of breast symmetry in plastic surgery.
Thursday,
November
21,
2024
2:00
PM
-
4:00
PM
PGH 501B
Dr. Fatima Merchant, dissertation advisor
Faculty, students, and the general public are invited.
