Calendar - 海角社区

海角社区

Skip to main content

[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.

Dissertation Defense Thumbnail (3 of 3)