Jeffrey Dominic

Mr. Jeffrey Dominic


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 October 2021 in Radiology
Verified
Journal Article
Open access
NBNicholas Burris
Nicholas Burris
ZBZhangxing Bian
Zhangxing Bian
JDJeffrey Dominic
Jeffrey Dominic
JZJianyang Zhong
Jianyang Zhong
IHIgnas B. Houben
Ignas B. Houben
CHCharles R. Hatt
Charles R. Hatt
Vascular deformation mapping, a deformable image registration-based technique, enabled reliable comprehensive assessment of the degree and extent of three-dimensional growth among patients with a t... Background Aortic diameter measurements in patients with a thoracic aortic aneurysm (TAA) show wide variation. There is no technique to quantify aortic growth in a three-dimensional (3D) manner. Pu...

4 February 2023 in Bioengineering
Verified
Journal Article
Open access
PDF file
JDJeffrey Dominic
Jeffrey Dominic
NBNandita Bhaskhar
Nandita Bhaskhar
ADArjun D. Desai
Arjun D. Desai
ASAndrew Schmidt
Andrew Schmidt
ERElka Rubin
Elka Rubin
ACAkshay Chaudhari
Akshay Chaudhari
We systematically evaluate the training methodology and efficacy of two inpainting-based pretext tasks of context prediction and context restoration for medical image segmentation using self-supervised learning (SSL). Multiple versions of self-supervised U-Net models were trained to segment MRI and CT datasets, each using a different combination of design choices and pretext tasks to determine the effect of these design choices on segmentation performance. The optimal design choices were used to train SSL models that were then compared with baseline supervised models for computing clinically-relevant metrics in label-limited scenarios. We observed that SSL pretraining with context restoration using 32 × 32 patches and Poission-disc sampling, transferring only the pretrained encoder weights, and fine-tuning immediately with an initial learning rate of 1 × 10−3 provided the most benefit over supervised learning for MRI and CT tissue segmentation accuracy (p < 0.001). For both datasets and most label-limited scenarios, scaling the size of unlabeled pretraining data resulted in improved segmentation performance. SSL models pretrained with this amount of data outperformed baseline supervised models in the computation of clinically-relevant metrics, especially when the performance of supervised learning was low. Our results demonstrate that SSL pretraining using inpainting-based pretext tasks can help increase the robustness of models in label-limited scenarios and reduce worst-case errors that occur with supervised learning.