Loading...
ThreshNet: A novel machine learning technique to optimize sensitivity and specificity performance
Xu, Shirley
Xu, Shirley
Citations
Altmetric:
Files
Loading...
Conference paper
Adobe PDF, 756.43 KB
Authors
Other Names
Location
Time Period
Advisors
Original Date
Digitization Date
Issue Date
2023-03
Type
Conference paper
Genre
Keywords
Engineering
Subjects (LCSH)
Citation
Xu, S. (2023). ThreshNet: A novel machine learning technique to optimize sensitivity and specificity performance. Proceedings of the 2023 IEMS Conference, 29, 34-44. https://doi.org/10.62704/10057/26118
Abstract
In image classification applications for medical diagnosis, sensitivity and specificity are important performance metrics that are often inversely related. Both high sensitivity and high specificity are not always achievable for a given neural network; the trade-off and balance between them are not easily controllable. This paper proposes "ThreshNet", a novel method to address this dilemma. ThreshNet is composed of an ensemble of different neural networks. Many well-known networks were leveraged through transfer learning. With custom-designed dense layers, network parameters were tuned to optimize performance and enhance the diversity of members in the ThreshNet networks ensemble. To yield the ThreshNet system's decision, a threshold-based algorithm is proposed. Demonstrated with a brain tumor MRI dataset, ThreshNet systems consistently outperform individual networks. Specific sensitivity-specificity trade-offs and optimization goals can conveniently be achieved by adjusting the threshold parameter. Performance variance among ThreshNet systems is smaller than those among individual networks. To locate tumor(s) predicted by ThreshNet, a ResUNet-based image segmentation model was developed, achieving a Tversky index of 90.49% in predicting pixel-wise masks to mark tumor locations.
Table of Contents
Description
Published in SOAR: Shocker Open Access Repository by Wichita State University Libraries Technical Services, January 2024.
Publisher
Association for Industry, Engineering, and Management Systems
Journal
Book Title
Series
Proceedings of the 2023 IEMS Conference
v.29
v.29
Digital Collection
Finding Aid URL
Use and Reproduction
Archival Collection
PubMed ID
ISSN
2690-3210 (print)
2690-3229 (online)
2690-3229 (online)