DEEP Q-NAS: A new algorithm based on neural architecture search and reinforcement learning for brain tumor identification from MRI.
Authors
Affiliations (6)
Affiliations (6)
- Precision Agriculture and Intelligent Robotics Laboratory, Department of Soil and Water Systems, University of Idaho, Moscow, ID, United States. Electronic address: [email protected].
- School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, Queensland, Australia; Commonwealth Scientific and Industrial Research Organization, Brisbane, Queensland, Australia. Electronic address: [email protected].
- Department of Electrical and Electronic Engineering, Bangladesh Army University of Engineering and Technology, Natore, Bangladesh. Electronic address: [email protected].
- Ecosystem Change and Population Health Research Group, Centre for Immunology and Infection Control, School of Public Health and Social Work, Queensland University of Technology, Kelvin Grove, Brisbane, Queensland, Australia. Electronic address: [email protected].
- Department of Dental Surgery, Dhaka Dental College, University of Dhaka, Dhaka, Bangladesh. Electronic address: [email protected].
- Department of Electrical Engineering, New Mexico Institute of Mining and Technology, Socorro, NM, United States. Electronic address: [email protected].
Abstract
A significant obstacle in brain tumor treatment planning is determining the tumor's actual size. Magnetic resonance imaging (MRI) is one of the first-line brain tumor diagnosis. It takes a lot of effort and mostly depends on the operator's experience to manually separate the size of a brain tumor from 3D MRI volumes. Machine learning has been vastly enhanced by deep learning and computer-aided tumor detection methods. This study proposes to investigate the architecture of object detectors, specifically focusing on search efficiency. In order to provide more specificity, our goal is to effectively explore the Feature Pyramid Network (FPN) and prediction head of a straightforward anchor-free object detector called DEEP Q-NAS. The study utilized the BraTS 2021 dataset which includes multi-parametric magnetic resonance imaging (mpMRI) scans. The architecture we found outperforms the latest object detection models (like Fast R-CNN, YOLOv7, and YOLOv8) by 2.2 to 7 points with average precision (AP) on the MS COCO 2017 dataset. It has a similar level of complexity and less memory usage, which shows how effective our proposed NAS is for object detection. The DEEP Q-NAS with ResNeXt-152 model demonstrates the highest level of detection accuracy, achieving a rate of 99%.