Developing and Evaluating Deep Learning Algorithms for Object Detection: Key Points for Achieving Superior Model Performance

• Published in: Korean journal of radiology Vol. 24; no. 7; pp. 698 - 714
• Main Authors: Oh, Jang-Hoon, Kim, Hyug-Gi, Lee, Kyung Mi
• Format: Journal Article
• Language: English
• Published: Korea (South) The Korean Society of Radiology 01.07.2023
• Subjects: Accuracy; Brain cancer; Brain research; Classification; Data collection; Datasets; Deep learning; Disease; Labeling; Magnetic resonance imaging; Medical imaging; Medical research; Metastasis; Performance evaluation; Sinusitis; Technology, Experiment, and Physics; Telematics; Tomography; Deep learning; Image modality; Object detection; Disease subclass; Data augmentation; Hyperparameter optimization; Diseases with small sizes; Deep learning workflow
• ISSN: 1229-6929; 2005-8330; 2005-8330
• DOI: 10.3348/kjr.2022.0765

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.