A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization

Abstract

Edge detection is a fundamental image analysis task, as it provides insight on the content of an image. There are weaknesses in some of the edge detectors developed until now, such as disconnected edges, the impossibility to detect branching edges, or the need for a ground truth that is not always accessible. Therefore, a specialized detector that is optimized for the image particularities can help improve edge detection performance. In this paper, we apply transfer learning to optimize cellular automata (CA) rules for edge detection using particle swarm optimization (PSO). Cellular automata provide fast computation, while rule optimization provides adaptability to the properties of the target images. We use transfer learning from synthetic to medical images because expert-annotated medical data is typically difficult to obtain. We show that our method is tunable for medical images with different properties, and we show that, for more difficult edge detection tasks, batch optimization can be used to boost the quality of the edges. Our method is suitable for the identification of structures, such as cardiac cavities on medical images, and could be used as a component of an automatic radiology decision support tool.

Precision Marketing and Brand Communication Model Using Particle Swarm Optimization Algorithm

“…e proportion of these three is not much different. Although young people are very dependent on online consumption at present, the convenient experience of offline purchase can not be ignored [13].…”

Defects Prediction Method for Radiographic Images Based on Random PSO Using Regional Fluctuation Sensitivity

“…Entropy theory has been effectively applied in image processing, including the use of PSO models for edge detection, segmentation, and thresholding [ 31 , 32 , 33 ]. Despite its ability to optimize global values by analyzing regional variations, PSO fails to detect defects on a global statistical scale.…”

“…The relationship between exposure settings and image quality relies on a quantified method to determine whether the actual data are optimal for detection purposes. In contrast to the International Electrotechnical Commission (IEC) standard guidelines [33,34], conventional exposure indicators employ a preset reference for exposure settings as directed by the manufacturer. Conversely, the entropy algorithm offers a quantified approach to assess image quality, utilizing abundance as a reference for specific tested objects.…”

Modeling and Numerical Validation for an Algorithm Based on Cellular Automata to Reduce Noise in Digital Images

“…Meanwhile, in [21], cellular automata rules are optimized for edge detection employing Particle Swarm Optimization (PSO). In this work, it is exposed that cellular automata provides fast computation, the optimization rule, and the adaptability to target images.…”