ABSTRACT
With the development of machine learning techniques in the image processing field, research related to semantic segmentation has attracted much attention. Especially in medical image segmentation requires highly pixel-by-pixel accurate results. Given that it is difficult to obtain test images with their ground truth in the medical field, we aim to develop a robust method in an environment with few test images. Specifically, we improve Textonboost by using differential evolution and stochastic hill climbing methods. Experimental results showed that the proposed method outperformed conventional methods in terms of accuracy.
- Janez Brest, Ales Zamuda, Borko Boskovic, Mirjam Sepesy Maucec, and Viljem Zumer. 2009. Dynamic optimization using Self-Adaptive Differential Evolution. In 2009 IEEE Congress on Evolutionary Computation. 415--422. Google ScholarCross Ref
- Keiko Ono, Daisuke Tawara, and Yoshiko Hanada. 2019. Textonboost based on differential evolution. In Proceedings of the Genetic and Evolutionary Computation Conference Companion. 322--323. Google ScholarDigital Library
- Jamie Shotton, John Winn, Carsten Rother, and Antonio Criminisi. 2009. Texton-boost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context. International journal of computer vision 81, 1 (2009), 2--23. Google ScholarDigital Library
Index Terms
- Textonmap optimization for spine segmentation using adaptive differential evolution
Recommendations
Brain voxel classification in magnetic resonance images using niche differential evolution based Bayesian inference of variational mixture of Gaussians
Classification of brain voxels into gray matter, white matter, and cerebrospinal fluid (CSF) using magnetic resonance imaging (MRI) is pivotal for quantitative brain analyses. In spite of its computational effectiveness, the most commonly used ...
Automatic method for white matter lesion segmentation based on T1‐fluid‐attenuated inversion recovery images
The authors propose a fast and effective solution for automatic segmentation of white matter lesions by using T1 and fluid‐attenuated inversion recovery (FLAIR) image modalities with no need for manual segmentation and atlas registration. Initially, a ...
Adaptive 3-D segmentation algorithms for microscope images using local in-focus, and contrast features: application to Pap smears
ICIP '95: Proceedings of the 1995 International Conference on Image Processing (Vol. 3)-Volume 3 - Volume 3Presents algorithms for segmenting three-dimensional (3-D) brightfield microscope images of thick and overlapped regions of Pap smears, acquired using a specially-developed high-speed 3-D microscope system. Algorithms for segmenting these images require ...
Comments