Skip to main content
main-content

Über dieses Buch

The objective of this Brief is to provide a solution to the unsolved technical problem in segmentation for the automated bone age assessment system. The task is accomplished by first applying the modified histogram equalized module, then applying the proposed automated anisotropic diffusion technique. It is followed by a novel fuzzy quadruple division scheme to optimize the central segmentation algorithm, and then an additional quality assurance scheme. The designed segmentation framework works without demanding scarce resources such as training sets and skillful operators. The results have shown that the designed framework is capable of separating the soft-tissue and background from the hand bone with high accuracy. This Brief should be especially useful for students and professional researchers in the Biomedical and image processing fields.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract
This chapter informs the readers about the background of bone age assessment of which include the clinical practicality, and the pros and cons of the conventional methods of this assessment. After that, we explain the automated system that is capable of substituting the conventional methods by further elaborating the pitfalls and constraints of this alternative. Then, we define our objective in this book and delimit the discussion scope of this book follow by stating the contributions of this book for the field in hand bone segmentation. Lastly, we provide the outline of the book.
Yan Chai Hum

Chapter 2. Literature Reviews

Abstract
In this chapter, we review the techniques of histogram equation, hand bone segmentation and image segmentation techniques. The basic concepts of those techniques will be analyzed and compared. The objective of this chapter is to show to readers that current techniques are not sufficient to address the hand bone segmentation problems due to various restrictions. Hence, this motivates the need for new technique that is capable of segmenting the hand bone so that the segmented hand bone can be established and implemented in the fully automated computer-aided skeletal age scoring system. The proposed novel framework of hand bone segmentation will then be presented in next Chap.​ 3.
Yan Chai Hum

Chapter 3. Design and Implementation

Abstract
In previous chapter, the weaknesses of conventional segmentation methods have been identified. This concludes the desired segmentation criteria in order to guide the mechanism of the proposed framework of segmentation. The segmentation is performed to partition the hand bone from its background and soft-tissue region in the beginning of this chapter. The challenges of hand bone segmentation are the overlapping intensity between the soft-tissue region and the spongy bone region within the hand bone. Three modules of techniques will be discussed and implemented to solve the problem in this chapter.
Yan Chai Hum

Chapter 4. Result and Discussion

Abstract
In this chapter, the functionality of proposed MBOBHE and the modified anisotropic diffusion will be justified. Both techniques create a suitable environment for the subsequent segmentation modules by reducing the disturbance of uneven illumination, sharpening the edge and smoothing the texture; at the same time, MBOBHE is capable of enhancing the features of ossification sites to improve the performance of computerized BAA. After that, an analytical comparison of AAM segmentation framework with the proposed segmentation framework is performed.
Yan Chai Hum

Chapter 5. Conclusion and Future Works

Abstract
The main book objective has been achieved by designing a segmentation framework that is invariant to both the limitations but at the same time exhibiting accurate and consistent in comparisons to basic segmentation approaches. As a result, empirical and analytical experiments showed that the proposed segmentation framework was able to achieve relatively high accuracy despite the low number of user-specified parameters and no training sample is needed. This property of invariance, automaticity and other desired properties of segmentation have been considered and incorporated in the designed framework in order to make it becoming more practical in many daily applications such as the segmentation stage in computer-aided skeletal age scoring system. This proposed framework minimizes the labor-intensity, time consumption and high dependency on operator expertise and subjectivity; automaticity also implies perfect repeatability and consistency advantage.
Yan Chai Hum

Backmatter

Weitere Informationen