Computational Anatomy Based on Whole Body Imaging

This chapter presents the background and purpose of the computational anatomy research field from medical (needs) and technical (seeds) perspectives. We begin with a historical overview of the emergence of the discipline of computational anatomy (Sect. 1.1). Then, overviews of existing fields and the potential impact of computational anatomy on them are described (Sect. 1.2). To clarify the value of computational anatomy from the clinical viewpoint, medical education, diagnostic imaging, surgery, and radiation therapy are discussed, including situations that motivated the emergence of computational anatomy (Sect. 1.2.1). Similarly, from the technical (computer science) viewpoint, important technological developments providing the theoretical and algorithmic basis of computational anatomy are explored (Sect. 1.2.2). This book mainly addresses the development of whole-body computational anatomy, which is supported by the rapid progress of whole-body 3D imaging technologies. Thus, the impact of whole-body imaging (Sect. 1.3.1) and its utilization (Sect. 1.3.2) are discussed. Finally, the structure of this book is outlined (Sect. 1.4).

In this section, fundamental theories and techniques for understanding computational anatomy are described. First, the mathematical foundations of a signal processing and of statistics are discussed. Signal processing is the basis of the image processing required for extracting local image features that are useful for the identification of the organ regions in medical images, which is one of the most important tasks in CA. A knowledge of statistics is needed for understanding the statistical shape models (SSMs) of the organs and the registration of the models to given medical images, which is one of the most basic techniques used for the organ region identification. Second, model representations of the organs, e.g., point distribution models (PDMs), medial representations (m-reps), and nonuniform rational basis splines (NURBS), are described. Different models, e.g., a point distribution model (PDM), a medial representation (m-rep), or nonuniform rational basis splines (NURBS), can be employed for representing a target organ, and a region of a target organ in a given image can be identified by registering the employed model to the image: Several techniques for the model registration are also discussed in this chapter. The performance of the organ region identification can change depending on the employed representation and on the employed registration technique. Finally, the difficulties posed by multiple organ registration and the handling of anatomical anomalies are considered.

This chapter presents examples of medical image understanding algorithms using computational anatomy models explained in Chap. 2. After the introductory in Sect. 3.1, Sect. 3.2 shows segmentation algorithms for vertebrae, ribs, and hip joints. Segmentation algorithms for skeletal muscle and detection algorithms for lymph nodes are explained in Sects. 3.3 and 3.4, respectively. Section 3.5 deals with algorithms for understanding organs/tissues in the head and neck regions and starts with computational neuroanatomy, followed by analysis and segmentation algorithms for white matter, brain CT, oral regions, fundus oculi, and retinal optical coherence tomography (OCT). Algorithms useful in the thorax, specifically for the lungs, tracheobronchial tree, vessels, and interlobar fissures from a thoracic CT volume, are presented in Sect. 3.6. Section 3.7 provides algorithms for breast ultrasound imaging, i.e., mammography and breast MRI. Cardiac imaging algorithms in an echocardiographic image sequence and MR images as well as coronary arteries in a CT volume are explained in Sect. 3.8. Section 3.9 deals with segmentation algorithms of abdominal organs, including the liver, pancreas, spleen, kidneys, gastrointestinal tract, and abdominal blood vessels, followed by anatomical labeling of segmented vessels.

This chapter shows applied technologies using computational anatomy (CA) models. CA systems based on clinical images assist physicians by providing useful information related to diagnostic and therapeutic procedures. Such systems include computer-aided diagnosis and computer-assisted surgery systems. A thorough understanding of anatomy is essential when designing these systems. It is important to understand how anatomical information extracted by a computer is used. In this chapter, we introduce applications of CA in three categories: (a) computer-aided diagnosis, (b) computer-assisted therapy and intervention, and (c) computer-assisted autopsy imaging. The technical details of these applications are discussed.

Computational anatomy (CA) is still a developing discipline. It offers a wide variety of research areas for applications in clinical support and medical science. The editors and the authors hope this book will serve as a guide to students and researchers interested in this exciting new discipline.