Text

theses

In recent decades, with increasing amount of medical data, clinical trials are designed and conducted to explore whether a medical strategy, treatment, or device is safe and effective for humans. In clinical trials, due to the large variance of collected image data and limited golden standard training samples, designing a robust and automated algorithm or framework for quantitative medical image analysis is still challenging and active field of research. Many state-of-the-art algorithms are designed/trained for specific anatomies or tasks with corresponding prior knowledge. In this dissertation, we focus on robust and easy-to-use solutions for two fundamental and key modules in medical image analysis, specifically, anatomy recognition and segmentation. The medical image recognition is formulated as a classification problem to identify the body section from which the image is taken. The problem is solved by a patch-based convolutional neural network (CNN). The proposed method can utilize the image-level label to discover discriminative local patches without local annotations and train classifier using these local features. Its performance in our application is superior to conventional models using ad-hoc designed features as well as standard CNN. Accurate and efficient image recognition serves as a reliable initialization module for anatomy segmentation algorithms. In medical image segmentation, precise labeling usually relies on prior knowledge due to ambiguous visual clues of different anatomies and between-subject variance. We use Gaussian Mixture Model and Markov Random Field to model the appearances and spatial relationships of voxels in medical image. To finely utilize the prior knowledge from training atlases (medical image and its corresponding label image), we design an adaptive statistical atlas based method to segment new subjects which could be very different from the training samples. The method is shown robust and accurate in brain segmentation and can be easily applied in other applications.

ETD_7618

Ph.D.

Includes bibliographical references

by Zhennan Yan

doi:10.7282/T3GM89MG

ETD doctoral

The author owns the copyright to this work.