ATD: A Multiplatform for Semiautomatic 3-D Detection of Kidneys and Their Pathology in Real Time

作者：Skounakis Emmanouil^*; Banitsas Konstantinos; Badii Atta; Tzoulakis Stavros; Maravelakis Emmanuel; Konstantaras Antonios

来源：IEEE Transactions on Human-Machine Systems, 2014, 44(1): 146-153.

DOI：10.1109/THMS.2013.2290011

• Abnormalities detection
• automatic annotation
• kidney
• kidney pathology
• kidney segmentation
• region of interest (ROI)
• stone
• tumor

This research presents a novel multifunctional platform focusing on the clinical diagnosis of kidneys and their pathology (tumors, stones and cysts), using a %26quot;templates%26quot;-based technique. As a first step, specialist clinicians train the system by accurately annotating the kidneys and their abnormalities creating %26quot;3-D golden standard models.%26quot; Then, medical technicians experimentally adjust rules and parameters (stored as %26quot;templates%26quot;) for the integrated %26quot; automatic recognition framework%26quot; to achieve results which are closest to those of the clinicians. These parameters can later be used by nonexperts to achieve increased automation in the identification process. The system%26apos;s functionality was tested on 20 MRI datasets (552 images), while the %26quot; automatic 3-D models%26quot; created were validated against the %26quot; 3-D golden standard models.%26quot; Results are promising as they yield an average accuracy of 97.2% in successfully identifying kidneys and 96.1% of their abnormalities thus outperforming existing methods both in accuracy and in processing time needed.

• 出版日期2014-2