腎臟癌以主動式輪廓模式的機器學習對腎臟癌圈選的研究
盧致誠1,2 許巍嚴2 林憲雄１ 林嘉禾１ 邱毅平１ 范文宙１鄭哲舟１
１奇美醫療財團法人柳營奇美醫院 外科部 泌尿外科
２國立中正大學 資訊管理研究所
Active contour model of machine learning to evlauate the kidney cancer
Chih-Cheng Lu1,2, Wei-Yen Shiu2, Chian-Shiung Lin1, Chia-Ho Lin1, Yi-Ping Chiu1, Wen-Chou Fan1, Tse-Chou Cheng1
１Division of Urology, Department of Surgery, Chi Mei Medical Center, Liouying, Tainan
2Department of Management Information System, National Chung Cheng University, Chiayi
Purpose:
In the present study, we retrospectively analyzed the records of surgical confirmed kidney cancer with renal cell carcinoma (RCC) pathology in the database of the hospital. We evaluated the significance of cancer size by assessing its active contour model (ACM) outcomes. The aim of our study was to develop an ACM method to measure the radiological size of kidney cancer on CT in the hospital patients.
Materials and Methods:
This paper proposed a set of medical image processing, applying images provided by the hospital and select the more obvious cases by the doctors, after the first treatment to remove noise image, and the kidney cancer contour would be circled by using snakes (ACM) method. The study protocol was approved by the institutional review board of the hospital.
Results:
Two hundred and seventy-seven files of CT imaging were collected. The results showed that the experimental outcome has highly similarity with the medical professional manual contour as ground truth. The accuracy rate is higher than 99%.
Conclusion:
We have developed a novel ACM approach that well combines a knowledge-based system to contour the kidney cancer size in CT imaging to support the clinical decision. The innovative methods of ACM of our study is not going to replace the present staging system of kidney cancers based on AJCC system. It may provide a linchpin of further machine learning of kidney cancer staging which is critical for treatment planning in the future.