Chapter title |
An Integrated Framework for Automatic Ki-67 Scoring in Pancreatic Neuroendocrine Tumor
|
---|---|
Chapter number | 55 |
Book title |
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013
|
Published in |
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention, September 2013
|
DOI | 10.1007/978-3-642-40811-3_55 |
Pubmed ID | |
Book ISBNs |
978-3-64-240810-6, 978-3-64-240811-3
|
Authors |
Xing F, Su H, Yang L, Fuyong Xing, Hai Su, Lin Yang, Xing, Fuyong, Su, Hai, Yang, Lin |
Abstract |
The Ki-67 labeling index is a valid and important biomarker to gauge neuroendocrine tumor cell progression. Automatic Ki-67 assessment is very challenging due to complex variations of cell characteristics. In this paper, we propose an integrated learning-based framework for accurate Ki-67 scoring in pancreatic neuroendocrine tumor. The main contributions of our method are: a novel and robust cell detection algorithm is designed to localize both tumor and non-tumor cells; a repulsive deformable model is applied to correct touching cell segmentation; a two stage learning-based scheme combining cellular features and regional structure information is proposed to differentiate tumor from non-tumor cells (such as lymphocytes); an integrated automatic framework is developed to accurately assess the Ki-67 labeling index. The proposed method has been extensively evaluated on 101 tissue microarray (TMA) whole discs, and the cell detection performance is comparable to manual annotations. The automatic Ki-67 score is very accurate compared with pathologists' estimation. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Mexico | 1 | 3% |
United States | 1 | 3% |
Pakistan | 1 | 3% |
Unknown | 32 | 91% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 7 | 20% |
Student > Ph. D. Student | 6 | 17% |
Student > Bachelor | 4 | 11% |
Student > Master | 4 | 11% |
Other | 3 | 9% |
Other | 5 | 14% |
Unknown | 6 | 17% |
Readers by discipline | Count | As % |
---|---|---|
Medicine and Dentistry | 11 | 31% |
Computer Science | 10 | 29% |
Agricultural and Biological Sciences | 3 | 9% |
Engineering | 3 | 9% |
Social Sciences | 1 | 3% |
Other | 1 | 3% |
Unknown | 6 | 17% |