Chapter title |
Automatic Fetal Measurements in Ultrasound Using Constrained Probabilistic Boosting Tree
|
---|---|
Chapter number | 69 |
Book title |
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007
|
Published in |
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention, October 2007
|
DOI | 10.1007/978-3-540-75759-7_69 |
Pubmed ID | |
Book ISBNs |
978-3-54-075758-0, 978-3-54-075759-7
|
Authors |
Carneiro, Gustavo, Georgescu, Bogdan, Good, Sara, Comaniciu, Dorin, Gustavo Carneiro, Bogdan Georgescu, Sara Good, Dorin Comaniciu |
Abstract |
Automatic delineation and robust measurement of fetal anat-omical structures in 2D ultrasound images is a challenging task due to the complexity of the object appearance, noise, shadows, and quantity of information to be processed. Previous solutions rely on explicit encoding of prior knowledge and formulate the problem as a perceptual grouping task solved through clustering or variational approaches. These methods are known to be limited by the validity of the underlying assumptions and cannot capture complex structure appearances. We propose a novel system for fast automatic obstetric measurements by directly exploiting a large database of expert annotated fetal anatomical structures in ultrasound images. Our method learns to distinguish between the appearance of the object of interest and background by training a discriminative constrained probabilistic boosting tree classifier. This system is able to handle previously unsolved problems in this domain, such as the effective segmentation of fetal abdomens. We show results on fully automatic measurement of head circumference, biparietal diameter, abdominal circumference and femur length. Unparalleled extensive experiments show that our system is, on average, close to the accuracy of experts in terms of segmentation and obstetric measurements. Finally, this system runs under half second on a standard dual-core PC computer. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
China | 2 | 4% |
Italy | 1 | 2% |
Germany | 1 | 2% |
India | 1 | 2% |
United States | 1 | 2% |
Unknown | 48 | 89% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 13 | 24% |
Student > Ph. D. Student | 11 | 20% |
Student > Doctoral Student | 6 | 11% |
Student > Bachelor | 5 | 9% |
Student > Master | 5 | 9% |
Other | 7 | 13% |
Unknown | 7 | 13% |
Readers by discipline | Count | As % |
---|---|---|
Computer Science | 16 | 30% |
Medicine and Dentistry | 13 | 24% |
Engineering | 7 | 13% |
Sports and Recreations | 3 | 6% |
Mathematics | 2 | 4% |
Other | 6 | 11% |
Unknown | 7 | 13% |