Title | ||
---|---|---|
CNN Architecture for Surgical Image Segmentation Systems with Recursive Network Structure to Mitigate Overfitting |
Abstract | ||
---|---|---|
Laparoscopic surgery, a minimally invasive camera-aided surgery, is performed commonly. However, it requires a camera assistant who holds and maneuvers a laparoscope. If the laparoscope can be controlled automatically using a robot, a surgeon can perform the operation without a camera assistant, which would be beneficial in the areas suffering from lack of surgeons. In this paper, a prototype image segmentation architecture, based on a convolutional neural network, is proposed to realize an automatic laparoscope control for cholecystectomy. Since the learning dataset is annotated manually by a few surgeons, its scale is currently quite limited. Therefore, we devised a recursive network structure, with some sub-networks which are used multiple times, to mitigate overfitting. Furthermore, instead of the common transposed convolution, the flip-based subpixel reconstruction is introduced into upsampling layers. Evaluation results reveal that these improvements bring better classification accuracy without increasing the number of parameters. The system shows a throughput sufficient for real-time laparoscope robot control with a single NVIDIA GTX 1080 GPU. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CANDAR.2019.00029 | 2019 Seventh International Symposium on Computing and Networking (CANDAR) |
Keywords | Field | DocType |
CNN,Image Segmentation,Surgical Image,Recursive Network | Computer vision,Robot control,Convolutional neural network,Computer science,Image segmentation,Artificial intelligence,Overfitting,Subpixel rendering,Robot,Upsampling,Recursion | Conference |
ISSN | ISBN | Citations |
2379-1888 | 978-1-7281-4726-0 | 0 |
PageRank | References | Authors |
0.34 | 2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taito Manabe | 1 | 3 | 3.15 |
Koki Tomonaga | 2 | 0 | 1.69 |
Yuichiro Shibata | 3 | 157 | 37.99 |