Bayesian CNN for Segmentation Uncertainty Inference on 4D Ultrasound Images of the Femoral Cartilage for Guidance in Robotic Knee Arthroscopy
| Autor: | Davide Fontanarosa, Maria Antico, Fumio Sasazawa, Gustavo Carneiro, Ajay K. Pandey, Yu Takeda, Ross Crawford, Anjali Jaiprakash, Marie-Luise Wille |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
General Computer Science
Computer science robotic knee arthroscopy Monte Carlo method Bayesian probability ultrasound guided arthroscopy Inference 01 natural sciences Convolutional neural network ultrasound guided minimally invasive surgery 03 medical and health sciences 0302 clinical medicine 0103 physical sciences medicine General Materials Science Segmentation Computer vision MRI-US registration uncertainty 010301 acoustics ultrasound guidance Pixel medicine.diagnostic_test business.industry General Engineering Magnetic resonance imaging Image segmentation Artificial intelligence lcsh:Electrical engineering. Electronics. Nuclear engineering business lcsh:TK1-9971 030217 neurology & neurosurgery |
| Zdroj: | IEEE Access, Vol 8, Pp 223961-223975 (2020) |
| ISSN: | 2169-3536 |
| Popis: | Ultrasound (US) imaging is a complex imaging modality, where the tissues are typically characterised by an inhomogeneous image intensity and by a variable image definition at the boundaries that depends on the direction of the incident sound wave. For this reason, conventional image segmentation approaches where the regions of interest are represented by exact masks are inherently inefficient for US images. To solve this issue, we present the first application of a Bayesian convolutional neural network (CNN) based on Monte Carlo dropout on US imaging. This approach is particularly relevant for quantitative applications since differently from traditional CNNs, it enables to infer for each image pixel not only the probability of being part of the target but also the algorithm confidence (i.e. uncertainty) in assigning that probability. In this work, this technique has been applied on US images of the femoral cartilage in the framework of a new application, where high-refresh-rate volumetric US is used for guidance in minimally invasive robotic surgery for the knee. Two options were explored, where the Bayesian CNN was trained with the femoral cartilage contoured either on US, or on magnetic resonance imaging (MRI) and then projected onto the corresponding US volume. To evaluate the segmentation performance, we propose a novel approach where a probabilistic ground-truth annotation was generated combining the femoral cartilage contours from registered US and MRI volumes. Both cases produced a significantly better segmentation performance when compared against traditional CNNs, achieving a dice score coefficient increase of about 6% and 8%, respectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|