Automatic Segmentation of Meniscus in Multispectral MRI Using Regions with Convolutional Neural Network (R-CNN)
- PDF / 4,199,676 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 79 Downloads / 220 Views
ORIGINAL PAPER
Automatic Segmentation of Meniscus in Multispectral MRI Using Regions with Convolutional Neural Network (R-CNN) Emre ÖLMEZ 1 & Volkan AKDOĞAN 2 & Murat KORKMAZ 3 & Orhan ER 4
# Society for Imaging Informatics in Medicine 2020
Abstract The meniscus has a significant function in human anatomy, and Magnetic Resonance Imaging (MRI) has an essential role in meniscus examination. Due to a variety of MRI data, it is excessively difficult to segment the meniscus with image processing methods. An MRI data sequence contains multiple images, and the region features we are looking for may vary from each image in the sequence. Therefore, feature extraction becomes more difficult, and hence, explicitly programming for segmentation becomes more difficult. Convolutional Neural Network (CNN) extracts features directly from images and thus eliminates the need for manual feature extraction. Regions with Convolutional Neural Network (R-CNN) allow us to use CNN features in object detection problems by combining CNN features with Region Proposals. In this study, we designed and trained an R-CNN for detecting meniscus region in MRI data sequence. We used transfer learning for training R-CNN with a small amount of meniscus data. After detection of the meniscus region by R-CNN, we segmented meniscus by morphological image analysis using two different MRI sequences. Automatic detection of the meniscus region with R-CNN made the meniscus segmentation process easier, and the use of different contrast features of two different image sequences allowed us to differentiate the meniscus from its surroundings. Keywords Automatic segmentation of meniscus . Regions with convolutional neural network . Region proposals . Transfer learning . Deep learning
Introduction The meniscus is a significant part of human anatomy. In each knee, there are two (inner and outer) fibro cartilaginous meniscus tissues. Menisci are in the shape of a half-moon, and peripheric parts of the meniscus are convex and triangle, getting thinner from outward to inward and is placed the way that
* Emre ÖLMEZ [email protected] 1
Department of Mechatronics Engineering, Yozgat Bozok University, 66200 Yozgat, Turkey
2
Department of Electrical and Electronics Engineering, Yozgat Bozok University, 66200 Yozgat, Turkey
3
Department of Orthopedic Surgery, Yozgat Bozok University, 66200 Yozgat, Turkey
4
Department of Computer Engineering, Yozgat Bozok University, 66200 Yozgat, Turkey
covers 3/2 part of the face of tibia joint. Menisci are elastic structures, and they consist of dense and firm braid shaped collagen fibres to resist compression pressures. Shock absorbing function of the meniscus provides knee stability that helps to feed joint cartilage and assists to spread weight evenly and protects joint cartilage from high pressure. For these reasons, this paper focused on segmenting the critical meniscus tissue [1, 2]. Usually, segmentation of Region of Interest (ROI) is the first main problem in medical image processing [3–5]. Technics used for extract
Data Loading...
