Furukawa Ryo, Nagamatsu Genki, Oka Shiro, Kotachi Takahiro, Okamoto Yuki, Tanaka Shinji, Kawasaki Hiroshi
Graduate School of Information Sciences, Hiroshima City University, Hiroshima, Japan.
Graduate School and Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan.
Healthc Technol Lett. 2019 Nov 26;6(6):249-254. doi: 10.1049/htl.2019.0070. eCollection 2019 Dec.
For effective in situ endoscopic diagnosis and treatment, measurement of polyp sizes is important. For this purpose, 3D endoscopic systems have been researched. Among such systems, an active stereo technique, which projects a special pattern wherein each feature is coded, is a promising approach because of simplicity and high precision. However, previous works of this approach have problems. First, the quality of 3D reconstruction depended on the stabilities of feature extraction from the images captured by the endoscope camera. Second, due to the limited pattern projection area, the reconstructed region was relatively small. In this Letter, the authors propose a learning-based technique using convolutional neural networks to solve the first problem and an extended bundle adjustment technique, which integrates multiple shapes into a consistent single shape, to address the second. The effectiveness of the proposed techniques compared to previous techniques was evaluated experimentally.
为了实现有效的原位内镜诊断和治疗，息肉大小的测量至关重要。为此，人们对三维内镜系统进行了研究。在这类系统中，主动立体技术通过投射一种对每个特征进行编码的特殊图案，因其简单性和高精度而成为一种很有前景的方法。然而，该方法先前的研究存在问题。首先，三维重建的质量取决于从内镜摄像头拍摄的图像中提取特征的稳定性。其次，由于图案投影区域有限，重建区域相对较小。在本信函中，作者提出了一种基于卷积神经网络的学习技术来解决第一个问题，并提出了一种扩展的光束平差技术，即将多个形状整合为一个一致的单一形状，以解决第二个问题。通过实验评估了所提出技术与先前技术相比的有效性。
