Search

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.

Abstract: Objective: To assess the correlation between the size of endometrial polyps and the histopathologic diagnosis of hyperplasia or cancer. Methods: A retrospective study was conducted using databases of the outpatient clinic at Antonio Pedro University Hospital in Niterói, Brazil, and of a private hysteroscopy service. The analysis included 1136 asymptomatic patients with an endometrial polyp identified on hysteroscopy, with pathologic examination, during the period 1999–2012. The polyp size, the patients’ age, the indication for hysteroscopic examination, and the use of hormone medication were compared with the finding of hyperplasia in the pathologic examination. Results: Only polyp size showed statistical significance among the variables analyzed (P <0.05). Endometrial polyps greater than 15mm showed a hyperplasia rate of 14.8%, compared with 7.7% in the group with smaller polyps (P <0.05). Conclusion: Endometrial polyps measuring more than 15mm were associated with hyperplasia. [Copyright &y& Elsevier]