No abstract

A novel computer-aided detection method based on deep learning framework was proposed to detect small intestinal ulcer and erosion in wireless capsule endoscopy (WCE) images. To the best of our knowledge, this is the first time that deep learning framework has been exploited on automated ulcer and erosion detection in WCE images. Compared with the traditional detection method, deep learning framework can produce image features directly from the data and increase recognition accuracy as well as efficiency, especially for big data. The developed method included image cropping and image compression. The AlexNet convolutional neural network was trained to the database with tens of thousands of WCE images to differentiate lesion and normal tissue. The results of ulcer and erosion detection reached a high accuracy of 95.16% and 95.34%, sensitivity of 96.80% and 93.67%, and specificity of 94.79% and 95.98%, correspondingly. The area under the receiver operating characteristic curve was over 0.98 in both of the networks. The promising results indicate that the proposed method has the potential to work in tandem with doctors to efficiently detect intestinal ulcer and erosion.

We proposed a dual focus dual channel spectral domain optical coherence tomography (SD-OCT) for simultaneous imaging of the whole eye segments from cornea to the retina. By using dual channels the system solved the problem of limited imaging depth of SD-OCT. By using dual focus the system solved the problem of simultaneous light focusing on the anterior segment of the eye and the retina. Dual focusing was achieved by adjusting the collimating lenses so the divergence of the two probing beams was tuned to make them focused at different depth in the eye. We further achieved full range complex (FRC) SD-OCT in one channel to increase the depth range for anterior segment imaging. The system was successfully tested by imaging a human eye in vivo.

High‐resolution and real‐time visualization of the morphological changes during embryonic development are critical for studying congenital anomalies. Optical coherence tomography (OCT) has been used to investigate the process of embryogenesis. However, the structural visibility of the embryo is decreased with the depth due to signal roll‐off and high light scattering. To overcome these obstacles, in this study, combined is a spectral‐domain OCT (SD‐OCT) with gold nanorods (GNRs) for 2D/3D imaging of live mouse embryos. Inductively coupled plasma mass spectrometry is used to confirm that GNRs can be effectively delivered to the embryos during ex vivo culture. OCT signal, image contrast, and penetration depth are all enhanced on the embryos with GNRs. These results show that after GNR treatment, more accurate spatial localization and better contrasting of the borders among organs can be observed on E9.5 and E10.5 mouse embryos. Furthermore, the strong optical absorbance of GNRs results in much clearer 3D images of the embryos, which can be used for calculating the heart areas and volumes of E9.5 and E10.5 embryos. These findings provide a promising strategy for monitoring organ development and detecting congenital structural abnormalities in mice.

SD-OCT, via extended imaging depth through a dual-channel, dual-focus approach, is a feasible and practical modality for noninvasive imaging and measurement of ocular accommodation.