7 February 2019 in Biomedical Optics Express
We report parallel-trained deep neural networks for automated endoscopic OCT image segmentation feasible even with a limited training data set. These U-Net-based deep neural networks were trained using a modified dice loss function and manual segmentations of ultrahigh-resolution cross-sectional images collected by an 800 nm OCT endoscopic system. The method was tested on in vivo guinea pig esophagus images. Results showed its robust layer segmentation capability with a boundary error of 1.4 µm insensitive to lay topology disorders. To further illustrate its clinical potential, the method was applied to differentiating in vivo OCT esophagus images from an eosinophilic esophagitis (EOE) model and its control group, and the results clearly demonstrated quantitative changes in the top esophageal layers’ thickness in the EOE model.
8 June 2020 in Biomedical Optics Express
We report an end-to-end image compression framework for retina optical coherence tomography (OCT) images based on convolutional neural networks (CNNs), which achieved an image size compression ratio as high as 80. Our compression scheme consists of three parts: data preprocessing, compression CNNs, and reconstruction CNNs. The preprocessing module was designed to reduce OCT speckle noise and segment out the region of interest. Skip connections with quantization were developed and added between the compression CNNs and the reconstruction CNNs to reserve the fine-structure information. Two networks were trained together by taking the semantic segmented images from the preprocessing module as input. To train the two networks sensitive to both low and high frequency information, we leveraged an objective function with two components: an adversarial discriminator to judge the high frequency information and a differentiable multi-scale structural similarity (MS-SSIM) penalty to evaluate the low frequency information. The proposed framework was trained and evaluated on ophthalmic OCT images with pathological information. The evaluation showed reconstructed images can still achieve above 99% similarity in terms of MS-SSIM when the compression ratio reached 40. Furthermore, the reconstructed images after 80-fold compression with the proposed framework even presented comparable quality with those of a compression ratio 20 from state-of-the-art methods. The test results showed that the proposed framework outperformed other methods in terms of both MS-SSIM and visualization, which was more obvious at higher compression ratios. Compression and reconstruction were fast and took only about 0.015 seconds per image. The results suggested a promising potential of deep neural networks on customized medical image compression, particularly valuable for effective image storage and tele-transfer.
9 January 2020 in Biomedical Optics Express
An ultra-sensitive, wide-range force loading scheme is proposed for compression optical coherence elastography (OCE) that allows for the quantitative analysis of cervical tissue elasticity ex vivo. We designed a force loading apparatus featuring a water sink for minuscule incremental loading through a volume-controlled water droplet, from which the Young’s modulus can be calculated by fitting the stress-strain curve. We validated the performance of the proposed OCE system on homogenous agar phantoms, showing the Young’s modulus can be accurately estimated using this scheme. We then measured the Young’s modulus of rodent cervical tissues acquired at different gestational ages, showing that the cervical rigidity of rodents was significantly dropped when entering the third trimester of pregnancy.
5 January 2020 in Advances in Polymer Technology
Bone tuberculosis (TB) caused by mycobacterium tuberculosis continues to present a formidable challenge to humans. To effectively cure serious bone TB, a novel kind of composite scaffolds with long-term dual drug release behaviours were prepared to satisfy the needs of both bone regeneration and antituberculosis drug therapy. In virtue of an improved O/W emulsion technique, water-soluble isoniazid (INH)-loaded gelatin microparticles were obtained by tailoring the content of β-tricalcium phosphate (β-TCP), which played significant roles in INH entrapment efficiency and drug release behaviours. By mixing with the poly(ε-caprolactone)-block-poly (lactic-co-glycolic acid) (b-PLGC) solution containing oil-soluble rifampicin (RFP) via the particle leaching combined with phase separation technique, the dual drugs-loaded composite scaffolds were fabricated, which possessed interconnected porous structures and achieved the steady release of INH and RFP drugs for three months. Moreover, this dual drugs-loaded system could basically achieve their expectant roles of respective drugs without obvious influences with each other. This strategy on preparation of intelligent composite scaffolds with the multi-drugs loading capacity and controlled long-term release behaviour will be potential and promising substrates in clinical treatment of bone tuberculosis.