Many surgeries are complicated by the need to anastomose, or reconnect, micron-scale vessels. Although suturing remains the gold standard for anastomosing vessels, it is difficult to place sutures correctly through collapsed lumen, making the procedure prone to failure. Here, we report a multi-phase transitioning peptide hydrogel that can be injected into the lumen of vessels to facilitate suturing. The peptide, which contains a photocaged glutamic acid, forms a solid-like gel in a syringe and can be shear-thin delivered to the lumen of collapsed vessels (where it distends the vessel), and the space between two vessels (where it is used to approximate the vessel ends). Suturing is performed directly through the gel. Light is used to initiate the final gel-sol phase transition that disrupts the hydrogel network, allowing the gel to be removed and blood flow to resume. This gel adds a new tool to the armamentarium for micro- and supermicrosurgical procedures.

The liver segmentation in CT scan images is a significant step toward the development of a quantitative biomarker for computer-aided diagnosis. In this paper, we propose an automatic feature learning algorithm based on the deep belief network (DBN) for liver segmentation. The proposed method was based on training by a DBN for unsupervised pretraining and supervised fine tuning. The whole method of pretraining and fine tuning is known as DBN-DNN. In traditional machine learning algorithms, the pixelby-pixel learning is a time-consuming task; therefore, we use blocks as a basic unit for feature learning to identify the liver, which saves memory and computational time. An automatic active contour method is applied to refine the liver in post-processing. The experiments on test images show that the proposed algorithm obtained satisfactory results on healthy and pathological liver CT images. Our algorithm achieved 94.80% Dice similarity coefficient on mixed (healthy and pathological) images while 91.83% on pathological liver images, which is better than those of the state-of-the-art methods. INDEX TERMS Liver segmentation, deep learning, deep belief network, restricted Boltzmann machine.

Background Compressed sensing (CS) has been widely used to improve the speed of MRI, but the feasibility of application in 3D intracranial MR angiography (MRA) needs to be evaluated in clinical practice. Purpose To evaluate the clinical feasibility of CS‐MRA in comparison with conventional 3D‐MRA (Con‐MRA). Study Type Retrospective. Subjects Forty‐nine consecutive patients with suspected intracranial arterial disease. Field Strength/Sequence 3T MRI. 3D time‐of‐flight (TOF) MRA using a CS algorithm and conventional 3D TOF MRA scan. Assessment Three radiologists (4, 11, and 12 years of experience in neuroradiology) independently assessed the image quality, vascular lesions, and variations of intracranial arteries of both CS‐MRA and Con‐MRA, respectively. Statistical Tests The Kendall W test was performed to assess the interobserver agreement of image quality and intracranial arterial stenosis. A nonparametric test (Wilcoxon test) was used for comparison of the image quality and definition of the external carotid artery (ECA). Weighted kappa analysis was performed for the interstudy agreement of intracranial arterial stenosis. The aneurysm, decreased branches, congenital hypoplasia, absence, and variant branching of intracranial arteries were observed and evaluated for interobserver agreement and interstudy agreement by kappa analysis. Paired‐t‐tests for signal‐to‐noise ratio (SNR) and contrast‐to‐noise ratio (CNR) were conducted. Results Image quality is better for CS‐MRA compared with Con‐MRA with significance (Z = –3.710 to –2.673, with P < 0.01). The interstudy agreement of lesion and variation of intracranial arteries assessment for each observer was excellent. The SNR and CNR were significantly higher in CS‐MRA compared with Con‐MRA (P < 0.001). The definition of ECA of CS‐MRA was significantly better (Z = –4.9, P < 0.001). Data Conclusion CS‐MRA showed significantly higher image quality with less blur, comparable image diagnostic performance of intracranial arteries, and better display of ECA than Con‐MRA. Level of Evidence: 3 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019;50:1843–1851.

Hand-held OCT systems that offer physicians greater freedom to access imaging sites of interest could be useful for many clinical applications. In this study, by incorporating the theoretical speckle model into the decorrelation function, we have explicitly correlated the cross-correlation coefficient to the lateral displacement between adjacent A-scans. We used this model to develop and study a freehand-scanning OCT system capable of real-time scanning speed correction and distortion-free imaging—for the first time to the best our knowledge. To validate our model and the system, we performed a series of calibration experiments. Experimental results show that our method can extract lateral scanning distance. In addition, using the manually scanned hand-held OCT system, we obtained OCT images from various samples by freehand manual scanning, including images obtained from human in vivo.

We propose an inter-Ascan speckle decorrelation based method that can quantitatively assess blood flow normal to the direction of the OCT imaging beam. To validate this method, we performed a systematic study using both phantom and in vivo animal models. Results show that our speckle analysis method can accurately extract transverse flow speed with high spatial and temporal resolution.