The Effects of Different Adaptive Statistical Iterative Reconstruction-V and Convolution Kernel Parameters on Auto-Segmentation Stability in CT Images / 中国医疗器械杂志

Objective The study aims to investigate the effects of different adaptive statistical iterative reconstruction-V（ ASiR-V） and convolution kernel parameters on stability of CT auto-segmentation which is based on deep learning. Method Twenty patients who have received pelvic radiotherapy were selected and different reconstruction parameters were used to establish CT images dataset. Then structures including three soft tissue organs (bladder, bowelbag, small intestine) and five bone organs (left and right femoral head, left and right femur, pelvic) were segmented automatically by deep learning neural network. Performance was evaluated by dice similarity coefficient（ DSC） and Hausdorff distance, using filter back projection(FBP) as the reference. Results Auto-segmentation of deep learning is greatly affected by ASIR-V, but less affected by convolution kernel, especially in soft tissues. Conclusion The stability of auto-segmentation is affected by parameter selection of reconstruction algorithm. In practical application, it is necessary to find a balance between image quality and segmentation quality, or improve segmentation network to enhance the stability of auto-segmentation.

Using stacked neural network to improve the auto-segmentation accuracy of Graves' ophthalmopathy target volumes for radiotherapy / 生物医学工程学杂志

Compared with the previous automatic segmentation neural network for the target area which considered the target area as an independent area, a stacked neural network which uses the position and shape information of the organs around the target area to regulate the shape and position of the target area through the superposition of multiple networks and fusion of spatial position information to improve the segmentation accuracy on medical images was proposed in this paper. Taking the Graves' ophthalmopathy disease as an example, the left and right radiotherapy target areas were segmented by the stacked neural network based on the fully convolutional neural network. The volume Dice similarity coefficient (DSC) and bidirectional Hausdorff distance (HD) were calculated based on the target area manually drawn by the doctor. Compared with the full convolutional neural network, the stacked neural network segmentation results can increase the volume DSC on the left and right sides by 1.7% and 3.4% respectively, while the two-way HD on the left and right sides decrease by 0.6. The results show that the stacked neural network improves the degree of coincidence between the automatic segmentation result and the doctor's delineation of the target area, while reducing the segmentation error of small areas. The stacked neural network can effectively improve the accuracy of the automatic delineation of the radiotherapy target area of Graves' ophthalmopathy.

Current researches in gene therapy for optic nerve injury / 中华实验眼科杂志

Optic nerve is a part of the central nerve system,therefore,it can not regenerate after injury.In recent years,more attentions have been focused on optic nerve regeneration research.The primary pathological basis of optic nerve injury is loss of retinal ganglion cells (RGCs) and irreversible visual dysfunction.A certain number of RGCs survival and/or rescue allow the recovery of visual function.So gene therapy for optic nerve regeneration becomes a hotspot in recent years.Genetic therapy alters the expression of DNA or RNA in the target cells and thus achieves the purpose of treating disease.Whether genetic therapeutic is successful or not depends on the characteristics of gene vectors,tissue microenvironment and transfection technology.This review summarized recent studies and aimed at a better understanding to gene therapy vectors and methods in rescuing optic nerve injury.

An Improved Method for Preparation of Paraffin Slices of Rat Retina / 昆明医科大学学报

Objective To solve the problem that the rat retina paraffin sections are easily exfoliated from the slides and each layer are easily separation and fracture,we need to find a way to improve the retina paraffin section method and evaluate the tissue fixation. Methods We used 4 fixation liquids including 10%paraformaldehyde,4%paraformaldehyde, 4% paraformaldehyde and 95% alcohol and glacial acetic acid mixed liquid (FAA fixatiue solution ) combined with paraformaldehyde to fix the retinal tissue, and observed the fixation efficacy under microscope after HE staining. Results The effects of 10%paraformaldehyde and 4%paraformaldehyde fixed samples showed moderate separation and fracture of retina,but the HE staining retinal slices pre-treated by the FAA fixafive solution had bright and uniform color,although occasionally some parts of the retina were exfoliated from the slide, but it was not easy to take off,and had complete structure without separation and rupture. Conclusion The retina paraffin section fixed by FAA ixafive solution with 4% paraformaldehyde is superior to pure paraformaldehyde, and the paraformaldehyde concentration has no obviously influence on HE staining results.