FITC-conjugated dextran (70 kDa, 0.1 mg/g; Thermo Fisher Scientific; D1822) was injected retro-orbitally and allowed to circulate for 1 hour. Mice were then euthanized, and eyes were enucleated. Eyes were lightly fixed with 4% paraformaldehyde (PFA) for 15 min at room temperature, and retinas were dissected and flat-mounted. Whole-mounted retinas were imaged using confocal microscopy (LSM 880; Zeiss, Oberkochen, Germany). The fluorescence intensity of FITC-dextran was analyzed with Zeiss microscope software ZEN Intellesis to segment and quantify vascular leakage from retinal vessels based on previous protocols (60 ). Retinas were costained with Alexa Fluor 594–conjugated isolectin GS-IB4 (Thermo Fisher Scientific; I21413).
Zen intellesis
Manufactured by Zeiss
Sourced in Germany
ZEN Intellesis is an image analysis software tool developed by Zeiss. It is designed to facilitate automated image segmentation and classification tasks. The software utilizes artificial intelligence and machine learning algorithms to enable efficient and accurate analysis of microscopy images.
Automatically generated - may contain errors
4 protocols using zen intellesis
1
Retinal Vascular Leakage Quantification
2
Quantification of Aortic Macrophage Burden
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
Following the last imaging procedure, the rabbits were euthanized by intravenous injection of sodium-pentobarbital (120 mg/kg), and the aortas were harvested for further analysis. Autoradiography of the abdominal aorta was performed for all three tracers (n = 2 per group for each tracer).Formalin-fixed, paraffin-embedded sections of the aortas (n = 23) were stained as described earlier and using manufacturer's protocols with hematoxylin and eosin stain (HE), Masson's Trichrome (MT), Alizarin Red and immunohistochemical (IHC) staining for RAM-11 [18 (link)].The deep learning segmentation software Zen Intellesis (Carl Zeiss Microscopy, Oberkochen, Germany) was used to quantify the ratio (%) between macrophage-rich area and total vessel area from RAM-11 stained cross-sections of the aorta.
3
Deep Learning-Based Image Segmentation
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
The tool used for image segmentation in the present study is the Python-based deep learning software package ZEN Intellesis (Zeiss Microscopy)71 (link). The software allows for a supervised training of the pixel classifier on the microscopy images. For feature extraction the software employs very deep convolutional neural network the VGG-19, which was adopted by Zeiss Microscopy from the work of Simonian and Zisserman72 without any considerable changes or additional training. According to the authors, the training of the neural network was done using mini-batch gradient descent as optimization algorithm for multimodal logistic regression objective, the batch size was 256 and the number of epochs was 74, for more details please refer to the original work72 . From the third layer of the VGG-19, 256 features were extracted and used to train random forest classification algorithm73 . For the structured predictions, conditional random fields74 were applied for all datasets except normal brain vasculature segmentation of which was satisfactory with basic settings.
The workstation used for image analysis had following characteristics, CPU: dual Xeon processors E5-2670, 2.6 GHz (96 GB RAM) and GPU: GeForce RTX 2080Ti (11 GB RAM).
The workstation used for image analysis had following characteristics, CPU: dual Xeon processors E5-2670, 2.6 GHz (96 GB RAM) and GPU: GeForce RTX 2080Ti (11 GB RAM).
4
Quantitative Cardiac Tissue Analysis
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
Tissue samples from the free wall (1 × 1 cm, avoiding areas where leads were implanted) of left atrium, right atrium, left ventricle and right ventricle from 8 SHAM pigs and 9 A-TP pigs were used for picrosirius red staining to separate and quantify the relative amounts of cardiomyocytes, collagen and background. Each location was sliced in a maximum of three selections (4 μm). Slides were automatically scanned by the confocal microscope Axio Scan.Z1 slide scanner (Zeiss, Germany) with 20X magnification with 0.8 objective for brightfield lens. From each slide, 3- 12 regions of interest (ROI) were randomly selected and blindly scored by an unrelated person aiming to cover between 10 and 15% of each selection for a total of 30–45% of each location. From 3 to 20 ROIs per chamber resulting in a total of 22–50 images per animal were collected and analyzed. The selection criteria aimed to exclude epicardium, endocardial adipose tissue and large blood vessels from the chosen ROI (Figures 4A,B ). Image segmentation was done by creating a trained model (Figures 4C,D ) in order to differentiate between cardiomyocytes, collagen and background (ZEN Intellesis, Zeiss, Germany). The analyses were performed with ZEN 2.3 Blue edition software (Zeiss, Germany). A detailed description of the trained model can be found in the Supplementary Materials .
About PubCompare
Our mission is to provide scientists with the largest repository of trustworthy protocols and intelligent analytical tools, thereby offering them extensive information to design robust protocols aimed at minimizing the risk of failures.
We believe that the most crucial aspect is to grant scientists access to a wide range of reliable sources and new useful tools that surpass human capabilities.
However, we trust in allowing scientists to determine how to construct their own protocols based on this information, as they are the experts in their field.
Ready to get started?
Sign up for free.
Registration takes 20 seconds.
Available from any computer
No download required
Revolutionizing how scientists
search and build protocols!