AI-based Automatic
Blood Vessel Analysis
Software

Diagnostic Assistance Solution for Big 3 Chest Disease

Medical 3D Printing Solution

As medical 3D printing becomes prevalent in healthcare, its true value is defined by modeling precision.
Modeler is a comprehensive solution designed to support communication between
physicians and 3D printing operators and to provide tools for medical 3D modeling.

Key features

Provide multiple feature for medical 3D modeling.

01Convenient and advanced tools

Semi-automatic 3D segmentation replaces manual slice-by-slice editing, synchronizing all results across 2D and 3D views.
Various rendering options support segmentation during labeling.

Brush

Pick

Sculpt

Magic cut segmentation

Brush

Add or remove free drawing dots or lines from masks

Pick

Click to separate linked masks.

Sculpt

Adjust straight, curved, and free-draw lines for desired body parts from masks.

Magic cut segmentation

Automatically segment boundaries of body parts by drawing reference lines on a slice.

02Generate and modify guide models.

Split Model

Align Model

Transform Model

Split Model

Split areas

Align Model

Align objects to a desired position.

Transform Model

Move, rotate and adjust size to desired values

Collaboration tools for model review and communication

Enable collaboration through web-based access tools.

Operate software without installing on PC.

Medical staff and engineers can share URL links to review results using a web-based viewer.
Job and confirmation history can be reviewed through the system.

aview modeler Operate software without installing on PC

Data Management

Manage medical images systematically.

Organize databases by purpose.

Save work in progress and manage job history.
Manage all operator results within one integrated worklist.

Generate database by purpose

Review Work history by time

Advanced Add-ons

Provide additional features to support segmentation and modeling workflows.

01
Smart slicer

Reconstruct CT datasets into finer slice thicknesses for anatomical precision.

Before

After

02
Organ segmentation and contouring functions

Integrate with aview RT ACS for specialized organ segmentation and contouring.

Head & Neck

22 Organs
Abdomen

5 Organs
Breast

12 Organs
Pelvis

10 Organs

Publications

Refer to the following research papers

These contents represent summaries of scientific
publications and are unrelated to any form of advertising.

This study aimed at evaluating the difference between amorphous bone fracture (AFF) patients and general population between patients and general population between the general population between patients and general population.
In order to obtain a wide range of 46 patients including geometric analysis software analysis software analysis software, including geometric analysis software analysis software analysis software analysis software, including geometric analysis software.
Importantly CT image using aview Model for the core line software image, and created 3D Sampling. This study found that it has increased from executives AFF, but it found that it is similar to electronic HaFF, but compared to general population.

Jung IJ, Kim JW. “Differences in femur geometry and bone markers in atypical femur fractures and the general population.” Sci Rep. 2021 Dec 17;11(1):24149.
The goal of this study is to develop an automated method of imaging and tracking the location of the Hachijo nerve (IAN) using artificial intelligence (AI) on the cone beam computed tomography data set.
We used customized 3D nnU-Net for image segmentation, and we repeatedly performed active learning on 83 datasets. Using the remaining 50 datasets, we evaluated the accuracy of the model for IAN segmentation and compared the Dice Similarity Factor (DSC) values and segmentation times for each stage of learning.
Deep active learning frameworks have been found to be fast, accurate and powerful clinical tools for distinguishing IAN locations.
The full segmentation was performed using the aview Modeler, and ground truth in IAN was provided by three experts.

Lim HK, Jung SK, Kim SH, Cho Y, Song IS. “Deep semi-supervised learning for automatic segmentation of inferior alveolar nerve using a convolutional neural network.” BMC Oral Health. 2021 Dec 7;21(1):630

More Publications

Intended purpose

AVIEW is intended to support CT interpretation by providing information on the detection of pulmonary nodules and the analysis of coronary artery calcification, and by enabling inquiry and analysis of medical images through functions such as zoom in/out, segmentation, and quantification. It also provides capabilities to store, transfer, and display output results.

Intended user

Healthcare professionals, such as radiologists, physicians, can interpret thoracic CT with or without abnormal findings.

Warning

Please use the product for its intended purpose when in use.
Software installed on a PC can be infected by malicious software if it is connected to a network with the following conditions
1. In case of exposure to malicious code
2. In case of absence of PC security solution installation
If the software is installed on a PC is infected with malicious software, normal software use might be unavailable, or the integrity of the saved data could become corrupt.
Any serious incident that has occurred in relation to the device should be reported to the manufacturer and the competent authority of the Member State in which the user and/or patient is established.

Caution

For detailed information on cautions, please refer to the instructions for use.