Coronary calcium scoring software

Step 2. Step 3. Deep learning for semantic segmentation of CAC images. Among the individuals in these cohorts, 35 were excluded because of the lack of CAC image data, previous coronary stent insertion, or overlapping of cohorts. Finally, individuals were included in the validation dataset. The baseline and CT imaging characteristics are presented in Table 1. The screening, FFR, and valve groups underwent CT examinations between and , and , and and , respectively.

Among the enrollees, Four types of CT machines from two companies GE, Siemens were used in this study, and all the scans were taken in electrocardiography-triggered mode with a slice thickness of 2. The labeled mask containing binary information indicating the presence or absence of calcium in each image slice was saved for per-lesion analysis. After all CT data were loaded in a desktop computer Intel Core 3. It is possible to distinguish calcium located in the heart region from that in the coronary artery or other areas, such as the aortic valve and MA.

Additionally, the coronary tree mask enables the localization of calcium within blood vessels i. For each CAC scan, the initial masks were generated by connected component analysis after applying thresholding at HU and discarding all masks that were less than 2. The masks were compared with manual masks. All mismatched lesions were subsequently reviewed by a senior cardiovascular radiologist to analyze the causes of mismatches and lesion locations. Systemic deviations did not occur in any subgroup or during the per-vessel analysis.

The reliability of the calcium volume mm 3 was also high, with similar values yielded by the Agatston score measurement for both the per-patient and per-vessel analyses Table 2. Screening group. FFR group. Valvular heart disease valve group. CAC 0— group. CAC — group. Outliers are indicated by arrows and their values. Only 0. The main causes of false positive results were image noise or artifacts Among 81 false-positive pericardial calcifications, 26 Of interest, Among the patients, 5.

In the areas pink; spine, rib, and image noise where the Hounsfield number was or more, each coronary artery calcification was marked with a different color i. Data are number with percentage in the parentheses. Several of the anatomical errors were caused by the aortic wall and pericardial calcium, and the extracardiac error rate was low. We followed the atlas-based approach [ 8 , 9 ] but incorporated a deep-learning-based semantic segmentation model to replace the time-consuming non-rigid registration of the multi-atlas method.

The false-positive rate of 0. However, the investigators did not perform per-lesion analyses. Moreover, the sample sizes of electrocardiogram-synchronized CT scans were relatively small: 87 scans by van Velzen et al. Isgum et al. Kurkure et al. These feature-based approaches do not require the spatial information of coronary arteries.

However, the results were not comprehensive and required careful selection of several operational parameters for calcium candidate object detection and classification. In another method, Brunner et al. This method incorporates image transformation to align cardiac volumes across patients and provides coronary artery zones and sections. However, the performance of this atlas-based method was inferior to that of feature-based methods.

To combine the benefits of feature- and atlas-based methods, Shahzad et al. Spatial information was obtained from the pairwise registration of the 10 atlas images.

However, this multi-atlas-based method had a scalability problem. The method was slower when more atlases were included because of the heavy computation of non-rigid registration. In our previous study, when atlases were used, it took approximately 30 minutes [ 25 ].

In the present study, to solve the problem of atlas-based methods using registration, we incorporated deep learning-based semantic segmentation to reduce the execution time. Lessmann et al. In this approach, two 2. This algorithm can eliminate the feature extraction step in previous approaches and can be trained on large datasets.

However, this did not provide spatial information about the coronary artery regions or other surrounding structures. It also requires more computation time to apply voxel-by-voxel classification. Martin et al. The first step was used to identify and segment the regions, such as the coronary artery, aorta, aortic valve, and mitral valve. The second step classified the voxels as coronary calcium. Zhang et al. The incremental value of this current approach is that it can precisely detect coronary artery regions with a deep learning model based on semantic segmentation in a single step.

Features The syngo Calcium Scoring package allows accurate visualization and quick quantification of calcified coronary lesions. General Requirements. Other Please Note: Additional technical pre-requisites may apply. Get a Quote Get a Recommendation. Did this information help you? Thank you. The syngo Calcium Scoring package allows accurate visualization and quick quantification of calcified coronary lesions.

It is also possible to blow up the display for easier identification of small lesions. The user can perform a freehand ROI definition of lesions in addition to the seeding method.

A default threshold of HU is used for score calculation but can be modified based on user preference. The software allows 3D editing for separation and modification of lesions within a defined volume depth in mm or on 2D-slices.