HeartBeatCVI

Empowers clinicians to quickly identify cardiovascular issues, determine treatment and track progress.


Why HeartBeatCVI?

HeartBeatCVI uses Tech Vedika’s Vision Analytics platform to analyze a MRI scan from all points of the cardiac life cycle in under 2 minutes, thereby saving 28 minutes of the clinician’s time, every time. (The current manual process takes over 30 minutes to analyze the scan for 2 points of the cardiac life cycle).

Read More

Functions of HeartBeatCVI

HeartBeatCVI leverages AI to analyse large scale cardiac MRI datasets to create a high performance cardiac segmentation model for analysing MRI images across all points of the cardiac life cycle. The following are the functions of HeartBeatCVI:

  • Segmentation Analysis
  • Segmentation Report
  • 17 Segment Model

Read More

Functions of HeartBeatCVI

How HeartBeatCVI works?

HeartBeatCVI uses a fully convolutional neural network (CNN). It takes the MRI images as input, learns image features from fine to coarse scales through a series of convolutions, concatenates multi-scale features and finally predicts a pixel-wise image segmentation.

Read More

How HeartBeatCVI works?

Why HeartBeatCVI?

AI Powered

HeartBeatCVI uses Tech Vedika’s unique and advanced Deep Learning algorithms for analysing cardiovascular images.

Our AI powered Vision Analytics platform for analyzing cardiovascular images has outperformed other similar state-of-the-art methods in terms of accuracy, robustness and computational time.

AI Powered

100% Cloud Based

HeartBeatCVI permits:

  • 24×7 cloud-based global access, eliminating the need to manage software and hardware. Significant cost savings and greater flexibility
  • Scalability-on-demand through addition of more Graphical Processing Units (GPUs) ensuring 100% uptime

100% Cloud Based

Trained on 1000’s of images

HeartBeatCVI algorithms are validated using 1000’s of MRI images for human level accuracy and fine-tuned for lightning speed.

HeartBeatCVI algorithms are pre-trained; they are productive from Day 1.

Trained on 1000’s of images

Simple User Interface

HeartBeatCVI is browser-based and designed to deliver superior user experience.

  • Simple and user friendly interface
  • Quick to learn, deploy and use
  • Deliver powerful insights
  • Allows for collaboration with other clinicians

Simple User Interface

Visualization

Image visualization can help unlock critical information of objects and their properties in the medical images.

HeartBeatCVI uses the most advanced web rendering technology for 2D/3D image visualization, appropriate annotation and highlighting of critical aspects. This technology employs state-of-the-art graphics to deliver a comprehensive view.

Visualization

Reporting

Easy-to-use reporting tools provide detailed quantitative information in a structured format.

The reports help clinicians to quickly assess the key parameters for quick diagnosis of cardio-vascular conditions.

Reporting

Functions of HeartBeatCVI

Segmentation Analysis

Segmentation of left and right ventricles plays a crucial role in quantitative analysis of the cardiovascular Images.

Highlights:

  • Full ventricular and atrial assessment
  • Assessment of atrioventricular junction
  • Contour detection
  • Thresholding tool
  • Comparison of baseline with follow-up scans

Segmentation Analysis

Segmentation Report

HeartBeatCVI can quantify 10 critical statistics of the heart, as displayed.

Highlights:

  • Drag and drop images
  • Multiple export formats including DICOM encapsulated PDF
  • Detailed measurements of key statistics

Segmentation Report

17 Segment Model*

HeartBeatCVI follows the 17 segment model as recommended by The American Heart Association to study Coronary Arterial Anatomy.

Highlights:

  • Creates a distribution of 35%, 35%, and 30% for the basal, mid-cavity and apical thirds of the heart
  • Cardiac segmentations and their assignment to coronary arterial territories

17 Segment Model*

How HeartBeatCVI works?

HeartBeatCVI uses a fully Convolutional Neural Network (CNN). It takes the MRI images as input, learns image features from fine to coarse scales through a series of convolutions, concatenates multi-scale features and finally performs a pixel-wise image segmentation for cardiovascular analysis.

Input

The dataset consists of short-axis and long-axis cine MRI images. Manual image annotation is undertaken by a team of clinicians. 

For short-axis images, the LV endocardial and epicardial borders and the RV endocardial borders are manually traced at ED and ES time frames. 

For long-axis 2-chamber view (2Ch) images, the left atrium (LA) endocardial border are traced. For long-axis 4-chamber view (4Ch) images, the LA and the right atrium (RA) endocardial borders are also traced.

Image Preprocessing

The Cardiovascular DICOM images are converted into Neuroimaging Informatics Technology Initiative (NifTI) format. The manual annotations from the CVI software is exported as XML files as well as in NIfTI format. 

Automated Image Analysis

For automated CMR image analysis, HeartBeatCVI utilizes a fully convolutional network architecture, which is a type of neural network that can predict a pixel wise image segmentation by applying a number of convolutional filters onto an input image. 

The fully convolutional network learns image features from fine to coarse scales using convolutions and combines multi-scale features for predicting the label class at each pixel.

The network consists of a number of convolutional layers for extracting image features. Each convolution uses 3X3 kernel and it is followed by batch normalization and rectified linear unit (RELU). After every two or three convolutions, the feature map is down sampled by a factor of 2 so as to learn features at a more global scale. 

Feature maps learnt at different scales are up sampled to the original resolution using transposed convolutions and the multi-scale feature maps are then concatenated. Finally, three convolutional layers of kernel size 1X1, followed by a softmax function, are used to predict a probabilistic label map. The segmentation is determined at each pixel by the label class with highest softmax probability. The mean cross entropy between the probabilistic label map and the manually annotated label map is used as the loss function.

Network Training and Testing

Networks are trained for segmenting short-axis images, long-axis 2Ch images and 4Ch images. Data augmentation is performed on-the-fly, which includes random translation, rotation, scaling and intensity variation to each mini-batch of images before feeding them to the network.

Evaluation of the Method

HeartBeatCVI’s performance was evaluated and the results were comparable/better than competing models using commonly used metrics for segmentation accuracy assessment, such as Dice metric, mean contour distance and Hausdorff distance and clinical measures derived from segmentations, including ventricular volume and mass.