Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

IntelliCardiac: An Intelligent Platform for Cardiac Image Segmentation and Classification

Ting Yu Tsai, An Yu, Meghana Spurthi Maadugundu, Ishrat Jahan Mohima, Umme Habiba Barsha, Mei-Hwa F. Chen, Balakrishnan Prabhakaran, Ming-Ching Chang

TL;DR

IntelliCardiac presents a web-based platform for simultaneous 4D cardiac MRI segmentation and five-category disease classification, trained on the public ACDC dataset. The system combines a 3D residual U-Net segmentation module with a two-stage classification pipeline (Random Forest followed by an expert SVM) and utilizes ROI-aware preprocessing, dynamically weighted Focal Dice Loss, and Largest Connected Component post-processing to achieve 92.6% segmentation Dice and 98% classification accuracy. Real-time visualization and clinician-friendly workflows enable AI-assisted diagnosis with interpretability, achieving superior performance over prior state-of-the-art methods. This work demonstrates practical deployment potential, scalability, and extensibility to other modalities and clinical settings, bridging research and real-world cardiac diagnostics.

Abstract

Precise and effective processing of cardiac imaging data is critical for the identification and management of the cardiovascular diseases. We introduce IntelliCardiac, a comprehensive, web-based medical image processing platform for the automatic segmentation of 4D cardiac images and disease classification, utilizing an AI model trained on the publicly accessible ACDC dataset. The system, intended for patients, cardiologists, and healthcare professionals, offers an intuitive interface and uses deep learning models to identify essential heart structures and categorize cardiac diseases. The system supports analysis of both the right and left ventricles as well as myocardium, and then classifies patient's cardiac images into five diagnostic categories: dilated cardiomyopathy, myocardial infarction, hypertrophic cardiomyopathy, right ventricular abnormality, and no disease. IntelliCardiac combines a deep learning-based segmentation model with a two-step classification pipeline. The segmentation module gains an overall accuracy of 92.6%. The classification module, trained on characteristics taken from segmented heart structures, achieves 98% accuracy in five categories. These results exceed the performance of the existing state-of-the-art methods that integrate both segmentation and classification models. IntelliCardiac, which supports real-time visualization, workflow integration, and AI-assisted diagnostics, has great potential as a scalable, accurate tool for clinical decision assistance in cardiac imaging and diagnosis.

IntelliCardiac: An Intelligent Platform for Cardiac Image Segmentation and Classification

TL;DR

IntelliCardiac presents a web-based platform for simultaneous 4D cardiac MRI segmentation and five-category disease classification, trained on the public ACDC dataset. The system combines a 3D residual U-Net segmentation module with a two-stage classification pipeline (Random Forest followed by an expert SVM) and utilizes ROI-aware preprocessing, dynamically weighted Focal Dice Loss, and Largest Connected Component post-processing to achieve 92.6% segmentation Dice and 98% classification accuracy. Real-time visualization and clinician-friendly workflows enable AI-assisted diagnosis with interpretability, achieving superior performance over prior state-of-the-art methods. This work demonstrates practical deployment potential, scalability, and extensibility to other modalities and clinical settings, bridging research and real-world cardiac diagnostics.

Abstract

Precise and effective processing of cardiac imaging data is critical for the identification and management of the cardiovascular diseases. We introduce IntelliCardiac, a comprehensive, web-based medical image processing platform for the automatic segmentation of 4D cardiac images and disease classification, utilizing an AI model trained on the publicly accessible ACDC dataset. The system, intended for patients, cardiologists, and healthcare professionals, offers an intuitive interface and uses deep learning models to identify essential heart structures and categorize cardiac diseases. The system supports analysis of both the right and left ventricles as well as myocardium, and then classifies patient's cardiac images into five diagnostic categories: dilated cardiomyopathy, myocardial infarction, hypertrophic cardiomyopathy, right ventricular abnormality, and no disease. IntelliCardiac combines a deep learning-based segmentation model with a two-step classification pipeline. The segmentation module gains an overall accuracy of 92.6%. The classification module, trained on characteristics taken from segmented heart structures, achieves 98% accuracy in five categories. These results exceed the performance of the existing state-of-the-art methods that integrate both segmentation and classification models. IntelliCardiac, which supports real-time visualization, workflow integration, and AI-assisted diagnostics, has great potential as a scalable, accurate tool for clinical decision assistance in cardiac imaging and diagnosis.
Paper Structure (19 sections, 3 equations, 5 figures, 4 tables)

This paper contains 19 sections, 3 equations, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Web platform design
  5. Segmentation module
  6. Data Pre-processing
  7. Network Architecture for Segmentation
  8. Loss Function
  9. Data Post-processing
  10. Classification module
  11. Feature Extraction
  12. Network Architecture for Classification
  13. Application and Experiment
  14. Application
  15. Doctor Module
  16. ...and 4 more sections

Figures (5)

  • Figure 1: Overview of IntelliCardiac system pipeline.
  • Figure 2: Proposed AI model architecture consisting of segmentation (top) and two-stage classification (bottom).
  • Figure 3: User interface overview of IntelliCardiac: the left shows the doctor’s view with patient results and diagnostic insights; the right shows the patient’s view with AI-generated cardiac evaluation results.
  • Figure 4: Segmentation and classification results from proposed model on sample images from the ACDC dataset. The ground truth is displayed in the first and third columns, while the corresponding segmented images and classification results are presented in the second and fourth columns.
  • Figure 5: Confusion matrices before (right) and after (left) expert refinement in IntelliCardiac classification module.