An Interpretable CNN for the Segmentation of the Left Ventricle in Cardiac MRI by Real-Time Visualization
Open Access
- 1 January 2023
- journal article
- research article
- Published by Tech Science Press in Computer Modeling in Engineering & Sciences
- Vol. 135 (2) , 1571-1587
Abstract
The interpretability of deep learning models has emerged as a compelling area in artificial intelligence research. The safety criteria for medical imaging are highly stringent, and models are required for an explanation. However, existing convolutional neural network solutions for left ventricular segmentation are viewed in terms of inputs and outputs. Thus, the interpretability of CNNs has come into the spotlight. Since medical imaging data are limited, many methods to fine-tune medical imaging models that are popular in transfer models have been built using massive public ImageNet datasets by the transfer learning method. Unfortunately, this generates many unreliable parameters and makes it difficult to generate plausible explanations from these models. In this study, we trained from scratch rather than relying on transfer learning, creating a novel interpretable approach for autonomously segmenting the left ventricle with a cardiac MRI. Our enhanced GPU training system implemented interpretable global average pooling for graphics using deep learning. The deep learning tasks were simplified. Simplification included data management, neural network architecture, and training. Our system monitored and analyzed the gradient changes of different layers with dynamic visualizations in real-time and selected the optimal deployment model. Our results demonstrated that the proposed method was feasible and efficient: the Dice coefficient reached 94.48%, and the accuracy reached 99.7%. It was found that no current transfer learning models could perform comparably to the ImageNet transfer learning architectures. This model is lightweight and more convenient to deploy on mobile devices than transfer learning models.Keywords
This publication has 19 references indexed in Scilit:
- IEEE Journal of Biomedical and Health Informatics2023
- An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasetsNature Biomedical Engineering, 2018
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- Visual Analytics for Explainable Deep LearningIEEE Computer Graphics and Applications, 2018
- Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?IEEE Transactions on Medical Imaging, 2018
- An explainable deep machine vision framework for plant stress phenotypingProceedings of the National Academy of Sciences, 2018
- Fast automatic myocardial segmentation in 4D cine CMR datasetsMedical Image Analysis, 2014
- Molecular evolution and diversification of the moss family Daltoniaceae (Hookeriales, Bryophyta) with emphasis on the unravelling of the phylogeny of Distichophyllum and its alliesBotanical Journal of the Linnean Society, 2012
- Automatic Left Ventricle Segmentation in Cardiac MRI Using Topological Stable-State Thresholding and Region Restricted Dynamic ProgrammingAcademic Radiology, 2012
- An Image-Based Comprehensive Approach for Automatic Segmentation of Left Ventricle from Cardiac Short Axis Cine MR ImagesJournal of Digital Imaging, 2010