Fully convolutional multi‐scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers

By Mahendra Khened, Alex Varghese, Ganapathy Krishnamurthi. Medical Image Anal., 2018

351 citations recorded by the source corpus.

&NA; Deep fully convolutional neural network (FCN) based architectures have shown great potential in medical image segmentation. However, such architectures usually have millions of parameters and inadequate number of training samples leading to over‐fitting and poor generalization. In this paper, we present a novel DenseNet based FCN architecture for cardiac segmentation which is parameter and memory efficient. We propose a novel up‐sampling path which incorporates long skip and short‐cut connections to overcome the feature map explosion in conventional FCN based architectures. In order to process the input images at multiple scales and view points simultaneously, we propose to incorporate Inception module's parallel structures. We propose a novel dual loss function whose weighting scheme allows to combine advantages of cross‐entropy and Dice loss leading to qualitative improvements in segmentation. We demonstrate computational efficacy of incorporating conventional computer vision techniques for region of interest detection in an end‐to‐end deep learning based segmentation framework. From the segmentation maps we extract clinically relevant cardiac parameters and hand‐craft features which reflect the clinical diagnostic analysis and train an ensemble system for cardiac disease classification. We validate our proposed network architecture on three publicly available datasets, namely: (i) Automated Cardiac Diagnosis Challenge (ACDC‐2017), (ii) Left Ventricular segmentation challenge (LV‐2011), (iii) 2015 Kaggle Data Science Bowl cardiac challenge data. Our approach in ACDC‐2017 challenge stood second place for segmentation and first place in automated cardiac disease diagnosis tasks with an accuracy of 100% on a limited testing set (n=50). In the LV‐2011 challenge our approach attained 0.74 Jaccard index, which is so far the highest published result in fully automated algorithms. In the Kaggle challenge our approach for LV volume gave a Continuous Ranked Probability Score (CRPS) of 0.0127, which would have placed us tenth in the original challenge. Our approach combined both cardiac segmentation and disease diagnosis into a fully automated framework which is computationally efficient and hence has the potential to be incorporated in computer‐aided diagnosis (CAD) tools for clinical application.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/1acdfdf6e24dc6c89f61aa7600648b38870bbc9b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images (2018, neutral): “The contributions of this work can be summarised as follows:”
Attention U-Net: Learning Where to Look for the Pancreas (2018, methodology): “The application areas include cardiac MRI [14], cardiac CT [23], abdominal CT [26, 27] segmentation, and lung CT nodule detection [17].”
Deep Learning for Cardiac Image Segmentation: A Review (2019, methodology): “(29) 2D Dense U-net with inception module SAX Bi-ventricle”
Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining (2024, neutral): “It is still challenging to efficiently capture complex and long-range global dependencies from image data [22,30].”
TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation (2021, background): “Convolutional neural networks (CNNs) have achieved unprecedented performance in numerous medical image segmentation tasks, such as pelvis segmentation [3], cardiac diagnosis [11] and polyp segmentation [5,10].”
INet: Convolutional Networks for Biomedical Image Segmentation (2021, methodology): “It was observed that the binary-cross-entropy loss optimized for pixel-level accuracy whereas the dice loss helped in improving the segmentation quality [53].”
Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge (2021, methodology): “Note that our study, while it focuses on multi-scanner generalizable segmentation, conﬁrms several of the results already obtained by the ACDC challenge and other previous works.”