CNN-based Segmentation of Medical Imaging Data

By Baris Kayalibay, Grady Jensen, Patrick van der Smagt. 2017

473 citations recorded by the source corpus.

Convolutional neural networks have been applied to a wide variety of computer vision tasks. Recent advances in semantic segmentation have enabled their application to medical image segmentation. While most CNNs use two-dimensional kernels, recent CNN-based publications on medical image segmentation featured three-dimensional kernels, allowing full access to the three-dimensional structure of medical images. Though closely related to semantic segmentation, medical image segmentation includes specific challenges that need to be addressed, such as the scarcity of labelled data, the high class imbalance found in the ground truth and the high memory demand of three-dimensional images. In this work, a CNN-based method with three-dimensional filters is demonstrated and applied to hand and brain MRI. Two modifications to an existing CNN architecture are discussed, along with methods on addressing the aforementioned challenges. While most of the existing literature on medical image segmentation focuses on soft tissue and the major organs, this work is validated on data both from the central nervous system as well as the bones of the hand.

Subfields: Artificial Intelligence, Biomedical Engineering, Neurology

How researchers see this paper

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

In Artificial Intelligence

In Biomedical Engineering

In Neurology

Citations in the corpus

Scalable Neural Architecture Search for 3D Medical Image Segmentation (2019, methodology): “ropose a NAS framework for AutoML in designing neural networks especially for 3D medical image segmentation. 3D U-Net [1] has been popularly used for segmenting high-resolution 3D medical images (see [4,8,11]) since both semantic as well as spatial information can be eciently exploited through skip ”
DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks (2018, methodology): “We employ an instance from a family of network architectures, ResUNets (Kayalıbay et al., 2017; Zhang et al., 2017), which learns a transformation between images.”
Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge (2017, methodology): “Being both based on the U-Net, our network architecture shares some similarities with [9].”
Recurrent residual U-Net for medical image segmentation (2019, methodology): “33 The U-Net model only shows the benefit during the training process in the form of better convergence.”
Autofocus Layer for Semantic Segmentation (2018, methodology): “Our model is only surpassed by the pipelines of [10] and [7], who both used ensembles of CNNs with deep supervision and more aggressive data augmentation.”
Segment Anything Model for medical image analysis: an experimental study (2023, background): “Image segmentation is a central task in medical image analysis, ranging from the segmentation of organs [31], abnormalities [3], bones [17], and others [28], which has received significant advancements from deep learning [13, 30].”
Explaining Therapy Predictions with Layer-Wise Relevance Propagation in Neural Networks (2018, unknown): “Convolution neural networks, for instance, can be applied for the classification and segmentation of medical imaging data [12, 13, 14].”
Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation (2018, methodology): “Meanwhile, different variants of U-Net models have been proposed, including a very simple variant of U-Net for CNN-based segmentation of Medical Imaging data [32].”
Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis (2017, methodology): “The network was trained using gradient descent backpropagation, with the Adam optimizer and a Jaccard index-based loss function, as in [18].”
3D Deep Learning on Medical Images: A Review (2020, methodology): “[58] presented a modified 3D U-Net architecture for brain tumor segmentation where they introduce some nonlinearity in the”
No New-Net (2018, background): “Recently, a growing number of architectural modiﬁcations to encoder-decoder networks have been proposed that are designed to improve the performance of the networks for their speciﬁc tasks [17,19,20,21,10,6,22,7].”