KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations (2020-06-08T00:00:00.000000Z)

TL;DR

This work proposes an over-complete architecture (Ki-Net) which involves projecting the data onto higher dimensions (in the spatial sense) and results in significant improvements in the case of segmenting small anatomical landmarks and blurred noisy boundaries while obtaining better overall performance.

Abstract

Due to its excellent performance, U-Net is the most widely used backbone architecture for biomedical image segmentation in the recent years. However, in our studies, we observe that there is a considerable performance drop in the case of detecting smaller anatomical structures with blurred noisy boundaries. We analyze this issue in detail, and address it by proposing an over-complete architecture (Ki-Net) which involves projecting the data onto higher dimensions (in the spatial sense). This network, when augmented with U-Net, results in significant improvements in the case of segmenting small anatomical landmarks and blurred noisy boundaries while obtaining better overall performance. Furthermore, the proposed network has additional benefits like faster convergence and fewer number of parameters. We evaluate the proposed method on the task of brain anatomy segmentation from 2D Ultrasound (US) of preterm neonates, and achieve an improvement of around \(4\%\) in terms of the DICE accuracy and Jaccard index as compared to the standard-U-Net, while outperforming the recent best methods by \(2\%\). Code: https://github.com/jeya-maria-jose/KiU-Net-pytorch

Authors

Vishal M. Patel

23 papers

Vishwanath A. Sindagi

8 papers

Jeya Maria Jose Valanarasu

3 papers

TL;DR

Abstract

Authors

References27 items

Learning to Segment Brain Anatomy From 2D Ultrasound With Less Data

UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Brain Tumor Segmentation and Survival Prediction Using 3D Attention UNet

Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting

Image-to-Images Translation for Multi-Task Organ Segmentation and Bone Suppression in Chest X-Ray Radiography

Fully Automated Pancreas Segmentation with Two-stage 3D Convolutional Neural Networks

Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks

Automatic Segmentation of the Cerebral Ventricle in Neonates Using Deep Learning with 3D Reconstructed Freehand Ultrasound Imaging

Ischemic Stroke Lesion Segmentation Using Adversarial Learning

Automatic Segmentation of Neonatal Ventricles from Cranial Ultrasound for Prediction of Intraventricular Hemorrhage Outcome

H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes

Dilatation of Lateral Ventricles with Brain Volumes in Infants with 3D Transfontanelle US

Automatic real-time CNN-based neonatal brain ventricles segmentation

Image-to-Image Translation with Conditional Adversarial Networks

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

Adam: A Method for Stochastic Optimization

Rectified Linear Units Improve Restricted Boltzmann Machines

Neuroimaging and Neurodevelopmental Outcome of Premature Infants

Imaging biomarkers of outcome in the developing preterm brain

Learning Overcomplete Representations

Deep learning approaches to biomedical image segmentation

Automatic segmentation approach to extracting neonatal cerebral ventricles from 3D ultrasound images

Title Suppressed Due to Excessive Length 13

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names