Frangi-Net: A Neural Network Approach to Vessel Segmentation

11/09/2017

∙

by Weilin Fu, et al.

∙

FAU

∙

In this paper, we reformulate the conventional 2-D Frangi vesselness measure into a pre-weighted neural network ("Frangi-Net"), and illustrate that the Frangi-Net is equivalent to the original Frangi filter. Furthermore, we show that, as a neural network, Frangi-Net is trainable. We evaluate the proposed method on a set of 45 high resolution fundus images. After fine-tuning, we observe both qualitative and quantitative improvements in the segmentation quality compared to the original Frangi measure, with an increase up to 17% in F1 score.

READ FULL TEXT

Frangi-Net: A Neural Network Approach to Vessel Segmentation

A Deep Learning-based in silico Framework for Optimization on Retinal Prosthetic Stimulation

DoubleU-Net++: Architecture with Exploit Multiscale Features for Vertebrae Segmentation

SVS-net: A Novel Semantic Segmentation Network in Optical Coherence Tomography Angiography Images

Fooling Neural Network Interpretations via Adversarial Model Manipulation

The Mertens Unrolled Network (MU-Net): A High Dynamic Range Fusion Neural Network for Through the Windshield Driver Recognition

Automated Pavement Crack Segmentation Using Fully Convolutional U-Net with a Pretrained ResNet-34 Encoder

Semantic Segmentation of Thigh Muscle using 2.5D Deep Learning Network Trained with Limited Datasets

Frangi-Net: A Neural Network Approach to Vessel Segmentation

Related Research

A Deep Learning-based in silico Framework for Optimization on Retinal Prosthetic Stimulation

DoubleU-Net++: Architecture with Exploit Multiscale Features for Vertebrae Segmentation

SVS-net: A Novel Semantic Segmentation Network in Optical Coherence Tomography Angiography Images

Fooling Neural Network Interpretations via Adversarial Model Manipulation

The Mertens Unrolled Network (MU-Net): A High Dynamic Range Fusion Neural Network for Through the Windshield Driver Recognition

Automated Pavement Crack Segmentation Using Fully Convolutional U-Net with a Pretrained ResNet-34 Encoder

Semantic Segmentation of Thigh Muscle using 2.5D Deep Learning Network Trained with Limited Datasets