【医学+深度论文：F34】2018 CVPR Retinal Optic Disc Segmentation using Conditional Generative Adversarial

34

2018 CVPR

Retinal Optic Disc Segmentation using Conditional Generative Adversarial Network

dataset	-	introduce	github
Grishti-GS1	2017 keras	F21 复现	https://github.com/abhinav-iiit/fundus-image-segmentation
Grishti-GS1	2017 CVPR keras	F21	https://github.com/seva100/optic-nerve-cnn
-	pytorch	retinal-cGAN	https://github.com/shuangyueliao/retinal-cGAN

Method ：分割 OD
Dataset： DRISHTI GS1
RIM-ONE
Architecture： cGAN
Results:

Dataset	Accuracy	Dice	JACC	Senstivity	Specificity
DRISHTI	GS1	0.98	0.97	0.96	0.98
RIM-ONE	0.98	0.98	0.93	0.98	0.99

Method

The Proposed cGAN network

cGANs is a deep learning network that can learn the statistical invariant features (texture, color etc.) of input image and segment the optic disc region.
generator
learns the mapping from the input, a fundus image,to the output, a segmented image.
discriminator
learns a loss function to train this mapping by comparing the ground-truth and the predicted output
the whole cGAN network
optimizes a loss function that combines a conventional binary cross-entropy loss with an adversarial term.
The adversarial term encourages the generator to produce output that cannot be distinguished from ground-truth ones.

generator

based on encoding and decoding layers
LeakyRelu（slope 0.2）
image 256×256

discriminator

5conv （3 × 3 stride 2）
output 30×30 512
the concatenation of the retinal image and the segmentation mask as an input to be evaluated as real or fake
在生成器的损失计算中包含对抗性 score 有助于增强网络分割的能力

train

epoch 200 ， batch size 4 ， Adam 0.0002

Result

Experience

和 FCN、SegNet、U-Net 比较
和论文 F14 等共三篇文章做比较
cGAN 效果最好,OD分割更接近地面真实情况，边界更精确。U-Net也提供了可接受的分割。在五种测试方法中，SegNet的分割效果最差。

Discussion

cGAN网络不需要大量的图像来训练
由于最后的分割只在生成器网络中实现，因此在不增加任何复杂度的情况下，它可以获得很高的分割性能。
cGAN算法优于目前最先进的 OD 分割方法

【医学+深度论文：F34】2018 CVPR Retinal Optic Disc Segmentation using Conditional Generative Adversarial相关推荐

【医学+深度论文：F04】Integrated Optic Disc and Cup Segmentation with Deep Learning
04 Integrated Optic Disc and Cup Segmentation with Deep Learning 2015 年比较老分割问题 : 青光眼筛查,视盘分割,视杯分割 Da ...
【医学+深度论文：F25】2018 CVPR Enhanced Optic Disk and Cup Segmentation with Glaucoma Screening from Fundus
25 2018 CVPR Enhanced Optic Disk and Cup Segmentation with Glaucoma Screening from Fundus Images usi ...
【医学+深度论文：F10】ISBI Using Deep Learning for Robustness to Parapapillary Atrophy in Optic Disc
10 2015 ISBI Using Deep Learning for Robustness to Parapapillary Atrophy in Optic Disc Segmentation ...
论文阅读 [TPAMI-2022] DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement
论文阅读 [TPAMI-2022] DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement 论文搜索 ...
CGAN论文解读：Conditional Generative Adversarial Nets
论文链接:Conditional Generative Adversarial Nets 代码解读:Keras-CGAN_MNIST 代码解读目录一.前言二.相关工作三.网络结构 CGAN N ...
论文阅读：Single Image Dehazing via Conditional Generative Adversarial Network
Single Image Dehazing via Conditional Generative Adversarial Network Runde Li∗ Jinshan Pan∗ Zechao L ...
【医学+深度论文：F14】2018 Joint Optic Disc and Cup Segmentation Based on Multi Label Deep Network
14 2018 T-MI (IEEE Transactions on Medical Imaging ) Joint Optic Disc and Cup Segmentation Based on ...
【医学+深度论文：F23】2018 symmetry Dense Fully Convolutional Segmentation of the Optic Disc and
23 2018 symmetry Dense Fully Convolutional Segmentation of the Optic Disc and Cup in Colour Fundus f ...
【医学+深度论文：F21】2017 CVPR Optic Disc and Cup Segmentation Methods for Glaucoma Detection
21 2017 CVPR Optic Disc and Cup Segmentation Methods for Glaucoma Detection with Modification of U-N ...

【医学+深度论文：F34】2018 CVPR Retinal Optic Disc Segmentation using Conditional Generative Adversarial

34

Method

Result

Discussion

【医学+深度论文：F34】2018 CVPR Retinal Optic Disc Segmentation using Conditional Generative Adversarial相关推荐

最新文章

热门文章