【医学影像系列三】青光眼诊断眼底图像数据集｜代码｜论文总结｜结果汇总｜名词解析｜评价指标

导语：这是之前做青光眼诊断研究时候整理的资料，所有的文章数字编号都对应我之前发表的论文阅读博客，比如方法汇总 No.15 对应【医学+深度论文：F15】这篇文章。有一些对大家有用但是我没有用到的学习资料也放在文中。汇总整理难免有遗漏，希望大家能够提出和补充，谢谢～

Dataset

数据集汇总

Dataset	Name & Paper	Country	Photo	Feature	Equipment	disease
Drishti-GS	Retinal image dataset for optic nerve head(ONH) segmentation Paper	India	101	OD/OC	FOV 30° 2896×1944 png	Glaucoma
DRIONS-DB	Identification of the optic nerve head with genetic algorithms Paper		110	OD	600×400	Glaucoma
HRF	High-Resolution Fundus (HRF) Image Database		15N，G15，DR15	vessel segment	Canon CR-1 fundus camera FOV 45°	Glaucoma DR
ORIGA	Digital Retinal Images for Vessel Extraction ORIGA-light Paper		650（168G、482N）	OD/OC	3072×2048
RIM-ONE	An open retinal image database for optic nerve evaluation Paper		455 (255 N,200G) 159 (74G,85N)	OD/OC	Nidek AFC210 with a body of a Canon EOS 5D Mark II of 21.1 megapixels 2144×1424
RIM-ONE r1			158( 40 G ,118 N)	OD/OC
RIM-ONE r2			425 (200 G , 225 N)	OD/OC
RIM-ONE r3			159( 74 G, 85 N)		stereo fundus
ONHSD	Optic nerve head segmentation Paper		99 (50 G,49 N)	OD	Canon CR6 45MNf fundus camera FOV 45° 640×480	Glaucoma
SEED-DB
MESSIDOR	Methods to evaluate segmentation and indexing techniques in the field of retinal ophthalmology		1200	DR		DR
SCES	Singapore Chinese Eye Study		1676 (46G,1630N)
SINDI	Singapore Indian Eye Study		5783（5670N，113G）
REFUGE			400 (360N ， 40 G)	macula/OD	Zeiss Visucam 500 2124x2056
GRI	GRI’s Sustainability Disclosure Database
DIARETDB1	DIARETDB1-Standard Diabetic Retinopathy Database Calibration level 1
STARE	Structured Analysis of the Retina
sjchoi86-HRF
ACRIMA
Tajimi	The Tajimi study report 2:prevalence of primary angle closure and secondary glaucoma in a Japanese population	Japan	162 (81 NFLDs , 81 N) 261 (130 NFLDs ,131 N)	NFLD	IMAGEnet digital fundus camera system (TRC-NW6S, Topcon, Tokyo, Japan) 768x576，JPEG
AREDS	Age-Related Eye Disease Study–Results					AMD /cataract

其他

下面是待整理数据集，大家有需要可以自己查，我当时没有用到这些。

Website. http://www.ukbio- bank.ac.uk/about-biobank-uk. Accessed December 5, 2018

OD

SiMES
INSPIRE-AVR
Shifa
3CHASE-DB1
3DIARETDB1
DIARETDB1
DIARETDB0
CHASE-DB1

OC
Bin Rushed
Magrabi

标注相关工具

Tools	introduce	Reference	Introduce
labelme	分割 、分类	https://blog.youkuaiyun.com/heiheiya/article/details/88342597	最著名的标注工具之一，虽然其用户界面有点慢，特别是缩放高清图像时。
RectLabel			简单易用，只在 Mac 可用。
LabelBox			对于大型标记项目很合适，提供不同类型标记任务的选项。
COCO UI			用于标注 COCO 数据集的工具。

数据集相关代码

dataset	-	introduce	github
Grishti-GS1	2015	An adaptive threshold based algorithm for optic disc and cup segmentation in fundus images	https://github.com/NupurBhaisare/Cup-and-disc-segmentation-for-glaucoma-detection-CDR-Calculation-
Grishti-GS1	MICCAI 2018	Towards a glaucoma risk index based on simulated hemodynamics from fundus images	https://github.com/ignaciorlando/glaucoma-hemodynamics
Grishti-GS1 RIMONE	keras	GAN For Glaucome segmentation	https://github.com/tomazrvb/Paper/tree/d638050a3cad67a9c00bd9977be8a01877bdc5e7
Grishti-GS1	2017	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

---

论文

常见会议&期刊

⭐	TOP		introduce
1	ISBI	The IEEE International Symposium on Biomedical Imaging	⭐
2	MICCA	International Conference on Medical Image Computing and Computer-Assisted Intervention	医学影像分析 (Medical Image Analysis) 研究领域的顶尖年会
3	CVPR	IEEE Conference on Computer Vision and Pattern Recognition	计算机视觉和模式识别领域的顶级会议
4	IEEE TMI	transactions on medical imaging	医学图像处理顶级的顶级期刊,生物医学图像。
5	-	Medical Image Analysis	医学影像分析期刊
6	MICS		国内医学图像领域规模最大的学术会议之一

论文期刊会议索引

N	-	-	introduce	-
4	IPMI	Information Processing in Medical Imaging	⭐
4	-	OPHTHALMOLOGY	SCI 1
5	KBS	Knowledge-Based Systems	SCI
6	-	Ophthalmology Glaucoma	SCI 2
7	ICTAI	IEEE International Conference on Tools with Artificial Intelligence
8	ICIP	IEEE International Conference on Image Processing
9	SSD
10	-	scientific reports	SCI 3
11		Information Sciences	SCI 2
12	PLOS ONE		SCI 3
-	PLOS MED		SCI 1
13	IJACSA	International Journal of Advanced Computer Science and Applications
14	T-MI	IEEE Transactions on Medical Imaging	SCI 2
15	EMBC	IEEE Engineering in Medicine and Biology Society
16		Computerized Medical Imaging and Graphics	SCI 4	36
17		Journal of Intelligent Systems	SCI 2
18		BMC Medical Imaging	SCI 4
-		BMC Ophthalmology	SCI 4
19	IOVS	investigatice ophthalmology & visual science	SCI 2
20	OMIA	Ophthalmic Medical Image Analysis	2/1
21		American Journal of Ophthalmology	SCI 2
22		Journal of Glaucoma	SCI 4
23		JAMA Ophthalmol	SCI 2	35

其他

N	-	-	introduce
PRCV	中国模式识别与计算机视觉大会
CCF-GAIR	全球人工智能与机器人峰会

方法汇总

Classification Segmentation Detection	Fundus OCT VF	No.	Position	Method	Introduce
C	F	1	global Image	Inception-v3	三分类(unlikely,suspect, certain)
C+S	F	2	global Image + domain knowledge feature	Faster Rcnn，CNN，FCN,MB-NN （multi-brance neural network model）
C	F	3	OD	difference-of-Gaussian blob detector + Resnet50	二分类(青光眼/正常眼)
S	F	4	OD/OC	定位 Daubechies wavelet transform + 去血管 + 9-layer CNN	CDR
S	F	5	OD/OC	FCN + Post-processing	CDR
S+C	F	6	OD/OC	ROI extraction + Multi-task CNN + Post-processing	二分类(青光眼/正常眼)
C	F	7	OD	CNN+SVM	二分类(青光眼/正常眼)
C	F	8	ONH	transfer Resnet50	二分类(青光眼/正常眼)评估了几种深度学习架构和迁移学习
C	F	9	global Image	18 layer CNN	二分类(青光眼/正常眼)
S+C	F	10	OD	ROI+Extraction+DNN(SAE)+ASM	减弱PPA对分割OD影响
C	F	11	OD	CNN（3con+3maxpooling+2FC）	二分类(青光眼/正常眼)晚期和早期青光眼检测
C	F	12	global Image	Glaucoma-Deep（CNN，DBM，softmax）	二分类(青光眼/正常眼)
C	F	13	global Image	ResNet	CNN、SVM、Random Forest对比
S	F	14	OD、OC	Polar coordinate + M-Net (Multi-Scale input layer + U-Net +Side-Output Layer + Multi-Label Loss Function)	CDR
C	F	15	global Image + local Image(optic disk region)	DENet（4个流）	Disc-aware,Multi-level ,multi-model
C	F	16	global Image	CNN (4con+4fc)	二分类(青光眼/正常眼)
C	F	17	global Image	基于RNN的补丁分类来划分真实的RNFLD边界像素	RNFLD 边界
S	F	18	global Image	Unet （encoder ：pre-trained ResNet34）	RIGA 训练；DRISHTI-GS1、RIM-ONE测试
C	F	19	global Image	CNN+SVM	ROI deformable shape model 检测 OD边界， 集成了局部和整体特征
C	F	20	global Image	AG-CNN ( Attention 、Guide BP 、 ResNet)	二分类(青光眼/正常眼) 建立了一个注意力dataset 与F01/F16对比
S	F	21	OD/OC	crop ROI + FC-DenseNet （ FCN + DenseNet）+ Refinement
S	F	34		cGAN (generator + discriminator)	分割OD

---

结果汇总

Paper	Method	Dataset	OD/ DC(F)	OD/ JC(O)	OD / Acc	OC / DC(F)	OC /JC(O)	OC /Acc	SE	SP
21	Modified U-Net CNN (DL)	Drishti-GS	0.85	0.75	-	-	-	-
35	Large pixel patch based CNN (DL)	Drishti-GS	0.9373	0.8775	-	-	-	-
33	Ensemble learning based CNN (DL)	Drishti-GS	0.871	0.85	-	0.973	0.914	-
23	Fully convolutional DenseNet (DL)	Drishti-GS	0.8282	0.7113	0.9948	0.949	0.9042	0.9969
14	multi-label deep learning and Polar transformation (DL)	ORIGA	-	0.77	-	-	0.929	-
23	Fully convolutional DenseNet(DL)	ORIGA	0.8659	0.7688	-	0.9653	0.9334	-
21	Modified U-Net CNN (DL)	RIM-ONE	0.82	0.69	-	0.94	0.89	-
36	Fully convolutional and adversarial network (DL)	RIM-ONE	0.94	0.768		0.977	0.897
21	Modified U-Net CNN (DL)	DRIONS-DB	0.94	0.89
23	Fully convolutional DenseNet(DL)	DRIONS-DB	0.9415	0.8912
23	Fully convolutional DenseNet(DL)	ONHSD	0.9556	0.9155	0.999

名词解析

青光眼 GON

GON	mean	chinese
CDR	cup-to disc ratio	杯盘比 杯区最大垂直高度除以盘区最大垂直高度
cpRNFLT	circumpapillary retinal nerve fiber layer thickness	视网膜乳头周围神经纤维层厚度
FOV	field of views	视野
GCS	ganglion cells	神经节细胞
GCC	ganglion cell complex	神经节细胞复合体
ISNT	inferior, superior, nasal and temporal
IOP	intraocular pressure	眼压
mIRT	macular inner retinal thickness	黄斑内视网膜厚度
ONH	optic nerve head	视神经乳头
OD	optic disc	视盘
OC	optic cup	视杯
ODD	optic disc diameter	视杯直径
PPA	peripapillary atrophy	视盘旁萎缩弧
PPA	parapapillary atrophy	萎缩弧
POAG	primary open-angle glaucoma	原发性开角型青光眼
PACG	primary angle closure glaucoma	原发性闭角型青光眼
RNFLD	retinal nerve fiber layer defects	视网膜神经纤维层缺损
RPE	Retinal Pigment Epithelium	视网膜色素上皮细胞
RNFL	retinal nerve fiber layer	视网膜神经纤维层
RGC	retinal ganglion cells	视网膜神经节细胞
RGC+	retinal ganglion cell plus inner plexiform layer	视网膜神经节细胞加内丛状层
VCD	vertical cup diameter	垂直杯径
VDD	vertical disc diameter	垂直盘直径
VF	visual fields
-	sclera	巩膜
-	choroid	脉络膜
-	macula	黄斑
-	vasculature hemorrhage	血管出血
-	cornea	角膜
-	neuroretinal rim	视网膜边缘

仪器

image	mean	chinese
OCT	optical coherence tomography	光学相干断层成像术
CFI	color fundus imaging	彩色眼底成像
MRI	magnetic resonance imaging	磁共振成象
FOV	field of view	视野
CAD	Computer aided diagnosis	一种利用数字眼底图像对青光眼做早期诊断的无创技术
GDx	scanning laser polarimetry (GDx: Carl Zeiss Meditec, Dublin, CA)	扫描激光偏振测量仪
HRT	Heidelberg Retina Tomograph Heidelberg Engineering GmbH，Heidelberg，Germany	海德堡视网膜层析x射线摄影机
RS-3000 Advance	spectral-domain OCT (RS-3000 Advance, Nidek, Gamagori, Japan) images	光谱域OCT
OA-1000	OA-1000 optical biometer (Tomey, Nagoya, Japan)	光学生物仪 （测量轴向长度）
RC-5000	RC-5000 refract-keratometer (Tomey)	折射角膜曲率计（记录屈光不正）
RC-5000	RC-5000 non-contact tonometer (Tomey)	非接触眼压计（测定IOP）
-	Goldmann applanation tonometer	压平式眼压计（测定IOP）
-	Kowa nonmyd WX camera	后眼底照片

其他疾病

Other disease	mean	chinese
DR	diabetic retinopathy	糖尿病视网膜病变
-	ophthalmology	眼科
-	cataract	白内障
AMD	age related macular degeneration	年龄相关性黄斑变性
BCVA	Best-corrected visual acuity	最佳矫正视力
logMAR	logarithm of the mimimum angle of resolution	最小分辨角的对数
ANOVA	one-way analysis of variance	单因素方差分析
-	myopia	近视

---

评价指标

Evalution	mean	chinese	Math
AUC	area under the receiver opterating characteristic curve	接收机光电特性曲线下面积
ROC	receiver operating characteristic	受试者工作特征
AROC	receiver operating characteristic curve	接受者操作特征曲线
IoU	intersection over union	交并比	$$IoU=\frac{TP}{TP+FP+FN}$$
SD	standard deviation	标准偏差
CI	confidence interval	置信区间
MD	mean deviation	平均偏差
FP	False Positive	假正例
FN	False Negative	假负例
TP	True Positive	真正例
TN	True Negative	真负例
AC	accuracy	正确率	$$AC=\frac{TP+TN}{TP+TN+FP+FN}$$
SE	sensitivity	灵敏度，将实际有病的人正确地判定为患者的比例。	$$SE=\frac{TP}{TP+FN}$$
SP	specificity	特异度，将实际无病的人正确地判定为非患者的比例。	$$SP=\frac{TN}{TN+FP}$$
PC	precision	精确率针对所有正例(TP+FP)而言 其中真正例(TP)占的比例 精确率也叫查准率	$$PC=\frac{TP}{TP+FP}$$
PPV	positive predictive value	正例预测值
E	overlapping error	重叠的错误	$$E=1-\frac{Area(S\cap G)}{Area(S\cup G)}$$
A	balanced accuracy	平均正确率
$ δ_E $	CDR error	CDR减去ground truth CDR值	$$δ_E=
-	Euclidean distance	欧几里得距离 (mean ± standard deviation)
-	Dice coefficient		$$Dice =2× \frac{
-	Jaccard Index	实质是 IoU	$$JS=\frac {

Example，10病人 7P，3N；
分类结果 正类6个（4P，2N） 负类4个（1N,3P）
TP : 4
TN : 2
FN : 1
FP : 3

$$IoU=\frac{TP}{TP+FP+FN}$$

$$E=1-\frac{Area(S\cap G)}{Area(S\cup G)}$$

$$A=\frac{1}{2}（SE+SP）$$

$$AC=\frac{TP+TN}{TP+TN+FP+FN}$$

$$SE=\frac{TP}{TP+FN}$$

$$SP=\frac{TN}{TN+FP}$$

$$PC=\frac{TP}{TP+FP}$$

$$F1=2\ast \frac{PC\ast SE}{PC+SE}$$

$$F-socre=\frac{2\ast TP}{2\ast TP+FP+FN}$$

$${\delta }_E=|CD{R}_S-CD{R}_G|$$

$$Dice=2\times \frac{|S\cap G|}{|S|+|G|}$$

$$JS=\frac{|GT\cap SR|}{|GT\cup SR|}=\frac{|GT\cap SR|}{|GT|+|SR|-|GT\cap SR|}$$