Supported Datasets¶

Here is a list of currently support datasets in this package, alongside notable properties. Each dataset name is linked to the current location where raw data can be downloaded. We include the reference of the data split protocols used to generate iterators for training and testing.

Retinography¶

Table 1 Supported Retinography Datasets (`*`: provided within this package)¶
Dataset	Reference	H x W	Samples	Mask	Vessel	OD	Cup	Split Reference	Train	Test
DRIVE	[DRIVE-2004]	584 x 565	40	`x`	`x`			[DRIVE-2004]	20	20
STARE	[STARE-2000]	605 x 700	20	`*`	`x`			[MANINIS-2016]	10	10
CHASE-DB1	[CHASEDB1-2012]	960 x 999	28	`*`	`x`			[CHASEDB1-2012]	8	20
HRF	[HRF-2013]	2336 x 3504	45	`x`	`x`			[ORLANDO-2017]	15	30
IOSTAR	[IOSTAR-2016]	1024 x 1024	30	`x`	`x`	`x`		[MEYER-2017]	20	10
DRIONS-DB	[DRIONSDB-2008]	400 x 600	110			`x`		[MANINIS-2016]	60	50
RIM-ONE r3	[RIMONER3-2015]	1424 x 1072	159			`x`	`x`	[MANINIS-2016]	99	60
Drishti-GS1	[DRISHTIGS1-2014]	varying	101			`x`	`x`	[DRISHTIGS1-2014]	50	51
REFUGE	[REFUGE-2018]	2056 x 2124 (1634 x 1634)	1200			`x`	`x`	[REFUGE-2018]	400 (+400)	400
DRHAGIS	[DRHAGIS-2017]	Varying	39	`x`	`x`			[DRHAGIS-2017]	19	20

Warning

REFUGE Dataset Support

The original directory Training400/AMD in REFUGE is considered to be replaced by an updated version provided by the AMD Grand-Challenge (with matching names).

The changes concerns images A0012.jpg, which was corrupted in REFUGE, and A0013.jpg, which only exists in the AMD Grand-Challenge version.

X-Ray¶

Table 2 Supported X-Ray Datasets¶
Dataset	Reference	H x W	Radiography Type	Samples	Mask	Split Reference	Train	Test
Montgomery County	[MC-2014]	4020 x 4892, or 4892 x 4020	Digital Radiography (DR)	138	`*`	[GAAL-2020]	96 (+14)	28
JSRT	[JSRT-2000]	2048 x 2048	Digitized Radiography (laser digitizer)	247	`*`	[GAAL-2020]	172 (+25)	50
Shenzhen	[SHENZHEN-2014]	Varying	Computed Radiography (CR)	662	`*`	[GAAL-2020]	396 (+56)	114
CXR8	[CXR8-2017]	1024 x 1024	Digital Radiography	112120	`x`	[GAAL-2020]	78484 (+11212)	22424

Warning

SHENZHEN/JSRT/CXR8 Dataset Support

For some datasets (in which the annotations/masks are downloaded separately from the dataset with the original images), both the original images and annotations must be downloaded and placed inside the same directory, to match the dataset reference dictionary’s path.

The Shenzhen root directory should then contain at least these two subdirectories:
- CXR_png/ (directory containing the CXR images)
- mask/ (contains masks downloaded from Shenzhen Annotations)
The CXR8 root directory:
- images/ (directory containing the CXR images)
- segmentations/ (contains masks downloaded from CXR8 Annotations)
The JSRT root directory:
- All247images/ (directory containing the CXR images, in raw format)
- scratch/ (contains masks downloaded from JSRT Annotations)