Repeat chest CT, same patient, tumour truth

1 datasets, 10 test pairs. A method is ranked here when it has a result on every pair of every one of them.

Read before comparing

Ranked apart: one small tumour is the only scored structure, so its contour cannot establish registration accuracy across the whole chest.

Ranking Official Research

#	Method	Mean rank	RIDER Lung CT
1	greedyCPUapp	1.671.0–2.0	1
2	NiftyRegCPUapp	2.001.0–2.0	2
3	DemonsCPUapp	3.003.0–5.0	3
4	ConvexAdam (MIND)GPUapp	3.673.0–5.0	4
5	deedsCPUapp	4.673.0–5.0	5

1 place in that table, 1 is best2/10 cases done, not ranked yetn/a does not apply not run some cases failed

Under each dataset, the method's place in that dataset's table: 1 is best, the darker the better. The mean rank averages its places over the datasets.

The scores, dataset by dataset

Each score is followed by its change against no registration: green when the method did better, red when it did worse.

RIDER Lung CT

10 pairs · ordered on Dice and SDlogJ

#	Method	Dice	Change	SDlogJ
1	greedy	0.782	+0.046	0.049
2	NiftyReg	0.785	+0.049	0.061
3	Demons	0.781	+0.045	0.054
4	ConvexAdam (MIND)	0.784	+0.048	0.081
5	deeds	0.780	+0.044	0.070
	No registration	0.736		0.000

Repeat chest CT, same patient, tumour truth

Read before comparing

Ranking OfficialResearch

The scores, dataset by dataset

Ranking Official Research