HQColon, colon

CT colonography of one patient, with the whole colon segmented, its gas- and fluid-filled parts together (HQColon).

11 test casesabdomenimage CT

Read before comparing (1)

Cases. HQColon's fixed images: a test pair's image is a test case, a development pair's a development case. The moving images are left out: their headers carry the pair's start, so they are not the images as delivered.

		Accuracy			Cost
#	Method	Dice	Surface Dice	HD95 mm	Time s	RAM GB	GPU GB	Machine	Images
11–4	KonfAI segmentation app · TotalSegmentator (total), the authors' packageGPUapp	0.871 ±0.021	0.462 ±0.029	10.77 ±0.95		26.2	5.3	Workstation
21–4	KonfAI segmentation app · TotalSegmentator (total), KonfAI appGPUapp	0.871 ±0.020	0.448 ±0.031	10.59 ±0.95	20	2.8	5.7	Workstation
31–4	KonfAI segmentation app · MRSegmentator, KonfAI appGPUapp1 failed	0.783 ±0.176	0.432 ±0.100	11.44 ±1.54	62	20.0	8.8	Workstation
41–4	MONAI wholeBody CTGPUapp	0.695 ±0.066	0.371 ±0.034	21.39 ±5.64	25	3.6	16.3	Laptop

The order averages each method's ranks on Dice, Surface Dice, HD95 mm, so the first one is not always the best in every column. ± is the 95% interval of the mean over the 11 cases. Two neighbours are tied when a paired Wilcoxon test on the shared cases does not find the upper one better on Dice (5%): the places a method could hold are then shown under its own. The best value of each column is in colour. Click a row to see its images, a column title to sort by it.

1 result not ranked: an older run, cases still missing, or a failure on every case

		Accuracy			Cost
#	Method	Dice	Surface Dice	HD95 mm	Time s	RAM GB	GPU GB	Machine	Images
	MONAI wholeBody CTGPUappfailed on every case	0.000 ±0.000	0.000 ±0.000					Workstation

Dice: how much the organ contours overlap, 1 is perfect. Surface Dice: the share of the contours' surfaces within a tolerance of each other, 1 is perfect. HD95: distance between the contours' surfaces.

Case by case

Measure

Dice	1	2	3	4	5	6	7	8	9	10	11
KonfAI segmentation app · TotalSegmentator (total), the authors' package	0.889	0.890	0.870	0.889	0.842	0.888	0.801	0.856	0.912	0.887	0.860
KonfAI segmentation app · TotalSegmentator (total), KonfAI app	0.888	0.885	0.861	0.884	0.852	0.894	0.796	0.860	0.905	0.889	0.867
KonfAI segmentation app · MRSegmentator, KonfAI app	0.879	failed	0.870	0.874	0.817	0.824	0.802	0.870	0.901	0.893	0.881
MONAI wholeBody CT	0.729	0.557	0.812	0.585	0.770	0.733	0.770	0.536	0.679	0.666	0.807

Click a score to look at that result: the image, the truth in green and the method's map in red. Underlined scores have their image; for the others you see the case without the result.

About the data

The first test caseClick to look at every case.

Truth: contours by a program, verified by people the whole colon (1), its gas- and fluid-filled parts, the dataset's mask on each scan
Source: doi.org/10.1038/s41597-025-06518-z
doi.org/10.17605/OSF.IO/8TKPM
github.com/horizon-europe-2023-ire/colon-segmentation-dataset
www.cancerimagingarchive.net/collection/ct-colonography
doi.org/10.7937/K9/TCIA.2015.NWTESAY1
Licence: masks CC BY 4.0, images CC BY 3.0

10 cases for tuning, never tested

1.3.6.1.4.1.9328.50.4.0511/fixed, 1.3.6.1.4.1.9328.50.4.0776/fixed, 1.3.6.1.4.1.9328.50.4.0195/fixed, 1.3.6.1.4.1.9328.50.4.0423/fixed, 1.3.6.1.4.1.9328.50.4.0328/fixed, 1.3.6.1.4.1.9328.50.4.0659/fixed, CTC-3304961391/fixed, 1.3.6.1.4.1.9328.50.4.0007/fixed, 1.3.6.1.4.1.9328.50.4.0005/fixed, 1.3.6.1.4.1.9328.50.4.0060/fixed