Colorectal-Liver-Metastases, liver and veins

Portal venous CT of one patient with colorectal liver metastases, with the liver, the hepatic veins and the portal veins segmented (Colorectal-Liver-Metastases).

10 test casesabdomenimage CT

Look at the images

Read before comparing (1)

Cases. The cases are the fixed images of CRLMCT's pairs, each on its pair's side of the split. 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	Images
11–5	MONAI wholeBody CTGPUapp1 of 3 structures	0.949 ±0.004	0.645 ±0.047	19.35 ±2.04	16	3.8	7.1
21–5	KonfAI segmentation app · TotalSegmentator (total), KonfAI appGPUapp1 of 3 structures	0.948 ±0.005	0.636 ±0.052	18.98 ±1.87	20	3.5	5.6
31–5	KonfAI segmentation app · TotalSegmentator (total), the authors' packageGPUapp1 of 3 structures	0.948 ±0.005	0.636 ±0.055	19.05 ±1.74		19.8	3.6
41–5	KonfAI segmentation app · MRSegmentator, KonfAI appGPUapp1 of 3 structures2 failed	0.759 ±0.286	0.519 ±0.204	19.57 ±2.48	22	3.7	6.4
51–5	CT-FM whole-body segmentationGPUapp1 of 3 structures	0.861 ±0.089	0.453 ±0.093	31.13 ±11.80	24	7.2	6.9

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 10 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. Time and memory measured on Workstation.

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 CTGPUapp1 of 3 structuresolder run	0.949 ±0.004	0.645 ±0.047	19.35 ±2.04	11	2.4	6.9	Laptop

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
MONAI wholeBody CT	0.314	0.316	0.315	0.315	0.320	0.316	0.316	0.320	0.314	0.317
KonfAI segmentation app · TotalSegmentator (total), KonfAI app	0.314	0.315	0.316	0.315	0.321	0.315	0.316	0.319	0.313	0.317
KonfAI segmentation app · TotalSegmentator (total), the authors' package	0.314	0.314	0.316	0.315	0.321	0.316	0.316	0.319	0.314	0.317
KonfAI segmentation app · MRSegmentator, KonfAI app	0.313	failed	0.317	0.316	failed	0.316	0.315	0.322	0.316	0.317
CT-FM whole-body segmentation	0.283	0.314	0.301	0.292	0.319	0.312	0.312	0.208	0.214	0.314

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 experts 3 structures, the dataset's segmentations: 1 the liver, its tumours included, then 2 the hepatic veins and 3 the portal veins over it; made semi-automatically in Scout Liver by an expert radiologist or fellow
Source: www.cancerimagingarchive.net/collection/colorectal-liver-metastases
doi.org/10.7937/QXK2-QG03
doi.org/10.1038/s41597-024-02981-2
Licence: CC BY 4.0

10 cases for tuning, never tested

1037_1030/fixed, 1063_1164/fixed, 1054_1176/fixed, 1167_1004/fixed, 1137_1062/fixed, 1003_1091/fixed, 1028_1100/fixed, 1180_1020/fixed, 1134_1013/fixed, 1192_1105/fixed