Towards Reinforced Brain Tumor Segmentation on MRI Images Based on Temperature Changes on Pathologic Area

Table 2

The calculated segmentation evaluation metrics for level set method and proposed approach.

Patient No.	Method	TP	FP	TN	FN	Sensitivity	Specificity	Accuracy	Dice index	Jaccard
Patient 1	T1c	593	191	14609	0	1	0.987	0.9875	0.8612	0.7563
	Flair	592	285	14515	1	0.9983	0.9807	0.9814	0.8054	0.6742
	Thermal map	556	5	14795	37	0.9376	0.9996	0.9972	0.9636	0.9297
Patient 2	T1c	1160	287	18241	0	1	0.9845	0.9854	0.8899	0.8016
	Flair	1138	369	18159	22	0.981	0.98	0.9801	0.8533	0.7442
	Thermal map	1112	37	18491	48	0.9586	0.998	0.9956	0.9631	0.9289
Patient 3	T1c	1593	105	18116	28	0.9827	0.9942	0.9932	0.9599	0.9229
	Flair	1598	431	17790	23	0.9858	0.9763	0.9771	0.8756	0.7787
	Thermal map	1547	7	18214	74	0.9543	0.9996	0.9959	0.9744	0.9502
Patient 4	T1c	2224	109	17545	204	0.9159	0.9938	0.9844	0.9342	0.8766
	Flair	2428	418	17236	0	1	0.9763	0.9791	0.9207	0.8531
	Thermal map	2375	25	17629	53	0.9781	0.9985	0.9961	0.9838	0.9682