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

Table 6

The calculated segmentation evaluation metrics for level set method and proposed approach in BRATS Training data 2013.

Patient No.	Method	TP	FP	TN	FN	Sensitivity	Specificity	Accuracy	Dice index	Jaccard
Patient 1	Flair	2831	371	16731	106	0.9639	0.9783	0.9761	0.9223	0.8558
	Thermal map	2803	71	17031	134	0.9543	0.9958	0.9897	0.9647	0.9318
Patient 2	Flair	1378	331	13666	26	0.9814	0.9763	0.9768	0.8853	0.7942
	Thermal map	1307	34	13963	97	0.9309	0.9975	0.9914	0.9522	0.9089
Patient 3	Flair	1274	413	17336	10	0.9922	0.9767	0.9777	0.8576	0.7507
	Thermal map	1236	8	17741	48	0.9626	0.9995	0.997	0.9778	0.9566
Patient 4	Flair	1762	560	18243	1	0.9994	0.9702	0.9727	0.8626	0.7585
	Thermal map	1660	33	18770	103	0.9415	0.9982	0.9933	0.9606	0.9242
Patient 5	Flair	2015	807	13191	0	1	0.9423	0.9496	0.8331	0.714
	Thermal map	1901	12	13986	114	0.9434	0.9991	0.9921	0.9679	0.9378
Patient 6	Flair	1383	644	13522	0	1	0.9545	0.9585	0.8111	0.6822
	Thermal map	1271	20	14146	112	0.91901	0.9985	0.9915	0.9506	0.9059