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

Table 5

The calculated segmentation evaluation metrics for level set method and proposed approach in BRATS Training data 2012.

Patient No.	Method	TP	FP	TN	FN	Sensitivity	Specificity	Accuracy	Dice index	Jaccard
Patient 1	Flair	1102	178	17090	66	0.9434	0.9896	0.9867	0.9	0.818
	Thermal map	1142	18	17250	26	0.9777	0.9989	0.9976	0.9811	0.9629
Patient 2	Flair	1067	165	15176	2	0.9981	0.9892	0.9898	0.9274	0.8646
	Thermal map	1038	18	15323	31	0.971	0.9988	0.997	0.9769	0.9549
Patient 3	Flair	2891	498	14358	4	0.9986	0.9664	0.9717	0.9201	0.852
	Thermal map	2767	41	14815	128	0.9557	0.9972	0.9904	0.9703	0.9424
Patient 4	Flair	1678	342	9386	4	0.9976	0.9648	0.9696	0.9065	0.829
	Thermal map	1561	44	9684	121	0.928	0.9954	0.9855	0.9498	0.9044
Patient 5	Flair	1810	191	17340	69	0.9632	0.9891	0.9866	0.9329	0.8743
	Thermal map	1803	123	17408	76	0.9595	0.9929	0.9897	0.9477	0.9005
Patient 6	Flair	1982	628	16415	1	0.9994	0.9631	0.9669	0.863	0.759
	Thermal map	1916	32	17011	67	0.9662	0.9981	0.9947	0.9748	0.9508