Automatic identification of suspicious bone metastatic lesions in bone scintigraphy using convolutional neural network

Table 5 The lesion-based diagnostic performance of AI model in the testing cohort and the comparison of the AI performance among lung, prostate and breast cancers

	Group for primary tumor types			χ²	P value
	Lung cancer	Prostate cancer	Breast cancer	χ²	P value
Sensitivity	76.16	84.66	81.65	12.88	0.002
Specificity	82.52	79.07	81.78	2.08	0.354
Accuracy	79.40	82.30	81.82	3.13	0.209
PPV	81.12	84.43	78.33	6.52	0.038
NPV	77.70	79.52	85.05	8.85	0.012

Chi-square test was performed to compare the performance of AI model among different tumor types

ISSN: 1471-2342