Automatic segmentation of hepatic metastases on DWI images based on a deep learning method: assessment of tumor treatment response according to the RECIST 1.1 criteria

Table 5 The agreement of treatment response assessment

	Testing dataset	Validation cohort
R1 vs. reference standard	0.48 (0.21–0.74)	0.63 (0.43–0.84)
R2 vs. reference standard	0.30 (0.11–0.40)	0.45 (0.20–0.69)
Automated segmentation vs. reference standard	0.51 (0.23–0.79)	0.60 (0.34–0.84)
R1 vs. R2	0.58 (0.33–0.84)	0.55 (0.32–0.78)
R1 vs. Automated segmentation	0.85 (0.70–1.00)	0.74 (0.53–0.96)
R2 vs. Automated segmentation	0.46 (0.20–0.72)	0.50 (0.24–0.75)

R1: an attending radiologist with 8 year’s reading experience; R2: a fellow radiologist with 4 year’s reading experience

ISSN: 1471-2407