AI analytics can be used as imaging biomarkers for predicting invasive upgrade of ductal carcinoma in situ

Yoon, Jiyoung; Yang, Juyeon; Lee, Hye Sun; Kim, Min Jung; Park, Vivian Youngjean; Rho, Miribi; Yoon, Jung Hyun

doi:10.1186/s13244-024-01673-0

Insights into Imaging

Table 4 Multivariable analysis for predictors of invasive upgrade in the 341 mammographically detected DCIS patients

From: AI analytics can be used as imaging biomarkers for predicting invasive upgrade of ductal carcinoma in situ

Variables		Clinicopathologic features + mammographic features		Clinicopathologic features + BI-RADS assessments		Clinicopathologic features + AI-CAD scores		Clinicopathologic features + dichotomized AI-CAD score		Clinicopathologic features + graded AI-CAD score
Variables		OR (95% CI)	p value	OR (95% CI)	p value	OR (95% CI)	p value	OR (95% CI)	p value	OR (95% CI)	p value
Related symptoms	No	ref		ref		ref		ref		ref
Related symptoms	Yes	1.518 (0.860–2.681)	0.150	1.317 (0.746–2.323)	0.343	1.534 (0.887–2.652)	0.126	1.533 (0.887–2.652)	0.126	1.537 (0.886–2.665)	0.126
Biopsy method	Core needle biopsy	ref		ref		ref		ref		ref
Biopsy method	Vacuum-assisted biopsy	0.419 (0.223–0.787)	0.007	0.495 (0.264–0.929)	0.029	0.417 (0.227–0.768)	0.005	0.411 (0.223–0.756)	0.004	0.406 (0.220–0.748)	0.004
Nuclear grade	Low	ref		ref		ref		ref		ref
	Intermediate	2.115 (1.138–3.931)	0.018	1.773 (0.953–3.298)	0.070	1.878 (1.003–3.515)	0.049	1.990 (1.071–3.697)	0.029	1.925 (1.033–3.587)	0.039
	High	3.028 (1.370–6.690)	0.006	2.148 (0.949–4.862)	0.067	2.709 (1.223–6.002)	0.014	2.915 (1.330–6.388)	0.008	2.725 (1.236–6.012)	0.013
Imaging features on mammography	Mass/asymmetry/distortion	ref
	Calcifications only	1.519 (0.716–3.223)	0.276
	Combined	2.194 (1.057–4.557)	0.035
Final assessment for mammography	BI-RADS 3			ref
	BI-RADS 4a			0.816 (0.196–3.399)	0.780
	BI-RADS 4b			1.190 (0.287–4.932)	0.811
	BI-RADS 4c			1.660 (0.423–6.511)	0.467
	BI-RADS 5			3.507 (0.861–14.280)	0.080
Raw numerical AI-CAD score						1.008 (1.000–1.017)	0.047
Dichotomized AI-CAD score	AI-CAD score < 50%							ref
Dichotomized AI-CAD score	AI-CAD socre ≥ 50%							1.735 (0.904–3.330)	0.098
Graded AI-CAD score	AI-CAD score < 25%									ref
	AI-CAD score 25–50%									1.371 (0.443–4.249)	0.584
	AI-CAD score 50–75%									1.191 (0.394–3.601)	0.757
	AI-CAD score ≥ 75%									2.145 (0.944–4.873)	0.069
AUC (95% CI)		0.691 (0.630–0.751)		0.712 (0.653–0.772)		0.688 (0.627–0.749)		0.677 (0.615–0.738)		0.683 (0.623–0.744)

DCIS Ductal carcinoma in situ, OR Odds ratio, 95% CI 95% confidence interval, ref Reference, BI-RADS Breast Imaging Reporting And Data System, AI-CAD AI-based computer-aided detection/diagnosis, AUC Area under curve

Back to article page