Performance of high-resolution diffusion-weighted magnetic resonance imaging for detecting clinically occult early breast cancers: a multi-reader study

To compare mammography, breast ultrasound (US), high-resolution diffusion-weighted magnetic resonance imaging (DW-MRI), dynamic contrast-enhanced breast MRI (DCE-MRI), and their combinations for detecting clinically occult early breast cancers (EBCs), including ductal carcinoma in situ (DCIS).

Three hundred and three consecutive women with screening imaging-detected early breast cancers (60 pure DCIS, 36 DCIS with microinvasion, and 207 invasive carcinoma less than 20 mm) who underwent breast MRI at 3 T including DW-MRI (b-values of 0, 800 and 1200 s/mm²; in-plane resolution, 1.1 × 1.1 mm² or 1.3 × 1.3 mm²; section thickness, 3 mm) were retrospectively reviewed. Three radiologists independently reviewed each examination. Statistical analysis included Chi-square test, McNemar test for comparison of cancer detection rates, and Fleiss’ Kappa for interreader agreement. Mixed-effect logistic regression analysis was employed to evaluate factors associated with cancer detection on DW-MRI.

The overall cancer detection rates were 54.8% on mammography, 71.0% on breast US, 81.5% on DW-MRI, and 87.1% on DCE-MRI. On McNemar test, DW-MRI detected more cancers than mammography (adjusted p < 0.001), and its combination with mammography showed a similar cancer detection rate to DCE-MRI combined with mammography (adjusted p = 0.808). On multivariable analysis, histologic type, lesion size, ADC and CNR on DW-MRI were independent factors for cancer detection on DW-MRI. The interreader agreement for cancer detection was moderate to substantial (Fleiss’ kappa: 0.52–0.65) across each modality.

High-resolution DW-MRI plus mammography showed comparable cancer detection rate to DCE-MRI plus mammography for detecting clinically occult EBCs including DCIS.