Detalle Publicación


The accuracy of titanium contrast-enhanced mammography: a retrospective multicentric study

Título de la revista: ACTA RADIOLOGICA
ISSN: 0284-1851
Volumen: 61
Número: 10
Páginas: 1335 - 1342
Fecha de publicación: 2020
Background Recently, a new mammography system to perform contrast-enhanced mammography has become available in the market. For the high-energy acquisition, it uses a titanium filter instead of a copper one, reducing the tube load while maintaining image quality. Purpose To retrospectively evaluate the accuracy of contrast-enhanced mammography with a titanium filter (TiCEM) in three readers with different grades of experience. Material and Methods IRB-approved retrospective multicentric lesion by lesion study with 200 lesions, all of them initially classified as BI-RADS categories 0/3/4/5 on mammography and/or ultrasound and with pathological confirmation, in 135 patients. Three readers with different levels of experience (expert, resident, intermediate) blinded to the final diagnosis, retrospectively evaluated the low-energy (LE) images and the combination of LE and recombined (subtracted) images and classified the lesions according to the BI-RADS categories. Reader 1 also categorized the breast density. ROC curves were performed for each reader. Results Out of the 200 lesions, 82 were benign and 118 malignant (20 DCIS, 10 ILC, 88 IDC). The AUCs of LE versus TiCEM for were: Reader 1: 0.7 vs. 0.88, P < 0.001; Reader 2: 0.63 vs. 0.83, P < 0.001; and Reader 3: 0.63 vs. 0.84, P < 0.001. For the three readers, the AUCs of LE versus TiCEM were significantly superior in both dense and non-dense breasts (P < 0.001). Comparing the AUC of LE for Reader 1 (expert) versus the AUC of TiCEM for Reader 2 (resident) there were significant differences (0.7 vs. 0.83, P < 0.001). Conclusion The accuracy of TiCEM was significantly better for all the readers, in both dense and non-dense breasts. The accuracy of a resident reading a TiCEM study was better than the accuracy of an expert radiologist reading LE images.