Abstract #1211

Usefulness of Deep Learning Models of DWI in Direct Differentiating Malignant and Benign Breast Tumors Without Lesion Segmentation

Mami Iima^1,2, Kazuki Tsuji³, Ryosuke Mizuno⁴, Toshiki Yamazaki³, Masako Kataoka¹, Maya Honda^1,5, Rie Ota^1,6, Aika Okazawa⁷, Keiho Imanishi⁸, Masakazu Toi⁹, and Yuji Nakamoto¹

¹Kyoto University Graduate School of Medicine, Kyoto, Japan, ²Kyoto University Hospital, Institute for Advancement of Clinical and Translational Science (iACT), Kyoto University Hospital, Kyoto, Japan, ³Kyoto University Faculty of Medicine, Kyoto, Japan, ⁴A.I.System Research CO.,Ltd., Kyoto, Japan, ⁵Diagnostic Radiology, Kansai Electric Power Hospital, Osaka, Japan, ⁶Diagnostic Radiology, Tenri Hospital, Nara, Japan, ⁷Kyoto University Graduate School of Medi, Kyoto, Japan, ⁸e-Growth Co., Ltd., Kyoto, Japan, ⁹Breast Surgery, Kyoto University Graduate School of Medi, Kyoto, Japan

Synopsis

Keywords: Breast, Breast

348 women suspected of breast tumors were enrolled, and 206 breast lesions (139 malignant, 67 benign) were further analyzed. Breast 5b-value-DWI was performed, and a deep learning model dedicated to this breast DWI dataset was established. Several comparative experiments were performed; comparison of data augmentations, small network VS. large network, 2DCNN VS. 3DCNN, and analysis in 5b-DWI VS. ADC maps. Augmentations using elastic deformation, affine transform, and Gaussian noise improved diagnostic performance up to AUC=0.90. The use of small CNN and without ADC map also showed higher diagnostic performance (AUC=0.88-0.90), showing AI potential to improve breast DWI diagnostic performance.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.