TY - GEN
T1 - Automated lesion detection and segmentation in digital mammography using a u-net deep learning network
AU - De Moor, Timothy
AU - Rodriguez-Ruiz, Alejandro
AU - Gubern Mérida, Albert
AU - Mann, Ritse
AU - Teuwen, Jonas
PY - 2018/1/1
Y1 - 2018/1/1
N2 - Computer-aided detection or decision support systems aim to improve breast cancer screening programs by helping radiologists to evaluate digital mammography (DM) exams. Commonly such methods proceed in two steps: Selection of candidate regions for malignancy, and later classification as either malignant or not. In this study, we present a candidate detection method based on deep learning to automatically detect and additionally segment soft tissue lesions in DM. A database of DM exams (mostly bilateral and two views) was collected from our institutional archive. In total, 7196 DM exams (28294 DM images) acquired with systems from three different vendors (General Electric, Siemens, Hologic) were collected, of which 2883 contained malignant lesions verified with histopathology. Data was randomly split on an exam level into training (50%), validation (10%) and testing (40%) of deep neural network with u-net architecture. The u-net classifies the image but also provides lesion segmentation. Free receiver operating characteristic (FROC) analysis was used to evaluate the model, on an image and on an exam level. On an image level, a maximum sensitivity of 0.94 at 7.93 false positives (FP) per image was achieved. Similarly, per exam a maximum sensitivity of 0.98 at 7.81 FP per image was achieved. In conclusion, the method could be used as a candidate selection model with high accuracy and with the additional information of lesion segmentation.
AB - Computer-aided detection or decision support systems aim to improve breast cancer screening programs by helping radiologists to evaluate digital mammography (DM) exams. Commonly such methods proceed in two steps: Selection of candidate regions for malignancy, and later classification as either malignant or not. In this study, we present a candidate detection method based on deep learning to automatically detect and additionally segment soft tissue lesions in DM. A database of DM exams (mostly bilateral and two views) was collected from our institutional archive. In total, 7196 DM exams (28294 DM images) acquired with systems from three different vendors (General Electric, Siemens, Hologic) were collected, of which 2883 contained malignant lesions verified with histopathology. Data was randomly split on an exam level into training (50%), validation (10%) and testing (40%) of deep neural network with u-net architecture. The u-net classifies the image but also provides lesion segmentation. Free receiver operating characteristic (FROC) analysis was used to evaluate the model, on an image and on an exam level. On an image level, a maximum sensitivity of 0.94 at 7.93 false positives (FP) per image was achieved. Similarly, per exam a maximum sensitivity of 0.98 at 7.81 FP per image was achieved. In conclusion, the method could be used as a candidate selection model with high accuracy and with the additional information of lesion segmentation.
KW - automatic lesion detection
KW - automatic lesion segmentation
KW - deep learning
KW - digital mammography
UR - http://www.scopus.com/inward/record.url?scp=85050189231&partnerID=8YFLogxK
U2 - 10.1117/12.2318326
DO - 10.1117/12.2318326
M3 - Conference contribution
AN - SCOPUS:85050189231
VL - 10718
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - 14th International Workshop on Breast Imaging (IWBI 2018)
A2 - Krupinski , E.A.
PB - SPIE
T2 - 14th International Workshop on Breast Imaging (IWBI 2018)
Y2 - 8 July 2018 through 11 July 2018
ER -