TY - GEN
T1 - Breast Mass Tumor Classification using Deep Learning
AU - Abdel Rahman, Anas S.
AU - Belhaouari, Samir B.
AU - Bouzerdoum, Abdesselam
AU - Baali, Hamza
AU - Alam, Tanvir
AU - Eldaraa, Ahmed M.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/2
Y1 - 2020/2
N2 - This study presents pre-trained Convolutional Neural Network (CNN) models to classify pre-segmented mammogram mass tumors as benign or malignant. Transfer learning, particular pre-processing and data augmentation were applied to overcome the limitation of the scarcity of available training dataset. The proposed models are based on modified versions of Inception V3 and ResNet50 to tackle the classification problem mentioned above. The proposed architectures have been tested on the Digital Database for Screening Mammography (DDSM) dataset, and it achieved an accuracy of 0.796, precision of 0.754, and a recall of 0.891 on InceptionV3-like CNN model. On the other hand, an accuracy of 0.857, precision of 0.857, and a recall rate of 0.873 have been achieved with the ResNet50-like CNN network. Overall, the proposed ResNet50-like model achieved a 5% improvement in accuracy compared to the existing state-of-the-art method for this dataset.
AB - This study presents pre-trained Convolutional Neural Network (CNN) models to classify pre-segmented mammogram mass tumors as benign or malignant. Transfer learning, particular pre-processing and data augmentation were applied to overcome the limitation of the scarcity of available training dataset. The proposed models are based on modified versions of Inception V3 and ResNet50 to tackle the classification problem mentioned above. The proposed architectures have been tested on the Digital Database for Screening Mammography (DDSM) dataset, and it achieved an accuracy of 0.796, precision of 0.754, and a recall of 0.891 on InceptionV3-like CNN model. On the other hand, an accuracy of 0.857, precision of 0.857, and a recall rate of 0.873 have been achieved with the ResNet50-like CNN network. Overall, the proposed ResNet50-like model achieved a 5% improvement in accuracy compared to the existing state-of-the-art method for this dataset.
KW - breast cancer
KW - convolutional neural network
KW - deep learning
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85085497566&partnerID=8YFLogxK
U2 - 10.1109/ICIoT48696.2020.9089535
DO - 10.1109/ICIoT48696.2020.9089535
M3 - Conference contribution
AN - SCOPUS:85085497566
T3 - 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies, ICIoT 2020
SP - 271
EP - 276
BT - 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies, ICIoT 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies, ICIoT 2020
Y2 - 2 February 2020 through 5 February 2020
ER -