Multi-detection and Segmentation of Breast Lesions Based on Mask RCNN-FPN

The presence of different malicious regions on a single breast reveal some necessary information for breast cancer early detection. In current computer-aided diagnosis models, different lesions contained in a single mammogram are not detected and segmented individually. Therefore, the multidetection and segmentation of the breast lesions can help the radiologists for an accurate diagnosis. This study aims to develop a model based on regional learning technique and RoI-based Convolutional neural network (CNN), which is known as Masked Regional Convolutional Neural Network embedded with Feature Pyramid Network. By using Mask RCNN-FPN, we can handle multi-detection, instance segmentation, and classification simultaneously. FPN extracts semantic features at different resolution scales and it can exhibit lesions at multiple scales. The training and testing of the model are performed on the DDSM and Inbreast respectively. In comparison, this model achieved mean average precision 0.84 for multi-detection and segmentation and 91% overall accuracy performance over SegNet and U-Net CNN encoder and decoder segmentation architecture.

[1]  Christopher Ré,et al.  Learning to Compose Domain-Specific Transformations for Data Augmentation , 2017, NIPS.

[2]  Ronan Collobert,et al.  Learning to Refine Object Segments , 2016, ECCV.

[3]  Jeon-Hor Chen,et al.  Computer-aided classification of breast masses using speckle features of automated breast ultrasound images. , 2012, Medical physics.

[4]  Jian Sun,et al.  Convolutional feature masking for joint object and stuff segmentation , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Nico Karssemeijer,et al.  Large scale deep learning for computer aided detection of mammographic lesions , 2017, Medical Image Anal..

[6]  Sheida Nabavi,et al.  Deep convolutional neural networks for mammography: advances, challenges and applications , 2019, BMC Bioinformatics.

[7]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[8]  Taghi M. Khoshgoftaar,et al.  A survey on Image Data Augmentation for Deep Learning , 2019, Journal of Big Data.

[9]  S. Feig,et al.  Screening mammography benefit controversies: sorting the evidence. , 2014, Radiologic clinics of North America.

[10]  Xiaohui Xie,et al.  Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification , 2016, bioRxiv.

[11]  Ronan Collobert,et al.  Learning to Segment Object Candidates , 2015, NIPS.

[12]  Nan Wu,et al.  Improving localization-based approaches for breast cancer screening exam classification , 2019, ArXiv.

[13]  Berkman Sahiner,et al.  Computer-aided detection of breast masses on mammograms: dual system approach with two-view analysis. , 2009, Medical physics.

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[15]  S. Poonguzhali,et al.  Automatic detection and classification of benign and malignant lesions in breast ultrasound images using texture morphological and fractal features , 2017, 2017 10th Biomedical Engineering International Conference (BMEiCON).

[16]  Sotirios A. Tsaftaris,et al.  Medical Image Computing and Computer Assisted Intervention , 2017 .

[17]  Jitendra Malik,et al.  Simultaneous Detection and Segmentation , 2014, ECCV.

[18]  Ying Wang,et al.  Asymmetry Analysis with Sparse Autoencoder in Mammography , 2016, ICIMCS.

[19]  Jonathan T. Barron,et al.  Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Sidi Ahmed Mahmoudi,et al.  MRI Breast Tumor Segmentation Using Different Encoder and Decoder CNN Architectures , 2019, Comput..

[21]  Jitendra Malik,et al.  Hypercolumns for object segmentation and fine-grained localization , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Wael E. Fathy,et al.  A Deep Learning Approach for Breast Cancer Mass Detection , 2019, International Journal of Advanced Computer Science and Applications.

[23]  Håkan Jonsson,et al.  The Impact of Mammographic Screening on Breast Cancer Mortality in Europe: A Review of Observational Studies , 2012, Journal of medical screening.

[24]  István Csabai,et al.  Detecting and classifying lesions in mammograms with Deep Learning , 2017, Scientific Reports.

[25]  Tianfu Wang,et al.  Breast Cancer Detection and Diagnosis Using Mammographic Data: Systematic Review , 2019, Journal of medical Internet research.

[26]  Mick J. Ridley,et al.  Optimisation of Classifier Ensemble for Predictive Toxicology Applications , 2012, 2012 UKSim 14th International Conference on Computer Modelling and Simulation.

[27]  H. Welch,et al.  Quantifying the benefits and harms of screening mammography. , 2014, JAMA internal medicine.

[28]  Geoffrey G. Zhang,et al.  Detection and classification the breast tumors using mask R-CNN on sonograms , 2019, Medicine.

[29]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Dar-Ren Chen,et al.  Speckle reduction imaging of breast ultrasound does not improve the diagnostic performance of morphology‐based CAD System , 2012, Journal of Clinical Ultrasound.

[31]  Lazaros T. Tsochatzidis,et al.  Deep Learning for Breast Cancer Diagnosis from Mammograms—A Comparative Study , 2019, J. Imaging.

[32]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[33]  Edwin Valarezo,et al.  Simultaneous Detection and Classification of Breast Masses in Digital Mammograms via a Deep Learning YOLO-based CAD System , 2018, Comput. Methods Programs Biomed..

[34]  Jie Li,et al.  Mammographic Mass Detection Based on Saliency with Deep Features , 2016, ICIMCS.

[35]  Kai Chen,et al.  Hybrid Task Cascade for Instance Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Sotirios A. Tsaftaris,et al.  Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 , 2015, Lecture Notes in Computer Science.