BM-Net: CNN-Based MobileNet-V3 and Bilinear Structure for Breast Cancer Detection in Whole Slide Images

Breast cancer is one of the most common types of cancer and is the leading cause of cancer-related death. Diagnosis of breast cancer is based on the evaluation of pathology slides. In the era of digital pathology, these slides can be converted into digital whole slide images (WSIs) for further analysis. However, due to their sheer size, digital WSIs diagnoses are time consuming and challenging. In this study, we present a lightweight architecture that consists of a bilinear structure and MobileNet-V3 network, bilinear MobileNet-V3 (BM-Net), to analyze breast cancer WSIs. We utilized the WSI dataset from the ICIAR2018 Grand Challenge on Breast Cancer Histology Images (BACH) competition, which contains four classes: normal, benign, in situ carcinoma, and invasive carcinoma. We adopted data augmentation techniques to increase diversity and utilized focal loss to remove class imbalance. We achieved high performance, with 0.88 accuracy in patch classification and an average 0.71 score, which surpassed state-of-the-art models. Our BM-Net shows great potential in detecting cancer in WSIs and is a promising clinical tool.

[1]  Steve A. Adeshina,et al.  Performance Evaluation of Deep Learning Models on Mammogram Classification Using Small Dataset , 2022, Bioengineering.

[2]  G. Battineni,et al.  Cascaded Deep Learning Frameworks in Contribution to the Detection of Parkinson’s Disease , 2022, Bioengineering.

[3]  A. Jemal,et al.  Cancer statistics, 2022 , 2022, CA: a cancer journal for clinicians.

[4]  Andrea Bizzego,et al.  Improving the Efficacy of Deep-Learning Models for Heart Beat Detection on Heterogeneous Datasets , 2021, Bioengineering.

[5]  Ming-Chin Lin,et al.  Artificial Intelligence in Gastric Cancer: Identifying Gastric Cancer Using Endoscopic Images with Convolutional Neural Network , 2021, Cancers.

[6]  Tie-Qiang Li,et al.  Detection of Cervical Cancer Cells in Whole Slide Images Using Deformable and Global Context Aware Faster RCNN-FPN , 2021, Current oncology.

[7]  F. Kanavati,et al.  Breast Invasive Ductal Carcinoma Classification on Whole Slide Images with Weakly-Supervised and Transfer Learning , 2021, bioRxiv.

[8]  Mohamed Medhat Gaber,et al.  3E-Net: Entropy-Based Elastic Ensemble of Deep Convolutional Neural Networks for Grading of Invasive Breast Carcinoma Histopathological Microscopic Images , 2021, Entropy.

[9]  Yongdong Zhang,et al.  Self-Supervised Attention Mechanism for Pediatric Bone Age Assessment With Efficient Weak Annotation , 2020, IEEE Transactions on Medical Imaging.

[10]  Satoshi Takahashi,et al.  Application of Artificial Intelligence Technology in Oncology: Towards the Establishment of Precision Medicine , 2020, Cancers.

[11]  May D. Wang,et al.  Generating Region of Interests for Invasive Breast Cancer in Histopathological Whole-Slide-Image , 2020, 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC).

[12]  K. Arihiro,et al.  Deep Learning Models for Histopathological Classification of Gastric and Colonic Epithelial Tumours , 2020, Scientific Reports.

[13]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Jyotirmoy Chatterjee,et al.  Detection of Breast Cancer From Whole Slide Histopathological Images Using Deep Multiple Instance CNN , 2020, IEEE Access.

[15]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[16]  Hong Liu,et al.  WSI-Net: Branch-Based and Hierarchy-Aware Network for Segmentation and Classification of Breast Histopathological Whole-Slide Images , 2019, MLMI@MICCAI.

[17]  Anne L. Martel,et al.  Multi-layer Domain Adaptation for Deep Convolutional Networks , 2019, DART/MIL3ID@MICCAI.

[18]  Shubham Sharma,et al.  Classification of Breast Microscopic Imaging using Hybrid CLAHE-CNN Deep Architecture , 2019, 2019 Twelfth International Conference on Contemporary Computing (IC3).

[19]  Quoc V. Le,et al.  Searching for MobileNetV3 , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[20]  Jason Y. Park,et al.  Trends in the US and Canadian Pathologist Workforces From 2007 to 2017 , 2019, JAMA network open.

[21]  Soman K P,et al.  Breast Cancer Classification using Capsule Network with Preprocessed Histology Images , 2019, 2019 International Conference on Communication and Signal Processing (ICCSP).

[22]  Shaojie Shen,et al.  Stereo R-CNN Based 3D Object Detection for Autonomous Driving , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Phedias Diamandis,et al.  Deep learning for image analysis: Personalizing medicine closer to the point of care , 2019, Critical reviews in clinical laboratory sciences.

[24]  Catarina Eloy,et al.  BACH: Grand Challenge on Breast Cancer Histology Images , 2018, Medical Image Anal..

[25]  Murat Haciomeroglu,et al.  Classification of TrashNet Dataset Based on Deep Learning Models , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[26]  Yongxiang Huang,et al.  Improving High Resolution Histology Image Classification with Deep Spatial Fusion Network , 2018, COMPAY/OMIA@MICCAI.

[27]  Scotty Kwok,et al.  Multiclass Classification of Breast Cancer in Whole-Slide Images , 2018, ICIAR.

[28]  Pedro Costa,et al.  Classification of Breast Cancer Histology Images Through Transfer Learning Using a Pre-trained Inception Resnet V2 , 2018, ICIAR.

[29]  Bahram Marami,et al.  Ensemble Network for Region Identification in Breast Histopathology Slides , 2018, ICIAR.

[30]  Jin Tae Kwak,et al.  Micro and Macro Breast Histology Image Analysis by Partial Network Re-use , 2018, ICIAR.

[31]  Sameh Galal,et al.  Candy Cane: Breast Cancer Pixel-Wise Labeling with Fully Convolutional Densenets , 2018, ICIAR.

[32]  Maximilian Baust,et al.  Assessment of Breast Cancer Histology using Densely Connected Convolutional Networks , 2018, ICIAR.

[33]  Hang Zhang,et al.  Deep Texture Manifold for Ground Terrain Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[34]  G. Ball,et al.  Breast cancer histologic grading using digital microscopy: concordance and outcome association , 2018, Journal of Clinical Pathology.

[35]  Andreas K. Maier,et al.  Classification of breast cancer histology images using transfer learning , 2018, ICIAR.

[36]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[37]  Catarina Eloy,et al.  Classification of breast cancer histology images using Convolutional Neural Networks , 2017, PloS one.

[38]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[39]  Adrien Depeursinge,et al.  Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles , 2016, Medical Image Anal..

[40]  H. Kreipe,et al.  Histologisches Grading beim Mammakarzinom , 2016, Der Pathologe.

[41]  Subhransu Maji,et al.  Bilinear CNN Models for Fine-Grained Visual Recognition , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[42]  J. Elmore,et al.  Diagnostic concordance among pathologists interpreting breast biopsy specimens. , 2015, JAMA.

[43]  Andrew H. Beck,et al.  Systematic Analysis of Breast Cancer Morphology Uncovers Stromal Features Associated with Survival , 2011, Science Translational Medicine.

[44]  D. C. Carter,et al.  Histological grading in breast cancer. , 1969, British Journal of Cancer.