Computer-aided diagnosis system for breast ultrasound images using deep learning.

The purpose of this study was to develop a computer-aided diagnosis (CAD) system for the classification of malignant and benign masses in the breast using ultrasonography based on a convolutional neural network (CNN), a state-of-the-art deep learning technique. We explored the regions for the correct classification by generating a heat map that presented the important regions used by the CNN for human malignancy/benign classification. Clinical data was obtained from a large-scale clinical trial previously conducted by the Japan Association of Breast and Thyroid Sonology. Images of 1536 breast masses (897 malignant and 639 benign) confirmed by pathological examinations were collected, with each breast mass captured from various angles using an ultrasound imaging probe. We constructed an ensemble network by combining two CNN models (VGG19 and ResNet152) fine-tuned on balanced training data with augmentation and used the mass-level classification method to enable the CNN to classify a given mass using all views. For an independent test set consisting of 154 masses (77 malignant and 77 benign), our network showed outstanding classification performance with a sensitivity of 90.9% (95% confidence interval 84.5-97.3), a specificity of 87.0% (79.5-94.5), and area under the curve of 0.951 (0.916-0.987) compared to that of the two CNN models. In addition, our study indicated that the breast masses themselves were not detected by the CNN as important regions for correct mass classification. Collectively, this CNN-based CAD system is expected to assist doctors by improving the diagnosis of breast cancer in clinical practice.

[1]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  N. Karssemeijer,et al.  Discriminating solitary cysts from soft tissue lesions in mammography using a pretrained deep convolutional neural network , 2017, Medical physics.

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

[4]  Kenji Suzuki,et al.  Overview of deep learning in medical imaging , 2017, Radiological Physics and Technology.

[5]  Yuya Kajikawa,et al.  Computer-aided diagnosis: A survey with bibliometric analysis , 2017, Int. J. Medical Informatics.

[6]  Heng-Da Cheng,et al.  Breast Ultrasound Image Classification Based on Multiple-Instance Learning , 2012, Journal of Digital Imaging.

[7]  T. Endo,et al.  Sensitivity and specificity of mammography and adjunctive ultrasonography to screen for breast cancer in the Japan Strategic Anti-cancer Randomized Trial (J-START): a randomised controlled trial , 2016, The Lancet.

[8]  Wenjian Qin,et al.  Comparison of Transferred Deep Neural Networks in Ultrasonic Breast Masses Discrimination , 2018, BioMed research international.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Eun-Kyung Kim,et al.  Application of Computer‐Aided Diagnosis on Breast Ultrasonography: Evaluation of Diagnostic Performances and Agreement of Radiologists According to Different Levels of Experience , 2018, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[11]  M S Soo,et al.  Sonography of solid breast lesions: observer variability of lesion description and assessment. , 1999, AJR. American journal of roentgenology.

[12]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[13]  T. Uematsu,et al.  The need for supplemental breast cancer screening modalities: a perspective of population-based breast cancer screening programs in Japan , 2016, Breast Cancer.

[14]  J. Alison Noble,et al.  Ultrasound image segmentation: a survey , 2006, IEEE Transactions on Medical Imaging.

[15]  B. Goldberg,et al.  Application of the compound probability density function for characterization of breast masses in ultrasound B scans , 2005, Physics in medicine and biology.

[16]  S. Nomura,et al.  Application of Convolutional Neural Networks in the Diagnosis of Helicobacter pylori Infection Based on Endoscopic Images , 2017, EBioMedicine.

[17]  Jean B. Cormack,et al.  Combined screening with ultrasound and mammography vs mammography alone in women at elevated risk of breast cancer. , 2008, JAMA.

[18]  Michael Galperin,et al.  Breast mass classification in sonography with transfer learning using a deep convolutional neural network and color conversion , 2019, Medical physics.

[19]  Ling Zhang,et al.  Automated breast cancer detection and classification using ultrasound images: A survey , 2015, Pattern Recognit..

[20]  Pavel Crystal,et al.  Using sonography to screen women with mammographically dense breasts. , 2003, AJR. American journal of roentgenology.

[21]  Yi-Ping Phoebe Chen,et al.  Image based computer aided diagnosis system for cancer detection , 2015, Expert Syst. Appl..

[22]  Isabelle Borget,et al.  Evaluation of the accuracy of a computer-aided diagnosis (CAD) system in breast ultrasound according to the radiologist's experience. , 2012, Academic radiology.

[23]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[24]  Haoran Dou,et al.  Two-stage CNNs for computerized BI-RADS categorization in breast ultrasound images , 2019, BioMedical Engineering OnLine.

[25]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[26]  Ukihide Tateishi,et al.  Distinction between benign and malignant breast masses at breast ultrasound using deep learning method with convolutional neural network , 2019, Japanese Journal of Radiology.

[27]  Bing Ou,et al.  Computer‐Aided Diagnosis of Solid Breast Lesions With Ultrasound: Factors Associated With False‐negative and False‐positive Results , 2019, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[28]  Noriaki Ohuchi,et al.  Age‐specific interval breast cancers in Japan: estimation of the proper sensitivity of screening using a population‐based cancer registry , 2008, Cancer science.

[29]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[30]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[31]  Sharon Bond,et al.  Screening With Ultrasound at Time of Mammography Improves Disease Detection in Women at Higher Risk for Breast Cancer, but False Positives Increase , 2008 .

[32]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[33]  Phoebe E. Freer,et al.  Mammographic breast density: impact on breast cancer risk and implications for screening. , 2015, Radiographics : a review publication of the Radiological Society of North America, Inc.

[34]  Seokmin Han,et al.  A deep learning framework for supporting the classification of breast lesions in ultrasound images , 2017, Physics in medicine and biology.

[35]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[36]  Jinlian Ma,et al.  A pre‐trained convolutional neural network based method for thyroid nodule diagnosis , 2017, Ultrasonics.

[37]  Jun Dong,et al.  Ensemble Deep Learning for Biomedical Time Series Classification , 2016, Comput. Intell. Neurosci..

[38]  Fei Wang,et al.  Deep learning for healthcare: review, opportunities and challenges , 2018, Briefings Bioinform..

[39]  M. Giger,et al.  Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer. , 2013, Annual review of biomedical engineering.