Breast Cancer Classification in Automated Breast Ultrasound Using Multiview Convolutional Neural Network with Transfer Learning

Wang, Yi; Choi, Eun Jung; Choi, Younhee; Zhang, Hao; Jin, Gong Yong; Ko, Seok‐Bum

doi:10.1016/j.ultrasmedbio.2020.01.001

Cited by 117 publications

(56 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…During the observer performance test, the diagnostic results of all human reviewers had increased area under the curve (AUC) values and sensitivities after referring to the classification results of the proposed CNN, and 80% of the AUCs were significantly improved. 23 Similarly, multi-magnification makes use of the different magnification layers in a WSI. This more closely resembles how a pathologist would analyze a slide using a microscope.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of the Use of Single- and Multi-Magnification Convolutional Neural Networks for the Determination and Quantitation of Lesions in Nonclinical Pathology Studies

et al. 2021

View full text Add to dashboard Cite

Digital pathology platforms with integrated artificial intelligence have the potential to increase the efficiency of the nonclinical pathologist’s workflow through screening and prioritizing slides with lesions and highlighting areas with specific lesions for review. Herein, we describe the comparison of various single- and multi-magnification convolutional neural network (CNN) architectures to accelerate the detection of lesions in tissues. Different models were evaluated for defining performance characteristics and efficiency in accurately identifying lesions in 5 key rat organs (liver, kidney, heart, lung, and brain). Cohorts for liver and kidney were collected from TG-GATEs open-source repository, and heart, lung, and brain from internally selected R&D studies. Annotations were performed, and models were trained on each of the available lesion classes in the available organs. Various class-consolidation approaches were evaluated from generalized lesion detection to individual lesion detections. The relationship between the amount of annotated lesions and the precision/accuracy of model performance is elucidated. The utility of multi-magnification CNN implementations in specific tissue subtypes is also demonstrated. The use of these CNN-based models offers users the ability to apply generalized lesion detection to whole-slide images, with the potential to generate novel quantitative data that would not be possible with conventional image analysis techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluation of the Use of Single- and Multi-Magnification Convolutional Neural Networks for the Determination and Quantitation of Lesions in Nonclinical Pathology Studies

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In this study, we chose a wellknown CNN framework, Google's Inception V3 (38), as the patch-level classifier. Inception V3 has been extensively adopted for different kinds of digital histopathological image analysis, such as for bladder (39), breast (40), and liver (41). In contrast, state-of-the-art CNNs have not been widely used for the classification of pancreatic histopathological images.…”

Section: Patch-level Classificationmentioning

confidence: 99%

Automatic Pancreatic Ductal Adenocarcinoma Detection in Whole Slide Images Using Deep Convolutional Neural Networks

Pan

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest cancer types worldwide, with the lowest 5-year survival rate among all kinds of cancers. Histopathology image analysis is considered a gold standard for PDAC detection and diagnosis. However, the manual diagnosis used in current clinical practice is a tedious and time-consuming task and diagnosis concordance can be low. With the development of digital imaging and machine learning, several scholars have proposed PDAC analysis approaches based on feature extraction methods that rely on field knowledge. However, feature-based classification methods are applicable only to a specific problem and lack versatility, so that the deep-learning method is becoming a vital alternative to feature extraction. This paper proposes the first deep convolutional neural network architecture for classifying and segmenting pancreatic histopathological images on a relatively large WSI dataset. Our automatic patch-level approach achieved 95.3% classification accuracy and the WSI-level approach achieved 100%. Additionally, we visualized the classification and segmentation outcomes of histopathological images to determine which areas of an image are more important for PDAC identification. Experimental results demonstrate that our proposed model can effectively diagnose PDAC using histopathological images, which illustrates the potential of this practical application.

show abstract

“…The performance of proposed hybridized FCI such as accuracy did not clarify in the results of research. Wang et al [20] proposed a convolutional neural network (CNN) which adopted on a modified Inception-v3 architecture to enable a good feature extraction of ABUS imaging. The developed CNN algorithm was tested and assessed using 316 breast cancer cases (135 malignant and 181 benign).…”

Section: Related Workmentioning

confidence: 99%

The Use of Modified K-Means Algorithm to Enhance the Performance of Support Vector Machine in Classifying Breast Cancer

Al-Yaseen¹,

Jehad²,

Abed³

et al. 2021

IJIES

View full text Add to dashboard Cite

Breast cancer has been recently considered as one of the broadly spread diseases that causes death among women. Early disease diagnosis is a critical aim in building the treatment policies and is extremely related to safety of patient. Therefore, there is a necessity for computer aided detection (CAD) in order to provide accurate and rapid diagnosis for breast cancer. Recently, many classification models utilizing machine learning approaches have been adopted and modified to diagnose breast cancer disease. Moreover, the performance of each model depends on different compositions such as the number and type of data features and the parameters of model. In order to enhance the performance of classification model, this research proposes a model using modified K-means algorithm to create a new training dataset of breast cancer which can highly improve the performance of support vector machine model. A modified K-means algorithm is also proposed to build a high quality training dataset that contributes significantly to reduce the training time of classifiers, and improve the performance of classifier. The proposed model handles the noise and irregularity in data and produce high quality dataset which represents all the cases of disease. The two recognized datasets Wisconsin Breast Cancer (WBC) and Wisconsin Diagnostic Breast Cancer (WDBC) have been used to examine and appraise the performance of the proposed model. The experimental results show that the proposed model has a significant performance compared to other previous works and with accuracy level of 98.067%, sensitivity of 100%, specificity of 94.811%, precision of 97.011% and finally with area under the curve related to the receiver operating characteristic of 97.406%.

show abstract

Breast Cancer Classification in Automated Breast Ultrasound Using Multiview Convolutional Neural Network with Transfer Learning

Cited by 117 publications

References 24 publications

Evaluation of the Use of Single- and Multi-Magnification Convolutional Neural Networks for the Determination and Quantitation of Lesions in Nonclinical Pathology Studies

Evaluation of the Use of Single- and Multi-Magnification Convolutional Neural Networks for the Determination and Quantitation of Lesions in Nonclinical Pathology Studies

Automatic Pancreatic Ductal Adenocarcinoma Detection in Whole Slide Images Using Deep Convolutional Neural Networks

The Use of Modified K-Means Algorithm to Enhance the Performance of Support Vector Machine in Classifying Breast Cancer

Contact Info

Product

Resources

About