Optimizing the Performance of Breast Cancer Classification by Employing the Same Domain Transfer Learning from Hybrid Deep Convolutional Neural Network Model

@article{Alzubaidi2020OptimizingTP,
  title={Optimizing the Performance of Breast Cancer Classification by Employing the Same Domain Transfer Learning from Hybrid Deep Convolutional Neural Network Model},
  author={Laith Alzubaidi and Omran Al-Shamma and Mohammed Abdulraheem Fadhel and Laith Farhan and Jinglan Zhang and Ye Duan},
  journal={Electronics},
  year={2020},
  volume={9},
  pages={445}
}
Breast cancer is a significant factor in female mortality. An early cancer diagnosis leads to a reduction in the breast cancer death rate. With the help of a computer-aided diagnosis system, the efficiency increased, and the cost was reduced for the cancer diagnosis. Traditional breast cancer classification techniques are based on handcrafted features techniques, and their performance relies upon the chosen features. They also are very sensitive to different sizes and complex shapes. However… 
Lung cancer classification with Convolutional Neural Network Architectures
TLDR
Pre-trained Convolutional Neural Networks include: AlexNet, ResNet18, Googlenet, and ResNet50 models are used for training the network and CT image classification and CNN and TL are used to achieve high performance resulting and specify lung cancer detection on CT images.
Deep Learning in Selected Cancers’ Image Analysis—A Survey
TLDR
The result of the review process indicated that deep learning methods have achieved state-of-the-art in tumor detection, segmentation, feature extraction and classification.
Classification of Microscopy Images of Breast Tissue: Region Duplication based Self-Supervision vs. Off-the Shelf Deep Representations
TLDR
A novel self-supervision pretext task to train a convolutional neural network (CNN) and extract domain specific features and results indicated that the best performance of 99% sensitivity was achieved for the deep features extracted using ResNet50 with concatenation of patch-level embedding.
BrC-MCDLM: breast Cancer detection using Multi-Channel deep learning model
TLDR
A computer-aided transfer learning based deep model is proposed as a binary classifier for breast cancer detection using multi-channel merging techniques for devising a dual-architecture ensemble.
Big transfer learning for automated skin cancer classification
TLDR
A novel approach of transfer learning is introduced by training the pre-trained models of the ImageNet (VGG, GoogleNet, and ResNet50) on a large number of unlabelled skin cancer images, first, and then train them on a small number of labeled skin images.
Robust application of new deep learning tools: an experimental study in medical imaging
TLDR
A new DL approach based on a hybrid deep convolutional neural network model is proposed for the automatic classification of several different types of medical images, which has proven its suitability and robustness by addressing several medical imaging tasks dealing with complex and challenging scenarios.
Automated brain tumor classification using various deep learning models: a comparative study
TLDR
Four deep learning models: AlexNet, VGG16, GoogleNet, and RestNet50, are used in this comparative study to classify brain tumors and the results showed that Rest net50 is the best model with an accuracy of 95.8%, while AlexNet has the fast performance with a processing time of 1.2 seconds.
Dilated Semantic Segmentation for Breast Ultrasonic Lesion Detection Using Parallel Feature Fusion
TLDR
A 24-layer CNN that uses transfer learning-based feature extraction to further validate and ensure the enriched features with target intensity is proposed, which achieves a better breast cancer diagnosis rate.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 43 REFERENCES
Breast Cancer Diagnosis with Transfer Learning and Global Pooling
TLDR
A fully automatic, deep learning-based, method using descriptor features extracted by Deep Convolutional Neural Network models and pooling operation for the classification of hematoxylin and eosin stain histological breast cancer images provided as a part of the International Conference on Image Analysis and Recognition (ICIAR) 2018 Grand Challenge on BreAst Cancer Histology (BACH) Images is developed.
Breast Cancer Histological Image Classification Using Fine-Tuned Deep Network Fusion
TLDR
This paper proposes a fully automatic method to classify breast cancer histological images to four classes, namely normal, benign, in situ carcinoma and invasive carcinoma, and finds that this approach outperformed a previous published method by a large margin.
Inception Architecture and Residual Connections in Classification of Breast Cancer Histology Images
TLDR
This paper presents results of applying Inception v4 deep convolutional neural network to ICIAR-2018 Breast Cancer Classification Grand Challenge, part a, and reports 89% accuracy on 4 class classification task and 93.7% on carcinoma/non-carcinoma two class classificationtask.
Classification Of Breast Cancer Histology Images Using ALEXNET
TLDR
This paper fine tune a deep convolutional neural network (ALEXNET) by changing and inserting input layer convolutionAL layers and fully connected layer and Experimental results show that this method achieves a patch and image-wise accuracy of 75.73% and 81.25% respectively.
Parallel Structure Deep Neural Network Using CNN and RNN with an Attention Mechanism for Breast Cancer Histology Image Classification
TLDR
A new deep learning model to classify hematoxylin–eosin-stained breast biopsy images into four classes (normal tissues, benign lesions, in situ carcinomas, and invasive carcinomas), which significantly outperforms state-of-the-art methods.
Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks
TLDR
The method yielded the best quantitative results for automatic detection of IDC regions in WSI in terms of F-measure and balanced accuracy and suggest that at least some of the tissue classification mistakes were less due to any fundamental problems associated with the approach, than the inherent limitations in obtaining a very highly granular annotation of the diseased area of interest by an expert pathologist.
An Ensemble of Fine-Tuned Convolutional Neural Networks for Medical Image Classification
TLDR
A new method for classifying medical images that uses an ensemble of different convolutional neural network (CNN) architectures that achieves a higher accuracy than established CNNs and is only overtaken by those methods that source additional training data.
Fusion High-Resolution Network for Diagnosing ChestX-ray Images
TLDR
The experimental results showed that the proposed FHRNet yields a better disease classification performance for the ChestX-ray 14 dataset, according to the receiver operating characteristic curve and area-under-the-curve score.
...
1
2
3
4
5
...