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

Abstract

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, histopathological breast cancer images are very complex in shape. Currently, deep learning models have become an alternative solution for diagnosis, and have overcome the drawbacks of classical classification techniques. Although deep learning has performed well in various tasks of computer vision and pattern recognition, it still has some challenges. One of the main challenges is the lack of training data. To address this challenge and optimize the performance, we have utilized a transfer learning technique which is where the deep learning models train on a task, and then fine-tune the models for another task. We have employed transfer learning in two ways: Training our proposed model first on the same domain dataset, then on the target dataset, and training our model on a different domain dataset, then on the target dataset. We have empirically proven that the same domain transfer learning optimized the performance. Our hybrid model of parallel convolutional layers and residual links is utilized to classify hematoxylin–eosin-stained breast biopsy images into four classes: invasive carcinoma, in-situ carcinoma, benign tumor and normal tissue. To reduce the effect of overfitting, we have augmented the images with different image processing techniques. The proposed model achieved state-of-the-art performance, and it outperformed the latest methods by achieving a patch-wise classification accuracy of 90.5%, and an image-wise classification accuracy of 97.4% on the validation set. Moreover, we have achieved an image-wise classification accuracy of 96.1% on the test set of the microscopy ICIAR-2018 dataset.

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

“…Based on our experiments in different DL applications [ 86 – 88 ]. We can conclude the most active solutions that may improve the performance of CNN are: Expand the dataset with data augmentation or use transfer learning (explained in latter sections).…”

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

“…The accuracy obtained by the trained model was 93.67%. In [ 84 , 85 ], the researchers suggested a first round of training using transfer learning from the original and augmented samples of a large-scale dataset which is in the same domain of the targeted dataset, followed by re-training the model using the original and augmented samples of the target dataset. The highest accuracy achieved was 97.40%.…”

“…These methods has been compared in ( Figure 6 ) with different types of technique that handle features in a way that makes classifiers able to diagnose the target object, Where in refrences [ 105 , 106 ], effective results were achieved in disease identification levels due to the ability of the model to categorise the factors of the symptoms. However the high accuracy achieved using shallow classifiers [ 25 , 26 ] with the handcrafted techniques, deep classifiers are still obtaining [ 82 , 84 ] better accuracy thant shallow ones.…”

Early Disease Classification of Mango Leaves Using Feed-Forward Neural Network and Hybrid Metaheuristic Feature Selection

“…TL means using the knowledge from a specific task to solve another correlated task. In deep learning, TL helps the model learn the features from a large dataset so that it performs better on a relevant dataset but may be smaller in size, and this method has shown effectiveness in image classification task [7], [34], [35]. In our work, the models are first trained on the Plant Village dataset.…”