Breast cancer classification using digital biopsy histopathology images through transfer learning

Abstract

Breast cancer (BC) infection, which is peculiar to women, brings about the high rate of deaths among women in every part of the world. The early investigation of BC has minimized the severe effects of cancer as compared to the last stage diagnosis. Doctors for diagnostic tests usually suggest the medical imaging modalities like mammograms or biopsy histopathology (Hp) images. However, Hp image analysis gives doctors more confidence to diagnose BC as compared to mammograms. Many studies used Hp images to develop BC classification models to assist doctors in early BC diagnosis. However, these models lack better and reliable results in terms of reporting multiple performance evaluation metrics. Therefore, the goal of this study is to create a reliable, more accurate model that consumes minimum resources by using transfer learning based convolution neural network model. The proposed model uses the trained model after fine tuning, hence requires less number of images and can show better results on minimum resources. BreakHis dataset, which is available publicly has been employed in overall experiments in this research. BreakHis dataset is separated into training, testing, and validation for the experimentation. In addition, the dataset for training was augmented followed by stain normalization. By using the concept of transfer learning (TL), AleNext was retained after fine-tuning the last layer for binary classification like benign and malignant. Afterward, preprocessed images are fed into the TL based model for training. The model training was performed many times by changing the hyper-parameters randomly until the minimum validation loss was achieved. Now the trained model was used for feature extraction. The extracted features were further evaluated by using six ML classifiers (i.e. softmax, Decision tree, Naïve Bayes, Linear discriminant analysis, Support vector machine, k-nearest neighbor) through five performance measures such as precision, F-measure, accuracy, specificity, and sensitivity for experimental evaluation. The softmax has outperformed among all classifiers. Furthermore, to reduce the wrong prediction, a misclassification reducing (MR) algorithm was developed. After using the MR algorithm the proposed model produced better and reliable results. The observed accuracy, specificity, sensitivity, precision and F measure are 81.25%, 77.47%, 82.49%, 91.70%, and 86.80% respectively. These results show that the proposed TL based model along with misclassification reduction algorithm produced comparable results to the current baseline models. Hence, the expected model could serve as a second opinion for BC classification in any healthcare center.

Cancer Diagnosis of Microscopic Biopsy Images Using Social Spider Optimization Tuned Neural Network

“…However, the model cannot make exact predictions as errors in one class affects the accuracy in diagnosis. Ghulam Murtaza et al [5] created a consistent and more precise model that used minimum resources with the aid of transfer learning based convolution neural network (CNN) model. However, it is a tedious task to gather more number of images of all types of cancers with proper labels.…”

“…The DNN based strategies, particularly the CNN based methods has solved the problem of handcrafted extraction of features. However, when this model is trained from scratch, it need a more annotated images and requires very high resources [5].…”

“…The microscopic investigation is carried out by expert pathologist, and the final conclusion is made after the agreement of more than two pathologists for enhanced diagnosis. However, it may need increase time for diagnosis and there may be a disagreement of opinion among two pathologists [5].…”

“…As the incidence rate of cancer and its mortality have risen sharply, prolonging survival and reducing local recurrence depends on laparoscopy surgery, robotic surgery, tumor adjuvant therapy, and other new technologies [4]. There exist multiple options in treating cancer [5]. This led to the increase in the effectiveness of cancer treatment [6].…”

A hybrid ensemble deep learning approach for reliable breast cancer detection

“…However, the presented average accuracy is only 88%. A TL-based model is proposed and trained, in [11], on stain normalized and augmented BreakHis dataset. Based on accuracy and precision metrics, the observed results are 81.25% and 91.79%, respectively.…”