Classification of Breast Cancer Histopathological Images Using DenseNet and Transfer Learning

Abstract

Breast cancer is one of the most common invading cancers in women. Analyzing breast cancer is nontrivial and may lead to disagreements among experts. Although deep learning methods achieved an excellent performance in classification tasks including breast cancer histopathological images, the existing state-of-the-art methods are computationally expensive and may overfit due to extracting features from in-distribution images. In this paper, our contribution is mainly twofold. First, we perform a short survey on deep-learning-based models for classifying histopathological images to investigate the most popular and optimized training-testing ratios. Our findings reveal that the most popular training-testing ratio for histopathological image classification is 70%: 30%, whereas the best performance (e.g., accuracy) is achieved by using the training-testing ratio of 80%: 20% on an identical dataset. Second, we propose a method named DenTnet to classify breast cancer histopathological images chiefly. DenTnet utilizes the principle of transfer learning to solve the problem of extracting features from the same distribution using DenseNet as a backbone model. The proposed DenTnet method is shown to be superior in comparison to a number of leading deep learning methods in terms of detection accuracy (up to 99.28% on BreaKHis dataset deeming training-testing ratio of 80%: 20%) with good generalization ability and computational speed. The limitation of existing methods including the requirement of high computation and utilization of the same feature distribution is mitigated by dint of the DenTnet.

Analyzing Histological Images Using Hybrid Techniques for Early Detection of Multi-Class Breast Cancer Based on Fusion Features of CNN and Handcrafted

“…Deep learning networks outperformed machine learning networks in performance. Wakili et al [13] proposed the DenTnet's method for classifying breast cancer images. The technique works based on transfer learning to extract features from the same distribution of the DenseNet model.…”

“…In 2020, more than 2.3 million women were diagnosed with breast cancer, and 685,000 women died of breast cancer worldwide [2]. Over the past five years, more than 7.8 million women have been diagnosed with breast cancer, which Diagnostics 2023, 13,1753 2 of 41 indicates its increased risk. Breast cancer arises in the breast's glandular tissue, in the cells of the epithelium of the ducts 85% or the cells of the lobules 15%.…”

Ensemble Deep Learning-Based Image Classification for Breast Cancer Subtype and Invasiveness Diagnosis from Whole Slide Image Histopathology

“…For classification between benign and malignant, [17] proposed DenTnet, a deep learning model that achieved accuracy of 99.28% on the BreakHis dataset. Comparably, [32] introduced BreastNet, an end-to-end model that incorporates a convolutional block attention module (CBAM), dense block, residual block, and hypercolumn technique.…”

Applying Explainable Machine Learning Models for Detection of Breast Cancer Lymph Node Metastasis in Patients Eligible for Neoadjuvant Treatment

“…Furthermore, more complicated models, such as the gradient-boosted trees and eXtreme Gradient Boosting (XGBoost), were used to predict survival outcomes in patients with epithelial ovarian cancer and the prediction of metastatic status in breast cancer, respectively [18,19]. The latest machine learning studies that focus on breast cancer achieved excellent performances, and are using deep learning techniques with radionics to classify breast cancer in radiological images or histopathological slides [20][21][22][23]. On the other hand, there are not many studies that utilize only clinicopathological features.…”