Ensemble of adapted convolutional neural networks (CNN) methods for classifying colon histopathological images

Abstract

Deep convolutional neural networks (CNN) manifest the potential for computer-aided diagnosis systems (CADs) by learning features directly from images rather than using traditional feature extraction methods. Nevertheless, due to the limited sample sizes and heterogeneity in tumor presentation in medical images, CNN models suffer from training issues, including training from scratch, which leads to overfitting. Alternatively, a pre-trained neural network’s transfer learning (TL) is used to derive tumor knowledge from medical image datasets using CNN that were designed for non-medical activations, alleviating the need for large datasets. This study proposes two ensemble learning techniques: E-CNN (product rule) and E-CNN (majority voting). These techniques are based on the adaptation of the pretrained CNN models to classify colon cancer histopathology images into various classes. In these ensembles, the individuals are, initially, constructed by adapting pretrained DenseNet121, MobileNetV2, InceptionV3, and VGG16 models. The adaptation of these models is based on a block-wise fine-tuning policy, in which a set of dense and dropout layers of these pretrained models is joined to explore the variation in the histology images. Then, the models’ decisions are fused via product rule and majority voting aggregation methods. The proposed model was validated against the standard pretrained models and the most recent works on two publicly available benchmark colon histopathological image datasets: Stoean (357 images) and Kather colorectal histology (5,000 images). The results were 97.20% and 91.28% accurate, respectively. The achieved results outperformed the state-of-the-art studies and confirmed that the proposed E-CNNs could be extended to be used in various medical image applications.

Toward Improving Breast Cancer Classification Using an Adaptive Voting Ensemble Learning Algorithm

“…Moreover, in [17], article classification accuracy is 95%, and the author achieved the accuracy using texture classification and maximum perimeter. The authors of [19], [20] presented a method for detecting and characterizing cell structure. The study [21]on breast cancer categorized as C3 and C4 on fine needle aspiration cytology aims to correlate with the histopathology examination.…”

Detection of Lung and Colon Cancer using Average and Weighted Average Ensemble Models

“…Albashish et al [18] proposed two different types of ensemble learning techniques such as product rule and majority voting. These strategies are intended to categorize colon cancer histopathology images into distinct classifications.…”

Benchmarking Deep Learning-based Image Retrieval of Oral Tumor Histology

“…Recent developments showed that deep learning models outperformed traditional features [6,7]. Several deep learning methods, such as supervised learning where models are pre-trained on general images or fine-tuned on histopathological images, have been used to train feature extractors [9][10][11][12][13], and self-supervised learning (SSL), which allows learning from unlabeled images [14][15][16]. However, no studies have reviewed which method is most suitable for CBIR in oral tumors.…”