Using Deep Learning with Bayesian–Gaussian Inspired Convolutional Neural Architectural Search for Cancer Recognition and Classification from Histopathological Image Frames

Abstract

We propose a neural architectural search model which examines histopathological images to detect the presence of cancer in both lung and colon tissues. In recent times, deep artificial neural networks have made tremendous impacts in healthcare. However, obtaining an optimal artificial neural network model that could yield excellent performance during training, evaluation, and inferencing has been a bottleneck for researchers. Our method uses a Bayesian convolutional neural architectural search algorithm in collaboration with Gaussian processes to provide an efficient neural network architecture for efficient colon and lung cancer classification and recognition. The proposed model learns by using the Gaussian process to estimate the required optimal architectural values by choosing a set of model parameters through the exploitation of the expected improvement (EI) values, thereby minimizing the number of sampled trials and suggesting the best model architecture. Several experiments were conducted, and a landmark performance was obtained in both validation and test data through the evaluation of the proposed model on a dataset consisting of 25,000 images of five different classes with convergence and F1-score matrices.

Recognizing Breast Cancer Using Edge-Weighted Texture Features of Histopathology Images

“…Several machine learning models, including SVMs, KNNs, random forests, and CNNs, were tested and compared for their ability to classify breast cancer histology. Compared to the other approaches, CNN had the highest accuracy (96.8%) [15].…”

“…The CNN model had the greatest accuracy (95.29%) of all the machine-learning methods. An interesting case in point is the classification of breast cancer using histopathology images, where different deep-learning models were compared, and the best model achieved an accuracy of 97.3% [11][12][13][14][15]. Combining histopathology images with a cutting-edge deep learning model called Deep Attention Ensemble Network (DAEN) [14] further demonstrates the superiority of deep learning models over conventional machine learning algorithms for breast cancer classification.…”

Colon and lung cancer classification from multi-modal images using resilient and efficient neural network architectures

“…Stephen and Sain [ 17 ] provided a neural architecture search algorithm that efficiently detects colon and lung cancers in histological images. Their method produced an accurate neural network architecture for categorization and detection of colon and lung cancers, achieving an accuracy rate of 93.91 % on the LC25000 dataset.…”

“…Other researchers, such as Iqbal et al [ 15 ], focused on achieving higher F1-scores, while others emphasized transfer learning, as exemplified by the studies conducted by Kumar et al [ 18 ] and Al Ghamdi et al [ 16 ]. Neural architecture searches were employed by Stephen and Sain [ 17 ].…”

“…Tested only on one dataset. Hadiyoso et al [ 13 ] VGG16 with CLAHE LC25000 Image enhancement 98.96 Wahid et al [ 14 ] Various CNNs LC25000 Multiple models Up to 99.87 Iqbal et al [ 15 ] ColonNet LC25000 High F1-score 96.31 Al Ghamdi et al [ 16 ] ShuffleNet, DCRNN LC25000 Transfer learning 98.99 Stephen and Sain [ 17 ] Neural Arch Search LC25000 Neural net search 93.91 Kumar et al [ 18 ] Transfer Learning LC25000 Feature extraction 98.60 Hage Chehade et al [ 19 ] Various ML models LC25000 Multiple models Up to 99 Mridha et al [ 20 ] DL Framework LC25000 5 types of cells 98.30 Mehmood et al [ 21 ] Modified AlexNet LC25000 Fine-tuned model 98.40 Provat et al [ 22 ] Custom CNN LC25000 Cyclic learning rates ...…”