A bioinspired neural architecture search based convolutional neural network for breast cancer detection using histopathology images

Abstract

The design of neural architecture to address the challenge of detecting abnormalities in histopathology images can leverage the gains made in the field of neural architecture search (NAS). The NAS model consists of a search space, search strategy and evaluation strategy. The approach supports the automation of deep learning (DL) based networks such as convolutional neural networks (CNN). Automating the process of CNN architecture engineering using this approach allows for finding the best performing network for learning classification problems in specific domains and datasets. However, the engineering process of NAS is often limited by the potential solutions in search space and the search strategy. This problem often narrows the possibility of obtaining best performing networks for challenging tasks such as the classification of breast cancer in digital histopathological samples. This study proposes a NAS model with a novel search space initialization algorithm and a new search strategy. We designed a block-based stochastic categorical-to-binary (BSCB) algorithm for generating potential CNN solutions into the search space. Also, we applied and investigated the performance of a new bioinspired optimization algorithm, namely the Ebola optimization search algorithm (EOSA), for the search strategy. The evaluation strategy was achieved through computation of loss function, architectural latency and accuracy. The results obtained using images from the BACH and BreakHis databases showed that our approach obtained best performing architectures with the top-5 of the architectures yielding a significant detection rate. The top-1 CNN architecture demonstrated a state-of-the-art performance of base on classification accuracy. The NAS strategy applied in this study and the resulting candidate architecture provides researchers with the most appropriate or suitable network configuration for using digital histopathology.

Immunity-based Ebola optimization search algorithm for minimization of feature extraction with reduction in digital mammography using CNN models

“…Interestingly, this solution has been widened to address the bigger challenge of selecting the best hyperparameters suitable for configuring a DL model that can address the same classification problem. Further to this, studies like 15 , which is one of our research outputs, have even advanced research using metaheuristic algorithms in automating the design and building of DL architectures so that the same classification problem is addressed. In this study, we further advance research in this direction by focusing on detected features rather than only the architecture, so that we minimize the number of features the classifier will have to sieve through in addressing the classification problem.…”

“…As a result, several techniques have been proposed to address drawbacks, such as overfitting, and inefficient parameter and hyperparameter combination or selection, which are associated with CN design. For instance, choice image preprocessing, data augmentation 14 , optimization of weights and hyperparameters using metaheuristic algorithms 2 , auto-design of CNN 15 , and many more, have shown to be promising techniques in addressing those drawbacks. Deserving further mention is the use of metaheuristic algorithms which have played multi-functional roles in hyping the performance and use of DL models.…”

Advanced dwarf mongoose optimization for solving CEC 2011 and CEC 2017 benchmark problems

“…Efforts to address these using heuristic methods such as in [65,66], have further revealed the complexity of the optimization problem. To remedy this, studies [32,[67][68][69][70]have approached the use of metaheuristic algorithms, or a hybrid of metaheuristic algorithms, or even some high-performing variants.…”

“…Similarly, metaheuristic algorithms were employed to address the challenge of network weight optimization in [ 70 ]. Authors in [ 69 ]have also adapted metaheuristic algorithms to the evolution of neural architectures, a combinatorial problem consisting of finding the best neural network components for obtaining the best performing architecture suitable for solving a particular classification problem. In [ 68 ], the problem of feature selection for reducing classifier bottleneck was addressed using the GA metaheuristic method.…”

A comparative performance study of random‐grid model for hyperparameters selection in detection of abnormalities in digital breast images

“…This therefore requires the need to use an efficient computational solution in selecting influential parameters and narrowing down the search space. Several approaches have been proposed such as grid search, 27 random search, 28 manual method, Bayesian method, the tree of parzen estimators (TPEs), sequential model-based algorithm configuration (SMAC), genetic algorithm (GA), 25 bioinspired optimization algorithm, 29 swarm-based parameter optimization, 9,30 the weighted random search (WRS) method, 31 deterministic RBF surrogates. 32 Owning to unsatisfactory results obtained in our previous studies, 11 this study is therefore aimed at investigating a hybrid optimization approaches earlier listed.…”