Computer Aided Classifier of Colorectal Cancer on Histopatological Whole Slide Images Analyzing Deep Learning Architecture Parameters

Abstract

The diagnosis of different pathologies and stages of cancer using whole histopathology slide images (WSI) is the gold standard for determining the degree of tissue metastasis. The use of deep learning systems in the field of medical images, especially histopathology images, is becoming increasingly important. The training and optimization of deep neural network models involve fine-tuning parameters and hyperparameters such as learning rate, batch size (BS), and boost to improve the performance of the model in task-specific applications. Tuning hyperparameters is a major challenge in designing deep neural network models, having a large impact on the performance. This paper analyzes how the parameters and hyperparameters of a deep learning architecture affect the classification of colorectal cancer (CRC) histopathology images using the well-known VGG19 model. This paper also discusses the pre-processing of these images, such as the use of color normalization and stretching transformations on the data set. Among these hyperparameters, the most important neural network hyperparameter is the learning rate (LR). In this paper, different strategies for the optimization of LR are analyzed (both static and dynamic) and a new experiment based on the variation of LR is proposed (the relevance of dynamic strategies over fixed LR is highlighted), after each layer of the neural network together with decreasing variations according to the epochs. The results obtained are very remarkable, obtaining in the simulation an accurate system that achieves 96.4% accuracy on test images (for nine different tissue classes) using the triangular-cyclic learning rate.

Ensemble Residual Network with Iterative Randomized Hyperparameter Optimization for Colorectal Cancer Classification

“…The researchers evaluated the results on datasets including [9]. The Epistroma dataset was mentioned earlier in [11]. By implementing SVM classification they achieved outcomes with a training accuracy of 95.4% and an AUC of 0.906, for Kathers proposed problem.…”

“…is challenging since a too-small value can prolong the training process or lead to stagnation, while a too-high value can result in suboptimal weight sets learned too quickly. Although there have been various contributions to hyperparameter optimization, this still remains an open research problem that heavily depends on the nature of the data and the problem being addressed in [4][5][6]. In most classification systems studies related to histopathological images for diagnosing colorectal cancer highlighted in [7][8], deep learning models are typically employed with default parameters, without conducting a detailed analysis of hyperparameter influence on system behavior.…”