CroReLU: Cross-Crossing Space-Based Visual Activation Function for Lung Cancer Pathology Image Recognition

SIMPLE SUMMARY: In the clinical diagnosis of lung cancer, doctors mainly rely on pathological images to make decisions about the patient’s condition. Therefore, pathology diagnosis is known as the gold standard for disease diagnosis. In recent years, convolutional neural networks have been widely used for computer-aided diagnosis to relieve the work pressure of pathologists. However, this method still faces two problems: from the perspective of clinical application, the current neural network model can only perform simple lung cancer type detection; From the perspective of model design, the strategy adopted by researchers to improve the accuracy of diagnosis is often to carry out complex model design, which will cause the model parameters to be too large to be clinically deployed. In this study, we first prepared a lung cancer dataset that can provide more complex cancer information to the model. Then, using only a novel visual activation function, the ability of convolutional neural networks to detect interclass and intraclass differences in cancer pathological images is enhanced. ABSTRACT: Lung cancer is one of the most common malignant tumors in human beings. It is highly fatal, as its early symptoms are not obvious. In clinical medicine, physicians rely on the information provided by pathology tests as an important reference for the final diagnosis of many diseases. Therefore, pathology diagnosis is known as the gold standard for disease diagnosis. However, the complexity of the information contained in pathology images and the increase in the number of patients far outpace the number of pathologists, especially for the treatment of lung cancer in less developed countries. To address this problem, we propose a plug-and-play visual activation function (AF), CroReLU, based on a priori knowledge of pathology, which makes it possible to use deep learning models for precision medicine. To the best of our knowledge, this work is the first to optimize deep learning models for pathology image diagnosis from the perspective of AFs. By adopting a unique crossover window design for the activation layer of the neural network, CroReLU is equipped with the ability to model spatial information and capture histological morphological features of lung cancer such as papillary, micropapillary, and tubular alveoli. To test the effectiveness of this design, 776 lung cancer pathology images were collected as experimental data. When CroReLU was inserted into the SeNet network (SeNet_CroReLU), the diagnostic accuracy reached 98.33%, which was significantly better than that of common neural network models at this stage. The generalization ability of the proposed method was validated on the LC25000 dataset with completely different data distribution and recognition tasks in the face of practical clinical needs. The experimental results show that CroReLU has the ability to recognize inter- and intra-class differences in cancer pathology images, and that the recognition accuracy exceeds the extant research work on the complex design of network layers.