MCLNet: An multidimensional convolutional lightweight network for gastric histopathology image classification

As global cancer, gastric cancer is a severe threat to the health of people all over the world. In China, young people easily misdiagnose gastric cancer, and its misdiagnosis rate can be as high as 27%. To improve the accuracy and efficiency of gastric cancer detection and the fit goodness of the convolutional neural network, we propose a multidimensional convolutional lightweight network, named MCLNet , based on ShuffleNetV2 . ShuffleNetV2 is a model with low computational complexity, memory consumption, and high GPU parallelism. However, ShuffleNetV2 has too few convolutional layers, only two-dimensional convolution, resulting in insufficient extracted features is not sufficient. Therefore, we consider the association between pixels of the same category in an image. To tap this association, we one-dimensionalize the image and introduce one-dimensional convolution. Since one-dimensional convolution can extract the association of words in a sentence, applying it to images can extract the association between image elements. Adding one-dimensional convolution expands the information exchange between channels and enriches the information, which complements the lack of two-dimensional convolution in global feature extraction. In addition, we compare the proposed MCLNet with the state-of-the-art (SOTA) method and illustrate the best results of the proposed MCLNet model through experiments. • Proposes and implements a lightweight network architecture named MCLNet. • Allows the trained model to be deployed on mobile or small devices, more easily assisting medical personnel. • We design a new network structure using one-dimensional convolution to extract the association between images’ pixels. • We propose an integrated method of one-dimensional convolution and two-dimensional convolution. This approach complements the extracted features so that these features can be best applied to subsequent tasks such as classification. • Tests are performed on the patch level dataset GasHisSDB to demonstrate the accuracy and robustness of the model classification.