Diagnostic Classification of Lung Cancer Using Deep Transfer Learning Technology and Multi‐Omics Data

Abstract

In recent years, with the increasing application of highthroughput sequencing technology, researchers have obtained and accumulated a large amount of multi‐omics data, making it possible to diagnose cancer at the gene expression level. The proliferation of various omics data can provide a large amount of biological information, which brings new opportunities and great challenges as well to cancer classification and diagnosis. Machine learning algorithms for early diagnosis of lung cancer have emerged that distinguish cancers of the early and late stages by using genomic features. Omics data are generally characterized with low sample size, high dimensionality and high noise. Therefore, simple direct application of common classification methods cannot achieve better performance and must be improved in a targeted manner. This paper puts forward a combined convolutional neural network and convolutional auto‐encoders approach to construct a deep migratory learning classification model for early lung cancer diagnosis. First, the convolutional auto‐encoders algorithm is used to reduce the dimensionality of the dataset in order to make it better meet the requirements of migration learning. Second, a neural network model is constructed with the original dataset and the existing labeled dataset, and the model migration rules are set as well. Finally, a small number of labeled target datasets are used in the training to complete the construction of the classification model. The proposed convolutional neural network method based on model migration and five other popular machine learning models are used to classify and predict the three lung cancer gene datasets and the integrated dataset. The experimental results show that such four evaluation metrics as accuracy, precision, recall, and f1‐score with our proposed method have obtained better prediction performance, and the average area under curve result also shows our proposed method is optimal.

A machine learning and deep learning-based integrated multi-omics technique for leukemia prediction

“…Without activation functions, the neural network can be a simple linear regression model. A Rectified linear unit is [ 77 , 78 ] an activation function, which works with a threshold value of 0 and can be defined with the equation below: where A defines the relu activation function, y denotes the variable. From the above equation, we can say that there are two possibilities for calculating the Relu of any variable.…”

Brain tumour detection in magnetic resonance imaging using Levenberg–Marquardt backpropagation neural network

“…Although the use of omics information for cancer prediction improves classification accuracy, omics data generally have problems with multiple samples, high dimensions, and high noise. So, the conventional classification methods do not attain high performance and targeted improvements are required [47]. Contrary to the features extracted from the proposed methods, omics data is inherently highly variable and noisy.…”

“…Therefore, the autoencoder was first used to reduce the dimensionality of the features of each omics data, and only some features with a larger contribution rate were retained in each omics data sets [46]. The autoencoder was used with machine learning algorithms for the early diagnosis of lung cancer by using genomic features and a deep migratory learning classification model [47]. The types of brain tumours have been verified by an automated multimodal classification, deep learning, and correntropy‐based joint learning [48].…”

Classification Prediction of Lung Cancer Based on Machine Learning Method

“…The results show that the prediction effect of the support vector machine prediction model is the best, and the prediction effect of sample lifting tree model is not ideal. Researchers have proposed the optimal deep neural network and linear discriminant algorithm to analyze lung CT images after computed tomography (Zhu et al, 2021). By extracting lung CT image features and reducing the dimensionality of image features, the lung cancer labels are divided into two types: benign and malignant.…”