A novel adversarial learning strategy for medical image classification

Abstract

Deep learning (DL) techniques have been extensively utilized for medical image classification. Most DL-based classification networks are generally structured hierarchically and optimized through the minimization of a single loss function measured at the end of the networks. However, such a single loss design could potentially lead to optimization of one specific value of interest but fail to leverage informative features from intermediate layers that might benefit classification performance and reduce the risk of overfitting. Recently, auxiliary convolutional neural networks (AuxCNNs) have been employed on top of traditional classification networks to facilitate the training of intermediate layers to improve classification performance and robustness. In this study, we proposed an adversarial learning-based AuxCNN to support the training of deep neural networks for medical image classification. Two main innovations were adopted in our AuxCNN classification framework. First, the proposed AuxCNN architecture includes an image generator and an image discriminator for extracting more informative image features for medical image classification, motivated by the concept of generative adversarial network (GAN)

Medical image classification using self-supervised learning-based masked autoencoder

“…Over the past decade, deep learning (DL) technique has been widely applied in various medical image classification tasks, ranging from disease grading and patient cohort stratification to treatment response prediction. [1][2][3][4][5] Yet, developing DLbased classification models for medical images still faces several challenges due to the unique characteristics of medical images. 4 The tedious and time-consuming labeling process hinders the creation of large-scale labeled medical image datasets for supervised learning.…”

Interpretable graph convolutional network enables triple negative breast cancer detection in imaging mass cytometry

“…Machine learning and deep learning algorithms have been widely used in biomedical image and data analysis. [7][8][9][10][11][12][13] Among these approaches, graph convolutional network (GCN) enables utilization of both cell marker expressions and spatial information, which makes higherorder analysis possible for multiplexed data. 12,13 However, previous strategies 12 focus on tissue-level label prediction, which overlooks the cell-level community detection.…”