CNN-based Classification Framework for Lung Tissues with Auxiliary Information
This work addresses the need for enhanced automated decision-making in diagnosing interstitial lung diseases, which is crucial for treatment planning, but it appears incremental as it builds on existing CNN methods by adding auxiliary information.
The study tackled the problem of accurately classifying interstitial lung diseases from CT images by proposing a CNN-based framework that incorporates auxiliary medical and location information, resulting in improved classification precision compared to state-of-the-art methods on a public database.
Interstitial lung diseases are a large group of heterogeneous diseases characterized by different degrees of alveolitis and pulmonary fibrosis. Accurately diagnosing these diseases has significant guiding value for formulating treatment plans. Although previous work has produced impressive results in classifying interstitial lung diseases, there is still room for improving the accuracy of these techniques, mainly to enhance automated decision-making. In order to improve the classification precision, our study proposes a convolutional neural networks-based framework with auxiliary information. Firstly, ILD images are added with their medical information by re-scaling the original image in Hounsfield Units. Secondly, a modified CNN model is used to produce a vector of classification probability for each tissue. Thirdly, location information of the input image, consisting of the occurrence frequencies of different diseases in the CT scans on certain locations, is used to calculate a location weight vector. Finally, the Hadamard product between two vectors is used to produce a decision vector for the prediction. Compared to the state-of-the-art methods, the results using a publicly available ILD database show the potential of predicting these using different auxiliary information.