Adapted generative latent diffusion models for accurate pathological analysis in chest X-ray images
Open Access
- 19 March 2024
- journal article
- research article
- Published by Springer Nature in Medical & Biological Engineering & Computing
- Vol. 62 (7) , 2189-2212
Abstract
Respiratory diseases have a significant global impact, and assessing these conditions is crucial for improving patient outcomes. Chest X-ray is widely used for diagnosis, but expert evaluation can be challenging. Automatic computer-aided diagnosis methods can provide support for clinicians in these tasks. Deep learning has emerged as a set of algorithms with exceptional potential in such tasks. However, these algorithms require a vast amount of data, often scarce in medical imaging domains. In this work, a new data augmentation methodology based on adapted generative latent diffusion models is proposed to improve the performance of an automatic pathological screening in two high-impact scenarios: tuberculosis and lung nodules. The methodology is evaluated using three publicly available datasets, representative of real-world settings. An ablation study obtained the highest-performing image generation model configuration regarding the number of training steps. The results demonstrate that the novel set of generated images can improve the performance of the screening of these two highly relevant pathologies, obtaining an accuracy of 97.09%, 92.14% in each dataset of tuberculosis screening, respectively, and 82.19% in lung nodules. The proposal notably improves on previous image generation methods for data augmentation, highlighting the importance of the contribution in these critical public health challenges. GraphicalKeywords
Funding Information
- Ministerio de Ciencia e Innovación (PID2019-108435RB-I00, TED2021-131201B-I00, PDC2022-133132-I00)
- Xunta de Galicia (ED431C 2020/24, D481A 2021/196, ED431G 2019/01)
This publication has 67 references indexed in Scilit:
- Spot the Fake Lungs: Generating Synthetic Medical Images Using Neural Diffusion Models2023
- A new generative approach for optical coherence tomography data scarcity: unpaired mutual conversion between scanning presetsMedical & Biological Engineering & Computing, 2023
- Brain Imaging Generation with Latent Diffusion Models2022
- Image-to-image translation with Generative Adversarial Networks via retinal masks for realistic Optical Coherence Tomography imaging of Diabetic Macular Edema disordersBiomedical Signal Processing and Control, 2022
- Multi-resolution convolutional networks for chest X-ray radiograph based lung nodule detectionArtificial Intelligence in Medicine, 2020
- Deep Learning in Medical Image Analysis2020
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Evaluating diagnostic tests: The area under the ROC curve and the balance of errorsStatistics in Medicine, 2010
- Mechanisms of symptoms of common cold and flu2009
- Magnetic Resonance Imaging2003