Abstract :

Paediatric pneumonia is a leading cause of morbidity and mortality worldwide, necessitating accurate and timely diagnosis. This study explores the application of Generative AI for categorising paediatric pneumonia using chest radiographs. Leveraging deep learning techniques, including Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), we enhance image quality, generate synthetic training data, and improve model generalizability. The proposed framework integrates AI-driven feature extraction, convolutional neural networks (CNNs), and attention mechanisms to improve diagnostic accuracy. The results demonstrate significant improvements in classification performance compared to traditional methods, with a focus on interpretability and clinical usability.

---

Keywords :

Chest Radiographs, Convolutional Neural Networks (CNN), Data Augmentation, Deep learning, Generative Adversarial Networks (GAN), Generative AI, Medical Image Classification, Paediatric Pneumonia, Pneumonia Diagnosis, Synthetic Data.

---

References :

1. Krishna Nand Keshavamurthy, Carsten Eickhoff, and Krishna Juluru.Weakly supervised pneumonia localization in chest x-rays using generative adversarial networks.Medical Physics, 48(11):7154–7171, 2021.
2. Ujjwal Baid, Satyam Ghodasara, Michel Bilello, et al.The RSNA-ASNR-MICCAI brats 2021 benchmark on brain tumor segmentation and radiogenomic classification, 2021.
3. Spyridon Bakas, Hamed Akbari, Aristeidis Sotiras, et al.Advancing the cancer genome atlas glioma mri collections with expert segmentation labels and radiomic features.Scientific Data, 4:170117, 2017.
4. Christoph Baur, Benedikt Wiestler, Shadi Albarqouni, and Nassir Navab.Deep autoencoding models for unsupervised anomaly segmentation in brain MR images.In the 21st MICCAI Brainlesion Workshop, volume 11383, pages 161–169. Springer, September 2018.
5. Christoph Baur, Benedikt Wiestler, Shadi Albarqouni, and Nassir Navab.Bayesian skip-autoencoders for unsupervised hyperintense anomaly detection in high resolution brain mri.In the 17th ISBI, pages 1905–1909. IEEE, April 2020.
6. Christoph Baur, Benedikt Wiestler, Shadi Albarqouni, and Nassir Navab.Scale-space autoencoders for unsupervised anomaly segmentation in brain MRI.In the 23rd MICCAI, volume 12264, pages 552–561. Springer, October 2020.
7. Christoph Baur, Stefan Denner, Benedikt Wiestler, Nassir Navab, and Shadi Albarqouni.Autoencoders for unsupervised anomaly segmentation in brain MR images: A comparative study.Medical Image Analysis, 69:101952, 2021.
8. Finn Behrendt, Marcel Bengs, Debayan Bhattacharya, Julia Krüger, Roland Opfer, and Alexander Schlaefer.Capturing inter-slice dependencies of 3d brain MRI-scans for unsupervised anomaly detection.In the 5th MIDL. PMLR, July 2022.
9. Finn Behrendt, Debayan Bhattacharya, Julia Krüger, Roland Opfer, and Alexander Schlaefer.Patched diffusion models for unsupervised anomaly detection in brain MRI .https://doi.org/10.48550/arXiv.2303.03758, 2023.
10. Marcel Bengs, Finn Behrendt, Julia Krüger, Roland Opfer, and Alexander Schlaefer.Three-dimensional deep learning with spatial erasing for unsupervised anomaly segmentation in brain MRI.International Journal of Computer Assisted Radiology and Surgery, 16(9):1413–1423, 2021.
11. Xiaoran Chen, Suhang You, Kerem Can Tezcan, and Ender Konukoglu.Unsupervised lesion detection via image restoration with a normative prior.Medical Image Analysis, 64:101713, 2020.
12. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova.BERT: pre-training of deep bidirectional transformers for language understanding.In the 17th NAACL-HLT, pages 4171–4186. ACL, June 2019.
13. Prafulla Dhariwal and Alexander Quinn Nichol.Diffusion models beat gans on image synthesis.In the 34th NeurIPS, pages 8780–8794, December 2021.
14. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, et al.An image is worth 16×16 words: Transformers for image recognition at scale.In the 9th ICLR, May 2021.
15. Alessandro Fontanella, Grant Mair, Joanna M. Wardlaw, Emanuele Trucco, and Amos J. Storkey.Diffusion models for counterfactual generation and anomaly detection in brain images. https://doi.org/10.48550/arXiv.2308.02062, 2023.
16. Jonathan Ho, Ajay Jain, and Pieter Abbeel.Denoising diffusion probabilistic models.In the 33th NeurIPS, December 2020.
17. Fabian Isensee, Marianne Schell, Irada Pflueger, et al.Automated brain extraction of multisequence mri using artificial neural networks.Human Brain Mapping, 40(17):4952–4964, 2019.
18. Andreas Lugmayr, Martin Danelljan, Andrés Romero, Fisher Yu, Radu Timofte, and Luc Van Gool.Repaint: Inpainting using denoising diffusion probabilistic models.In the 33rd CVPR, pages 11451–11461. IEEE, June 2022.
19. Felix Meissen, Georgios Kaissis, and Daniel Rueckert.Challenging current semi-supervised anomaly segmentation methods for brain MRI.In the 24th MICCAI Brainlesion Workshop, volume 12962, pages 63–74. Springer, September 2021.
20. Bao Nguyen, Adam Feldman, Sarath Bethapudi, Andrew Jennings, and Chris G. Willcocks.Unsupervised region-based anomaly detection in brain MRI with adversarial image inpainting.In the 18th ISBI, pages 1127–1131. IEEE, April 2021.