Enhancing Computer-Aided Detection Systems for Chest X-ray Abnormalities using Deep Learning Techniques
Keywords:
Computer-aided detection, chest X-ray abnormalities, deep learning, Convolutional Neural Networks (CNNs).Abstract
The focus here revolves around enhancing computer-aided detection (CAD) systems, particularly in diagnosing chest X-ray abnormalities using deep learning, notably Convolutional Neural Networks (CNNs). The shift from traditional computer vision methods, reliant on manual feature crafting, to deep learning has marked a substantial transformation in addressing computer vision challenges. A significant hurdle in this domain is the scarcity of data, especially for rare diseases, potentially leading deep neural networks to encounter diminishing gradients with increased network depth. To counter this, data augmentation techniques are employed, mathematically transforming original images to create additional samples from limited datasets. These transformations encompass various methods like flips (horizontal and vertical), rotation, shearing, zooming, filtering, and scaling.
References
G. Litjens, T. Kooi, B.E. Bejnordi, A .A .A . Setio, F. Ciompi, M. Ghafoorian, J.A. Van Der Laak, B. Van Ginneken, C.I. Sánchez, A survey on deep learning in medical image analysis, Med. Image Anal. 42 (2017) 60–88 .
M. Xu, S. Yoon, A. Fuentes, J. Yang, D. Park, Style-consistent image translation: a novel data augmentation paradigm to improve plant disease recognition, Front. Plant Sci. 12: 773142. doi: 10.3389/fpls (2022) .
S.C. Wong, A. Gatt, V. Stamatescu, M.D. McDonnell, Understanding data aug- mentation for classification: when to warp? in: 2016 international conference on digital image computing: techniques and applications (DICTA), IEEE, 2016, pp. 1–6 .
