USE OF CONVOLUTIONAL NEURAL NETWORKS FOR X-RAY IMAGE ORIENTATION DETERMINATION

1st International Conference on Chemo and BioInformatics, ICCBIKG  2021, (263-266)

AUTHOR(S) / АУТОР(И): Sandi Baressi Šegota, Simon Lysdahlgaard, Søren Hess, Ronald Antulov, Martin Weber Kusk

E-ADRESS / Е-АДРЕСА: sbaressisegota@riteh.hr, Simon.Lysdahlgaard@rsyd.dk,  soren.hess@rsyd.dk,   Ronald.Antulov@rsyd.dk, Martin.Weber.Kusk@rsyd.dk

Download Full Pdf   

DOI: 10.46793/ICCBI21.263BS

ABSTRACT / САЖЕТАК:

The fact that Artificial Intelligence (AI) based algorithms exhibit a high performance on image classification tasks has been shown many times. Still, certain issues exist with the application of machine learning (ML) artificial neural network (ANN) algorithms. The best known is the need for a large amount of statistically varied data, which can be addressed with expanded collection or data augmentation. Other issues are also present. Convolutional neural networks (CNNs) show extremely high performance on image-shaped data. Despite their performance, CNNs exhibit a large issue which is the sensitivity to image orientation. Previous research shows that varying the orientation of images may greatly lower the performance of the trained CNN. This is especially problematic in certain applications, such as X-ray radiography, an example of which is presented here. Previous research shows that the performance of CNNs is higher when used on images in a single orientation (left or right), as opposed to the combination of both. This means that the data needs to be differentiated before it enters the classification model. In this paper, the CNN-based model for differentiation between left and right-oriented images is presented. Multiple CNNs are trained and tested, with the highest performing being the VGG16 architecture which achieved an Accuracy of 0.99 (+/- 0.01), and an AUC of 0.98 (+/- 0.01). These results show that CNNs can be used to address the issue of orientation sensitivity by splitting the data in advance of being used in classification models.

KEY WORDS / КЉУЧНЕ РЕЧИ:

artificial intelligence, machine learning, orientation detection, RTG imagery

REFERENCES / ЛИТЕРАТУРА:

  • Lorencin I, Baressi Šegota S, Anđelić N, Blagojević A, Šušteršić T, Protić A, Arsenijević M, Ćabov T, Filipović N, Car Automatic Evaluation of the Lung Condition of COVID-19 Patients Using X-ray Images and Convolutional Neural Networks. Journal of Personalized Medicine. 2021 Jan;11(1):28.
  • Musulin J, Štifanić D, Zulijani A, Ćabov T, Dekanić A, Car Z. An enhanced histopathology analysis: An ai-based system for multiclass grading of oral squamous cell carcinoma and segmenting of epithelial and stromal tissue. Cancers. 2021 Jan;13(8):1784
  • Chen Z, Pang M, Zhao Z, Li S, Miao R, Zhang Y, Feng X, Feng X, Zhang Y, Duan M, Huang L. Feature selection may improve deep neural networks for the bioinformatics problems. 2020 Mar 1;36(5):1542-52.
  • Kothari D, Patel M, Sharma Implementation of Grey Scale Normalization in Machine Learning & Artificial Intelligence for Bioinformatics using Convolutional Neural Networks. In2021 6th International Conference on Inventive Computation Technologies (ICICT) 2021 Jan 20 (pp. 1071- 1074). IEEE.
  • Lorencin I, Baressi Šegota S, Anđelić N, Mrzljak V, Ćabov T, Španjol J, Car On Urinary Bladder Cancer Diagnosis: Utilization of Deep Convolutional Generative Adversarial Networks for Data Augmentation. Biology. 2021 Mar;10(3):175.
  • Goodfellow I, Bengio Y, Courville A. Deep learning. MIT press; 2016 Nov
  • Lysdahlgaard S, Baressi Šegota S, Antulov R, Hess S, Weber Kusk M, Car Z. Validation of deep learning algorithms for quality assesment of lateral knee x-ray examinations. World Congress of International Society of Radiographers and Radiological Technologists, Dublin
  • Anđelić N, Car Z, Šercer M. Neural Network-Based Model for Classification of Faults During Operation of a Robotic Manipulator. Tehnički vjesnik. 2021 Jul 22;28(4):1380-7.
  • Morid MA, Borjali A, Del Fiol A scoping review of transfer learning research on medical image analysis using ImageNet. Computers in biology and medicine. 2020 Nov 13:104115.
  • Janardhanan PS. Project repositories for machine learning with TensorFlow. Procedia Computer Science. 2020 Jan 1;171:188-96.
  • Lorencin I, Anđelić N, Španjol J, Car Using multi-layer perceptron with Laplacian edge detector for bladder cancer diagnosis. Artificial Intelligence in Medicine. 2020 Jan 1;102:101746.
  • Richens JG, Lee CM, Johri S. Improving the accuracy of medical diagnosis with causal machine learning. Nature communications. 2020 Aug 11;11(1):1-9.
  • Lorencin I, Anđelić N, Mrzljak V, Car Z. Genetic algorithm approach to design of multi-layer perceptron for combined cycle power plant electrical power output estimation. Energies. 2019 Jan;12(22):4352.