Improving Tuberculosis Diagnosis using Explainable Artificial Intelligence in Medical Imaging

Yıl 2024, Cilt: 7 Sayı: 1, 33 - 44, 08.05.2024

Cem Özkurt

https://doi.org/10.33187/jmsm.1417160

Öz

The integration of artificial intelligence (AI) applications in the healthcare sector is ushering in a significant transformation, particularly in developing more effective strategies for early diagnosis and treatment of contagious diseases like tuberculosis. Tuberculosis, a global public health challenge, demands swift interventions to prevent its spread. While deep learning and image processing techniques show potential in extracting meaningful insights from complex radiological images, their accuracy is often scrutinized due to a lack of explainability.

This research navigates the intersection of AI and tuberculosis diagnosis by focusing on explainable artificial intelligence (XAI). A meticulously designed deep learning model for tuberculosis detection is introduced alongside an exploration of XAI to unravel complex decisions.

The core belief is that XAI, by elucidating diagnostic decision rationale, enhances the reliability of AI in clinical settings. Emphasizing the pivotal role of XAI in tuberculosis diagnosis, this study aims to impact future research and practical implementations, fostering the adoption of AI-driven disease diagnosis methodologies for global health improvement.

Anahtar Kelimeler

Artificial Intelligence, Deep Learning, Explainable AI, Medical Imaging, Tuberculosis Diagnosis

Etik Beyan

This research adheres to ethical principles and guidelines in conducting the comparative analysis of Explainable Artificial Intelligence (XAI) techniques, specifically SHAP (SHapley Additive exPlanations) and LIME , on tuberculosis x-ray dataset.

Destekleyen Kurum

Sakarya University of Applied Sciences AI And Data Science Research And Application Center

Kaynakça

• [1] C. Liu, Y. Cao, M. Alcantara, B. Liu, M. Brunette, J. Peinado, W. Curioso, TX-CNN: Detecting tuberculosis in chest x-ray images using convolutional neural network, IEEE Int. Conf. Image Process. (ICIP), 2017.
• [2] U.K. Lopes, J.F. Valiati, Pre-trained convolutional neural networks as seature extractors for tuberculosis detection, Comput. Biol. Med., 2017.
• [3] S. Mahamood, Explainable artificial intelligence and its potential within industry, in Proc. 1st Workshop Interactive Nat. Lang. Technol. Explainable Artif. Intell. (NL4XAI), J.M. Alonso, A. Catala (Eds.), Association for Computational Linguistics, 2019.
• [4] R. Guo, K. Passi, C.K. Jain, Tuberculosis diagnostics and localization in chest x-rays via deep learning models, Front. Artif. Intell., 3 (2020), 583427.
• [5] B. Oltu, S. G¨uney, B. Dengiz, M. A˘gıldere, Automated tuberculosis detection using pre-trained CNN and SVM, 44th Int. Conf. Telecommun. Signal Process. (TSP), 2021.
• [6] S. Stanisic, M. Perisic, G. Jovanovic, D. Maletic, D. Vudragovic, A. Vranic, A. Stojic, What Information on Volatile Organic Compounds Can Be Obtained from the Data of a Single Measurement Site Through the Use of Artificial Intelligence?, Artificial Intelligence: Theory Appl., E. Pap (Ed.), Springer International Publishing, 2021.
• [7] D. Chakraborty, A. Alam, S. Chaudhuri, H. Bas¸a˘gao˘glu, T. Sulbaran, S. Langar, Scenario-based prediction of climate change impacts on building cooling energy consumption with explainable artificial intelligence, Appl. Energy, 291 (2021), 116807.
• [8] B.H.M. van der Velden, H.J. Kuijf, K.G.A. Gilhuijs, M.A. Viergever, Explainable artificial intelligence (XAI) in deep learning-based medical image analysis, Med. Image Anal., 79 (2022), 102470.
• [9] A.D. Orjuela-Canon, A.L. Jutinico, C. Awad, E. Vergara, A. Palencia, Machine learning in the loop for tuberculosis diagnosis support, Front. Public Health, 10 (2022, 876949.
• [10] H.H. Rashidi, I.H. Khan, L.T. Dang, S. Albahra, U. Ratan, N. Chadderwala, W. To, P. Srinivas, J. Wajda, N.K. Tran, Prediction of tuberculosis using an automated machine learning platform for models trained on synthetic data, J. Pathol. Inform., 13 (2022), 100172.
• [11] A. Wong, J.R.H. Lee, H. Rahmat-Khah, A. Sabri, A. Alaref, H. Liu, TB-Net: A tailored, self-attention deep convolutional neural network design for detection of tuberculosis cases from chest x-ray images, Front. Artif. Intell., 5 (2022), 827299.
• [12] T. Yiğit, N. Şengöz, Ö. Özmen, J. Hemanth, A.H. Işık, Diagnosis of paratuberculosis in histopathological images based on explainable artificial intelligence and deep learning, Traitement du Signal, 39(3), 2022, 863-869.
• [13] J. Purohit, I. Shivhare, V. Jogani, S. Attari, S. Surtkar, Adversarial Attacks and Defences for Skin Cancer Classification, 2023 Int. Conf. Adv. Technol. (ICONAT), IEEE, Jan. 2023.
• [14] A.R. Bhatt, R. Vaghashiya, M. Kulkarni, P. Kamaraj, Explainable artificial intelligence in retinal imaging for the detection of systemic diseases, 2022.
• [15] S. Hansun, A. Argha, S.-T. Liaw, B.G. Celler, G.B. Marks, Machine and deep learning for tuberculosis detection on chest x-rays: systematic literature review, J. Med. Internet Res., 23 (2023), e43154.
• [16] H. Hajiyan, M. Ebrahimi, Multi-scale local explanation approach for image analysis using model-agnostic explainable artificial intelligence (XAI), in Med. Imaging 2023: Digital Comput. Pathol., J.E. Tomaszewski, A.D. Ward (Eds.), SPIE, 2023.
• [17] N.E. Jaimes, C. Zeng, R. Simha, Using biologically hierarchical modular architecture for explainable, tunable, generalizable, spatial AI, in Disruptive Technol. Inf. Sci. VII, M. Blowers, J. Holt, B.T. Wysocki (Eds.), 2023.
• [18] F. Mahmud, M.M. Mahfiz, M.Z.I. Kabir, Y. Abdullah, An Interpretable deep learning approach for skin cancer categorization, 2023.
• [19] NIAID TB portal program dataset [Online]. Available: https://tbportals.niaid.nih.gov/download-data.
• [20] M.M. Hasan, M.M. Hossain, M.M. Rahman, A.K. Azad, S.A. Alyami, M.A. Moni, FP-CNN: Fuzzy pooling-based convolutional neural network for lung ultrasound image classification with explainable AI, Comput. Biol. Med., 165 (2023), 107407.
• [21] E. Shoemaker, H. Malik, H. Narman, J. Chaudri, Explaining the unseen: Leveraging XAI to enhance the trustworthiness of black-box models in performance testing, Proc. Comput. Sci., 224 (2023), 83-90.
• [22] R. Younisse, A. Ahmad, Q. Abu Al-Haija, Explaining intrusion detection-based convolutional neural networks using Shapley additive explanations (SHAP), Big Data Cogn. Comput., 6(4) (2022), 126.