EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Explainable AI-Enabled Framework for Interpreting Pulmonary Diseases from Chest Radiographs

Zubaira Naz iD, Muhammad Usman Ghani Khan, Tanzila Saba, Amjad Rehman iD, Haitham Nobanee iD, Saeed Ali Bahaj

Cancers · 03.01.2023 · 15 (1) · 314

DOI: 10.3390/cancers15010314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 03.01.2023. Verfasst von Zubaira Naz und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Engineering and Technology Lahore, Lahore 54890, Pakistan. Die Arbeit wurde bisher 66-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Explainable Artificial Intelligence is a key component of artificially intelligent systems that aim to explain the classification results. The classification results explanation is essential for automatic disease diagnosis in healthcare. The human respiration system is badly affected by different chest pulmonary diseases. Automatic classification and explanation can be used to detect these lung diseases. In this paper, we introduced a CNN-based transfer learning-based approach for automatically explaining pulmonary diseases, i.e., edema, tuberculosis, nodules, and pneumonia from chest radiographs. Among these pulmonary diseases, pneumonia, which COVID-19 causes, is deadly; therefore, radiographs of COVID-19 are used for the explanation task. We used the ResNet50 neural network and trained the network on extensive training with the COVID-CT dataset and the COVIDNet dataset. The interpretable model LIME is used for the explanation of classification results. Lime highlights the input image’s important features for generating the classification result. We evaluated the explanation using radiologists’ highlighted images and identified that our model highlights and explains the same regions. We achieved improved classification results with our fine-tuned model with an accuracy of 93% and 97%, respectively. The analysis of our results indicates that this research not only improves the classification results but also provides an explanation of pulmonary diseases with advanced deep-learning methods. This research would assist radiologists with automatic disease detection and explanations, which are used to make clinical decisions and assist in diagnosing and treating pulmonary diseases in the early stage.

Schlagwörter

Stichwörter der Autor:innen

Grad-CAMLIMEclass activation mapcomputed tomographycoronavirus diseaseexplainable AIhealth riskshealthcarereverse transcription polymerase chain reaction

Autor:innen und Institutionen

  • Department of Computer Science, University of Engineering and Technology Lahore, Lahore 54890, Pakistan.
  • Artificial Intelligence & Data Analytics Lab, CCIS, Prince Sultan University, Riyadh 11586, Saudi Arabia.
  • College of Business, Abu Dhabi University, Abu Dhabi 59911, United Arab Emirates.
  • Oxford Center for Islamic Studies, University of Oxford, Oxford OX3 0EE, UK.
  • Faculty of Humanities & Social Sciences, University of Liverpool, Liverpool L69 7WZ, UK.
  • MIS Department, College of Business Administration, Prince Sattam bin Abdulaziz University, Alkharj 11942, Saudi Arabia.

ORCID-Profile: Zubaira Naz, Amjad Rehman, Haitham Nobanee

Zitieren

APA

Naz, Z., Khan, M. U. G., Saba, T., Rehman, A., Nobanee, H., & Bahaj, S. A. (2023). An Explainable AI-Enabled Framework for Interpreting Pulmonary Diseases from Chest Radiographs. Cancers, 15(1), 314. https://doi.org/10.3390/cancers15010314

Vancouver

Naz Z, Khan MUG, Saba T, Rehman A, Nobanee H, Bahaj SA. An Explainable AI-Enabled Framework for Interpreting Pulmonary Diseases from Chest Radiographs. Cancers. 2023;15(1):314. doi:10.3390/cancers15010314

BibTeX
@article{Naz2023,
  author = {Naz, Zubaira and Khan, Muhammad Usman Ghani and Saba, Tanzila and Rehman, Amjad and Nobanee, Haitham and Bahaj, Saeed Ali},
  title = {An Explainable AI-Enabled Framework for Interpreting Pulmonary Diseases from Chest Radiographs},
  journal = {Cancers},
  year = {2023},
  volume = {15},
  number = {1},
  pages = {314},
  doi = {10.3390/cancers15010314}
}
Kostenlos starten →