Related Experiment Video
Updated: Sep 27, 2025
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Generalizability assessment of COVID-19 3D CT data for deep learning-based disease detection
Maryam Fallahpoor1, Subrata Chakraborty2, Mohammad Tavakoli Heshejin3
1Center for Advanced Modelling and Geospatial Information Systems, Faculty of Engineering and IT, University of Technology Sydney, Sydney, NSW, 2007, Australia; Department of Nuclear Medicine, Vali-Asr Hospital, Tehran University of Medical Sciences, Tehran, Iran.
Background:
Artificial intelligence technologies in classification/detection of COVID-19 positive cases suffer from generalizability. Moreover, accessing and preparing another large dataset is not always feasible and time-consuming. Several studies have combined smaller COVID-19 CT datasets into "supersets" to maximize the number of training samples. This study aims to assess generalizability by splitting datasets into different portions based on 3D CT images using deep learning.
Method:
Two large datasets, including 1110 3D CT images, were split into five segments of 20% each. Each dataset's first 20% segment was separated as a holdout test set. 3D-CNN training was performed with the remaining 80% from each dataset. Two small external datasets were also used to independently evaluate the trained models.
Results:
The total combination of 80% of each dataset has an accuracy of 91% on Iranmehr and 83% on Moscow holdout test datasets. Results indicated that 80% of the primary datasets are adequate for fully training a model. The additional fine-tuning using 40% of a secondary dataset helps the model generalize to a third, unseen dataset. The highest accuracy achieved through transfer learning was 85% on LDCT dataset and 83% on Iranmehr holdout test sets when retrained on 80% of Iranmehr dataset.
Conclusion:
While the total combination of both datasets produced the best results, different combinations and transfer learning still produced generalizable results. Adopting the proposed methodology may help to obtain satisfactory results in the case of limited external datasets.
