Back to the list
Congress: ECR25
Poster Number: C-26007
Type: Poster: EPOS Radiologist (scientific)
Authorblock: S. Tyagi1, M. M. Jabeer1, J. Singh1, A. Chandalia1, S. Datta2, D. Mahapatra3; 1Bengaluru/IN, 2Delhi/IN, 3Abu Dhabi/AE
Disclosures:
Shweta Tyagi: Nothing to disclose
Mohammed Moosa Jabeer: Nothing to disclose
Jitender Singh: Nothing to disclose
Anuj Chandalia: Nothing to disclose
Suvrankar Datta: Nothing to disclose
Dwarikanath Mahapatra: Nothing to disclose
Keywords: Artificial Intelligence, Thorax, CT, CAD, Computer Applications-Detection, diagnosis, Atelectasis, Cancer, Sustainability
Purpose Many chest abnormalities can lead to life-threatening diseases if not detected and monitored early. Some of these abnormalities show radiologic progression and are associated with increased mortality rates. One such group of abnormalities is interstitial lung abnormalities (ILAs). Interstitial lung abnormalities can be defined as non-dependent, parenchymal abnormalities that are often found incidentally on chest CT scans. ILAs can pose a significant risk of progressing into interstitial lung diseases (ILDs), which can severely impact the overall health of a patient....
Read more Methods and materials DataTo develop the artificial intelligence (AI) algorithm for this study, we utilized a comprehensive CT chest dataset consisting of 1,500 cases. This dataset includes 23 labels, normal lung appearance, honeycombing, fibrosis, pulmonary edema, septal thickening, pleural effusion, reticulation, air-trapping, pneumothorax, emphysema, traction bronchiectasis, consolidation, atelectasis, lesions, mucous plugging, ground-glass opacity, peri-bronchial vascular thickening, pleural thickening, cavitation, centrilobular nodule (tree-in-bud appearance), calcification, cysts, and infiltrates.  Among these, reticulation, honeycombing, traction bronchiectasis, ground-glass opacities, cysts, septal thickening, and fibrosis are classified as...
Read more Results We first evaluated our approach on the test data comprising 300 samples. We achieved an overall accuracy of 90% and an area under the receiver operating characteristic (AUROC) of 70.8% for predicting all 23 labels. We achieved 97% accuracy and 84.1% AUROC for the eight top-performing labels, indicating its strong ability to differentiate between normal and abnormal cases with a high degree of confidence. To further validate the reliability of our method in a real-world clinical setting, we tested it on...
Read more Conclusion We have designed a simple, user-friendly interface that gives clinicians accurate and actionable insights to support better patient care. Some interstitial lung abnormalities (ILAs) are known to have a high risk of progression and mortality, so detecting them early is crucial. Our approach helps doctors plan treatments more effectively, giving patients a better chance at improved outcomes and survival. We added this feature to our chest CT analysis product, providing a more comprehensive overview that includes both major and incidental...
Read more References Hatabu, H., Hunninghake, G. M., Richeldi, L., Brown, K. K., Wells, A. U., Remy-Jardin, M., ... & Lynch, D. A. (2020). Interstitial lung abnormalities detected incidentally on CT: a Position Paper from the Fleischner Society. The lancet Respiratory medicine, 8(7), 726-737. Chae, K. J., Jin, G. Y., Goo, J. M., & Chung, M. J. (2020). Interstitial lung abnormalities: what radiologists should know. Korean Journal of Radiology, 22(3), 454.
Read more
GALLERY