Unboxing AI | Friday Webinars | Lynette Fong, Advahealth Solutions (Oct 11) @ 6pm SGT, Lawrence Tanenbaum, Ex-Radnet (Oct 25) @ 11 am ET | Register Now
  • 2019-01-09

Towards radiologist-level malignancy detection on chest CT scans: a comparative study of the performance of convolutional neural networks and four thoracic radiologists

Aims and objectives

The demonstration of a 20% reduction in lung cancer mortality in the USA National Lung Screening Trial (NLST) [1] and the subsequent decision by the U.S. Centers for Medicare and Medicaid Services to provide Medicare coverage for lung cancer screening has paved the way for nationwide lung cancer screening in the USA. Additionally, results of the NELSON trial also confirmed the value of low-dose CT screening with decreased mortality by 26% in high-risk men and 61% in high-risk women over a 10-year period.


Methods and materials

In this retrospective study, low-dose chest CTs were taken from the NLST dataset. 1245 CT scans were taken for training and 350 CT scans were taken for validation. Pathologically proven malignancy status of lung cancers was taken as ground-truth. Lung nodule annotations from 4 radiologists were taken from 888 CT scans from the publicly available LIDC-IDRI [3] dataset. CT scans with slice-thickness > 2.5mm were excluded to avoid partial-volume effect as recommended by Ginneken et al [4] and Setio et al [5].


Conclusion

The deep learning system shows better performance than experienced radiologists, individually and in aggregate, in predicting the presence of malignant nodules on the 96 CT scans obtained from the NLST dataset. The difference in the interpretation of radiologists were not found to be statistically significant. ­­­­

Clinically, as low-dose CT scans are non-contrast scans, the classically described contrast enhancement characteristics for diagnosing malignant nodules cannot be used to assess the risk of malignancy in these cases.

The availability of a highly sensitive nodule characterization tool will improve the early cancer detection rates. Radiologists aided by deep learning solutions for malignancy have the potential to identify lung cancer earlier as well as reduce unnecessary biopsies.


Link to complete publication here: https://scholar.google.com/citations?view_op=view_citation&hl=en&user=dqpMNRUAAAAJ&cstart=20&pagesize=80&citation_for_view=dqpMNRUAAAAJ:UebtZRa9Y70C

Unlock the potential of CARPL platform for optimizing radiology workflows

Talk to a Clinical Solutions Architect