Automatic lesion detection in high-definition white-light bronchoscopic video
- 2 April 2025
- conference paper
- Published by SPIE-Intl Soc Optical Eng
- Vol. 13410, 46-363
Abstract
The formation of bronchial lesions along the airway walls (mucosa) is known to be a potential indicator of early lung cancer. White-Light Bronchoscopy (WLB) has long been the standard minimally invasive modality for identifying bronchial lesions. To do this, the physician performs a procedure known as bronchoscopy, examining the major airways to interactively locate suspect lesion sites. Unfortunately, past clinical studies have established that such an exam demands a time-consuming, careful inspection of the lengthy incoming WLB video stream. Because suspect lesions are typically distinguished from normal background regions by subtle differences, many lesions are easily missed in the video stream, resulting in lesion detection rates as low as 29% in past clinical studies. The recent introduction of High-Definition (HD) WLB offers the potential for more detailed airway wall imaging, thereby offering a potentially more informative data source for identifying lesions. Nevertheless, the physician still must rely on interactive inspection to identify lesions. We consider deep learning approaches for automating the process of analyzing WLB video. In particular, we develop an HD WLB ground truth dataset and apply this dataset to a series of deep learning models to the problem of automatic bronchial lesion detection and segmentation. In our study, the best model achieved 97% detection accuracy and a Dice score of 0.54 for lesion segmentation.Keywords
This publication has 14 references indexed in Scilit:
- BM-BronchoLC - A rich bronchoscopy dataset for anatomical landmarks and lung cancer lesion recognitionScientific Data, 2024
- CaraNet: context axial reverse attention network for segmentation of small medical objectsJournal of Medical Imaging, 2023
- Deciphering the genomic, epigenomic, and transcriptomic landscapes of pre-invasive lung cancer lesionsNature Medicine, 2019
- The Airway Transcriptome as a Biomarker for Early Lung Cancer DetectionClinical Cancer Research, 2018
- Early Lung Cancer DetectionClinics in Chest Medicine, 2018
- You Only Look Once: Unified, Real-Time Object Detection2016
- Early lung cancer detection, mucosal, and alveolar imagingCurrent Opinion in Pulmonary Medicine, 2016
- Early Lung CancerClinics in Chest Medicine, 2013
- Detection and Localization of Intraepithelial Neoplasia and Invasive Carcinoma Using Fluorescence-Reflectance Bronchoscopy: An International, Multicenter Clinical TrialJournal of Thoracic Oncology, 2009
- Autofluorescence bronchoscopy with white light bronchoscopy compared with white light bronchoscopy alone for the detection of precancerous lesions: a European randomised controlled multicentre trialThorax, 2005