Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Mar 28;11(1):321.
doi: 10.1038/s41597-024-03145-y.

BM-BronchoLC - A rich bronchoscopy dataset for anatomical landmarks and lung cancer lesion recognition

Van Giap Vu  1   2 , Anh Duc Hoang  1   2 , Thu Phuong Phan  1   2 , Ngoc Du Nguyen  1   2 , Thanh Thuy Nguyen  1   2 , Duc Nghia Nguyen  1   2 , Ngoc Phu Dao  1   2 , Thi Phuong Lan Doan  1 , Thi Thanh Huyen Nguyen  1 , Thi Huong Trinh  1 , Thi Le Quyen Pham  1 , Thi Thu Trang Le  1 , Phan Thi Hanh  1 , Van Tuyen Pham  1 , Van Chuong Tran  1 , Dang Luu Vu  1   2 , Van Luong Tran  1 , Thi Thu Thao Nguyen  1 , Cam Phuong Pham  1 , Gia Linh Pham  3 , Son Ba Luong  3 , Trung-Dung Pham  3 , Duy-Phuc Nguyen  3 , Thi Kieu Anh Truong  3 , Quang Minh Nguyen  3 , Truong-Thuy Tran  3 , Tran Binh Dang  3 , Viet-Cuong Ta  3 , Quoc Long Tran  3 , Duc-Trong Le  3 , Le Sy Vinh  4
Affiliations

BM-BronchoLC - A rich bronchoscopy dataset for anatomical landmarks and lung cancer lesion recognition

Van Giap Vu et al. Sci Data. .

Abstract

Flexible bronchoscopy has revolutionized respiratory disease diagnosis. It offers direct visualization and detection of airway abnormalities, including lung cancer lesions. Accurate identification of airway lesions during flexible bronchoscopy plays an important role in the lung cancer diagnosis. The application of artificial intelligence (AI) aims to support physicians in recognizing anatomical landmarks and lung cancer lesions within bronchoscopic imagery. This work described the development of BM-BronchoLC, a rich bronchoscopy dataset encompassing 106 lung cancer and 102 non-lung cancer patients. The dataset incorporates detailed localization and categorical annotations for both anatomical landmarks and lesions, meticulously conducted by senior doctors at Bach Mai Hospital, Vietnam. To assess the dataset's quality, we evaluate two prevalent AI backbone models, namely UNet++ and ESFPNet, on the image segmentation and classification tasks with single-task and multi-task learning paradigms. We present BM-BronchoLC as a reference dataset in developing AI models to assist diagnostic accuracy for anatomical landmarks and lung cancer lesions in bronchoscopy data.

PubMed Disclaimer

Conflict of interest statement

We confirm there is no conflict of interest related to this research. All data and procedures were conducted under the approval of Bach Mai hospital’s ethics board (the reference number: 1139/BM - HĐĐĐ).

Figures

Fig. 1
Fig. 1
General workflow to produce the BM-BronchoLC dataset.
Fig. 2
Fig. 2
Binary mask transformation from (a) The original image to get (b) The transformed image.
Fig. 3
Fig. 3
The histogram of the ratio between the annotated segment size and the image size on BM-BronchoLC for (a) Anatomical Landmark Segmentation and (b) Lesion Segmentation.
Fig. 4
Fig. 4
The overall architecture of the multi-task framework.
Fig. 5
Fig. 5
The model performance for the segmentation task on BM-BronchoLC namely: (a) Anatomical Landmark Segmentation, (b) Lesion Segmentation.
Fig. 6
Fig. 6
The model performance for the classification task on BM-BronchoLC namely: (a) Anatomical Landmark Classification, (b) Lesion Classification.
Fig. 7
Fig. 7
Quantitative comparison between multi-task versus single-task models for the anatomical landmark analysis.
Fig. 8
Fig. 8
Quantitative comparison between multi-task versus single-task models for the lesion analysis.
See this image and copyright information in PMC

References

    1. Ikeda S, Yanai N, Ishikawa S. Flexible bronchofiberscope. The Keio J. Medicine. 1968;17(1):1–16. doi: 10.2302/kjm.17.1. - DOI - PubMed
    1. Rand IAD, et al. British Thoracic Society Bronchoscopy Guideline Group. British Thoracic Society guideline for diagnostic flexible bronchoscopy in adults: accredited by NICE. Thorax. 2013;68:i1–i44. doi: 10.1136/thoraxjnl-2013-203618. - DOI - PubMed
    1. Facciolongo N, et al. Incidence of complications in bronchoscopy. Multicentre prospective study of 20,986 bronchoscopies. Monaldi Arch Chest Dis. 2016;71(1):8–14. doi: 10.4081/monaldi.2009.370. - DOI - PubMed
    1. Sung H, et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021;71(3):209–249. doi: 10.3322/caac.21660. - DOI - PubMed
    1. Veaudor M, et al. Implementing flexible bronchoscopy in least developed countries according to international guidelines is feasible and sustainable: example from Phnom-Penh, Cambodia. BMC Pulm Med. 2017;17:10. doi: 10.1186/s12890-016-0354-6. - DOI - PMC - PubMed

Publication types

Grants and funding