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
. 2025 Jan 20;12(1):90.
doi: 10.3390/bioengineering12010090.

Precision Imaging for Early Detection of Esophageal Cancer

Po-Chun Yang  1 , Chien-Wei Huang  2   3 , Riya Karmakar  4 , Arvind Mukundan  4 , Tsung-Hsien Chen  5 , Chu-Kuang Chou  1   5   6   7 , Kai-Yao Yang  2 , Hsiang-Chen Wang  4   8   9
Affiliations

Precision Imaging for Early Detection of Esophageal Cancer

Po-Chun Yang et al. Bioengineering (Basel). .

Abstract

Early detection of early-stage esophageal cancer (ECA) is crucial for timely intervention and improved treatment outcomes. Hyperspectral imaging (HSI) and artificial intelligence (AI) technologies offer promising avenues for enhancing diagnostic accuracy in this context. This study utilized a dataset comprising 3984 white light images (WLIs) and 3666 narrow-band images (NBIs). We employed the Yolov5 model, a state-of-the-art object detection algorithm, to predict early ECA based on the provided images. The dataset was divided into two subsets: RGB-WLIs and NBIs, and four distinct models were trained using these datasets. The experimental results revealed that the prediction performance of the training model was notably enhanced when using HSI compared to general NBI training. The HSI training model demonstrated an 8% improvement in accuracy, along with a 5-8% enhancement in precision and recall measures. Notably, the model trained with WLIs exhibited the most significant improvement. Integration of HSI with AI technologies improves the prediction performance for early ECA detection. This study underscores the potential of deep learning identification models to aid in medical detection research. Integrating these models with endoscopic diagnostic systems in healthcare settings could offer faster and more accurate results, thereby improving overall detection performance.

Keywords: YOLOv5; esophageal cancer; hyperspectral imaging; object recognition; squamous esophageal carcinoma.

PubMed Disclaimer

Conflict of interest statement

Author Hsiang-Chen Wang was employed by Hitspectra Intelligent Technology Co., Ltd. The rest authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Experimental flow chart.
Figure 2
Figure 2
White light ECA image detection display: (a,c) are the results of white light ECA image detection models SCC and dysplasia, respectively, where the blue box is the real box position, and the red and orange boxes are the predicted boxes; (b,d) show the results of SCC and dysplasia categories of white light hyperspectral ECA image detection models. The blue box is the real box, and the red and orange boxes are the predicted boxes.
Figure 3
Figure 3
Narrow-band ECA image detection display: (a,c) are the results of narrow-band ECA image detection models SCC and dysplasia, respectively, where the blue box is the real box position, and the red and orange boxes are predicted boxes; (b,d) show the narrow-band hyperspectral ECA image detection model SCC and dysplasia category results. The blue box is the real box, and the red and orange boxes are the predicted boxes.
See this image and copyright information in PMC

References

    1. Ajani J.A., D’Amico T.A., Bentrem D.J., Chao J., Corvera C., Das P., Denlinger C.S., Enzinger P.C., Fanta P., Farjah F. Esophageal and esophagogastric junction cancers, version 2.2019, NCCN clinical practice guidelines in oncology. J. Natl. Compr. Cancer Netw. 2019;17:855–883. doi: 10.6004/jnccn.2019.0033. - DOI - PubMed
    1. Plum P.S., Hölscher A.H., Pacheco Godoy K., Schmidt H., Berlth F., Chon S.-H., Alakus H., Bollschweiler E. Prognosis of patients with superficial T1 esophageal cancer who underwent endoscopic resection before esophagectomy—A propensity score-matched comparison. Surg. Endosc. 2018;32:3972–3980. doi: 10.1007/s00464-018-6139-7. - DOI - PubMed
    1. Wang G., Abnet C., Shen Q., Lewin K., Sun X., Roth M., Qiao Y., Mark S., Dong Z., Taylor P. Histological precursors of oesophageal squamous cell carcinoma: Results from a 13 year prospective follow up study in a high risk population. Gut. 2005;54:187–192. doi: 10.1136/gut.2004.046631. - DOI - PMC - PubMed
    1. Sheikh M., Roshandel G., McCormack V., Malekzadeh R. Current status and future prospects for esophageal cancer. Cancers. 2023;15:765. doi: 10.3390/cancers15030765. - DOI - PMC - PubMed
    1. Liu C.Q., Ma Y.L., Qin Q., Wang P.H., Luo Y., Xu P.F., Cui Y. Epidemiology of esophageal cancer in 2020 and projections to 2030 and 2040. Thorac. Cancer. 2023;14:3–11. doi: 10.1111/1759-7714.14745. - DOI - PMC - PubMed

LinkOut - more resources