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 May 16;16(10):1900.
doi: 10.3390/cancers16101900.

Prediction of Lymph Node Metastasis in T1 Colorectal Cancer Using Artificial Intelligence with Hematoxylin and Eosin-Stained Whole-Slide-Images of Endoscopic and Surgical Resection Specimens

Joo Hye Song  1 , Eun Ran Kim  2 , Yiyu Hong  3 , Insuk Sohn  3 , Soomin Ahn  4 , Seok-Hyung Kim  4 , Kee-Taek Jang  4
Affiliations

Prediction of Lymph Node Metastasis in T1 Colorectal Cancer Using Artificial Intelligence with Hematoxylin and Eosin-Stained Whole-Slide-Images of Endoscopic and Surgical Resection Specimens

Joo Hye Song et al. Cancers (Basel). .

Abstract

According to the current guidelines, additional surgery is performed for endoscopically resected specimens of early colorectal cancer (CRC) with a high risk of lymph node metastasis (LNM). However, the rate of LNM is 2.1-25.0% in cases treated endoscopically followed by surgery, indicating a high rate of unnecessary surgeries. Therefore, this study aimed to develop an artificial intelligence (AI) model using H&E-stained whole slide images (WSIs) without handcrafted features employing surgically and endoscopically resected specimens to predict LNM in T1 CRC. To validate with an independent cohort, we developed a model with four versions comprising various combinations of training and test sets using H&E-stained WSIs from endoscopically (400 patients) and surgically resected specimens (881 patients): Version 1, Train and Test: surgical specimens; Version 2, Train and Test: endoscopic and surgically resected specimens; Version 3, Train: endoscopic and surgical specimens and Test: surgical specimens; Version 4, Train: endoscopic and surgical specimens and Test: endoscopic specimens. The area under the curve (AUC) of the receiver operating characteristic curve was used to determine the accuracy of the AI model for predicting LNM with a 5-fold cross-validation in the training set. Our AI model with H&E-stained WSIs and without annotations showed good performance power with the validation of an independent cohort in a single center. The AUC of our model was 0.758-0.830 in the training set and 0.781-0.824 in the test set, higher than that of previous AI studies with only WSI. Moreover, the AI model with Version 4, which showed the highest sensitivity (92.9%), reduced unnecessary additional surgery by 14.2% more than using the current guidelines (68.3% vs. 82.5%). This revealed the feasibility of using an AI model with only H&E-stained WSIs to predict LNM in T1 CRC.

Keywords: T1 colorectal cancer; artificial intelligence; lymph node metastasis; whole slide image.

PubMed Disclaimer

Conflict of interest statement

Insuk Sohn was employed by the company Arontier Co., Ltd. The remaining authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Pipeline of the approach for classifying lymph node metastasis. WSI, whole slide image.
Figure 2
Figure 2
Flow chart of study population. CCRT, concurrent chemoradiotherapy.
Figure 3
Figure 3
Area under the ROC curve for attention-based WSI-level classification deep learning model for predicting lymph node metastasis in T1 colorectal cancer. (A) Previous model, (B) Version 1, (C) Version 2, (D) Version 3, (E) Version 4 ROC, receiver operating characteristic; WSI, whole-slide image; Version 1, train and test: surgical specimen; Version 2, train and test: endoscopic and surgical specimen; Version 3, train: endoscopic and surgical specimens and test: surgical specimen; Version 4, train: endoscopic and surgical specimens and test: endoscopic specimen; AUC: area under the curve; Avg: average.
Figure 4
Figure 4
Attention score visualization in WSIs of positive lymph node metastasis. (A) Spatial distribution of attention scores on the WSIs, (B) Patch-images stratified by high attention scores WSIs, whole slide images.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

  • AI in Medical Imaging and Image Processing.
    Nurzynska K, Strzelecki M, Piórkowski A, Obuchowicz R. Nurzynska K, et al. J Clin Med. 2025 Jun 11;14(12):4153. doi: 10.3390/jcm14124153. J Clin Med. 2025. PMID: 40565899 Free PMC article.

References

    1. Wong M.C.S., Ding H., Wang J., Chan P.S.F., Huang J. Prevalence and risk factors of colorectal cancer in Asia. Intest. Res. 2019;17:317–329. doi: 10.5217/ir.2019.00021. - DOI - PMC - PubMed
    1. Sung H., Ferlay J., Siegel R.L., Laversanne M., Soerjomataram I., Jemal A., Bray F. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J. Clin. 2021;71:209–249. doi: 10.3322/caac.21660. - DOI - PubMed
    1. Winawer S.J., Zauber A.G. The advanced adenoma as the primary target of screening. Gastrointest. Endosc. Clin. N. Am. 2002;12:1–9. doi: 10.1016/S1052-5157(03)00053-9. - DOI - PubMed
    1. Wook H.S., Jeong-Sik B. Endoscopic diagnosis and treatment of early colorectal cancer. Intest. Res. 2022;20:281–290. - PMC - PubMed
    1. Kim S.Y., Kwak M.S., Yoon S.M., Jung Y., Kim J.W., Boo S.-J., Oh E.H., Jeon S.R., Nam S.-J., Park S.-Y., et al. Korean Guidelines for Postpolypectomy Colonoscopic Surveillance: 2022 revised edition. Intest. Res. 2023;21:20–42. doi: 10.5217/ir.2022.00096. - DOI - PMC - PubMed

LinkOut - more resources