Objectives Benign lymph node enlargement can mislead surgeons into overstaging colorectal cancer (CRC), causing unnecessarily extended lymphadenectomy. This study aimed to develop and validate a machine learning (ML) classifier utilizing multi-phase CT (MPCT) radiomics for accurate evaluation of the pre-treatment status of enlarged tumor-draining lymph nodes (TDLNs; defined as long-axis diameter ≥ 10 mm). Materials and methods This study included 430 pathologically confirmed CRC patients who underwent radical resection, stratified into a development cohort (n = 319; January 2015–December 2019, retrospectively enrolled) and test cohort (n = 111; January 2020–May 2023, prospectively enrolled). Radiomics features were extracted from multi-regional lesions (tumor and enlarged TDLNs) on MPCT. Following rigorous feature selection, optimal features were employed to train multiple ML classifiers. The top-performing classifier based on area under receiver operating characteristic curves (AUROCs) was validated. Results Ultimately, 15 classifiers based on features from multi-regional lesions were constructed (TumorN, A, V; LnN, A, V; Ln, lymph node; N, non-contrast phase; A, arterial phase; V, venous phase). Among all classifiers, the enlarged TDLNs fusion MPCT classifier (LnNAV) demonstrated the highest predictive efficacy, with AUROCs and AUPRCs of 0.820 and 0.883, respectively. When pre-treatment clinical variables were integrated (Clinical_LnNAV), the model’s efficacy improved, with AUROCs of 0.839, AUPRCs of 0.903, accuracy of 76.6%, sensitivity of 67.7%, and specificity of 89.1%. Conclusion The classifier Clinical_LnNAV demonstrated well performance in evaluating pre-treatment status of enlarged TDLNs. This tool may support clinicians in developing individualized treatment plans for CRC patients, helping to avoid inappropriate treatment. Key Points <Emphasis Type="BoldItalic">Question</Emphasis> There are currently no effective non-invasive tools to assess the status of enlarged tumor-draining lymph nodes in colorectal cancer prior to treatment. <Emphasis Type="BoldItalic">Findings</Emphasis> Pre-treatment multi-phase CT radiomics, combined with clinical variables, effectively assessed the status of enlarged tumor-draining lymph nodes, achieving a specificity of 89.1%. <Emphasis Type="BoldItalic">Clinical relevance statement</Emphasis> The multi-phase CT-based classifier may assist clinicians in developing individualized treatment plans for colorectal cancer patients, potentially helping to avoid inappropriate preoperative adjuvant therapy and unnecessary extended lymphadenectomy. Graphical Abstract

Non-invasive multi-phase CT artificial intelligence for predicting pre-treatment enlarged lymph node status in colorectal cancer: a prospective validation study

期刊论文
发表日期：

2025年6月12日

查看全文

Kui Sun,
Junwei Wang,
Bingyan Wang,
Ying Wang,
Siyi Lu,
Zhihan Jiang,
Wei Fu,
Xin Zhou

摘要

Objectives

Benign lymph node enlargement can mislead surgeons into overstaging colorectal cancer (CRC), causing unnecessarily extended lymphadenectomy. This study aimed to develop and validate a machine learning (ML) classifier utilizing multi-phase CT (MPCT) radiomics for accurate evaluation of the pre-treatment status of enlarged tumor-draining lymph nodes (TDLNs; defined as long-axis diameter ≥ 10 mm).

Materials and methods

This study included 430 pathologically confirmed CRC patients who underwent radical resection, stratified into a development cohort (n = 319; January 2015–December 2019, retrospectively enrolled) and test cohort (n = 111; January 2020–May 2023, prospectively enrolled). Radiomics features were extracted from multi-regional lesions (tumor and enlarged TDLNs) on MPCT. Following rigorous feature selection, optimal features were employed to train multiple ML classifiers. The top-performing classifier based on area under receiver operating characteristic curves (AUROCs) was validated.

Results

Ultimately, 15 classifiers based on features from multi-regional lesions were constructed (Tumor_{N, A}, _V; Ln_N, _A, _V; Ln, lymph node; _N, non-contrast phase; _A, arterial phase; _V, venous phase). Among all classifiers, the enlarged TDLNs fusion MPCT classifier (Ln_NAV) demonstrated the highest predictive efficacy, with AUROCs and AUPRCs of 0.820 and 0.883, respectively. When pre-treatment clinical variables were integrated (Clinical_Ln_NAV), the model’s efficacy improved, with AUROCs of 0.839, AUPRCs of 0.903, accuracy of 76.6%, sensitivity of 67.7%, and specificity of 89.1%.

Conclusion

The classifier Clinical_Ln_NAV demonstrated well performance in evaluating pre-treatment status of enlarged TDLNs. This tool may support clinicians in developing individualized treatment plans for CRC patients, helping to avoid inappropriate treatment.

Key Points

Question There are currently no effective non-invasive tools to assess the status of enlarged tumor-draining lymph nodes in colorectal cancer prior to treatment.

Findings Pre-treatment multi-phase CT radiomics, combined with clinical variables, effectively assessed the status of enlarged tumor-draining lymph nodes, achieving a specificity of 89.1%.

Clinical relevance statement The multi-phase CT-based classifier may assist clinicians in developing individualized treatment plans for colorectal cancer patients, potentially helping to avoid inappropriate preoperative adjuvant therapy and unnecessary extended lymphadenectomy.

Graphical Abstract