Artificial intelligence-driven neoadjuvant precision treatment of esophageal cancer

doi:10.3877/cma.j.issn.2095-8773.2025.02.04

Abstract

Abstract:

Esophageal cancer is a highly aggressive digestive tract malignancy with a poor prognosis.Its treatment strategies require individualization and precision.Recent advances in artificial intelligence （AI） have enhanced various aspects of esophageal cancer treatment， significantly improving the accuracy of treatment outcome prediction，treatment plan formulation，and dynamic intervention.This article systematically reviews the core applications and recent progress of AI in the treatment of esophageal cancer，and discusses the challenges and future directions for its clinical application.

Key words: Esophageal neoplasm, Neoadjuvant therapy, Artificial intelligence, Machine learning, Deep learning, Review

Yiming Xu, Xueyuan Fan, Shihao Li, Yifan Xu, Bowen Li, Zhenyang Geng, Yafei Liu, Guanchao Ye, Feng Li, Lan Huang, Yu Qi. Artificial intelligence-driven neoadjuvant precision treatment of esophageal cancer[J]. Chinese Journal of Thoracic Surgery(Electronic Edition), 2025, 12(02): 96-104.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://zhxbwkdzzz.cma-cmc.com.cn/EN/10.3877/cma.j.issn.2095-8773.2025.02.04

https://zhxbwkdzzz.cma-cmc.com.cn/EN/Y2025/V12/I02/96

Figures/Tables 2

References 52

1	Bray F，Laversanne M，Sung H，et al.Global cancer statistics 2022：GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries［J］.CA Cancer J Clin，2024，74（3）：229-263.
2	郑荣寿，陈茹，韩冰峰，等.2022年中国恶性肿瘤流行情况分析［J］.中华肿瘤杂志，2024，46（3）：221-231.
3	Siegel RL，Giaquinto AN，Jemal A.Cancer statistics，2024［J］.CA Cancer J Clin，2024，74（1）：12-49.
4	Tang H，Wang H，Fang Y，et al.Neoadjuvant chemoradiotherapy versus neoadjuvant chemotherapy followed by minimally invasive esophagectomy for locally advanced esophageal squamous cell carcinoma：a prospective multicenter randomized clinical trial［J］.Ann Oncol，2023，34（2）：163-172.
5	Klevebro F，Alexandersson von Döbeln G，Wang N，et al.A randomized clinical trial of neoadjuvant chemotherapy versus neoadjuvant chemoradiotherapy for cancer of the oesophagus or gastro-oesophageal junction［J］.Ann Oncol，2016，27（4）：660-667.
6	Deo RC.Machine Learning in Medicine［J］.Circulation，2015，132（20）：1920-1930.
7	Misra I，Maaten LVD.Self-Supervised Learning of Pretext-Invariant Representations［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）.Seattle，WA，USA：IEEE，2019：6706-6716.
8	Chauhan NK，Singh K.A Review on Conventional Machine Learning vs Deep Learning［C］//2018 International Conference on Computing， Power and Communication Technologies（GUCON）.Greater Noida：IEEE；2018.
9	Klionsky DJ，Abdelmohsen K，Abe A，et al.Guidelines for the use and interpretation of assays for monitoring autophagy（3rd edition）［J］.Autophagy，2016，12（1）：1-222.
10	Nohara Y，Matsumoto K，Soejima H，et al.Explanation of machine learning models using shapley additive explanation and application for real data in hospital［J］.Comput Methods Programs Biomed，2022，214：106584.
11	Okamura A，Watanabe M，Okui J，et al.Neoadjuvant Chemotherapy or Neoadjuvant Chemoradiotherapy for Patients with Esophageal Squamous Cell Carcinoma：Real-World Data Comparison from A Japanese Nationwide Study［J］.Ann Surg Oncol，2023，30（9）：5885-5894.
12	Reynolds JV，Preston SR，O’Neill B，et al.Trimodality therapy versus perioperative chemotherapy in the management of locally advanced adenocarcinoma of the oesophagus and oesophagogastric junction（Neo-AEGIS）：an open-label，randomised，phase 3 trial［J］.Lancet Gastroenterol Hepatol，2023，8（11）：1015-1027.
13	Kato K，Machida R，Ito Y，et al.Doublet chemotherapy，triplet chemotherapy，or doublet chemotherapy combined with radiotherapy as neoadjuvant treatment for locally advanced oesophageal cancer（JCOG1109 NExT）：a randomised，controlled，open-label，phase 3 trial［J］.Lancet，2024，404（10447）：55-66.
14	Wu YY，Dai L，Yang YB，et al.Long-Term Survival and Recurrence Patterns in Locally Advanced Esophageal Squamous Cell Carcinoma Patients with Pathologic Complete Response After Neoadjuvant Chemotherapy Followed by Surgery［J］.Ann Surg Oncol，2024，31（8）：5047-5054.
15	Ou J，Zhou HY，Qin HL，et al.Baseline CT radiomics features to predict pathological complete response of advanced esophageal squamous cell carcinoma treated with neoadjuvant chemotherapy using paclitaxel and cisplatin［J］.Eur J Radiol，2024，181：111763.
16	Liu Y，Wang Y，Wang X，et al.MR radiomics predicts pathological complete response of esophageal squamous cell carcinoma after neoadjuvant chemoradiotherapy：a multicenter study［J］.Cancer Imaging，2024，24（1）：16.
17	Fan L，Yang Z，Chang M，et al.CT-based delta-radiomics nomogram to predict pathological complete response after neoadjuvant chemoradiotherapy in esophageal squamous cell carcinoma patients［J］.J Transl Med，2024，22（1）：579.
18	Lu S，Wang C，Liu Y，et al.The MRI radiomics signature can predict the pathologic response to neoadjuvant chemotherapy in locally advanced esophageal squamous cell carcinoma［J］.Eur Radiol，2024，34（1）：485-494.
19	Wang J，Zhu X，Zeng J，et al.Using clinical and radiomic feature-based machine learning models to predict pathological complete response in patients with esophageal squamous cell carcinoma receiving neoadjuvant chemoradiation［J］.Eur Radiol，2023，33（12）：8554-8563.
20	Li Z，Wang F，Zhang H，et al.A radiomics strategy based on CT intra-tumoral and peritumoral regions for preoperative prediction of neoadjuvant chemoradiotherapy for esophageal cancer［J］.Eur J Surg Oncol，2024，50（4）：108052.
21	Noordman BJ，Verdam MGE，Lagarde SM，et al.Effect of Neoadjuvant Chemoradiotherapy on Health-Related Quality of Life in Esophageal or Junctional Cancer：Results From the Randomized CROSS Trial［J］.J Clin Oncol，2018，36（3）：268-275.
22	Buck A，Prade VM，Kunzke T，et al.Metabolic tumor constitution is superior to tumor regression grading for evaluating response to neoadjuvant therapy of esophageal adenocarcinoma patients［J］.J Pathol，2022，256（2）：202-213.
23	Xie Y，Liu Q，Ji C，et al.An artificial neural network-based radiomics model for predicting the radiotherapy response of advanced esophageal squamous cell carcinoma patients：a multicenter study［J］.Sci Rep，2023，13（1）：8673.
24	Li X，Gao H，Zhu J，et al.3D Deep Learning Model for the Pretreatment Evaluation of Treatment Response in Esophageal Carcinoma：A Prospective Study （ChiCTR2000039279）［J］.Int J Radiat Oncol Biol Phys，2021，111（4）：926-935.
25	Jin X，Zheng X，Chen D，et al.Prediction of response after chemoradiation for esophageal cancer using a combination of dosimetry and CT radiomics［J］.Eur Radiol，2019，29（11）：6080-6088.
26	Tolkach Y，Wolgast LM，Damanakis A，et al.Artificial intelligence for tumour tissue detection and histological regression grading in oesophageal adenocarcinomas：a retrospective algorithm development and validation study［J］.Lancet Digit Health，2023，5（5）：e265-e275.
27	Kotter E，Pinto Dos Santos D.Ethics and artificial intelligence［J］.Radiologie（Heidelb），2024，64（6）：498-502.
28	Morgan E，Soerjomataram I，Rumgay H，et al.The Global Landscape of Esophageal Squamous Cell Carcinoma and Esophageal Adenocarcinoma Incidence and Mortality in 2020 and Projections to 2040：New Estimates From GLOBOCAN 2020［J］.Gastroenterology，2022，163（3）：649-658.e2.
29	Cui Y，Li Z，Xiang M，et al.Machine learning models predict overall survival and progression free survival of non-surgical esophageal cancer patients with chemoradiotherapy based on CT image radiomics signatures［J］.Radiat Oncol，2022，17（1）：212.
30	Xiong J，Yu W，Ma J，et al.The Role of PET-Based Radiomic Features in Predicting Local Control of Esophageal Cancer Treated with Concurrent Chemoradiotherapy［J］.Sci Rep，2018，8（1）：9902.
31	Gong J，Lu J，Zhang W，et al.A CT-based subregional radiomics nomogram for predicting local recurrence-free survival in esophageal squamous cell cancer patients treated by definitive chemoradiotherapy：a multicenter study［J］.J Transl Med，2024，22（1）：1108.
32	Kawahara D，Nishioka R，Murakami Y，et al.A nomogram based on pretreatment radiomics and dosiomics features for predicting overall survival associated with esophageal squamous cell cancer［J］.Eur J Surg Oncol，2024，50（7）：108450.
33	Kouzu K，Tsujimoto H，Imamura Y，et al.Development and Validation Study of the Prognostic Impact of Deep Learning-Determined Myxoid Stroma After Neoadjuvant Chemotherapy in Patients with Esophageal Squamous Cell Carcinoma［J］.Ann Surg Oncol，2024，31（9）：6300-6308.
34	Draguet C，Barragán-Montero AM，Vera MC，et al.Automated clinical decision support system with deep learning dose prediction and NTCP models to evaluate treatment complications in patients with esophageal cancer［J］.Radiother Oncol，2022，176：101-107.
35	Chu Y，Zhu C，Hobbs BP，et al.Personalized Composite Dosimetric Score-Based Machine Learning Model of Severe Radiation-Induced Lymphopenia Among Patients With Esophageal Cancer［J］.Int J Radiat Oncol Biol Phys，2024，120（4）：1172-1180.
36	Li C，Zhang J，Ning B，et al.Radiation pneumonitis prediction with dual-radiomics for esophageal cancer underwent radiotherapy［J］.Radiat Oncol，2024，19（1）：72.
37	Skrede OJ，De Raedt S，Kleppe A，et al.Deep learning for prediction of colorectal cancer outcome：a discovery and validation study［J］.Lancet，2020，395（10221）：350-360.
38	Wang R，Dai W，Gong J，et al.Development of a novel combined nomogram model integrating deep learningpathomics，radiomics and immunoscore to predict postoperative outcome of colorectal cancer lung metastasis patients［J］.J Hematol Oncol，2022，15（1）：11.
39	Sun JM，Shen L，Shah MA，et al.Pembrolizumab plus chemotherapy versus chemotherapy alone for first-line treatment of advanced oesophageal cancer （KEYNOTE-590）：a randomised，placebo-controlled，phase 3 study［J］.Lancet，2021，398（10302）：759-771.
40	Janjigian YY，Shitara K，Moehler M，et al.First-line nivolumab plus chemotherapy versus chemotherapy alone for advanced gastric，gastro-oesophageal junction，and oesophageal adenocarcinoma （CheckMate 649）：a randomised，open-label，phase 3 trial［J］.Lancet，2021，398（10294）：27-40.
41	Shen L，Kato K，Kim SB，et al.Tislelizumab Versus Chemotherapy as Second-Line Treatment for Advanced or Metastatic Esophageal Squamous Cell Carcinoma （RATIONALE-302）：A Randomized Phase III Study［J］.J Clin Oncol，2022，40（26）：3065-3076.
42	Li C，Zhao S，Zheng Y，et al.Preoperative pembrolizumab combined with chemoradiotherapy for oesophageal squamous cell carcinoma （PALACE-1）［J］.Eur J Cancer，2021，144：232-241.
43	Wang JL，Tang LS，Zhong X，et al.A machine learning radiomics based on enhanced computed tomography to predict neoadjuvant immunotherapy for resectable esophageal squamous cell carcinoma［J］.Front Immunol，2024，15：1405146.
44	Zhu Y，Yao W，Xu BC，et al.Predicting response to immunotherapy plus chemotherapy in patients with esophageal squamous cell carcinoma using non-invasive Radiomic biomarkers［J］.BMC Cancer，2021，21（1）：1167.
45	Shi L，Li C，Bai Y，et al.CT radiomics to predict pathologic complete response after neoadjuvant immunotherapy plus chemoradiotherapy in locally advanced esophageal squamous cell carcinoma［J］.Eur Radiol，2025，35（3）：1594-1604.
46	Qi WX，Li S，Xiao J，et al.A machine learning approach using （18）F-FDG PET and enhanced CT scan-based radiomics combined with clinical model to predict pathological complete response in ESCC patients after neoadjuvant chemoradiotherapy and anti-PD-1 inhibitors［J］.Front Immunol，2024，15：1351750.
47	Lin F，Zhu LX，Ye ZM，et al.Computed Tomography-Based Intratumor Heterogeneity Predicts Response to Immunotherapy Plus Chemotherapy in Esophageal Squamous Cell Carcinoma［J］.Acad Radiol，2024，31（12）：4886-4899.
48	Li B，Qin W，Yang L，et al.From pixels to patient care：deep learning-enabled pathomics signature offers precise outcome predictions for immunotherapy in esophageal squamous cell cancer［J］.J Transl Med，2024，22（1）：195.
49	Yang Y，Yi Y，Wang Z，et al.A combined nomogram based on radiomics and hematology to predict the pathological complete response of neoadjuvant immunochemotherapy in esophageal squamous cell carcinoma［J］.BMC Cancer，2024，24（1）：460.
50	Qi Y，Hu Y，Lin C，et al.A preoperative predictive model based on multi-modal features to predict pathological complete response after neoadjuvant chemoimmunotherapy in esophageal cancer patients［J］.Front Immunol，2025，16：1530279.
51	Fick CN，Dunne EG，Sihag S，et al.Immunotherapy for Resectable Locally Advanced Esophageal Carcinoma［J］.Ann Thorac Surg，2024，118（1）：130-140.
52	Goetz L，Seedat N，Vandersluis R，et al.Generalization-a key challenge for responsible AI in patient-facing clinical applications［J］.NPJ Digit Med，2024，7（1）：126.

文献	研究类型	癌种	中心数量	组学数量	组学	模型算法	数据集分布			曲线下面积
文献	研究类型	癌种	中心数量	组学数量	组学	模型算法	训练集	测试集	外部验证集	训练集	测试集	外部验证集
Ou^［15］	回顾性	ESCC	2	1	CT	SVM	188	83	55	0.929	0.868	0.866
Liu^［16］	回顾性	ESCC	2	1	MRI	Random Forest	82	73	0	0.968	0.885
Fan^［17］	回顾性	ESCC	1	1	CT	Logistic	186	46	0	0.941	0.962
Lu^［18］	前瞻性	ESCC	1	1	MRI	Logistic	75	33	0	0.851	0.831
Wang^［19］	回顾性	ESCC	1	1	CT	Logistic	112	122	0	0.838	0.814
Li^［20］	回顾性	ESCC	2	1	CT	Random Forest	139	62	30	0.918	0.871	0.750
Xie^［23］	回顾性	ESCC	2	1	CT	CNN+Random Forest	154	45	49	0.876	0.802	0.732
Li^［24］	前瞻性	ESCC	9	1	CT	CNN	203	103		0.897	0.833
Jin^［25］	回顾性	EC	1	2	CT+Dosiomic	XGBoost	70	24		0.708	0.541
Tolakcn^［26］	回顾性	EAC	3	2	Pathomics+TCGA	CNN	93	320	1 407		0.998

文献	研究类型	癌种	中心数量	组学数量	组学	模型算法	数据集分布			曲线下面积
文献	研究类型	癌种	中心数量	组学数量	组学	模型算法	训练集	测试集	外部验证集	训练集	测试集	外部验证集
Ou^［15］	回顾性	ESCC	2	1	CT	SVM	188	83	55	0.929	0.868	0.866
Liu^［16］	回顾性	ESCC	2	1	MRI	Random Forest	82	73	0	0.968	0.885
Fan^［17］	回顾性	ESCC	1	1	CT	Logistic	186	46	0	0.941	0.962
Lu^［18］	前瞻性	ESCC	1	1	MRI	Logistic	75	33	0	0.851	0.831
Wang^［19］	回顾性	ESCC	1	1	CT	Logistic	112	122	0	0.838	0.814
Li^［20］	回顾性	ESCC	2	1	CT	Random Forest	139	62	30	0.918	0.871	0.750
Xie^［23］	回顾性	ESCC	2	1	CT	CNN+Random Forest	154	45	49	0.876	0.802	0.732
Li^［24］	前瞻性	ESCC	9	1	CT	CNN	203	103		0.897	0.833
Jin^［25］	回顾性	EC	1	2	CT+Dosiomic	XGBoost	70	24		0.708	0.541
Tolakcn^［26］	回顾性	EAC	3	2	Pathomics+TCGA	CNN	93	320	1 407		0.998

文献	研究类型	癌种	中心数量	组学数量	组学	模型算法	数据集分布			曲线下面积
文献	研究类型	癌种	中心数量	组学数量	组学	模型算法	训练集	测试集	外部验证集	训练集	测试集	外部验证集
Wang^［43］	回顾性	ESCC	1	1	CT	Logistic	57	25		0.93	0.85
Zhu^［44］	回顾性	ESCC	2	1	CT	SVM	64	交叉验证		0.843	0.914
Shi^［45］	回顾性	ESCC	1	1	CT	XGBoost	79	26		0.89	0.80
Qi^［46］	前瞻性	ESCC	1	1	CT+PET	SVM	100	26		0.997	0.852
Lin^［47］	回顾性	ESCC	2	1	CT	XGBoost	263	65	88	0.923	0.864	0.796
Li^［48］	回顾性	ESCC	1	1	Pathomics	CNN	227	97		0.904
Yang^［49］	回顾性	ESCC	1	2	CT+Hematology	LASSO	164	交叉验证		0.934
Qi^［50］	回顾性	ESCC	1	2	CT+Pathomics	CNN+SVM	223	交叉验证		0.99	0.89

文献	研究类型	癌种	中心数量	组学数量	组学	模型算法	数据集分布			曲线下面积
文献	研究类型	癌种	中心数量	组学数量	组学	模型算法	训练集	测试集	外部验证集	训练集	测试集	外部验证集
Wang^［43］	回顾性	ESCC	1	1	CT	Logistic	57	25		0.93	0.85
Zhu^［44］	回顾性	ESCC	2	1	CT	SVM	64	交叉验证		0.843	0.914
Shi^［45］	回顾性	ESCC	1	1	CT	XGBoost	79	26		0.89	0.80
Qi^［46］	前瞻性	ESCC	1	1	CT+PET	SVM	100	26		0.997	0.852
Lin^［47］	回顾性	ESCC	2	1	CT	XGBoost	263	65	88	0.923	0.864	0.796
Li^［48］	回顾性	ESCC	1	1	Pathomics	CNN	227	97		0.904
Yang^［49］	回顾性	ESCC	1	2	CT+Hematology	LASSO	164	交叉验证		0.934
Qi^［50］	回顾性	ESCC	1	2	CT+Pathomics	CNN+SVM	223	交叉验证		0.99	0.89

[1]	Yin Chen, Ying Tan, Bohan Tan, Guannan He, Lei Wang, Xin Wen, Qiaozhen Zhu, Bocheng Liang, Shengli1 Li. Intelligent quality assessment and diagnosis of fetal omphalocele using YOLO V8 in ultrasound imaging [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2025, 22(04): 305-310.
[2]	Shuhan Sun, Yajing Chen, Qingqing Zong, Cuiying Li, Shumei Miao, Bin Yang, Feihong Yu. Ultrasound-based deep learning nomogram for predicting axillary lymph node status after neoadjuvant chemotherapy for breast cancer [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2025, 22(02): 97-105.
[3]	Xinyue Wang, Ya Yuan, Hua Shu, Kunpeng Cao, Xinhua Ye, Lu Li. Development of a dose prediction model for ultrasound-guided thrombin treatment of pseudoaneurysms using the LightGBM algorithm [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2025, 22(02): 153-161.
[4]	Benke Guan, Lixuan Hu, Yu Liu. Application status and progress of arthroscopic assisted treatment of tibial plateau fractures [J]. Chinese Journal of Joint Surgery(Electronic Edition), 2025, 19(02): 243-248.
[5]	Haoyu Fang, Xiao Wang, Anwei Zhang, Dandan Shang, Jiong Yu, Hongcui Cao. Biomarkers of mesenchymal stem cell therapy in Crohn's disease model mice based on fecal metabolomics [J]. Chinese Journal of Critical Care Medicine(Electronic Edition), 2025, 18(02): 98-104.
[6]	Kecheng Zhang, Rui Wang, Lei Yi, Zengding Zhou. Establishment and test results of HFNet model for burn and scald wound depth assessment [J]. Chinese Journal of Injury Repair and Wound Healing(Electronic Edition), 2025, 20(03): 192-198.
[7]	Ruiming Guo, Wei Qiu, Fuchun Fang. Single-cell RNA sequencing in periodontal research：Technological development，applications，and future perspectives [J]. Chinese Journal of Stomatological Research(Electronic Edition), 2025, 19(02): 75-83.
[8]	Shiwang Huang, Yunkai Qie, Hailong Hu. Application of artificial intelligence in non-invasive urine-based diagnostic methods for bladder cancer [J]. Chinese Journal of Endourology(Electronic Edition), 2025, 19(03): 283-287.
[9]	Jun Yan, Qiang Zhou, Shixiang Guo. Systematic review of application of Heidelberg triangle dissection in surgical treatment of pancreatic cancer [J]. Chinese Journal of Hepatic Surgery(Electronic Edition), 2025, 14(03): 449-455.
[10]	Hanchuan Guo, Qianyu Wang, Bin Wu. The research progress of artificial intelligence in neural recognition and its application in autonomic nerve protection for rectal cancer [J]. Chinese Journal of Colorectal Diseases(Electronic Edition), 2025, 14(03): 273-276.
[11]	Yahui Li, Lin Luan, Huiyun Huang. Construction and validation of risk model for young and middle-aged patients with liver cancer at different recurrence stages after radical operation [J]. Chinese Journal of Digestion and Medical Imageology(Electronic Edition), 2025, 15(02): 112-119.
[12]	Ye Ma, Hang Qu, Wei Wang. Role of artificial intelligence in evaluation of cerebrovascular disease imaging [J]. Chinese Journal of Clinicians(Electronic Edition), 2025, 19(03): 211-215.
[13]	Hongyu Wu, Exian Mou, Hao Dong, Juan Ji, Shiwei Liu. Stromal tumor-infiltrating lymphocytes as a predictor of axillary pathological complete response after neoadjuvant therapy in young breast cancer patients with axillary lymph node metastasis [J]. Chinese Journal of Clinicians(Electronic Edition), 2025, 19(02): 102-107.
[14]	Jian Chen, Kaijian Xia, Lu Xu, Fuli Gao, Xiaodan Xu, Ganhong Wang. Development of a risk assessment model for acute kidney injury in cirrhotic patients based on automated machine learning [J]. Chinese Journal of Clinicians(Electronic Edition), 2025, 19(02): 129-139.
[15]	Hanran Wu, Changqing Liu, Xianning Wu, Gao Wu, Li Du, Li Zhang, Xinyu Mei. Efficacy of thoracoscopic indocyanine green fluorescence imaging of the thoracic duct in preventing chylothorax after minimally invasive McKeown esophagectomy [J]. Chinese Journal of Thoracic Surgery(Electronic Edition), 2025, 12(02): 55-65.

Please choose a citation manager

Content to export