|Table of Contents|

Diagnostic value of deep learning model based on CT images for adjacent tumor deposits in colorectal cancer

Journal Of Modern Oncology[ISSN:1672-4992/CN:61-1415/R]

Issue:
2025 04
Page:
620-627
Research Field:
Publishing date:

Info

Title:
Diagnostic value of deep learning model based on CT images for adjacent tumor deposits in colorectal cancer
Author(s):
LIU Yan; LUO Jinwen; LIU Yanli; TANG Yaxia
Department of Medical Imaging,the Fifth Affiliated Hospital of Guangzhou Medical University,Guangdong Guangzhou 510700,China.
Keywords:
computed tomography; deep learning; colorectal cancer; tumor deposits
PACS:
R735.3
DOI:
10.3969/j.issn.1672-4992.2025.04.011
Abstract:
Objective:To explore the value of deep learning model based on CT images in preoperative prediction of tumor deposits (TDs) adjacent to colorectal cancer (CRC).Methods:A retrospective analysis was conducted on CT images and clinical data of 300 CRC patients confirmed by postoperative pathology.The transverse venous phase enhanced CT images were normalized and resampled,and the ITK-SNAP software was used to annotate the entire tumor area on the images.The patients were divided into TDs group and non-TDs group based on pathological results,and randomly divided into a training set (210 cases) and a validation set (90 cases) in a 7∶3 ratio.Perform deep learning feature extraction and radiomics feature extraction on whole tumor annotated images,use the Least Absolute Shrinkage and Selection Operator (LASSO) regression to screen radiomics features,and establish radiomics model,deep learning model,and radiomics+deep learning model.Use area under the receiver operating characteristic curve (AUC) to evaluate the diagnostic performance of each model,and use decision curve analysis (DCA) to evaluate the clinical value of the model.Results:The AUC values (95%CI) of the radiomics model,deep learning model,and radiomics+deep learning model in the training set were 0.810 (0.776~0.872),0.846 (0.776~0.917),and 0.868 (0.812~0.924),respectively.The AUC values (95%CI) in the validation set were 0.800 (0.736~0.864),0.826 (0.761~0.891),and 0.855 (0.795~0.916),respectively.The sensitivities were 73.22%,56.56%,and 67.67%,and the specificities were 64.01%,85.93%,and 87.30%,respectively.There were statistically significant differences among the three models in the validation set by Delong test (P＜0.05).The three models in the training and validation sets had good calibration and discrimination abilities.The radiomics+deep learning model had the highest diagnostic performance.The DCA showed that the radiomics+deep learning model had the best net benefit for predicting TDs.Conclusion:The deep learning model based on CT images has good diagnostic value for preoperative prediction of CRC adjacent TDs.The radiomics combined with deep learning model has the highest diagnostic efficiency and the best net benefit for predicting TDs,which can help clinicians make better treatment decisions.

References:

［1］ DELATTRE JF,SELCEN OGUZ ERDOGAN A,COHEN R,et al.A comprehensive overview of tumour deposits in colorectal cancer:towards a next TNM classification［J］.Cancer Treat Rev,2022,103:102325.
［2］ WEISER MR.AJCC 8th edition:colorectal cancer［J］.Ann Surg Oncol,2018,25(6):1454-1455.
［3］ COHEN R,SHI Q,MEYERS J,et al.Combining tumor deposits with the number of lymph node metastases to improve the prognostic accuracy in stage III colon cancer:a post hoc analysis of the CALGB/SWOG 80702 phase III study (Alliance)［J］.Annals of Oncology，2021,32（10）：1267-1275.
［4］朱巧萍,李安川,徐本华.肿瘤沉积对ypⅢ期直肠癌患者预后的预测价值 ［J］.中华放射肿瘤学杂志,2021,30(1):47-53. ZHU Qiaoping,LI Anchuan,XU Benhua.Predictive value of tumor deposit for the prognosis of patients with yp-stage Ⅲ rectal cancer［J］.Chinese Journal of Radiation Oncology,2021,30(1):47-53.
［5］涂佳琪,罗中翔,刘建鹏,等.基于MRI的深度学习联合影像组学评估中线胶质瘤H3 K27状态 ［J］.中国医学影像技术,2024,40(06):810-814. TU Jiaqi,LUO Zhongxiang,LIU Jianpeng,et al.MRI-based deep learning combined with radiomics evaluation of the H3 K27 status of midline gliomas ［J］.Chinese Medical Imaging Technology,2024,40(06):810-814.
［6］何月明,罗锦文,戚莹莹,等.基于MRI图像的机器学习模型预测子宫肌瘤HIFU消融术后疗效的价值 ［J］.现代肿瘤医学,2024,32(06):1093-1100. HE Yueming,LUO Jinwen,QI Yingying,et al.The value of machine learning model based on MRI images in predicting the efficacy of HIFU ablation for uterine fibroids ［J］.Modern Oncology,2024,32(06):1093-1100.
［7］何月明,陈思琳,马跃昆,等.基于MR组学特征的诺模图(Nomogram)在术前预测宫颈癌淋巴血管间隙侵犯中应用的初步研究 ［J］.临床放射学杂志,2022,41 (08):1565-1574. HE Yueming,CHEN Silin,MA Yuekun,et al.Preliminary study on the application of Nomogram based on MR omics features in preoperative prediction of lymphatic vessel invasion in cervical cancer ［J］.Journal of Clinical Radiology,2022,41(08):1565-1574.
［8］罗锦文,何月明,张婷,等.基于MR-T2WI纹理分析在预测子宫肌瘤高强度聚焦超声消融术后疗效的价值［J］.中国医学计算机成像杂志,2024,30(02):250-258. LUO Jinwen,HE Yueming,ZHANG Ting,et al.The value of MR-T2WI texture analysis in predicting the efficacy of high-intensity focused ultrasound ablation for uterine fibroids ［J］.Chinese Journal of Medical Computer Imaging,2024,30(02):250-258.
［9］罗锦文.基于螺旋CT图像在鉴别结直肠癌旁肿瘤沉积与转移淋巴结的价值初步分析［D］.广州:广州医科大学,2019. LUO Jinwen.Preliminary analysis of the value of spiral CT images in distinguishing tumor deposition and metastatic lymph nodes adjacent to colorectal cancer ［D］.Guangzhou:Guangzhou Medical University,2019.
［10］ HAKKI L,KHAN A,DO E,et al.Tumour deposits are independently associated with recurrence in colon cancer［J］.Colorectal Disease,2024,26(3):459-465.
［11］ YAMAI D,SHIMADA Y,NAKANO M,et al.Clinical significance of metastatic tumor deposit foci in rectal cancer in the lateral pelvic lymph node area［J］.Int J Clin Oncol,2023,28(10):1388-1397.
［12］ AGGER E,JRGREN F,JUD A,et al.Negative prognostic impact of tumor deposits in rectal cancer:a national study cohort［J］.Ann Surg,2023,278(3):e526-e533.
［13］ LORD AC,GRAHAM MARTNEZ C,D' SOUZA N,et al.The significance of tumour deposits in rectal cancer after neoadjuvant therapy:a systematic review and meta-analysis［J］.Eur J Cancer,2019,122:1-8.
［14］ AMIN MB,GREENE FL,EDGE SB,et al.The eighth edition AJCC cancer staging manual:continuing to build a bridge from a population-based to a more "personalized" approach to cancer staging［J］.CA Cancer J Clin,2017,67(2):93-99.
［15］ GOLDSTEIN NS,TURNER JR.Pericolonic tumor deposits in patients with T3N+MO colon adenocarcinomas:markers of reduced disease free survival and intra-abdominal metastases and their implications for TNM classification［J］.Cancer 2000,88(10):2228-2238.
［16］ DELATTRE JF,COHEN R,HENRIQUES J,et al.Prognostic value of tumor deposits for disease-free survival in patients with stage III colon cancer:a post hoc analysis of the IDEA France phase III trial (PRODIGE-GERCOR)［J］.J Clin Oncol,2020,38(15):1702-1710.
［17］ NAGTEGAAL ID,KNIJN N,HUGEN N,et al.Tumor deposits in colorectal cancer:improving the value of modern staging-a systematic review and meta-analysis［J］.J Clin Oncol,2017,35(10):1119-1127.
［18］罗锦文,李新春,雷强,等.螺旋CT多参数测量对结直肠癌旁肿瘤沉积的诊断价值［J］.放射学实践,2019,34(08):901-905. LUO Jinwen,LI Xinchun,LEI Qiang,et al.The diagnostic value of multi parameter measurement of spiral CT for adjacent tumor deposition in colorectal cancer ［J］.Radiology Practice,2019,34(08):901-905.
［19］卞琳杰.结直肠癌旁肿瘤沉积的CT检查影像学特征及鉴别诊断［D］.南京:南京医科大学,2018. BIAN Linjie.Imaging features and differential diagnosis of colorectal paracancer tumor deposition on CT examination［D］.Nanjing:Nanjing Medical University,2018.
［20］李曼曼,符益纲,肖勇,等.CT影像组学列线图预测结直肠癌肿瘤沉积和预后［J/OL］.CT理论与应用研究,1-10［2024-11-13］.https://wap.cnki.net/touch/web/Journal/Article/CTLL20240812008.html?sid_for_share=99125_3. LI Manman,FU Yigang,XIAO Yong,et al.Prediction of tumor deposition and prognosis of colorectal cancer by CT radiomics nomogram ［J/OL］.CT Theory and Application,1-10［2024-11-13］.https://wap.cnki.net/touch/web/Journal/Article/CTLL20240812008.html?sid_for_share=99125_3.
［21］方著.基于MRI多区域影像组学模型在局部进展期直肠癌新辅助治疗后淋巴结转移和肿瘤沉积预测中的价值［D］.南充：川北医学院,2023. FANG Zhu.Value of MRI-based multi-regional radiomics model in predicting lymph node metastasis and tumor deposition after neoadjuvant therapy for locally advanced rectal cancer［D］.Nanchong:North Sichuan Medical College,2023.
［22］LI Hang,CHEN Xiaoli,LIU Huan,et al.MRI-based multiregional radiomics for preoperative prediction of tumor deposit and prognosis in resectable rectal cancer:a bicenter study［J］.European Radiology,2023,33(11)：7561-7572.

Memo

Memo:
广东省医学科学技术研究基金(编号：A2023485)；广东省广州市教育局高校研究生科研项目（编号：2024312248）
Last Update: 1900-01-01