Junfeng Yan; Qiushuang Wang; Qiang Li; Jiatong Lu; Qiang Tong

doi:10.3393/ac.2025.00689.0098

Articles

Page Path: HOME > Ann Coloproctol > Volume 41(6); 2025 > Article

Original Article Complications Preoperative magnetic resonance imaging–based radiomics nomogram model for predicting postoperative anastomotic leakage in colorectal cancer: Junfeng Yan^*, Qiushuang Wang^*, Qiang Li, Jiatong Lu, Qiang Tong; Annals of Coloproctology 2025;41(6):554-564.
DOI: https://doi.org/10.3393/ac.2025.00689.0098
Published online: December 26, 2025

Department of Gastrointestinal Surgery I Section, Renmin Hospital of Wuhan University, Wuhan, China

Correspondence to: Qiang Tong, PhD Department of Gastrointestinal Surgery I Section, Renmin Hospital of Wuhan University, Jiefang Rd 238, Wuchang District, Wuhan 430060, China Email: qiangtong@whu.edu.cn

*Junfeng Yan and Qiushuang Wang contributed equally to this study as co-first authors.

• Received: May 25, 2025 • Revised: July 31, 2025 • Accepted: August 17, 2025

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

prev next

434 Views
14 Download

Full Article

Download PDF

Abstract
INTRODUCTION
METHODS
RESULTS
DISCUSSION
ARTICLE INFORMATION
Supplementary materials
REFERENCES

Abstract

Purpose
Anastomotic leakage (AL) is a serious postoperative complication after colorectal cancer surgery, and accurate preoperative prediction remains challenging. This study aimed to develop and validate a magnetic resonance imaging (MRI)–based radiomics nomogram for the preoperative prediction of AL.
Methods
A total of 146 patients with colorectal cancer, including 11 with AL, were retrospectively enrolled and randomly divided into training and validation cohorts at a 7:3 ratio. Clinical variables and preoperative MRI-based radiomic features were analyzed. A clinical model was constructed using logistic regression. Radiomic features were selected using the least absolute shrinkage and selection operator method to develop a radiomics model, from which a radiomic score was calculated. A combined radiomics nomogram integrating the radiomic score and significant clinical factors was subsequently established. Model performance was evaluated using receiver operating characteristic curve analysis in both cohorts.
Results
The clinical model achieved an area under the curve (AUC) of 0.766 in the training cohort and 0.583 in the validation cohort. The radiomics model demonstrated improved discrimination, with AUCs of 0.822 and 0.800, respectively. The combined radiomics nomogram showed the best predictive performance, yielding AUCs of 0.869 in the training cohort and 0.858 in the validation cohort.
Conclusion
The proposed MRI-based radiomics nomogram demonstrates good predictive performance for postoperative anastomotic leakage and may serve as a useful tool for preoperative risk stratification in patients with colorectal cancer.
Keywords: Colorectal neoplasms; Anastomotic leak; Radiomics; Magnetic resonance imaging; Preoperative prediction

INTRODUCTION

Anastomotic leakage (AL) remains one of the most feared and devastating complications following colorectal cancer surgery. AL adversely affects surgical outcomes, prolongs hospital stays, increases healthcare costs, raises postoperative tumor recurrence rates, and reduces both overall and cancer-specific survival [1, 2]. Despite significant advancements in perioperative care, surgical techniques, and instrumentation, the incidence of AL has remained steady at 3% to 15% over the past several decades [3, 4]. For some patients, AL appears almost unavoidable, underscoring the importance of early identification and prevention. Numerous studies have reported various risk and predictive factors for AL, including tumor size, tumor height, sex, nutritional status, body weight, smoking, comorbid diabetes, and C-reactive protein levels [5–7]. Although many of these factors are unmodifiable, strategies such as prophylactic stoma creation, reinforcement of the anastomosis with additional sutures, and modifications in anastomotic technique may reduce or prevent AL [8–10].

Diagnosing AL is also challenging, as clinical manifestations range from asymptomatic presentations to life-threatening septic shock. Delayed diagnosis can result in delayed treatment and worse outcomes [11, 12]. Therefore, a reliable preoperative method for predicting AL is critically needed to facilitate timely intervention and preventive strategies.

Radiomics, an emerging technique, quantitatively extracts imaging features to evaluate tumor heterogeneity and biological behavior. It holds significant promise in personalized medicine for rectal cancer by improving diagnosis, guiding treatment, and predicting prognosis [13, 14]. Recent studies have increasingly applied radiomics for tumor diagnosis, therapeutic planning, and prognostic assessment, demonstrating its diagnostic and predictive value [15, 16]. Radiomics provides a comprehensive evaluation of tumor heterogeneity and biological behavior. However, only a few studies to date have explored its application for predicting AL in colorectal cancer. Thus, the present study aims to develop and validate a radiomics-based predictive model for the preoperative assessment of AL.

METHODS

Ethics statement

This study was approved by the Research Ethics Committee of Renmin Hospital of Wuhan University (No. WDRY2018-K055). Informed consent was waived due to the use of deidentified data and the retrospective nature of the study.

Patients

Patients who underwent surgery for colorectal cancer at the Gastrointestinal Surgery Center of Renmin Hospital of Wuhan University between January 2018 and December 2024 were screened for inclusion. All enrolled patients underwent colorectal cancer surgery and had complete clinical data, including magnetic resonance imaging (MRI) within 1 week prior to surgery. Inclusion criteria were as follows: (1) colorectal adenocarcinoma confirmed by pathology; (2) complete clinical data; and (3) preoperative MRI, including T1-weighted imaging (T1WI) and T2WI, performed within 14 days prior to surgery. Exclusion criteria were as follows: (1) nonprimary adenocarcinoma pathology; (2) incomplete clinical data or suboptimal image quality for analysis; and (3) patients who underwent Hartmann procedure, Miles procedure, or other procedures without intestinal anastomosis. Eligible patients were randomly divided into training and validation sets at a 7:3 ratio (Fig. 1). Two radiologists, with 5 and 7 years of experience respectively, independently analyzed MRI features without knowledge of postoperative outcomes, and their assessments were consistent.

A total of 146 patients were included in our study. Clinical characteristics, including age, sex, body mass index, and protective ostomy were obtained from hospital records. Postoperative AL was defined according to the International Study Group of Rectal Cancer (ISREC) criteria [12], including grade B and C leaks confirmed through clinical, radiological, or surgical evidence. All patients were followed for a minimum of 30 days postoperatively, during which all observed AL events were documented. Baseline patient data are detailed in Table 1.

Development of the clinical model

Clinical data collected included age, sex, body mass index, diabetes, neoadjuvant therapy, albumin levels, and distance from the tumor to the anal verge. Odds ratios (ORs) and 95% confidence intervals (CIs) were calculated for each factor. Based on univariate analysis, age, tumor distance from the anal verge, and neoadjuvant therapy showed significant differences between with and without AL groups (P<0.2). These 3 factors were subsequently incorporated into a multivariate logistic regression model, which constituted the clinical model.

Image segmentation, preprocessing, and radiomic feature extraction

Preprocessing steps were performed to standardize image quality and intensity. First, N4ITK bias field correction was applied to adjust for intensity inhomogeneity caused by scanner magnetic field variations during image acquisition [17, 18]. All images were then resampled to an isotropic voxel size of 1×1×1 mm³ to ensure spatial uniformity across datasets [19]. Finally, Z-score normalization was applied to the extracted features to minimize scale differences and improve reproducibility.

Without knowledge of clinical outcomes, 2 radiologists manually delineated the tumor boundaries on T1WI and fat-suppressed T2WI (fs-T2WI) using 3D Slicer ver. 5.6.2 (Slicer Community; https://www.slicer.org) (Fig. 2). Adjacent normal tissue and blood vessels were excluded. From the region of interest on the T1WI and fs-T2WI sequences, a total of 1,702 3-dimensional MR radiomic features were extracted.

To assess reproducibility, interobserver consistency was tested by randomly selecting 10 MRI images (5 with AL and 5 without AL). Two radiologists independently performed region of interest segmentation on both T1WI and fs-T2WI images. The intraclass correlation coefficient (ICC) was used to evaluate consistency, with ICC >0.75 indicating good agreement. Radiologist 1 then extracted radiomic features from the remaining images.

Feature selection and development of the radiomics model

Only features with ICC >0.75 were retained for further analysis. The least absolute shrinkage and selection operator (LASSO) algorithm was applied to the training set to identify optimal features. LASSO regression, a widely used shrinkage technique, reduces overfitting and improves predictive accuracy [20]. Radiomic features selected by LASSO were used to construct the radiomics model. A radiomic score (Rad score) was then calculated for each patient using a linear combination of selected feature values (A [wavelet.LLHglcmDifferenceVariance], measures the variance of gray-level differences in the gray-level co-occurrence matrix [GLCM], indicating texture variation and image detail; B [wavelet.LHLglcmJointEnergy], reflects the joint energy in the GLCM, reflecting the uniformity or simplicity of the texture; C [wavelet.HHHglcmImc1], based on informational measure of correlation 1 (IMC1) of the GLCM, it indicates the texture dependency, with higher values showing more regular textures; D [wavelet.HHHgldmSmallDependenceHighGrayLevelEmphasis], emphasizes small regions with high gray levels in the gray-level dependence matrix [GLDM], reflecting areas of high contrast; E [wavelet.HHHgldmSmallDependenceLowGrayLevelEmphasis], emphasizes small regions with low gray levels in the GLDM, highlighting low-contrast areas; F [originalngtdmStrength], measures the strength of the texture using the neighborhood gray-tone difference matrix [NGTDM], with higher values indicating stronger and more intricate textures; G [wavelet.LHLglcmImc1], similar to IMC1 of the GLCM, calculated from the LHL subband, reflecting texture complexity; H [wavelet.LHLglcmImc2], based on IMC2 of the GLCM, it reflects finer texture details and contrast in the image; I [wavelet.LHLgldmSmallDependenceEmphasis], measures the importance of small dependent regions in the image using the GLDM, indicating texture relevance) weighted by their corresponding nonzero coefficients. The Rad score was calculated using the following formula:

Rad score=A×0.0430−B×0.0008−C×0.0071+D×0.0183−E×0.0334−F×0.0949−G×0.0012−H×0.0142−I×0.0477

Development of the radiomics nomogram model

A radiomics nomogram model incorporating the Rad score and clinical factors selected by the clinical model (including age, tumor distance from the anal verge, and neoadjuvant therapy) was constructed using multivariable logistic regression. Supplementary Table 1 provides the regression coefficients and ORs corresponding to each included variable. Subsequently, a nomogram score was generated for each patient based on the model.

Model evaluation

The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was calculated for both training and validation sets to assess the discriminatory performance of the clinical model, the radiomics model, and the radiomics nomogram model. In addition, decision curve analysis was performed to evaluate the clinical utility of the 3 models by quantifying their net benefit across different threshold probabilities in the validation set.

Statistical analysis

Statistical analysis was performed using SPSS ver. 17.0 (SPSS Inc) and R ver. 4.4.1 (R Foundation for Statistical Computing). A 2-sided P-value of <0.05 was considered statistically significant. The chi-square test and Fisher exact test were used for categorical variables, and the independent samples t-test was used for continuous variables. The following R packages were applied: “pROC” for ROC curve analysis, “rms” for nomograms and calibration curves, “glmnet” for LASSO logistic regression, and “rmda” for decision curve analysis.

RESULTS

Development of the clinical model

A total of 146 patients were included in this study, among whom 11 (7.5%) developed postoperative AL. Table 1 summarizes the clinical characteristics of patients, stratified into with and without AL groups. ORs and 95% CIs were calculated for each independent factor. Univariate analysis indicated that age, tumor distance from the anal verge, and neoadjuvant therapy differed between with and without AL groups (P<0.2). These 3 variables were subsequently incorporated into the multivariate logistic regression model. The clinical model achieved an AUC of 0.766 in the training set and 0.583 in the validation set.

Radiomic feature extraction, selection, and development of the radiomics model

From T1- and fs-T2WI sequences, a total of 1,702 radiomic features were initially extracted. Of these, 1,356 features demonstrated ICCs between 0.75 and 1, and were therefore considered reproducible. These features were subsequently entered into the LASSO regression analysis to identify the most predictive characteristics. Nine features with nonzero coefficients were ultimately selected to construct the radiomics model. The optimal regularization parameter λ was determined as 0.0065 under the 1–standard error criterion (Fig. 3, Table 2). The Rad score was calculated for each patient using the aforementioned formula.

Development of the radiomics nomogram combined model and evaluation of the different models

The radiomics nomogram combined model was constructed by integrating Rad scores with independent clinical factors, including age, tumor distance from the anal verge, and preoperative neoadjuvant therapy. The regression coefficients and ORs for each variable were calculated (Supplementary Table 1). The ROC curves for each model in the training and validation sets are shown in Fig. 4. Performance metrics, including sensitivity and specificity, are summarized in Table 3 for both datasets. In both training and validation sets, the radiomics nomogram combined model demonstrated superior discriminative performance and higher AUC values compared with the clinical- and radiomics-only models. Decision curve analysis for the 3 models indicated that the radiomics nomogram combined model provided greater net clinical benefit across a wide range of threshold probabilities compared to either the clinical model or the radiomics model alone (Fig. 5).

DISCUSSION

Preoperative prediction of AL is crucial for optimizing surgical strategies and postoperative management in colorectal cancer. In this study, we developed a radiomics-based nomogram that integrates clinical risk factors with preoperative MRI-derived imaging features, providing a noninvasive tool for predicting postoperative AL. The radiomics nomogram model demonstrated strong predictive performance, with AUCs of 0.869 and 0.858 in the training and validation sets, respectively.

Many studies have reported associations between AL and various clinical factors. In our study, age, tumor distance from the anal verge, and preoperative neoadjuvant therapy emerged as predictors for constructing the multivariate logistic regression model. These findings are consistent with previously identified risk factors for AL [6, 21].

The relationship between neoadjuvant therapy and AL following colorectal cancer surgery has been extensively examined but remains controversial. Several large, high-impact studies suggest that neoadjuvant chemoradiotherapy (nCRT) does not significantly increase AL risk. For example, Bosset et al. [22] reported that preoperative chemoradiotherapy improved local control without increasing surgical complications, including AL. Similarly, Peeters et al. [23], in a landmark randomized trial, found no significant difference in AL rates between patients treated with nCRT and those undergoing surgery alone.

In contrast, an increasing body of high-quality evidence suggests a potential association between neoadjuvant therapy and AL, particularly in rectal cancer. A comprehensive meta-analysis by Yang et al. [24], which included 49 studies encompassing more than 23,000 patients, demonstrated that neoadjuvant radiotherapy significantly increased AL risk, with a pooled OR of 1.23 (95% CI, 1.07–1.41; P=0.004). This suggests that radiation-induced tissue changes may impair anastomotic healing. Likewise, a recent large-scale retrospective cohort study by Li et al. [25] found that nCRT was an independent risk factor for postoperative re-leakage after stoma reversal, with an OR of 4.07 (95% CI, 1.17–14.21; P=0.03). These findings underscore the need for individualized treatment strategies and careful perioperative planning in patients undergoing neoadjuvant therapy.

In our study, the leak rate in the neoadjuvant group was higher than in the non-neoadjuvant group (18.5% vs. 5.0%), aligning with the above evidence and suggesting that neoadjuvant therapy may contribute to AL risk under certain clinical circumstances. Variations in surgical technique, radiation dose, and patient-specific factors may further influence this risk. Prospective, multicenter trials with standardized protocols are warranted to optimize patient selection and perioperative strategies.

We also evaluated the role of protective ostomy in AL occurrence. Among patients with a diverting stoma, the AL rate was 4 of 23 (17.4%), compared with 7 of 123 (5.7%) in those without a stoma. The OR was 3.49 (95% CI, 0.93–13.07; P=0.073). However, this finding likely reflects surgical decision-making: patients considered at high risk were more often given a protective ostomy, rather than the ostomy itself increasing leak risk. This potential reverse causality should be taken into account when interpreting such results.

Previous studies have shown that while diverting stomas may not substantially reduce the incidence of AL, they can mitigate its clinical severity. For instance, Matthiessen et al. [26], in a randomized controlled trial, demonstrated that protective stomas significantly reduced the need for reoperation after low anterior resection. Similarly, a meta-analysis by Hüser et al. [27] concluded that although diverting stomas did not lower the overall incidence of AL, they were associated with decreased morbidity and reduced severity in patients who developed leaks. These findings emphasize the importance of protective ostomy in reducing the clinical impact of AL, even if it does not prevent its occurrence.

Surgical technique is another important factor influencing AL risk. In our cohort, higher AL incidence was observed among patients undergoing low anterior resection and those without a protective stoma, though not all comparisons reached statistical significance. Previous studies have shown that low anastomosis height and procedures such as total mesorectal excision are associated with increased AL risk due to compromised blood supply, greater anastomotic tension, and technical challenges [28, 29]. The absence of a diverting stoma has also been linked to higher rates of clinically significant leakage, suggesting a possible protective effect. Larger studies are needed to confirm these associations and further elucidate underlying mechanisms.

However, the clinical factors model alone did not achieve a high AUC for predicting AL. In our study, some clinical factors, such as sex, did not differ significantly between with and without AL groups, which contrasts with findings from previous reports [8, 30], This discrepancy may be attributable to the limited sample size and single-center design, underscoring the need for larger, multicenter studies.

Currently, no effective method exists for preoperative prediction of AL in colorectal cancer. Although a left-sided AL risk score has been developed, its external validation has produced unsatisfactory results [31]. Novel approaches such as intraoperative assessment of anastomotic perfusion may offer predictive value, but they also prolong operative time [32]. In contrast, our study provides a noninvasive and cost-effective method for preoperative AL prediction, representing an important clinical advantage.

Radiomics offers a promising tool for quantifying tumor heterogeneity and peritumoral tissue characteristics from routinely acquired images, detecting subtle features that are not discernible to the human eye. While previous radiomics research has largely focused on predicting tumor metastasis and treatment outcomes, less attention has been paid to surgical complications. Importantly, imaging features such as circumferential resection margin, extramural vascular invasion, and tumor deposits are key determinants in surgical planning [33, 34]. Certain factors, such as anastomotic perfusion and pelvic inflammation, have been confirmed to be associated with the occurrence of AL [35, 36]. Radiomics can capture and quantify these imaging characteristics, which may explain the strong predictive performance of our nomogram. Supporting this, previous radiomics-based models have also demonstrated predictive value for postoperative complications, such as pancreatic fistula [37]. Our findings therefore support the feasibility of incorporating radiomic biomarkers into predictive models for AL, providing added value beyond clinical variables alone.

In this study, we integrated clinical variables with MRI-derived radiomic features to develop a radiomics nomogram for AL prediction, achieving excellent predictive accuracy. To our knowledge, this represents one of the few studies employing an MRI-based radiomics model specifically for AL risk assessment in colorectal cancer.

Our study may have important clinical implications. Identification of high-risk patients preoperatively enables proactive measures such as intraoperative adjustments in surgical approach, placement of abdominal or anal drainage tubes, or the creation of a diverting stoma [38].

Our radiomics nomogram integrates MRI-derived radiomic features and key clinical factors to provide a personalized risk estimation for postoperative AL in colorectal cancer patients. In clinical practice, this tool can be used preoperatively to assist surgeons in stratifying patients according to their individual risk of developing AL. By inputting specific values of the predictors into the nomogram, clinicians can obtain a quantified probability of AL occurrence in an intuitive and user-friendly manner. This visualization facilitates rapid interpretation and supports risk stratification without requiring advanced computational tools.

Once high-risk patients are identified, tailored perioperative strategies may be implemented. These include conservative surgical approaches (e.g., temporary stoma formation), reinforcement of the anastomosis, application of sealants, or intensified postoperative surveillance (e.g., early imaging, closer clinical monitoring). Conversely, for patients with a low predicted risk, unnecessary protective interventions, such as diverting stomas that may impair quality of life, can be avoided. In this way, the nomogram enables more personalized and balanced decision-making, consistent with the principles of precision medicine.

The clinical value of our nomogram lies in supporting early risk prediction and informed surgical planning, with the potential to reduce both the incidence and clinical severity of AL. Given that AL is associated with increased morbidity, prolonged hospitalization, delayed initiation of adjuvant therapy, and greater healthcare costs, early identification of high-risk patients could mitigate these adverse outcomes. Additionally, the nomogram standardizes decision-making across clinicians by offering an evidence-based, reproducible tool. Its integration into preoperative workflows may enhance patient counseling, improve allocation of medical resources, and strengthen shared decision-making between surgeons and patients.

Limitations

Despite the promising findings, several limitations of this study must be acknowledged. First, the incidence of AL in our cohort was relatively low (11 out of 146 patients, 7.5%), which, although consistent with real-world clinical practice, significantly limits the statistical power for detecting meaningful associations and increases the risk of overfitting, even though we employed machine learning techniques to mitigate this issue. Moreover, the small number of leakage events may have constrained the identification of potential risk factors and reduced the robustness of model training. This also limits the generalizability of our findings to broader clinical populations.

Second, this study was conducted at a single center with a retrospective design, and internal validation was performed by randomly splitting the dataset into training and validation cohorts. Due to the lack of an independent external validation cohort, the generalizability and robustness of our model remain to be further verified. We acknowledge this important limitation and emphasize the need for future studies to include external or temporally distinct validation cohorts. Currently, we are actively collecting patient data from different time periods to facilitate such validation; however, the relatively low incidence of AL has slowed the accumulation of adequate sample sizes for meaningful analysis.

Third, radiomic features were extracted solely from noncontrast MRI sequences (T1WI and T2WI), which may restrict the imaging information captured. Incorporating contrast-enhanced or diffusion-weighted imaging could improve model comprehensiveness.

Lastly, variations in surgical techniques and the experience level of individual surgeons, both known risk factors for AL, were not fully accounted for due to data limitations.

To enhance the clinical applicability and translational potential of our model, future studies should focus on larger, prospective, multicenter cohorts with standardized imaging protocols and external validation across diverse institutions and populations. Integration of perioperative variables and real-time clinical data may also further optimize predictive performance.

Conclusions

Our study suggests that the proposed radiomics nomogram model may serve as a potentially useful tool for estimating the risk of postoperative AL in cancer patients. Moreover, transforming the nomogram into an automated software platform or online calculator could support its integration into clinical workflows and enhance decision-making in perioperative management.

ARTICLE INFORMATION

Conflict of interest

No potential conflict of interest relevant to this article was reported.

Funding

This study was supported by the National Natural Science Foundation of China (No. 81172186), the Natural Science Foundation of Hubei Province (No. 2018CFB504), and the Guidance Foundation of Renmin Hospital of Wuhan University (No. RMYD2018M67).

Author contributions

Conceptualization: JY, QW, QT; Data curation: JY, QW; Formal analysis: JY, QW, QT; Funding acquisition: QT; Investigation: JY, QW, QL, JL; Writing–original draft: JY, QW, QL, JL; Writing–review & editing: all authors. All authors read and approved the final manuscript.

Supplementary materials

Supplementary Table 1.

Multivariate analysis results of binary logistic regression

ac-2025-00689-0098-Supplementary-Table-1.pdf

Supplementary materials are available from https://doi.org/10.3393/ac.2025.00689.0098.

Fig. 1.

Study flowchart. AL, anastomotic leakage; MRI, magnetic resonance imaging; ROI, region of interest; Rad score, radiomic score.

Fig. 2.

Magnetic resonance imaging (MRI) of rectal tumors and regions of interest from a 49-year-old female patient in the training set. A mass (arrows) can be seen in the rectum in (A) T1-weighted MRI scan and (B) fat-saturated T2-weighted MRI scan. Manual segmentation of the mass in (C) T1-weighted MRI scan and (D) fat-saturated T2-weighted MRI scan.

Fig. 3.

Selection of radiomics features via the least absolute shrinkage and selection operator (LASSO) regression algorithm. (A) Tuning parameter (λ) selection in the LASSO model using 10-fold cross-validation and the 1–standard error criterion. The optimal λ value is indicated by the right vertical dotted line; λ=0.0065 was selected. (B) LASSO coefficient profiles of 1,356 radiomics features. A coefficient profile plot was generated against the log λ value using 10-fold cross-validation. Nine radiomics features with nonzero coefficients were ultimately selected. These included 5 gray-level co-occurrence matrix (GLCM) features, 3 gray-level dependence matrix (GLDM) features, and 1 neighborhood gray-tone difference matrix (NGTDM) feature.

Fig. 4.

Radiomics nomogram development and receiver operating characteristic curve analysis. (A) Age, tumor distance from the anal verge, neoadjuvant therapy, and the radiomic score (Rad score) were used to construct the radiomics nomogram. (B) The predictive performance of the clinical model in both the training and validation sets. (C) The predictive performance of the radiomics model in both the training and validation sets. (D) The predictive performance of the radiomics/nomogram combined model in both the training and validation sets. AUC, area under the curve.

Fig. 5.

Decision curve analysis for the 3 models. The y-axis represents net benefit, and the x-axis denotes threshold probability. The green line, red dashed line, and blue dashed line correspond to the clinical model, radiomics-only model, and radiomics nomogram combined model, respectively. Across the full range of threshold probabilities, the radiomics nomogram combined model demonstrated the greatest overall net clinical benefit for predicting anastomotic leakage.

Table 1.

Clinical characteristics of patients with and without AL

Characteristic	Total (n=146)	Without AL (n=135)	With AL (n=11)	OR (95% CI)	P-value
Age (yr)	64.0 (60.0–68.8)	63.0 (59.0–68.0)	67.0 (65.0–70.5)	0.952 (0.281–3.268)^a	0.113
Sex				1.178 (0.336–4.059)	0.790
Male	74 (50.7)	68 (50.4)	6 (54.5)
Female	72 (49.3)	67 (49.6)	5 (45.5)
Body mass index (kg/m²)	22.79 (21.22–24.69)	22.78 (21.16–24.68)	23.33 (21.25–24.53)	-	0.784
Tumor distance from anal verge (cm)	7.65 (6.10–9.50)	7.80 (6.20–9.55)	6.90 (5.05–7.75)	0.621 (0.167–2.199)^a	0.134
Albumin level (g/L)	40.08±4.26	40.08±4.38	39.99±2.60	-	0.921
Neoadjuvant therapy				4.284 (1.203–15.266)	0.046^*
No	119 (81.5)	113 (83.7)	6 (54.5)
Yes	27 (18.5)	22 (16.3)	5 (45.5)
Combined diabetes				1.918 (0.384–9.802)	0.768
No	130 (89.0)	121 (89.6)	9 (81.8)
Yes	16 (11.0)	14 (10.4)	2 (18.2)
Protective ostomy				3.492 (0.928–13.074)	0.073
No	123 (84.2)	116 (85.9)	7 (63.6)
Yes	23 (15.8)	19 (14.1)	4 (36.4)
Operation type				1.127 (0.134–9.635)	0.580
Open surgery	12 (8.2)	11 (8.1)	1 (9.1)
Endoscopic surgery	134 (91.8)	124 (91.9)	10 (90.9)

Values are presented as median (interquartile range), number (%), or mean±standard deviation.

AL, anastomotic leakage; OR, odds ratio; CI, confidence interval.

^aCalculated by dichotomizing age (≥65 years) or tumor distance (>7 cm).

^*P<0.05.

Table 2.

Radiomics feature selection results

Variable	Feature name	Coefficient	ICC
A	wavelet.LLHglcmDifferenceVariance	0.043047801	0.9962
B	wavelet.LHLglcmJointEnergy	–0.000821006	0.9895
C	wavelet.HHHglcmImc1	–0.007114313	0.9881
D	wavelet.HHHgldmSmallDependenceHighGrayLevelEmphasis	–0.018299704	0.9873
E	wavelet.HHHgldmSmallDependenceLowGrayLevelEmphasis	–0.034413994	0.9947
F	originalngtdmStrength	–0.094911828	0.9916
G	wavelet.LHLglcmImc1	0.014173249	0.9991
H	wavelet.LHLglcmImc2	0.025497865	0.9959
I	wavelet.LHLgldmSmallDependenceEmphasis	–0.047750961	0.9878

ICC, intraclass correlation coefficient.

Table 3.

Model performance

Model	Training set			Validation set
Model	AUC (95% CI)	Specificity	Sensitivity	AUC (95% CI)	Specificity	Sensitivity
Clinical model	0.766 (0.652–0.803)	0.752	0.705	0.583 (0.509–0.625)	0.534	0.553
Radiomics model	0.822 (0.754–0.905)	0.781	0.741	0.800 (0.698–0.895)	0.713	0.684
Combined model	0.869 (0.803–0.918)	0.824	0.813	0.858 (0.773–0.920)	0.806	0.763

AUC, area under the curve; CI, confidence interval.

REFERENCES

1. Wang S, Liu J, Wang S, Zhao H, Ge S, Wang W. Adverse effects of anastomotic leakage on local recurrence and survival after curative anterior resection for rectal cancer: a systematic review and meta-analysis. World J Surg 2017;41:277–84. Article PubMed PDF
2. Yang J, Chen Q, Jindou L, Cheng Y. The influence of anastomotic leakage for rectal cancer oncologic outcome: a systematic review and meta-analysis. J Surg Oncol 2020;121:1283–97. Article PubMed PDF
3. Boyce SA, Harris C, Stevenson A, Lumley J, Clark D. Management of low colorectal anastomotic leakage in the laparoscopic era: more than a decade of experience. Dis Colon Rectum 2017;60:807–14. Article PubMed
4. Frouws MA, Snijders HS, Malm SH, Liefers GJ, Van de Velde CJ, Neijenhuis PA, et al. Clinical relevance of a grading system for anastomotic leakage after low anterior resection: analysis from a national cohort database. Dis Colon Rectum 2017;60:706–13. Article PubMed
5. Abete M, Ronchetti V, Casano A, Pescio G. Anastomotic leakage after traditional surgery of the colon and rectum. Minerva Chir 2003;58:167–74. Italian. PubMed
6. Isohata N, Endo S, Nemoto T, Nemoto D, Aizawa M, Utano K, et al. Risk factors and predictive biomarkers for anastomotic leakage after colorectal cancer surgery with the double stapling technique. J Anus Rectum Colon 2023;7:196–205. Article PubMed PMC
7. Matthiessen P, Hallböök O, Andersson M, Rutegård J, Sjödahl R. Risk factors for anastomotic leakage after anterior resection of the rectum. Colorectal Dis 2004;6:462–9. Article PubMed
8. Alberts JC, Parvaiz A, Moran BJ. Predicting risk and diminishing the consequences of anastomotic dehiscence following rectal resection. Colorectal Dis 2003;5:478–82. Article PubMed
9. Chang D, Zhang Y, Dang C, Zhu K, Li K, Chen D, et al. Prevention of anastomotic leakage after low anterior resection in rectal cancers. Hepatogastroenterology 2010;57:477–81. PubMed
10. El-Ahmar M, Koch F, Ristig M, Lehmann K, Ritz JP. Reconstruction, oversewing, or taking the anastomosis down - which surgical intervention is most potent in the treatment of anastomotic leaks following colorectal resections? Langenbecks Arch Surg 2023;408:266.Article PubMed PDF
11. Floodeen H, Hallböök O, Rutegård J, Sjödahl R, Matthiessen P. Early and late symptomatic anastomotic leakage following low anterior resection of the rectum for cancer: are they different entities? Colorectal Dis 2013;15:334–40. Article PubMed
12. Rahbari NN, Weitz J, Hohenberger W, Heald RJ, Moran B, Ulrich A, et al. Definition and grading of anastomotic leakage following anterior resection of the rectum: a proposal by the International Study Group of Rectal Cancer. Surgery 2010;147:339–51. Article PubMed
13. Hou M, Sun JH. Emerging applications of radiomics in rectal cancer: state of the art and future perspectives. World J Gastroenterol 2021;27:3802–14. Article PubMed PMC
14. Miranda J, Horvat N, Araujo-Filho JA, Albuquerque KS, Charbel C, Trindade BM, et al. The role of radiomics in rectal cancer. J Gastrointest Cancer 2023;54:1158–80. Article PubMed PMC PDF
15. Fang Z, Pu H, Chen XL, Yuan Y, Zhang F, Li H. MRI radiomics signature to predict lymph node metastasis after neoadjuvant chemoradiation therapy in locally advanced rectal cancer. Abdom Radiol (NY) 2023;48:2270–83. Article PubMed PDF
16. Li ZY, Wang XD, Li M, Liu XJ, Ye Z, Song B, et al. Multi-modal radiomics model to predict treatment response to neoadjuvant chemotherapy for locally advanced rectal cancer. World J Gastroenterol 2020;26:2388–402. Article PubMed PMC
17. Collewet G, Strzelecki M, Mariette F. Influence of MRI acquisition protocols and image intensity normalization methods on texture classification. Magn Reson Imaging 2004;22:81–91. Article PubMed
18. Tustison NJ, Avants BB, Cook PA, Zheng Y, Egan A, Yushkevich PA, et al. N4ITK: improved N3 bias correction. IEEE Trans Med Imaging 2010;29:1310–20. Article PubMed PMC
19. Depeursinge A, Foncubierta-Rodriguez A, Van De Ville D, Müller H. Three-dimensional solid texture analysis in biomedical imaging: review and opportunities. Med Image Anal 2014;18:176–96. Article PubMed
20. Alhamzawi R, Ali HT. The Bayesian adaptive lasso regression. Math Biosci 2018;303:75–82. Article PubMed
21. Kostov GG, Dimov RS, Almeida DD. Risk factors for anastomotic leakage after low anterior resection. Folia Med (Plovdiv) 2020;62:290–4. Article PubMed PDF
22. Bosset JF, Collette L, Calais G, Mineur L, Maingon P, Radosevic-Jelic L, et al. Chemotherapy with preoperative radiotherapy in rectal cancer. N Engl J Med 2006;355:1114–23. Article PubMed
23. Peeters KC, van de Velde CJ, Leer JW, Martijn H, Junggeburt JM, Kranenbarg EK, et al. Late side effects of short-course preoperative radiotherapy combined with total mesorectal excision for rectal cancer: increased bowel dysfunction in irradiated patients: a Dutch colorectal cancer group study. J Clin Oncol 2005;23:6199–206. Article PubMed
24. Yang J, Luo Y, Tian T, Dong P, Fu Z. Effects of neoadjuvant radiotherapy on postoperative complications in rectal cancer: a meta-analysis. J Oncol 2022;2022:8197701.Article PubMed PMC PDF
25. Li Y, Hu G, Zhang J, Qiu W, Mei S, Wang X, et al. Nomogram for predicting the probability of rectal anastomotic re-leakage after stoma closure: a retrospective study. BMC Cancer 2024;24:834.Article PubMed PMC PDF
26. Matthiessen P, Hallböök O, Rutegård J, Simert G, Sjödahl R. Defunctioning stoma reduces symptomatic anastomotic leakage after low anterior resection of the rectum for cancer: a randomized multicenter trial. Ann Surg 2007;246:207–14. Article PubMed PMC
27. Hüser N, Michalski CW, Erkan M, Schuster T, Rosenberg R, Kleeff J, et al. Systematic review and meta-analysis of the role of defunctioning stoma in low rectal cancer surgery. Ann Surg 2008;248:52–60. Article PubMed
28. Daams F, Luyer M, Lange JF. Colorectal anastomotic leakage: aspects of prevention, detection and treatment. World J Gastroenterol 2013;19:2293–7. Article PubMed PMC
29. Kingham TP, Pachter HL. Colonic anastomotic leak: risk factors, diagnosis, and treatment. J Am Coll Surg 2009;208:269–78. Article PubMed
30. Gao J, Gu X, Pang M, Zhang H, Lian Y, Zhou L, et al. Risk factors for anastomotic leak and postoperative morbidity after right hemicolectomy for colon cancer: results from a prospective, multi-centre, snapshot study in China. Br J Surg 2024;111:znad316.Article PubMed
31. McKenna NP, Bews KA, Cima RR, Crowson CS, Habermann EB. Validation of a left-sided colectomy anastomotic leak risk score and assessment of diversion practices. Am J Surg 2022;224:971–8. Article PubMed
32. Wada T, Kawada K, Hoshino N, Inamoto S, Yoshitomi M, Hida K, et al. The effects of intraoperative ICG fluorescence angiography in laparoscopic low anterior resection: a propensity score-matched study. Int J Clin Oncol 2019;24:394–402. Article PubMed PDF
33. Fernandes MC, Gollub MJ, Brown G. The importance of MRI for rectal cancer evaluation. Surg Oncol 2022;43:101739.Article PubMed
34. Inchingolo R, Maino C, Cannella R, Vernuccio F, Cortese F, Dezio M, et al. Radiomics in colorectal cancer patients. World J Gastroenterol 2023;29:2888–904. Article PubMed PMC
35. Allison AS, Bloor C, Faux W, Arumugam P, Widdison A, Lloyd-Davies E, et al. The angiographic anatomy of the small arteries and their collaterals in colorectal resections: some insights into anastomotic perfusion. Ann Surg 2010;251:1092–7. Article PubMed
36. Vermeer TA, Orsini RG, Daams F, Nieuwenhuijzen GA, Rutten HJ. Anastomotic leakage and presacral abscess formation after locally advanced rectal cancer surgery: incidence, risk factors and treatment. Eur J Surg Oncol 2014;40:1502–9. Article PubMed
37. Skawran SM, Kambakamba P, Baessler B, von Spiczak J, Kupka M, Müller PC, et al. Can magnetic resonance imaging radiomics of the pancreas predict postoperative pancreatic fistula? Eur J Radiol 2021;140:109733.Article PubMed
38. Zhao Y, Li B, Sun Y, Liu Q, Cao Q, Li T, et al. Risk factors and preventive measures for anastomotic leak in colorectal cancer. Technol Cancer Res Treat 2022;21:15330338221118983.Article PubMed PMC PDF

Figure & Data

References

Citations

Citations to this article as recorded by

Cite this Article

Cite this Article: export Copy Download Format; Close

Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:

RIS — For EndNote, ProCite, RefWorks, and most other reference management software
BibTeX — For JabRef, BibDesk, and other BibTeX-specific software

Include:

Citation for the content below
Citation and abstract for the content below

Preoperative magnetic resonance imaging–based radiomics nomogram model for predicting postoperative anastomotic leakage in colorectal cancer

Ann Coloproctol. 2025;41(6):554-564. Published online December 26, 2025

DOI: https://doi.org/10.3393/ac.2025.00689.0098

XML Download

Figure

Preoperative magnetic resonance imaging–based radiomics nomogram model for predicting postoperative anastomotic leakage in colorectal cancer

Fig. 1. Study flowchart. AL, anastomotic leakage; MRI, magnetic resonance imaging; ROI, region of interest; Rad score, radiomic score.

Fig. 2. Magnetic resonance imaging (MRI) of rectal tumors and regions of interest from a 49-year-old female patient in the training set. A mass (arrows) can be seen in the rectum in (A) T1-weighted MRI scan and (B) fat-saturated T2-weighted MRI scan. Manual segmentation of the mass in (C) T1-weighted MRI scan and (D) fat-saturated T2-weighted MRI scan.

Fig. 3. Selection of radiomics features via the least absolute shrinkage and selection operator (LASSO) regression algorithm. (A) Tuning parameter (λ) selection in the LASSO model using 10-fold cross-validation and the 1–standard error criterion. The optimal λ value is indicated by the right vertical dotted line; λ=0.0065 was selected. (B) LASSO coefficient profiles of 1,356 radiomics features. A coefficient profile plot was generated against the log λ value using 10-fold cross-validation. Nine radiomics features with nonzero coefficients were ultimately selected. These included 5 gray-level co-occurrence matrix (GLCM) features, 3 gray-level dependence matrix (GLDM) features, and 1 neighborhood gray-tone difference matrix (NGTDM) feature.

Fig. 4. Radiomics nomogram development and receiver operating characteristic curve analysis. (A) Age, tumor distance from the anal verge, neoadjuvant therapy, and the radiomic score (Rad score) were used to construct the radiomics nomogram. (B) The predictive performance of the clinical model in both the training and validation sets. (C) The predictive performance of the radiomics model in both the training and validation sets. (D) The predictive performance of the radiomics/nomogram combined model in both the training and validation sets. AUC, area under the curve.

Fig. 5. Decision curve analysis for the 3 models. The y-axis represents net benefit, and the x-axis denotes threshold probability. The green line, red dashed line, and blue dashed line correspond to the clinical model, radiomics-only model, and radiomics nomogram combined model, respectively. Across the full range of threshold probabilities, the radiomics nomogram combined model demonstrated the greatest overall net clinical benefit for predicting anastomotic leakage.

Fig. 1.

Fig. 2.

Fig. 3.

Fig. 4.

Fig. 5.

Preoperative magnetic resonance imaging–based radiomics nomogram model for predicting postoperative anastomotic leakage in colorectal cancer

Characteristic	Total (n=146)	Without AL (n=135)	With AL (n=11)	OR (95% CI)	P-value
Age (yr)	64.0 (60.0–68.8)	63.0 (59.0–68.0)	67.0 (65.0–70.5)	0.952 (0.281–3.268)^a	0.113
Sex				1.178 (0.336–4.059)	0.790
Male	74 (50.7)	68 (50.4)	6 (54.5)
Female	72 (49.3)	67 (49.6)	5 (45.5)
Body mass index (kg/m²)	22.79 (21.22–24.69)	22.78 (21.16–24.68)	23.33 (21.25–24.53)	-	0.784
Tumor distance from anal verge (cm)	7.65 (6.10–9.50)	7.80 (6.20–9.55)	6.90 (5.05–7.75)	0.621 (0.167–2.199)^a	0.134
Albumin level (g/L)	40.08±4.26	40.08±4.38	39.99±2.60	-	0.921
Neoadjuvant therapy				4.284 (1.203–15.266)	0.046^*
No	119 (81.5)	113 (83.7)	6 (54.5)
Yes	27 (18.5)	22 (16.3)	5 (45.5)
Combined diabetes				1.918 (0.384–9.802)	0.768
No	130 (89.0)	121 (89.6)	9 (81.8)
Yes	16 (11.0)	14 (10.4)	2 (18.2)
Protective ostomy				3.492 (0.928–13.074)	0.073
No	123 (84.2)	116 (85.9)	7 (63.6)
Yes	23 (15.8)	19 (14.1)	4 (36.4)
Operation type				1.127 (0.134–9.635)	0.580
Open surgery	12 (8.2)	11 (8.1)	1 (9.1)
Endoscopic surgery	134 (91.8)	124 (91.9)	10 (90.9)

Variable	Feature name	Coefficient	ICC
A	wavelet.LLHglcmDifferenceVariance	0.043047801	0.9962
B	wavelet.LHLglcmJointEnergy	–0.000821006	0.9895
C	wavelet.HHHglcmImc1	–0.007114313	0.9881
D	wavelet.HHHgldmSmallDependenceHighGrayLevelEmphasis	–0.018299704	0.9873
E	wavelet.HHHgldmSmallDependenceLowGrayLevelEmphasis	–0.034413994	0.9947
F	originalngtdmStrength	–0.094911828	0.9916
G	wavelet.LHLglcmImc1	0.014173249	0.9991
H	wavelet.LHLglcmImc2	0.025497865	0.9959
I	wavelet.LHLgldmSmallDependenceEmphasis	–0.047750961	0.9878

Model	Training set			Validation set
Model	AUC (95% CI)	Specificity	Sensitivity	AUC (95% CI)	Specificity	Sensitivity
Clinical model	0.766 (0.652–0.803)	0.752	0.705	0.583 (0.509–0.625)	0.534	0.553
Radiomics model	0.822 (0.754–0.905)	0.781	0.741	0.800 (0.698–0.895)	0.713	0.684
Combined model	0.869 (0.803–0.918)	0.824	0.813	0.858 (0.773–0.920)	0.806	0.763

Table 1. Clinical characteristics of patients with and without AL

Values are presented as median (interquartile range), number (%), or mean±standard deviation.

AL, anastomotic leakage; OR, odds ratio; CI, confidence interval.

Calculated by dichotomizing age (≥65 years) or tumor distance (>7 cm).

P<0.05.

Table 2. Radiomics feature selection results

ICC, intraclass correlation coefficient.

Table 3. Model performance

AUC, area under the curve; CI, confidence interval.