Purpose To develop and validate a CT-based radiomics model for differentiating primary gastric lymphoma (PGL) from Borrmann type IV gastric cancer (GC). Materials and methods A total of 136 patients with pathologically confirmed PGL (n = 56) and Borrmann type IV GC (n = 80) were retrospectively enrolled between January 2016 and May 2022. The cohort was randomly partitioned into a training set (n = 95) and a testing set (n = 41) at a 7:3 ratio. Radiomics features were extracted from unenhanced, arterial, venous, double-phase (arterial + venous), and three-phase (unenhanced + arterial + venous) CT images. After feature selection using the Least Absolute Shrinkage and Selection Operator, radiomics models were constructed via logistic regression. A clinical-radiomics model was developed through multivariate analysis. The models were evaluated using Receiver Operating Characteristic (ROC) curves, calibration curves with the Hosmer-Lemeshow test, and decision Curve Analysis (DCA) for clinical net benefit. Results Clinical model comprised of high-enhanced serosa sign, normalized CT value on venous phase, and perigastric fat infiltration showed good performance with AUCs of 0.902 (training set) and 0.878 (testing set). Among the radiomics models, the three-phase model outperformed others (AUC: 0.871 training, 0.865 testing). The clinical-radiomics combined model further improved discriminatory performance, achieving AUCs of 0.960 and 0.932 in the training and testing sets, respectively. DCA confirmed that the combined model provided the highest clinical net benefit. Conclusion Clinical-radiomics model incorporating three-phase radiomics signatures and CT findings achieved satisfactory performance for differentiating PGL from Borrmann type IV GC, serving as a reliable non-invasive tool for clinical decision-making.

To evaluate the potential of dual-energy CT (DECT) quantitative parameters and clinical characteristics in predicting pathological nodal (pN) stage in colon cancer. A total of 205 patients with pathologically confirmed colon cancer who underwent DECT were retrospectively enrolled and were randomly divided into training (n = 148) and test sets (n = 57) at a 7:3 ratio. The DECT quantitative parameters, including extracellular volume fraction (ECV), clinical characteristics, and Node Reporting and Data System (Node-RADS), were analyzed. Univariable and multivariable logistic regression analysis were used to construct the DECT model, Clinical_model, and Combined model. The diagnostic performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC). Carbohydrate antigen 125 (CA125), carbohydrate antigen 242 (CA242), dual-energy index in venous phase (DEI_V), and ECV were independent factors for predicting pN+ (all p < 0.05). The Combined model (features: CA125, CA242, ECV, and DEI_V) showed significantly higher AUC than Node-RADS (0.845 vs. 0.727, p = 0.032), Clinical_model (features: CA125 and CA242) (0.845 vs. 0.692, p < 0.001), and DECT model (features: ECV and DEI_V) (0.845 vs. 0.774, p = 0.011) in the training set. The Combined model also demonstrated the highest AUC (0.849) in the test set. But there were no significant differences in AUC between the Combined model and Node-RADS (p = 0.158) in the test set. The combination of DECT quantitative parameters and clinical characteristics showed improved diagnostic performance in predicting pN stage in colon cancer. Question Does the combination of dual-energy CT (DECT) quantitative parameters and clinical characteristics predict pathological nodal (pN) stage in colon cancer? Findings The Combined model showed the highest AUC for predicting pN stage in the training set, but did not show better performance than Node-RADS in the test set. Clinical relevance The combination of DECT quantitative parameters and clinical characteristics may be useful for predicting pN stage in colon cancer as a noninvasive method.

RATIONALE AND OBJECTIVES:To assess the value of quantitative dual-energy CT (DECT) parameters for predicting resectable rectal cancer recurrence. MATERIALS AND METHODS:This retrospective study included 264 consecutive patients (182 in training cohort and 82 in validation cohort) with resectable rectal cancer who underwent upfront surgery without neoadjuvant therapy and preoperative contrast-enhanced CT at two centers between May 2019 and July 2022. DECT quantitative parameters, including iodine concentration (IC), normalized iodine concentration (NIC), electron density (Rho), effective atomic number (Z), spectral slope (K) and extracellular volume fraction (ECV) derived from both arterial and venous phases, were analysed. Univariate and multivariate Cox proportional hazards models were used to identify independent risk predictors of recurrence. A combined model was established and evaluated using the C-index, time-dependent ROC curves, calibration, decision curve analysis (DCA). The Kaplan-Meier survival curves were compared using the log-rank test. RESULTS:Recurrence occurred in 47 (25.8%) training cases and 21 (25.6%) in validation cases. The extracellular volume at venous phase (ECVV) (HR=1.82, 95%CI: 1.45-2.28, p<0.001), extramural venous invasion (EMVI) (HR=3.37, 95%CI: 1.83-6.20, p<0.001), carcinoembryonic antigen (CEA) (HR=1.87, 95%CI: 1.02-3.44, p=0.042), and carbohydrate antigen 19-9 (CA19-9) (HR=2.49, 95%CI: 1.31-4.74, p=0.005) were verified as significant predictors of recurrence. The combined model yielded a C-index of 0.792 (95% CI: 0.658-0.894) for predicting 3-year recurrence. Kaplan-Meier analysis showed significant differences in recurrence-free survival between the model-defined high- and low-risk groups (log-rank p values ranging from <0.001 to 0.020). CONCLUSION:Combining DECT-derived ECVV, EMVI, CEA, and CA19-9 demonstrates improved predictive discrimination for predicting rectal cancer recurrence.

To investigate the impact of different ROI delineation strategies on the utility of Time-dependent diffusion MRI (TDD-MRI)-derived microstructural parameters for distinguishing adenocarcinoma (AC) from squamous cell carcinoma (SCC). In this prospective study, patients with pathologically confirmed cervical cancer who underwent TDD-MRI between August 2024 and June 2025 were enrolled. Three region-of-interest (ROI) delineation strategies were used: small solid ROI (ROIs), single-slice ROI (ROIss), and whole-volume ROI (ROIwt). Microstructural parameters including intracellular volume fraction (fin), extracellular diffusion coefficient (Dex), diameter, and cellularity, along with three apparent diffusion coefficient (ADC) measures were investigated. The intraclass correlation coefficient (ICC) was used to determine inter- and intra-readers reproducibility. Logistic regression was performed to predict pathological subtypes. Diagnostic performance was quantified by area under the receiver operating characteristic curve (AUC). Pearson’s correlation analysis validated the relationship between TDD-MRI parameters and pathological measurements. A total of 92 women (79 with SCC and 13 with AC) with cervical cancer (mean age, 55.5 ± 10.4 years) were included. For TDD-MRI-derived microstructural parameters and ADCs, intra- and inter-reader ICCs were 0.910–0.971 and 0.904–0.981, respectively. The ROIss strategy showed significant differences between AC and SCC in four parameters (all P < 0.05); ROIwt showed significance only for cellularity, and ROIs showed none. The ROIss-derived parameters achieved relatively favorable performance for distinguishing histologic subtypes (AUC = 0.821). The combined Dex, cellularity, and ADC40Hz model based on the ROIss approach achieved an AUC of 0.917. TDD-MRI–derived parameters showed correlations with histopathologic measurements (n = 15; r = 0.698–0.794; P < 0.01). TDD-MRI–based microstructural parameters derived from the ROIss show promise as effective imaging biomarkers to assist in differentiating histologic subtypes in cervical cancer.

Abstract Objective To evaluate the value of time-dependent diffusion MRI (td-dMRI) derived microstructural parameters for predicting lymphovascular invasion (LVI) in rectal cancer. Materials and methods Eighty-four resectable rectal cancer patients (stage T1, T2, T3a, T3b, and T4a) who underwent preoperative td-dMRI between March 2023 and June 2025 without neoadjuvant therapy were enrolled. Manual segmentation of tumors was performed by an experienced radiologist on each tumor’s largest cross-sectional area. Microstructural parameters (intracellular volume fraction (ICVF), cell diameter, extracellular diffusivity and cellularity) were fitted using the limited spectrally edited diffusion model implemented in MATLAB (MathWorks, Inc.). Apparent diffusion coefficient (ADC) values at different diffusion times, relative ADC, ADC ratio, and MRI-reported extramural vascular invasion (EMVI) were also evaluated. Mann–Whitney U test was used to evaluate parameter differences between LVI-positive and LVI-negative. Logistic regression and receiver operating characteristic (ROC) curves (with DeLong test) were used to identify predictors of LVI and diagnostic performance. Results Of 84 participants (median age, 66 years; IQR, 60–70 years; 50 male), 30 were LVI-positive and 54 LVI-negative. ICVF, cell diameter, and cellularity were significantly higher in LVI-positive cases (all p < 0.05). MRI-EMVI (OR = 3.251), ICVF (OR = 8.137), and cellularity (OR = 1.159) were independent risk factors of LVI. The combined model integrating MRI-reported EMVI, cellularity, and ICVF achieved an area under the ROC curve (AUC) of 0.860, outperforming individual parameters including MRI-reported EMVI (AUC = 0.730), ICVF (AUC = 0.815), cellularity (AUC = 0.792) and ADC measurements (AUC = 0.631–0.710) (all p < 0.05). Conclusion td-dMRI-derived parameters, especially ICVF and cellularity combined with MRI-reported EMVI, show potential as noninvasive biomarkers for LVI prediction in rectal cancer. Critical relevance statement This study develops a preoperative time-dependent diffusion MRI-based microstructure parameters model that diagnoses and predicts lymphovascular invasion of rectal cancer, improving diagnostic accuracy and advancing personalized treatment strategies in clinical radiology. Key Points The time-dependent diffusion MRI-derived microstructural parameters model and clinical data for predicting lymphovascular invasion in rectal cancer. The combined model outperforms single-modality models with 0.860 AUC and 96.3% specificity. The combined model provides a noninvasive, reliable tool for personalized lymphovascular invasion diagnosis and treatment planning. Graphical Abstract

To investigate the clinical value of Time-dependent diffusion MRI (td-dMRI) quantitative parameters in differentiating between rectal neuroendocrine neoplasms (rNEN) and rectal adenocarcinoma (RAC) and in distinguishing between high and low Ki-67 expression in RAC. This two-center study prospectively enrolled 90 patients with rectal tumors who underwent td-dMRI (January 2024 to March 2025), including 85 with RAC (development cohort, n = 61, validation cohort, n = 24) and 5 with rNEN. The td-dMRI-derived microstructural parameters were estimated using the IMPULSED model, and apparent diffusion coefficient (ADC) values were measured at different diffusion times. Firth’s logistic regression was performed for rNEN-associated parameter selection, while standard logistic regression identified independent predictors to build a combined model for high Ki-67 stratification. Receiver operating characteristic analysis evaluated diagnostic performance. The td-dMRI-derived microstructural parameters were validated against histopathologic measurements. Significant differences in several td-dMRI parameters were observed between rNENs and RACs, as well as between groups with high and low Ki-67 expression. In the small rNEN cohort, td-dMRI parameters showed promising preliminary diagnostic performance in distinguishing rNEN from RAC (AUC = 0.882). For predicting high Ki-67 expression in RAC, the combined model yielded an AUC of 0.916 in the development cohort and 0.844 in the validation cohort. Microstructural parameters showed strong correlations with histopathology: cell diameter, cellularity, and intracellular volume fraction reached Pearson correlation coefficients (r) of 0.808, 0.773, and 0.765, respectively (all p < 0.001). Quantitative td-dMRI parameters may serve as a noninvasive tool for evaluating rectal tumor histological types (rNEN vs. RAC) and predicting Ki-67 expression in RAC.

OBJECTIVES:To evaluate if preoperative imaging features from CT at mass-forming intrahepatic cholangiocarcinoma (MF-iCCA) are related to histo-pathologic factors, and to evaluate if those associations can be used to construct an imaging score to predict postoperative recurrence. MATERIAL AND METHODS:Consecutive patients with MF-iCCA who underwent preoperative contrast-enhanced CT at two centers between September 2017 and December 2025 were retrospectively reviewed by two radiologists. After independent annotation of 16 imaging features, univariate and multivariate regression analyses were performed to identify independent predictors for high-risk histo-pathologic factors (microvascular invasion, LNM [lymph node metastasis], or poor tumor differentiation). A risk scoring system was developed and used to predict very early recurrence (VER) and early recurrence (ER). RESULTS:In total 152 patients (median age, 62 years [IQR, 54-69 years]; 57 women) were included from two medical centers (training cohort: n = 109; external validation cohort: n = 43). Peritumoral enhancement at arterial phase had the strongest association with high-risk histo-pathologic factors, followed by multinodularity, intrahepatic bile duct dilation, and CT-reported LNM (P < 0.05, all). The four features were used to construct the risk scoring system. Area under the curve (AUC) of VER-weighted and ER-weighted risk scoring system for high-risk histo-pathologic factors was 0.827 and 0.829 in external validation cohort, respectively. The risk scoring system based on high-risk histo-pathologic factors showed superior prognostic performance for VER (AUC, 0.870 [95% CI: 0.761, 0.978]) and ER (AUC, 0.860 [95% CI: 0.737, 0.983]) in external validation cohort. CONCLUSION:Recurrence of MF-iCCA can be predicted by evaluating preoperative imaging features at CT.

Background Lymph node metastasis (LNM) is a poor prognostic predictor and is highly correlated with local recurrence in rectal cancer patients. Objective To investigate the value of radiomics from dual-energy CT-derived iodine maps for the preoperative prediction of LNM in rectal cancer patients. Methods A total of 176 patients were enrolled in this study (training group, n = 123; validation group, n = 53). A radiomic signature was constructed via support vector machine (SVM) modeling. Seven models, including a clinical feature model (Model 1), an arterial model (Model 2), a venous model (Model 3), an arterial-venous model (Model 4), an arterial–clinical model (Model 5), a venous-clinical model (Model 6) and an arterial–venous–clinical model (Model 7), were established via logistic regression modeling. Diagnostic performance was assessed via receiver operating characteristic (ROC) curves. Results Tumor location and carcinoembryonic antigen levels were used to construct Model 1 (training group, AUC [area under the ROC curve] = 0.721, 95% CI [confidence intervals], 0.630–0.813; validation group, AUC = 0.729, 95% CI, 0.593–0.865). Model 6 and Model 7 further improved the discriminatory performance in the training (AUC = 0.850 and 0.869, 95% CI, 0.782–0.919 and 0.807–0.932, respectively; p = 0.250) and validation groups (AUC = 0.780 and 0.716, 95% CI, 0.653–0.906 and 0.576–0.856, respectively; p = 0.115). Moreover, decision curve analysis revealed a greater net benefit with Model 6. Conclusions The combination of radiomic features based on dual-energy CT-derived iodine maps and clinical features provides better diagnostic performance for predicting LNM in rectal cancer patients.

This study evaluates the potential of dual-energy CT (DECT) for preoperative prediction of tumor budding (TB) and lymphovascular invasion (LVI) in colon cancer. This prospective study enrolled 153 patients (mean age 61.33 years ± 0.88) with pathologically confirmed colon cancer. All participants underwent arterial and venous phase DECT scans within one week before surgery. Two radiologists independently analyzed the images, assessing tumor location, clinical N stage (cN stage), iodine concentration (IC), effective atomic number (Z-eff), and dual-energy index (DEI). The normalized iodine concentration (nIC) was obtained by comparing measured IC to the abdominal aortic IC. Logistic regression identified independent risk factors for high-grade TB and LVI positivity. The Akaike Information Criterion guided model selection, and the area under the curve (AUC) was calculated. Bootstrap validation with 1000 iterations was used for internal validation. Tumor location and cN stage were identified as independent risk factors for high-grade TB, and nICA tumor and cN stage for LVI positivity. The optimal model for predicting high-grade TB included tumor location, cN stage, and DEIV tumor, with an AUC of 0.763 (sensitivity: 75.0

Objective To investigate the utility values of time-dependent diffusion MRI (td-dMRI) in predicting differentiation degree and Ki-67 expression in rectal cancer. Methods Seventy-three resectable rectal cancer patients who underwent td-dMRI examination were consecutively enrolled. Intracellular volume fraction (ICVF), cell diameter, extracellular diffusivity (Dex), cellularity, apparent diffusion coefficient (ADC) values at different diffusion times, relative ADC value, and ADC ratio were investigated. Intraclass correlation coefficients and Bland-Altman plots were used to determine repeatability. Mann-Whitney U test, logistic regression analysis, receiver operating characteristic (ROC), and the Delong’s test were used for parameter differences evaluation, independent risk factor identifying, diagnostic ability assessing, and the area under the ROC curve (AUC) comparations for differentiation degree and Ki-67 expressions, respectively. Results The cellularity, ADCPGSE, and ADC40HZ in the low differentiation degree group were significantly higher than moderate to high differentiation degree group (all P < 0.05). While, ICVF was significantly lower in low differentiation group. Tumor length, ICVF, cellularity, ADCPGSE and ADC40HZ were independent risk factors for low differentiation degree. The combined model achieved the highest diagnostic performance, with an AUC of 0.831 (95 %CI: 0.73, 0.93) for differentiation. For Ki-67 expression, ICVF in the high Ki-67 expression group was lower than that of low Ki-67 expression group (P = 0.001). MR-reported lymph node stage, extramural vascular invasion (EMVI), and ICVF were independent clinical risk factors for predicting high Ki-67 expression. The diagnostic ability of combined indicators reached an AUC of 0.820 (95 %CI: 0.71, 0.93) surpassed the individual of ICVF (AUC = 0.750, 95 %CI: 0.62, 0.88, P < 0.01). Conclusion Td-dMRI-derived microstructural parameters may provide an alternative form of non-invasive imaging marker of differentiation degree and Ki-67 expression in rectal cancer and provide valuable information for treatment decisions.

To determine whether quantitative parameters derived from dual-energy CT (DECT) could predict prognosis in patients with resectable rectal cancer (RC). One hundred and thirty-four patients (recurrence/distant metastasis group, n = 36; non-metastasis/non-recurrence group, n = 98) with RC who underwent radical resection and DECT were retrospectively included. DECT quantitative parameters, including iodine concentration (IC), normalized iodine concentration (NIC), electron density (Rho), effective atomic number (Zeff), dual-energy index (DEI), the slope of the spectral Hounsfield unit curve (λHU) on arterial and venous phase images. Univariate and multivariate Cox proportional hazards models were employed to identify independent risk factors of prognosis. The area under the receiver operating characteristic curve (AUC) was used to assess the performance. Disease-free survival (DFS) curves were constructed using the Kaplan–Meier method. Patients in the metastasis/recurrence group had higher Rho in arterial phase (A-Rho), NIC in venous phase (V-NIC), Rho in venous phase (V-Rho), Zeff in venous phase (V-Zeff), λHU in venous phase (V-λHU), pT stage, pN stage, serum carcinoembryonic antigen (CEA), carbohydrate antigen-199 levels and more frequent in extramural venous invasion than those in non-metastasis/non-recurrence group (all p < 0.05). V-NIC, V-λHU, and CEA were independent risk factors of recurrence/distant metastasis (all p < 0.05). The AUC of combined indicator integrating three independent risk factors achieved the best diagnostic performance (AUC = 0.900). In stratified survival analysis, patients with high V-NIC, V-λHU, and CEA had lower 3-year DFS than those with low V-NIC, V-λHU, and CEA. Combining V-NIC, V-λHU, and CEA could be used to noninvasively predict prognosis in resectable RC. Question TNM staging fails to accurately prognosticate; can quantitative parameters derived from dual-energy CT predict prognosis in patients with resectable rectal cancer? Findings Normalized iodine concentration (V-NIC) and the slope of the spectral Hounsfield unit curve in venous phase (V-λHU), and carcinoembryonic antigen (CEA) are independent risk factors for recurrence/metastasis. Clinical relevance The combined indicator integrating V-NIC, V-λHU, and CEA could predict 3-year disease-free survival in patients with resectable rectal cancer and could aid in postoperative survival risk stratification to guide personalized treatment.

To explore intravoxel incoherent motion (IVIM) for evaluation of the perineural invasion (PNI) status and survival in patients with rectal cancer. The true diffusion coefficient (D), pseudo-diffusion coefficient (D*), and microvascular volume fraction (f) were recorded together with histogram metrics. Differences in IVIM histogram metrics between the PNI-positive group and the PNI-negative group were analyzed. Univariable and multivariable logistic regression analysis were used for model construction. The area under the receiver operating characteristic curve (AUC) was used to assess the diagnostic performance of the models. Histopathology was used as the PNI endpoint. Kaplan–Meier curve analysis was employed to estimate the disease-free survival (DFS) and overall survival (OS) of patients. A total of 175 patients were retrospectively enrolled in this study. Multivariable logistic regression analysis showed that higher D_median (odds ratio (OR) = 2.036, p = 0.003) and D_min (OR = 1.479, p = 0.002) and lower f_SD (OR = 0.697, p < 0.001) and f_kurtosis (OR = 0.485, p < 0.001) were independently associated with PNI-positive. The combined model showed the best performance in predicting the PNI status with AUCs, sensitivity, specificity, and accuracy of 0.885, 81.67

To determine whether intratumoral and peritumoral radiomics derived from dual-phase contrast-enhanced CT imaging could predict lymph node metastasis (LNM) in gastric cancer. Patients with gastric cancer from January 2017 to January 2022 were retrospectively collected and were randomly divided into training cohort (n = 287) and test cohort (n = 121) with a ratio of 7: 3. Clinical features and traditional radiological features were analyzed to construct clinical model. Radiomics features based on intratumoral (ITV) and peritumoral volumetric (PTV) regions of the tumor were extracted and screened to construct radiomics models. Clinical-radiomics combined model was constructed by the most predictive radiomics features and clinical independent predictors. The correlation between LNM predicted by the best model and 2-year disease-free survival (DFS) was evaluated by the Kaplan-Meier analysis. CT-LNM and CT-T stage were independent predictors of LNM. Compared with other radiomics models, ITV + PTV on atrial and venous phase (ITV + PTV-AP + VP) radiomics model presented moderate AUCs of 0.679 and 0.670 in the training cohort and validation cohort, respectively. Among the models, clinical-radiomics combined model achieved the highest AUC of 0.894 and 0.872 in the training and test cohorts, and 0.744 and 0.784 in the T1-2 and T3-4 subgroups, respectively. Clinical-radiomics combined model based LNM could stratify patients into high-risk and low-risk groups, and 2-year DFS of high-risk group was significantly lower than that of low-risk group (p < 0.001). Clinical-radiomics combined model integrating CT-LNM, CT-T stage, and ITV-PTV-AP + VP radiomics features could predict LNM, and this combined model based LNM was associated with 2-year DFS.

To evaluate the value of noise-optimized virtual monoenergetic image (VMI+) in dual-energy CT (DECT) in predicting tumor budding (TB) grade in colon cancer. Seventy-six patients with pathologically confirmed colon cancer who underwent contrast-enhanced DECT were retrospectively enrolled and were divided into low/intermediate-grade TB (n = 52) and high-grade TB groups (n = 24). The contrast-to-noise ratio (CNR), overall image quality, and lesion delineation were evaluated on VMI+ (40−0 keV with an interval of 10 keV). The DECT quantitative parameters were analyzed, including attenuation of VMI+, iodine concentration (IC), normalized IC (NIC), electron density (Rho), and effective atomic number (Zeff). The diagnostic performance in differentiating TB grade in colon cancer was evaluated using the area under the curve (AUC). 40 keV, 50 keV, and 60 keV showed good diagnostic performance in differentiating TB grade (AUC: 0.825, 0.833, and 0.843; sensitivity: 0.708, 0.708, and 0.750; specificity: 0.904, 0.904, and 0.846; cutoff value: 179.5 HU, 129.9 HU, and 101.2 HU) and had significantly higher AUC than IC (0.770), NIC (0.647), Rho (0.642), and Zeff (0.785) (all P < 0.05). 40 keV had the best lesion delineation and provided significantly higher CNR than other VMI + levels, while 60 keV provided better overall image quality than other VMI + levels (all corrected P < 0.05). The DECT-derived low-keV VMI+ (40 keV, 50 keV, and 60 keV) provided better diagnostic performance in differentiating TB grade in colon cancer. 40 keV showed better CNR and lesion delineation, while 60 keV provided better overall image quality.

To determine the value of intravoxel incoherent motion (IVIM) for quantitative tumor budding (TB) evaluation and prognostic stratification in patients with rectal cancer (RC). This study enrolled 189 RC patients (training set 148, validation set 41) who underwent IVIM and were subsequently treated surgically within 2 weeks between January 2022 and April 2023. Hematoxylin-eosin staining was used for TB scoring. IVIM metrics were calculated on MRI images using biexponential fitting and histogram analysis. Differences in IVIM histogram metrics between the low-intermediate grade budding (Bd 1 + 2) and the high-grade budding (Bd 3) were analyzed. Multivariate logistic regression analysis was used to build the Combined model. The area under the receiver operating characteristic curve (AUC) was used to assess the diagnostic performance of the IVIM histogram metrics and the Combined model. Kaplan-Meier analysis was employed to estimate disease-free and overall survival rates for patients. Multivariate logistic analysis showed that the D_25th percentile, D_75th percentile, D_90th percentile, and D_95th percentile were independent predictors of Bd 3 (all p < 0.05). The Combined model incorporating these four factors had the best diagnostic performance, with the AUC, sensitivity, and specificity of 0.852, 73.02

This study aims to compare, select, and investigate MRI-based multiregional radiomics model to predict pathologic complete response (pCR) in Locally advanced rectal cancer (LARC) patients after neoadjuvant chemoradiotherapy (nCRT). This retrospective study included 245 patients who underwent rectal MRI examination before nCRT were recruited and split into training (hospital 1, n = 177) and external validation cohort (hospital 2, n = 68). Pretreatment T2WI and ADC images were used to manually delineate volumetric region of interest. Intratumoral, peritumoral-2 mm, peritumoral-3 mm, peritumoral-5 mm, and peritumoral-mesorectal fat (MRF) radiomics features were extracted. Clinical model was built based on clinical and MRI features. Diagnosis performance was compared among models. 3-year recurrence-free survival (RFS) was evaluated by Kaplan-Meier curve. cN stage (odds ratio = 2.62, 95

BackgroundIn recent years, there has been significant research interest in immunotherapy for colorectal cancer (CRC). Specifically, immunotherapy has emerged as the primary treatment for patients with mismatch repair gene defects (dMMR) or microsatellite highly unstable (MSI-H) who have colorectal cancer. Yet, there is currently no data to support the practicality and safety of neoadjuvant immunotherapy for colorectal cancer with dMMR or MSI-H. Therefore, a study was conducted to identify the postoperative pathology, safety profile, and imaging features of patients with dMMR or MSI-H CRC following neoadjuvant immunotherapy.MethodsThe retrospective study was carried out on patients with locally advanced or metastatic CRC who received immunotherapy at Sichuan Cancer Hospital, with approval from the hospital’s ethics committee. The study aimed to assess the short-term effectiveness of immunotherapy by focusing on pathological complete response (pCR) as the primary outcome, while also considering secondary endpoints such as objective response rate, disease-free survival, and safety profile.ResultsTwenty patients with dMMR/MSI-H CRC who underwent neoadjuvant immunotherapy as part of the treatment were enrolled between May 2019 and February 2024 at Sichuan Cancer Hospital. Out of these patients, eight patients received PD-1 blockade monotherapy as neoadjuvant treatment, while 12 were administered a combined therapy of anti-CTLA-4 and anti-PD-1. 12 patients received Nivolumab plus Ipilimumab regimen and 8 patients received PD-1 blockades (2 patients were Pembrolizumab, 2 patients were Sintilimab, 4 patients were Tislelizumab) monotherapy. Additionally, 19 patients underwent surgery after immunotherapy and of these, 15 (75.0%) achieved complete pathological response (pCR), 8 (66.7%) achieved the same on Nivolumab plus Ipilimumab immunotherapy while 7 (87.5%) achieved on PD-1 antibody monotherapy. The overall response rate (ORR) was 75%, with 45.0% of patients experiencing grade I/II immunotherapy-related adverse events. The most frequent adverse event observed was increased ALT i.e. 20%. Notably, no postoperative complications were observed.ConclusionBased on the findings, neoadjuvant immunotherapy for colorectal cancer may be both safe and effective in clinical practice. Furthermore, the study suggested that dual immunotherapy could potentially increase the immunotherapy cycle and contribute to a superior pCR rate. However, the conclusion emphasized the need for further prospective clinical trials to validate these results.

Objective To explore the value of histogram parameters derived from intravoxel incoherent motion (IVIM) for predicting response to neoadjuvant chemoradiation (nCRT) in patients with rectal cancer. Methods 112 patients diagnosed with rectal cancer who underwent IVIM-DWI before nCRT were enrolled in this study, and true diffusion coefficient (D), pseudo-diffusion coefficient (D*), and microvascular volume fraction (f) calculated from IVIM, together with the histogram parameters were recorded. The patients were divided into the pathological complete response (pCR) group and the non-pCR group according to the tumor regression grade (TRG) system. We also divided the patients into low T stage (yp T0-2) and high T stage (ypT3-4) according to the pathologic T stage (ypT stage). Univariate logistic regression analysis was implemented to select independent risk factors, including clinical characteristics and IVIM histogram parameters, and the models for Clinical, Histogram, and Combined Clinical and Histogram were generated respectively by using multivariable binary logistic regression analysis for predicting pCR. The area under the Receiver operating characteristic (ROC) curve (AUCs) were used to compare the diagnostic performance among the three models. Results The values of D_ kurtosis, f_mean, and f_ median were significantly higher in the pCR group (n = 24) compared with the non-pCR group. The value of D*_ entropy was significantly lower in the pCR group compared with the non-pCR group. The values of D_ kurtosis, f_mean, and f_ median were significantly higher in the low T stage group (n=37) compared with the high T stage group. The value of D*_ entropy was significantly lower in the low T stage group compared with the high T stage group (allp < 0.05). ROC curves demonstrated that the Combined Clinical and Histogram model had the best diagnostic performance in predicting the pCR patients with optimal AUCs, sensitivity, specificity, and accuracy (0.916, 83.33%, 85.23%, and 84.82%, respectively). Conclusions IVIM histogram parameters which combined with clinical characteristics showed promising prospects in predicting the pCR patients before surgery.

PurposeTo establish and evaluate multiregional T2-weighted imaging (T2WI)-based clinical-radiomics model for predicting lymph node metastasis (LNM) and prognosis in patients with resectable rectal cancer. MethodsA total of 346 patients with pathologically confirmed rectal cancer from two hospitals between January 2019 and December 2021 were prospectively enrolled. Intra- and peritumoral features were extracted separately, and least absolute shrinkage and selection operator regression was applied for feature selection. Radiomics signatures were built using the selected features from different regions. The clinical-radiomic nomogram was developed by combining the intratumoral and peritumoral radiomics signatures score (radscore) and the most predictive clinical parameters. The diagnostic performances of the nomogram and clinical model were evaluated using the area under the receiver operating characteristic curve (AUC). The prognostic model for 3-year recurrence-free survival (RFS) was constructed using univariate and multivariate Cox analysis. ResultsThe intratumoral radscore (radscore 1) included four features, the peritumoral radscore (radscore 2) included five features, and the combined intratumoral and peritumoural radscore (radscore 3) included ten features. The AUCs for radscore 3 were higher than that of radscore 1 in training cohort (0.77 vs. 0.71, P=0.182) and internal validation cohort (0.76 vs. 0.64, P=0.041). The AUCs for radscore 3 were higher than that of radscore 2 in training cohort (0.77 vs. 0.74, P=0.215) and internal validation cohort (0.76 vs. 0.68, P=0.083). A clinical-radiomic nomogram showed a higher AUC compared with the clinical model in training cohort (0.84 vs. 0.67, P<0.001) and internal validation cohort (0.78 vs. 0.64, P=0.038) but not in external validation (0.72 vs. 0.76, P=0.164). Multivariate Cox analysis showed MRI-reported extramural vascular invasion (EMVI) (HR=1.099, 95%CI: 0.462-2.616; P=0.031) and clinical-radiomic nomogram-based LNM (HR=2.232, 95%CI:1.238-7.439; P=0.017) were independent risk factors for assessing 3-year RFS. Combined clinical-radiomic nomogram based LNM and MRI-reported EMVI showed good performance in training cohort (AUC=0.748), internal validation cohort (AUC=0.706) and external validation (AUC=0.688) for predicting 3-year RFS. ConclusionA clinical-radiomics nomogram exhibits good performance for predicting preoperative LNM. Combined clinical-radiomic nomogram based LNM and MRI-reported EMVI showed clinical potential for assessing 3-year RFS.