Can lymphovascular invasion be predicted by preoperative multiphasic dynamic CT in patients with advanced gastric cancer?

Diagnostic performance of fluorescent lymphography-guided lymph node dissection during minimally invasive gastrectomy following chemotherapy

INTRODUCTION

Fluorescent lymphography-guided lymph node dissection (FL) using indocyanine green (ICG) during radical gastrectomy for gastric cancer has shown enhanced lymph node (LN) retrieval and high sensitivity in detecting LN metastases. However, the impact of FL during gastrectomy following chemotherapy remains uncertain because changes in the ICG injection site due to tumor shrinkage may potentially visualize different lymphatic drainage from the tumor. This study aimed to assess the diagnostic performance of FL during gastrectomy after preoperative chemotherapy.

MATERIALS AND METHODS

This retrospective study included patients who underwent minimally invasive gastrectomy with FL following chemotherapy between January 2013 and February 2024. Patients were categorized according to their tumor response after chemotherapy based on endoscopic, radiologic, and pathological findings.

RESULTS

Of 29 patients, 9.4 (range 8-12) LN stations containing 6.9 (range 3-11) fluorescent LN stations, which had 56.3 (range 33-99) LNs including 33.4 (range 11-68) fluorescent LNs, were retrieved per patient. While 52 metastatic LN stations were fluorescent, three non-fluorescent metastatic LN stations were identified in one patient (3.4 %). FL showed 94.5 % (52/55) sensitivity and 95.9 % (70/73) negative predictive value for detecting metastatic LN stations. There was no significant difference in the number of retrieved LNs and the sensitivity for detecting metastatic LN stations between responders and non-responders.

CONCLUSION

Tumor response after chemotherapy did not influence the diagnostic performance of FL. The diagnostic performance of FL during gastrectomy following chemotherapy was acceptable. Similar to upfront surgery, FL can be safely applied even after chemotherapy.

Development and validation of a nomogram model based on vascular entry sign for predicting lymphovascular invasion in gastric cancer

BACKGROUND

To evaluate the predictive value of a nomogram based on the vascular entry sign for lymphovascular invasion in gastric cancer.

METHODS

A total of 135 patients with histopathologically confirmed gastric cancer from August 2021 to November 2022 were enrolled. All patients underwent contrast-enhanced CT scans. Utilizing a random number method, patients were randomly assigned to either a training dataset (n = 96) or a validation dataset (n = 39) in a 7:3 ratio. CT images and clinical characteristics of the patients were collected. Both univariate and multivariate analyses were conducted to identify independent factors influencing lymphovascular invasion in gastric cancer. A nomogram model was developed, and its diagnostic performance and clinical utility were assessed using receiver operating characterist (ROC) curves, calibration curves, and decision curve analysis (DCA).

RESULTS

The multivariate analysis revealed that the vascular entry sign, clinical T stage, and clinical N stage independently influenced the occurrence of factors for lymphovascular invasion in gastric cancer (P < 0.05). A predictive nomogram model was developed for determining LVI status in gastric cancer. The AUC of the nomogram model in the training dataset and validation dataset were 0.878 (95% CI: 0.808-0.948) and 0.866 (95% CI: 0.723-1.000), respectively. The calibration curve and decision curve showed that the model had good reliability and good clinical validity.

CONCLUSION

The model established based on the factors of vascular entry sign, clinical T stage, and clinical N stage can effectively predict lymphovascular invasion in gastric cancer.

Dual-phase contrast-enhanced CT-based intratumoral and peritumoral radiomics for preoperative prediction of lymphovascular invasion in gastric cancer

BACKGROUND

To develop and validate a dual-phase contrast-enhanced computed tomography (CT)-based intratumoral and peritumoral radiomics for the prediction of lymphovascular invasion (LVI) in patients with gastric cancer.

METHOD

Three hundred and eighty-three patients with gastric cancer (training cohort, 269 patients; test cohort, 114 patients) were retrospectively enrolled between January 2017 and June 2023. Radiomics features were extracted from the intratumoral volume (ITV) and peritumoral volume (PTV) on CT images at arterial phase (AP) and venous phase (VP), and selected by the least absolute shrinkage and selection operator. Radiomics models were constructed by logistic regression. The clinical-radiomics combined model incorporating the most predictive radiomics signature and clinical risk factors were developed with multivariate analysis. Receiver operating characteristic (ROC) curves were used to evaluate the prediction performance of models.

RESULTS

Clinical model comprised of three clinical risk factors including tumor differentiation, CT-reported lymph node metastasis status and CT-TNM staging showed good performance with an area under the ROC curve (AUC) of 0.804 and 0.825 in the training and test cohort, respectively. Compared with the other radiomics models, dual-phase (AP + VP) CT-based ITV + PTV radiomics model presented superior AUC of 0.844 and 0.835 in the training and test cohort, respectively. Clinical-radiomics combined model further improved the discriminatory performance (AUC, 0.903) in the training and test cohort (AUC, 0.901). Decision curve analysis confirmed the net benefit of clinical-radiomics combined model. Subgroup analyses showed that the clinical-radiomics nomogram showed the best performance with an AUC of 0.879 and 0.883 for predicting LVI in T1-T2 and T3-T4 gastric cancer compared with the clinical model and the ITV + PTV-AP + VP radiomics model, respectively.

CONCLUSIONS

Clinical-radiomics combined model integrating clinical risk factors and dual-phase contrast-enhanced CT-based intratumoral and peritumoral radiomics signatures provided favorable performance for predicting LVI in gastric cancer.

Predicting Lymphovascular Invasion in Non-small Cell Lung Cancer Using Deep Convolutional Neural Networks on Preoperative Chest CT

RATIONALE AND OBJECTIVES

Lymphovascular invasion (LVI) plays a significant role in precise treatments of non-small cell lung cancer (NSCLC). This study aims to build a non-invasive LVI prediction diagnosis model by combining preoperative CT images with deep learning technology.

MATERIALS AND METHODS

This retrospective observational study included a series of consecutive patients who underwent surgical resection for non-small cell lung cancer (NSCLC) and received pathologically confirmed diagnoses. The cohort was randomly divided into a training group comprising 70 % of the patients and a validation group comprising the remaining 30 %. Four distinct deep convolutional neural network (DCNN) prediction models were developed, incorporating different combination of two-dimensional (2D) and three-dimensional (3D) CT imaging features as well as clinical-radiological data. The predictive capabilities of the models were evaluated by receiver operating characteristic curves (AUC) values and confusion matrices. The Delong test was utilized to compare the predictive performance among the different models.

RESULTS

A total of 3034 patients with NSCLC were recruited in this study including 106 LVI+ patients. In the validation cohort, the Dual-head Res2Net_3D23F model achieved the highest AUC of 0.869, closely followed by the models of Dual-head Res2Net_3D3F (AUC, 0.868), Dual-head Res2Net_3D (AUC, 0.867), and EfficientNet-B0_2D (AUC, 0.857). There was no significant difference observed in the performance of the EfficientNet-B0_2D model when compared to the Dual-head Res2Net_3D3F and Dual-head Res2Net_3D23F.

CONCLUSION

Findings of this study suggest that utilizing deep convolutional neural network is a feasible approach for predicting pathological LVI in patients with NSCLC.

Preoperative prediction of perineural invasion and lymphovascular invasion with CT radiomics in gastric cancer

Objectives

To determine whether contrast-enhanced CT radiomics features can preoperatively predict lymphovascular invasion (LVI) and perineural invasion (PNI) in gastric cancer (GC).

Methods

A total of 148 patients were included in the LVI group, and 143 patients were included in the PNI group. Three predictive models were constructed, including clinical, radiomics, and combined models. A nomogram was developed with clinical risk factors to predict LVI and PNI status. The predictive performance of the three models was mainly evaluated using the mean area under the curve (AUC). The performance of three predictive models was assessed concerning calibration and clinical usefulness.

Results

In the LVI group, the predictive power of the combined model (AUC=0.871, 0.822) outperformed the clinical model (AUC=0.792, 0.728) and the radiomics model (AUC=0.792, 0.728) in both the training and testing cohorts. In the PNI group, the combined model (AUC=0.834, 0.828) also had better predictive power than the clinical model (AUC=0.764, 0.632) and the radiomics model (AUC=0.764, 0.632) in both the training and testing cohorts. The combined models also showed good calibration and clinical usefulness for LVI and PNI prediction.

Conclusion

CECT-based radiomics analysis might serve as a non-invasive method to predict LVI and PNI status in GC.

Radiomics Analysis to Predict Lymphovascular Invasion of Gastric Cancer Based on Iodine-Based Material Decomposition Images and Virtual Monoenergetic Images

OBJECTIVE

This study aimed to investigate the utility of virtual monoenergetic images (VMIs) and iodine-based material decomposition images (IMDIs) in the assessment of lymphovascular invasion (LVI) in gastric cancer (GC) patients.

METHODS

A total of 103 GC patients who underwent dual-energy spectral computed tomography preoperatively were enrolled. The LVI status was confirmed by pathological analysis. The radiomics features obtained from the 70 keV VMI and IMDI were used to build radiomics models. Independent clinical factors for LVI were identified and used to build the clinical model. Then, combined models were constructed by fusing clinical factors and radiomics signatures. The predictive performance of these models was evaluated.

RESULTS

The computed tomography-reported N stage was an independent predictor of LVI, and the areas under the curve (AUCs) of the clinical model in the training group and testing group were 0.750 and 0.765, respectively. The radiomics models using the VMI signature and IMDI signature and combining these 2 signatures outperformed the clinical model, with AUCs of 0.835, 0.855, and 0.924 in the training set and 0.838, 0.825, and 0.899 in the testing set, respectively. The model combined with the computed tomography-reported N stage and the 2 radiomics signatures achieved the best performance in the training (AUC, 0.925) and testing (AUC, 0.961) sets, with a good degree of calibration and clinical utility for LVI prediction.

CONCLUSIONS

The preoperative assessment of LVI in GC is improved by radiomics features based on VMI and IMDI. The combination of clinical, VMI-, and IMDI-based radiomics features effectively predicts LVI and provides support for clinical treatment decisions.

Prognostic Implication of Lymphovascular Invasion in Early Gastric Cancer Meeting Endoscopic Submucosal Dissection Criteria: Insights from Radical Surgery Outcomes

BACKGROUND

The management of early gastric cancer (EGC) has witnessed a rise in the utilization of endoscopic submucosal dissection (ESD) as a treatment modality, although prognostic markers are needed to guide management strategies. This study investigates the prognostic implications of lymphovascular invasion (LVI) in ESD-eligible EGC patients, specifically its implications for subsequent radical surgery.

MATERIAL AND METHODS

A retrospective, multicenter study from two primary hospitals analyzed clinicopathological data from 1369 EGC patients eligible for ESD, who underwent gastrectomy at Shanghai Cancer Center and Huashan Hospital between 2009 and 2018. We evaluated the relationship between LVI and lymph node metastasis (LNM), as well as the influence of LVI on recurrence-free survival (RFS) and overall survival (OS).

RESULTS

We found a strong association between LVI and LNM (p < 0.001). Advanced machine learning approaches, including Random Forest, Gradient Boosting Machine, and eXtreme Gradient Boosting, confirmed the pivotal role of LVI in forecasting LNM from both centers. Multivariate analysis identified LVI as an independent negative prognostic factor for both RFS and OS, with hazard ratios of 4.5 (95% CI: 2.4-8.5, p < 0.001) and 4.4 (95% CI: 2.1-8.9, p < 0.001), respectively.

CONCLUSIONS

LVI is crucial for risk stratification in ESD-eligible EGC patients, underscoring the necessity for radical gastrectomy. Future research should explore the potential incorporation of LVI status into existing TNM staging systems and novel therapeutic strategies.

Dual-layer detector spectral CT-based machine learning models in the differential diagnosis of solitary pulmonary nodules

The benign and malignant status of solitary pulmonary nodules (SPNs) is a key determinant of treatment decisions. The main objective of this study was to validate the efficacy of machine learning (ML) models featured with dual-layer detector spectral computed tomography (DLCT) parameters in identifying the benign and malignant status of SPNs. 250 patients with pathologically confirmed SPN were included in this study. 8 quantitative and 16 derived parameters were obtained based on the regions of interest of the lesions on the patients' DLCT chest enhancement images. 6 ML models were constructed from 10 parameters selected after combining the patients' clinical parameters, including gender, age, and smoking history. The logistic regression model showed the best diagnostic performance with an area under the receiver operating characteristic curve (AUC) of 0.812, accuracy of 0.813, sensitivity of 0.750 and specificity of 0.791 on the test set. The results suggest that the ML models based on DLCT parameters are superior to the traditional CT parameter models in identifying the benign and malignant nature of SPNs, and have greater potential for application.

A CT-based novel model to predict pathological complete response of locally advanced esophageal squamous cell carcinoma to neoadjuvant PD-1 blockade in combination with chemotherapy

PURPOSE

To develop a novel CT-based model to predict pathological complete response (pCR) of locally advanced esophageal squamous cell carcinoma (ESCC) to neoadjuvant PD-1 blockade in combination with chemotherapy.

METHODS

117 consecutive patients with locally advanced ESCC were stratified into training cohort (n = 82) and validation cohort (n = 35). All patients underwent non-contrast and contrast-enhanced thoracic and upper abdominal CT before neoadjuvant PD-1 blockade in combination with chemotherapy (CTpre), and after two cycles of the therapy before esophagectomy (CTpost), respectively. Univariate analyses and binary logistic regression analyses of ESCC quantitative and qualitative CT features were performed to determine independent predictors of pCR. Prediction performance of the model developed with independent predictors from training cohort was evaluated by receiver operating characteristic (ROC) analysis, and validated by Kappa test in validation cohort.

RESULTS

In training cohort, the difference in CT attenuation between tumor and background normal esophageal wall obtained from CTpre (ΔTNpre), tumoral increased CT attenuation after contrast-enhanced scan from CTpost images (ΔTpost) and gross tumor volume (GTV) from CTpre were independent predictors of pCR (odds ratio = 1.128 (95% confidence interval (CI): 0.997-1.277), 1.113 (95%CI: 0.965-1.239) and 1.133 (95%CI: 1.043-1.231), respectively, all P-values < 0.05). Logistic regression model equation (0.121 × ΔTNpre + 0.107 × ΔTpost + 0.125 × GTV - 9.856) to predict pCR showed the best performance with an area under the ROC of 0.876, compared with each independent predictor. The good performance was confirmed by the Kappa test (K-value = 0.796) in validation cohort.

CONCLUSIONS

This novel model can be reliable to predict pCR to neoadjuvant PD-1 blockade in combination with chemotherapy in locally advanced ESCC.

Dual-layer spectral-detector CT for predicting microsatellite instability status and prognosis in locally advanced gastric cancer

OBJECTIVE

To construct and validate a prediction model based on dual-layer detector spectral CT (DLCT) and clinico-radiologic features to predict the microsatellite instability (MSI) status of gastric cancer (GC) and to explore the relationship between the prediction results and patient prognosis.

METHODS

A total of 264 GC patients who underwent preoperative DLCT examination were randomly allocated into the training set (n = 187) and validation set (n = 80). Clinico-radiologic features and DLCT parameters were used to build the clinical and DLCT model through multivariate logistic regression analysis. A combined DLCT parameter (CDLCT) was constructed to predict MSI. A combined prediction model was constructed using multivariate logistic regression analysis by integrating the significant clinico-radiologic features and CDLCT. The Kaplan-Meier survival analysis was used to explore the prognostic significant of the prediction results of the combined model.

RESULTS

In this study, there were 70 (26.52%) MSI-high (MSI-H) GC patients. Tumor location and CT_N staging were independent risk factors for MSI-H. In the validation set, the area under the curve (AUC) of the clinical model and DLCT model for predicting MSI status was 0.721 and 0.837, respectively. The combined model achieved a high prediction efficacy in the validation set, with AUC, sensitivity, and specificity of 0.879, 78.95%, and 75.4%, respectively. Survival analysis demonstrated that the combined model could stratify GC patients according to recurrence-free survival (p = 0.010).

CONCLUSION

The combined model provides an efficient tool for predicting the MSI status of GC noninvasively and tumor recurrence risk stratification after surgery.

CRITICAL RELEVANCE STATEMENT

MSI is an important molecular subtype in gastric cancer (GC). But MSI can only be evaluated using biopsy or postoperative tumor tissues. Our study developed a combined model based on DLCT which could effectively predict MSI preoperatively. Our result also showed that the combined model could stratify patients according to recurrence-free survival. It may be valuable for clinicians in choosing appropriate treatment strategies to avoid tumor recurrence and predicting clinical prognosis in GC.

KEY POINTS

• Tumor location and CT_N staging were independent predictors for MSI-H in GC. • Quantitative DLCT parameters showed potential in predicting MSI status in GC. • The combined model integrating clinico-radiologic features and CDLCT could improve the predictive performance. • The prediction results could stratify the risk of tumor recurrence after surgery.

Development and validation of a multiphase CT radiomics nomogram for the preoperative prediction of lymphovascular invasion in patients with gastric cancer

AIM

To develop a nomogram to predict lymphovascular invasion (LVI) in gastric cancer by integrating multiphase computed tomography (CT) radiomics and clinical risk factors.

MATERIALS AND METHODS

One hundred and seventy-two gastric cancer patients (121 training and 51 validation) with preoperative contrast-enhanced CT images and clinicopathological data were collected retrospectively. The clinical risk factors were selected by univariate and multivariate regression analysis. Radiomic features were extracted and selected from the arterial phase (AP), venous phase (VP), and delayed phase (DP) CT images of each patient. Clinical risk factors, radiomic features, and integration of both were used to develop the clinical model, radiomic models, and nomogram, respectively.

RESULTS

Radiomic features from AP (n=6), VP (n=6), DP (n=7) CT images and three selected clinical risk factors were used for model development. The nomogram showed better performance than the AP, VP, DP, and clinical models in the training and validation datasets, providing areas under the curves (AUCs) of 0.890 (95% CI: 0.820-0.940) and 0.885 (95% CI:0.765-0.957), respectively. All models indicated good calibration, and decision curve analysis proved that the net benefit of the nomogram was superior to that of the clinical and radiomic models throughout the vast majority of the threshold probabilities.

CONCLUSIONS

The nomogram integrating multiphase CT radiomics and clinical risk factors showed favourable performance in predicting LVI of gastric cancer, which may benefit clinical practice.

A radiomics nomogram based on contrast-enhanced CT for preoperative prediction of Lymphovascular invasion in esophageal squamous cell carcinoma

Background and purpose

To develop a radiomics nomogram based on contrast-enhanced computed tomography (CECT) for preoperative prediction of lymphovascular invasion (LVI) status of esophageal squamous cell carcinoma (ESCC).

Materials and methods

The clinical and imaging data of 258 patients with ESCC who underwent surgical resection and were confirmed by pathology from June 2017 to December 2021 were retrospectively analyzed.The clinical imaging features and radiomic features were extracted from arterial-phase CECT. The least absolute shrinkage and selection operator (LASSO) regression model was used for radiomics feature selection and signature construction. Multivariate logistic regression analysis was used to develop a radiomics nomogram prediction model. The receiver operating characteristic (ROC) curve and decision curve analysis (DCA) were used to evaluate the performance and clinical effectiveness of the model in preoperative prediction of LVI status.

Results

We constructed a radiomics signature based on eight radiomics features after dimensionality reduction. In the training cohort, the area under the curve (AUC) of radiomics signature was 0.805 (95% CI: 0.740-0.860), and in the validation cohort it was 0.836 (95% CI: 0.735-0.911). There were four predictive factors that made up the individualized nomogram prediction model: radiomic signatures, TNRs, tumor lengths, and tumor thicknesses.The accuracy of the nomogram for LVI prediction in the training and validation cohorts was 0.790 and 0.768, respectively, the specificity was 0.800 and 0.618, and the sensitivity was 0.786 and 0.917, respectively. The Delong test results showed that the AUC value of the nomogram model was significantly higher than that of the clinical model and radiomics model in the training and validation cohort(P<0.05). DCA results showed that the radiomics nomogram model had higher overall benefits than the clinical model and the radiomics model.

Conclusions

This study proposes a radiomics nomogram based on CECT radiomics signature and clinical image features, which is helpful for preoperative individualized prediction of LVI status in ESCC.

Prediction model based on radiomics and clinical features for preoperative lymphovascular invasion in gastric cancer patients

Background: We explored whether a model based on contrast-enhanced computed tomography radiomics features and clinicopathological factors can evaluate preoperative lymphovascular invasion (LVI) in patients with gastric cancer (GC) with Lauren classification. Methods: Based on clinical and radiomic characteristics, we established three models: Clinical + Arterial phase_Radcore, Clinical + Venous phase_Radcore and a combined model. The relationship between Lauren classification and LVI was analyzed using a histogram. Results: We retrospectively analyzed 495 patients with GC. The areas under the curve of the combined model were 0.8629 and 0.8343 in the training and testing datasets, respectively. The combined model showed a superior performance to the other models. Conclusion: CECT-based radiomics models can effectively predict preoperative LVI in GC patients with Lauren classification.

Application of intravoxel incoherent motion diffusion-weighted imaging for preoperative knowledge of lymphovascular invasion in gastric cancer: a prospective study

PURPOSE

To investigate the potential of intravoxel incoherent motion diffusion-weighted imaging (IVIM) for preoperative prediction of lymphovascular invasion (LVI) in gastric cancer (GC).

METHODS

This study prospectively enrolled 90 patients (62 males, 28 females, 60.79 ± 9.99 years old) who received radical gastrostomy. Abdominal MRI examinations including IVIM were performed within 1 week before surgery. Patients were divided into LVI-positive and -negative group according to pathological diagnosis after surgery. The apparent diffusion coefficient (ADC) and IVIM parameters, including true diffusion coefficient (D), pseudodiffusion coefficient (D*), and pseudodiffusion fraction (f), were compared between the two groups. The relationship between MRI parameters and LVI was studied by Spearman's correlation analysis. Multivariable logistic regression analysis was used to screen independent predictors of LVI. Receiver-operating characteristic curve analyses were applied to evaluate the efficacy.

RESULTS

The ADC, D in LVI-positive group were lower, whereas tumor thickness and f parameter in LVI-positive group were higher than those in LVI-negative group, and they were statistically correlated with LVI (p < 0.05). D, f and tumor thickness were independent risk factors of LVI. The area under the curve of ADC, D, f, thickness, and the combined parameter (D + f + thickness) were 0.667, 0.754, 0.695, 0.792, and 0.876, respectively. The combined parameter demonstrated higher efficacy than any other parameters (p < 0.05).

CONCLUSION

The ADC, D, and f can effectively distinguish LVI status of GC. The D, f and thickness were independent predictors. The combination of the three predictors further improved the efficacy.

Development of a CT image analysis-based scoring system to differentiate gastric schwannomas from gastrointestinal stromal tumors

Purpose

To develop a point-based scoring system (PSS) based on contrast-enhanced computed tomography (CT) qualitative and quantitative features to differentiate gastric schwannomas (GSs) from gastrointestinal stromal tumors (GISTs).

Methods

This retrospective study included 51 consecutive GS patients and 147 GIST patients. Clinical and CT features of the tumors were collected and compared. Univariate and multivariate logistic regression analyses using the stepwise forward method were used to determine the risk factors for GSs and create a PSS. Area under the receiver operating characteristic curve (AUC) analysis was performed to evaluate the diagnostic efficiency of PSS.

Results

The CT attenuation value of tumors in venous phase images, tumor-to-spleen ratio in venous phase images, tumor location, growth pattern, and tumor surface ulceration were identified as predictors for GSs and were assigned scores based on the PSS. Within the PSS, GS prediction probability ranged from 0.60% to 100% and increased as the total risk scores increased. The AUC of PSS in differentiating GSs from GISTs was 0.915 (95% CI: 0.874-0.957) with a total cutoff score of 3.0, accuracy of 0.848, sensitivity of 0.843, and specificity of 0.850.

Conclusions

The PSS of both qualitative and quantitative CT features can provide an easy tool for radiologists to successfully differentiate GS from GIST prior to surgery.

Value of dual-layer spectral detector computed tomography in the diagnosis of benign/malignant solid solitary pulmonary nodules and establishment of a prediction model

Objective

This study aimed to investigate the role of spectral detector computed tomography (SDCT) quantitative parameters and their derived quantitative parameters combined with lesion morphological information in the differential diagnosis of solid SPNs.

Methods

This retrospective study included basic clinical data and SDCT images of 132 patients with pathologically confirmed SPNs (102 and 30 patients in the malignant and benign groups, respectively). The morphological signs of SPNs were evaluated and the region of interest (ROI) was delineated from the lesion to extract and calculate the relevant SDCT quantitative parameters, and standardise the process. Differences in qualitative and quantitative parameters between the groups were statistically analysed. A receiver operating characteristic (ROC) curve was constructed to evaluate the efficacy of the corresponding parameters in the diagnosis of benign and malignant SPNs. Statistically significant clinical data, CT signs and SDCT quantitative parameters were analysed using multivariate logistic regression to determine the independent risk factors for predicting benign and malignant SPNs, and the best multi-parameter regression model was established. Inter-observer repeatability was assessed using the intraclass correlation coefficient (ICC) and Bland-Altman plots.

Results

Malignant SPNs differed from benign SPNs in terms of size, lesion morphology, short spicule sign, and vascular enrichment sign (P< 0.05). The SDCT quantitative parameters and their derived quantitative parameters of malignant SPNs (SAR40keV, SAR70keV, Δ40keV, Δ70keV, CER40keV, CER70keV, NEF40keV, NEF70keV, λ, NIC, NZeff) were significantly higher than those of benign SPNs (P< 0.05). In the subgroup analysis, most parameters could distinguish between benign and adenocarcinoma groups (SAR40keV, SAR70keV, Δ40keV, Δ70keV, CER40keV, CER70keV, NEF40keV, NEF70keV, λ, NIC, and NZeff), and between benign and squamous cell carcinoma groups (SAR40keV, SAR70keV, Δ40keV, Δ70keV, NEF40keV, NEF70keV, λ, and NIC). However, there were no significant differences between the parameters in the adenocarcinoma and squamous cell carcinoma groups. ROC curve analysis indicated that NIC, NEF70keV, and NEF40keV had higher diagnostic efficacy for differentiating benign and malignant SPNs (area under the curve [AUC]:0.869, 0.854, and 0.853, respectively), and NIC was the highest. Multivariate logistic regression analysis showed that size (OR=1.138, 95% CI 1.022-1.267, P=0.019), Δ70keV (OR=1.060, 95% CI 1.002-1.122, P=0.043), and NIC (OR=7.758, 95% CI 1.966-30.612, P=0.003) were independent risk factors for the prediction of benign and malignant SPNs. ROC curve analysis showed that the AUC of size, Δ70keV, NIC, and a combination of the three for differential diagnosis of benign and malignant SPNs were 0.636, 0.846, 0.869, and 0.903, respectively. The AUC for the combined parameters was the largest, and the sensitivity, specificity, and accuracy were 88.2%, 83.3% and 86.4%, respectively. The SDCT quantitative parameters and their derived quantitative parameters in this study exhibited satisfactory inter-observer repeatability (ICC: 0.811-0.997).

Conclusion

SDCT quantitative parameters and their derivatives can be helpful in the differential diagnosis of benign and malignant solid SPNs. The quantitative parameter, NIC, is superior to the other relevant quantitative parameters and when NIC is combined with lesion size and Δ70keV value for comprehensive diagnosis, the efficacy could be further improved.

Spectral CT-based nomogram for preoperative prediction of perineural invasion in locally advanced gastric cancer: a prospective study

OBJECTIVES

This work focused on developing and validating the spectral CT-based nomogram to preoperatively predict perineural invasion (PNI) for locally advanced gastric cancer (LAGC).

METHODS

This work prospectively included 196 surgically resected LAGC patients (139 males, 57 females, 59.55 ± 11.97 years) undergoing triple enhanced spectral CT scans. Patients were labeled as perineural invasion (PNI) positive and negative according to pathologic reports, then further split into primary (n = 130) and validation cohort (n = 66). We extracted clinicopathological information, follow-up data, iodine concentration (IC), and normalized IC values against to aorta (nICs) at arterial/venous/delayed phases (AP/VP/DP). Clinicopathological features and IC values between PNI positive and negative groups were compared. Multivariable logistic regression was performed to screen independent risk factors of PNI. Then, a nomogram was established, and its capability was determined by ROC curves. Its clinical use was evaluated by decision curve analysis. The correlations of PNI and the nomogram with patients' survival were explored by log-rank survival analysis.

RESULTS

Borrmann classification, tumor thickness, and nICDP were independent predictors of PNI and used to build the nomogram. The nomogram yielded higher AUCs of 0.853 (0.744-0.928) and 0.782 (0.701-0.850) in primary and validation cohorts than any other parameters (p < 0.05). Both PNI and the nomogram were related to post-surgical treatment planning. Only PNI was associated with disease-free survival in the primary cohort (p < 0.05).

CONCLUSION

This work prospectively established a spectral CT-based nomogram, which can effectively predict PNI preoperatively and potentially guide post-surgical treatment strategy in LAGC.

KEY POINTS

• The present prospective study established a spectral CT-based nomogram for preoperative prediction of perineural invasion in LAGC. • The proposed nomogram, including morphological features and the quantitative iodine concentration values from spectral CT, had the potential to predict PNI for LAGC before surgery, along with guide post-surgical treatment planning. • Normalized iodine concentration at the delayed phase was the most valuable quantitative parameter, suggesting the importance of delayed enhancement in gastric CT.

Risk factors of lymph node metastasis or lymphovascular invasion for superficial esophageal squamous cell carcinoma: A practical and effective predictive nomogram based on a cancer hospital data

Background

Lymphovascular invasion (LVI) is mostly used as a preoperative predictor to establish lymph node metastasis (LNM) prediction models for superficial esophageal squamous cell carcinoma (SESCC). However, LVI still needs to be confirmed by postoperative pathology. In this study, we combined LNM and LVI as a unified outcome and named it LNM/LVI, and aimed to develop an LNM/LVI prediction model in SESCC using preoperative factors.

Methods

A total of 512 patients who underwent radical resection of SESCC were retrospectively collected. Logistic regression and least absolute shrinkage and selection operator (LASSO) regression were adopted to identify the predictive factors of LNM/LVI. Integrated discrimination improvement (IDI) and net reclassification improvement (NRI) were calculated to select the potential predictive factors from the results of LASSO and logistic regression. A nomogram for predicting LNM/LVI was established by incorporating these factors. The efficacy, accuracy, and clinical utility of the nomogram were, respectively, assessed with the area under the curve (AUC), calibration curve, and decision curve analysis (DCA). Finally, the random forest (RF) algorithm was used to further evaluate the impact of these factors included in the nomogram on LNM/LVI.

Results

Tumor size, tumor location, tumor invasion depth, tumor differentiation, and macroscopic type were confirmed as independent risk factors for LNM/LVI according to the results of logistic regression, LASSO regression, IDI, and NRI analyses. A nomogram including these five variables showed a good performance in LNM/LVI prediction (AUC = 0.776). The calibration curve revealed that the predictive results of this nomogram were nearly consistent with actual observations. Significant clinical utility of our nomogram was demonstrated by DCA. The RF model with the same five variables also had similar predictive efficacy with the nomogram (AUC = 0.775).

Conclusion

The nomogram was adopted as a final tool for predicting LNM/LVI because its risk score system made it more user-friendly and clinically useful than the random forest model, which can help clinicians make optimal treatment decisions for patients with SESCC.

Quantitative parameters of dynamic contrast-enhanced magnetic resonance imaging to predict lymphovascular invasion and survival outcome in breast cancer

BACKGROUND

Lymphovascular invasion (LVI) predicts a poor outcome of breast cancer (BC), but LVI can only be postoperatively diagnosed by histopathology. We aimed to determine whether quantitative parameters of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can preoperatively predict LVI and clinical outcome of BC patients.

METHODS

A total of 189 consecutive BC patients who underwent multiparametric MRI scans were retrospectively evaluated. Quantitative (K^trans, V_e, K_ep) and semiquantitative DCE-MRI parameters (W_- in, W_- out, TTP), and clinicopathological features were compared between LVI-positive and LVI-negative groups. All variables were calculated by using univariate logistic regression analysis to determine the predictors for LVI. Multivariate logistic regression was used to build a combined-predicted model for LVI-positive status. Receiver operating characteristic (ROC) curves evaluated the diagnostic efficiency of the model and Kaplan-Meier curves showed the relationships with the clinical outcomes. Multivariate analyses with a Cox proportional hazard model were used to analyze the hazard ratio (HR) for recurrence-free survival (RFS) and overall survival (OS).

RESULTS

LVI-positive patients had a higher K_ep value than LVI-negative patients (0.92 ± 0.30 vs. 0.81 ± 0.23, P = 0.012). N2 stage [odds ratio (OR) = 3.75, P = 0.018], N3 stage (OR = 4.28, P = 0.044), and K_ep value (OR = 5.52, P = 0.016) were associated with LVI positivity. The combined-predicted LVI model that incorporated the N stage and K_ep yielded an accuracy of 0.735 and a specificity of 0.801. The median RFS was significantly different between the LVI-positive and LVI-negative groups (31.5 vs. 34.0 months, P = 0.010) and between the combined-predicted LVI-positive and LVI-negative groups (31.8 vs. 32.0 months, P = 0.007). The median OS was not significantly different between the LVI-positive and LVI-negative groups (41.5 vs. 44.0 months, P = 0.270) and between the combined-predicted LVI-positive and LVI-negative groups (42.8 vs. 43.5 months, P = 0.970). LVI status (HR = 2.40), N2 (HR = 3.35), and the combined-predicted LVI model (HR = 1.61) were independently associated with disease recurrence.

CONCLUSION

The quantitative parameter of K_ep could predict LVI. LVI status, N stage, and the combined-predicted LVI model were predictors of a poor RFS but not OS.

Spectral CT for preoperative prediction of lymphovascular invasion in resectable gastric cancer: With external prospective validation

Objectives

To develop and externally validate a spectral CT based nomogram for the preoperative prediction of LVI in patients with resectable GC.

Methods

The two centered study contained a retrospective primary dataset of 224 pathologically confirmed gastric adenocarcinomas (161 males, 63 females; mean age: 60.57 ± 10.81 years, range: 20-86 years) and an external prospective validation dataset from the second hospital (77 males and 35 females; mean age, 61.05 ± 10.51 years, range, 31 to 86 years). Triple-phase enhanced CT scans with gemstone spectral imaging mode were performed within one week before surgery. The clinicopathological characteristics were collected, the iodine concentration (IC) of the primary tumours at arterial phase (AP), venous phase (VP), and delayed phase (DP) were measured and then normalized to aorta (nICs). Univariable analysis was used to compare the differences of clinicopathological and IC values between LVI positive and negative groups. Independent predictors for LVI were screened by multivariable logistic regression analysis in primary dataset and used to develop a nomogram, and its performance was evaluated by using ROC analysis and tested in validation dataset. Its clinical use was evaluated by decision curve analysis (DCA).

Results

Tumor thickness, Borrmann classification, CT reported lymph node (LN) status and nICDP were independent predictors for LVI, and the nomogram based on these indicators was significantly associated with LVI (P<0.001). It yielded an AUC of 0.825 (95% confidence interval [95% CI], 0.769-0.872) and 0.802 (95% CI, 0.716-0.871) in primary and validation datasets (all P<0.05), with promising clinical utility by DCA.

Conclusion

This study presented a dual energy CT quantification based nomogram, which enables preferable preoperative individualized prediction of LVI in patients with GC.

Can lymphovascular invasion be predicted by contrast-enhanced CT imaging features in patients with esophageal squamous cell carcinoma? A preliminary retrospective study

Background

To investigate the value of contrast-enhanced CT (CECT)-derived imaging features in predicting lymphovascular invasion (LVI) status in esophageal squamous cell carcinoma (ESCC) patients.

Methods

One hundred and ninety-seven patients with postoperative pathologically confirmed esophageal squamous cell carcinoma treated in our hospital between January 2017 and January 2019 were enrolled in our study, including fifty-nine patients with LVI and one hundred and thirty-eight patients without LVI. The CECT-derived imaging features of all patients were analyzed. The CECT-derived imaging features were divided into quantitative features and qualitative features. The quantitative features consisted of the CT attenuation value of the tumor (CTV_Tumor), the CT attenuation value of the normal esophageal wall (CTV_Normal), the CT attenuation value ratio of the tumor-to-normal esophageal wall (TNR), the CT attenuation value difference between the tumor and normal esophageal wall (ΔTN), the maximum thickness of the tumor measured by CECT (Thickness), the maximum length of the tumor measured by CECT (Length), and the gross tumor volume measured by CECT (GTV). The qualitative features consisted of an enhancement pattern, tumor margin, enlarged blood supply or drainage vessels to the tumor (EVFDT), and tumor necrosis. For the clinicopathological characteristics and CECT-derived imaging feature analysis, the chi-squared test was used for categorical variables, the Mann–Whitney U test was used for continuous variables with a nonnormal distribution, and the independent sample t-test was used for the continuous variables with a normal distribution. The trend test was used for ordinal variables. The association between LVI status and CECT-derived imaging features was analyzed by univariable logistic analysis, followed by multivariable logistic regression and receiver operating characteristic (ROC) curve analysis.

Results

The CTV_Tumor, TNR, ΔTN, Thickness, Length, and GTV in the group with LVI were higher than those in the group without LVI (P < 0.05). A higher proportion of patients with heterogeneous enhancement pattern, irregular tumor margin, EVFDT, and tumor necrosis were present in the group with LVI (P < 0.05). As revealed by the univariable logistic analysis, the CECT-derived imaging features, including CTV_Tumor, TNR, ΔTN and enhancement pattern, Thickness, Length, GTV, tumor margin, EVFDT, and tumor necrosis were associated with LVI status (P < 0.05). Only the TNR (OR 8.655; 95% CI 2.125–37.776), Thickness (OR 6.531; 95% CI 2.410–20.608), and tumor margin (OR 4.384; 95% CI 2.004–9.717) were independent risk factors for LVI in the multivariable logistic regression analysis. The ROC curve analysis incorporating the above three CECT-derived imaging features showed that the area under the curve obtained by the multivariable logistic regression model was 0.820 (95% CI 0.754–0.885).

Conclusion

The CECT-derived imaging features, including TNR, Thickness, tumor margin, and their combination, can be used as predictors of LVI status for patients with ESCC.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-022-00804-7.

Machine learning analysis for the noninvasive prediction of lymphovascular invasion in gastric cancer using PET/CT and enhanced CT-based radiomics and clinical variables

PURPOSE

Lymphovascular invasion (LVI) is associated with metastasis and poor survival in patients with gastric cancer, yet the noninvasive diagnosis of LVI is difficult. This study aims to develop predictive models using different machine learning (ML) classifiers based on both enhanced CT and PET/CT images and clinical variables for preoperatively predicting lymphovascular invasion (LVI) status of gastric cancer.

METHODS

A total of 101 patients with gastric cancer who underwent surgery were retrospectively recruited, and the LVI status was confirmed by pathological analysis. Patients were randomly divided into a training dataset (n = 76) and a validation dataset (n = 25). By 3D manual segmentation, radiomics features were extracted from the PET and venous phase CT images. Image models, clinical models, and combined models were constructed by selected enhanced CT-based and PET-based radiomics features, clinical factors, and a combination of both, respectively. Three ML classifiers including adaptive boosting (AdaBoost), linear discriminant analysis (LDA), and logistic regression (LR) were used for model development. The performance of these predictive models was evaluated with respect to discrimination, calibration, and clinical usefulness.

RESULTS

Ten radiomics features and eight clinical factors were selected for the development of predictive models. In the validation dataset, the area under curve (AUC) values of clinical models using AdaBoost, LDA, and LR classifiers were 0.742, 0.706, and 0.690, respectively. The image models using AdaBoost, LDA, and LR classifiers achieved an AUC of 0.849, 0.778, and 0.810, respectively. The combined models showed improved performance than the image models and the clinical models, with the AUC values of AdaBoost, LDA, and LR classifier yielding 0.944, 0.929, and 0.921, respectively. The combined models also showed good calibration and clinical usefulness for LVI prediction.

CONCLUSION

ML-based models integrating PET/CT and enhanced CT radiomics features and clinical factors have good discrimination capability, which could serve as a noninvasive, preoperative tool for the prediction of LVI and assist surgical treatment decisions in patients with gastric cancer.

Using quantitative parameters derived from pretreatment dual-energy computed tomography to predict histopathologic features in head and neck squamous cell carcinoma

BACKGROUND

Head and neck squamous cell carcinoma (HNSCC) patients with a high tumor grade, lymphovascular invasion (LVI), or perineural invasion (PNI) tend to demonstrate a poor prognosis in clinical series. Thus, the identification of histopathological features, including tumor grade, LVI, and PNI, before treatment could be used to stratify the prognosis of patients with HNSCC. This study aimed to assess whether quantitative parameters derived from pretreatment dual-energy computed tomography (DECT) can predict the histopathological features of patients with HNSCC.

METHODS

In this study, 72 consecutive patients with pathologically confirmed HNSCC were enrolled and underwent dual-phase (noncontrast-enhanced phase and contrast-enhanced phase) DECT examinations. Normalized iodine concentration (NIC), the slope of the spectral Hounsfield unit curve (λ_HU), and normalized effective atomic number (NZ_eff) were calculated. The attenuation values on 40-140 keV noise-optimized virtual monoenergetic images [VMIs (+)] in the contrast-enhanced phase were recorded. The diagnostic performance of the quantitative parameters for predicting histopathological features, including tumor grade, LVI, and PNI, was assessed by receiver operating characteristic curves.

RESULTS

The NIC, λ_HU, NZ_eff, and attenuation value on the VMIs (+) at 40 keV (A₄₀) in the grade III group, LVI-positive group, and PNI-positive group were significantly higher than those in the grade I and II groups, the LVI-negative group, and the PNI-negative group (all P values <0.05). A multivariate logistic regression model combining these 4 quantitative parameters improved the diagnostic performance of the model in predicting tumor grade, LVI, and PNI (areas under the curve: 0.969, 0.944, and 0.931, respectively).

CONCLUSIONS

Quantitative parameters derived from pretreatment DECT, including NIC, λ_HU, NZ_eff, and A_4,0 were found to be imaging markers for predicting the histopathological characteristics of HNSCC. Combining all these characteristics improved the predictive performance of the model.

Can Lymphovascular Invasion be Predicted by Preoperative Contrast-Enhanced CT in Esophageal Squamous Cell Carcinoma?

Objective: To explore whether preoperative contrast-enhanced computed tomogrpahy (CT) can predict lymphovascular invasion (LVI) in esophageal squamous cell carcinoma (ESCC), and provide a reliable reference for the formulation of clinical individualized treatment plans. Methods: This retrospective study enrolled 228 patients with surgically resected and pathologically confirmed ESCC, including 36 patients with LVI and 192 patients without LVI. All patients underwent contrast-enhanced CT (CECT) scan within 2 weeks before the operation. Tumor size (including tumor length and maximum tumor thickness), tumor-to-normal wall enhancement ratio (TNR), and gross tumor volume (GTV) were obtained. All clinical features and CECT-derived parameters associated with LVI were analyzed by univariate and multivariate analysis. The independent predictors for LVI were identified, and their combination was built by multivariate logistic regression analysis, using the significant variables from the univariate analysis as inputs. Results: Univariate analysis of clinical features and CECT-derived parameters revealed that age, TNR, and clinical N stage (cN stage) were significantly associated with LVI. The multivariable analysis results demonstrated that age (odds ratio [OR]: 5.32, 95% confidence interval [CI]: 2.224-12.743, P<.001), TNR (OR: 5.399, 95% CI: 1.609-18.110, P  =  .006), and cN stage (cN1: OR: 2.874, 95% CI: 1.182-6.989, P  =  .02; cN2: OR: 6.876, 95% CI: 2.222-21.227) were identified to be independent predictors for LVI. The combination of age, TNR, and cN stage achieved a relatively higher area under the curve (AUC) (0.798), accuracy (ACC) (65.4%), sensitivity (SEN) (69.4%), specificity (SPE) (79.7%), positive predictive value (PPV) (77.4%), and negative predictive value (NPV) (71.6%). Conclusions: The combination of clinical features and CECT-derived parameters may be effective in predicting LVI status preoperatively in ESCC.

Development and Validation of Multivariate Models Integrating Preoperative Clinicopathological Parameters and Radiographic Findings Based on Late Arterial Phase CT Images for Predicting Lymph Node Metastasis in Gastric Cancer

RATIONALE AND OBJECTIVES

To develop and validate multivariate models integrating endoscopic biopsy, tumor markers, computed tomography (CT) morphological characteristics based on late arterial phase (LAP), and CT value-related and texture parameters to predict lymph node (LN) metastasis in gastric cancers (GCs).

MATERIALS AND METHODS

The preoperative differentiation degree based on biopsy, 6 tumor markers, 8 CT morphological characteristics based on LAP, 18 CT value-related parameters, and 35 CT texture parameters of 163 patients (111 men and 52 women) with GC were analyzed retrospectively. The differences in parameters between N (-) and N (+) GCs were analyzed by the Mann-Whitney U test. Diagnostic performance was obtained by receiver operating characteristic (ROC) curve analysis. Multivariate models based on regression analysis and machine learning algorithms were performed to improve diagnostic efficacy.

RESULTS

The differentiation degree, carbohydrate antigen (CA) 199 and CA242, 5 CT morphological characteristics, and 22 CT texture parameters showed significant differences between N (-) and N (+) GCs in the primary cohort (all p < 0.05). The multivariate model integrating clinicopathological parameters and radiographic findings based on regression analysis achieved areas under the ROC curve (AUCs) of 0.936 and 0.912 in the primary and validation cohorts, respectively. The model generated by the support vector machine algorithm achieved AUCs of 0.914 and 0.948, respectively.

CONCLUSION

We developed and validated multivariate models integrating endoscopic biopsy, tumor markers, CT morphological characteristics based on LAP, and CT texture parameters to predict LN metastasis in GCs and achieved satisfactory performance.

Prediction of serosal invasion in gastric cancer: development and validation of multivariate models integrating preoperative clinicopathological features and radiographic findings based on late arterial phase CT images

BACKGROUND

To develop and validate multivariate models integrating endoscopic biopsy, tumor markers, and CT findings based on late arterial phase (LAP) to predict serosal invasion in gastric cancer (GC).

METHODS

The preoperative differentiation degree, tumor markers, CT morphological characteristics, and CT value-related and texture parameters of 154 patients with GC were analyzed retrospectively. Multivariate models based on regression analysis and machine learning algorithms were performed to improve the diagnostic efficacy.

RESULTS

The differentiation degree, carbohydrate antigen (CA) 199, CA724, CA242, and multiple CT findings based on LAP differed significantly between T1-3 and T4 GCs in the primary cohort (all P < 0.05). Multivariate models based on regression analysis and random forest achieved AUCs of 0.849 and 0.865 in the primary cohort, respectively.

CONCLUSION

We developed and validated multivariate models integrating endoscopic biopsy, tumor markers, CT morphological characteristics, and CT value-related and texture parameters to predict serosal invasion in GCs and achieved favorable performance.

Performance of quantitative CT texture analysis in differentiation of gastric tumors

PURPOSE

To examine the computed tomography (CT) images of patients with a diagnosis of gastric tumor by texture analysis and to investigate its place in differential diagnosis.

MATERIALS AND METHODS

Contrast enhanced venous phase CT images of 163 patients with pathological diagnosis of gastric adenocarcinoma (n = 125), gastric lymphoma (n = 12) and gastrointestinal stromal tumors (n = 26) were retrospectively analyzed. Pixel size adjustment, gray-level discretization and gray-level normalization procedures were applied as pre-processing steps. Region of interest (ROI) was determined from the axial slice that represented the largest lesion area and a total of 40 texture features were calculated for each patient. Texture features were compared between the tumor subtypes and between adenocarcinoma grades. Statistically significant texture features were combined into a single parameter by logistic regression analysis. The sensitivity and specificity of these features and the combined parameter were measured to differentiate tumor subtypes by receiver-operating characteristic curve (ROC) analysis.

RESULTS

Classifications between adenocarcinoma versus lymphoma, adenocarcinoma vs. gastrointestinal stromal tumor (GIST) and well-differentiated adenocarcinoma versus poorly differentiated adenocarcinoma using texture features yielded successful results with high sensitivity (98, 91, 96%, respectively) and specificity (75, 77, 80%, respectively).

CONCLUSIONS

CT texture analysis is a non-invasive promising method for classifying gastric tumors and predicting gastric adenocarcinoma differentiation.

Contrast-Enhanced CT-Based Radiomics Analysis in Predicting Lymphovascular Invasion in Esophageal Squamous Cell Carcinoma

Objectives

To develop a radiomics model based on contrast-enhanced CT (CECT) to predict the lymphovascular invasion (LVI) in esophageal squamous cell carcinoma (ESCC) and provide decision-making support for clinicians.

Patients and Methods

This retrospective study enrolled 334 patients with surgically resected and pathologically confirmed ESCC, including 96 patients with LVI and 238 patients without LVI. All enrolled patients were randomly divided into a training cohort and a testing cohort at a ratio of 7:3, with the training cohort containing 234 patients (68 patients with LVI and 166 without LVI) and the testing cohort containing 100 patients (28 patients with LVI and 72 without LVI). All patients underwent preoperative CECT scans within 2 weeks before operation. Quantitative radiomics features were extracted from CECT images, and the least absolute shrinkage and selection operator (LASSO) method was applied to select radiomics features. Logistic regression (Logistic), support vector machine (SVM), and decision tree (Tree) methods were separately used to establish radiomics models to predict the LVI status in ESCC, and the best model was selected to calculate Radscore, which combined with two clinical CT predictors to build a combined model. The clinical model was also developed by using logistic regression. The receiver characteristic curve (ROC) and decision curve (DCA) analysis were used to evaluate the model performance in predicting the LVI status in ESCC.

Results

In the radiomics model, Sphericity and gray-level non-uniformity (GLNU) were the most significant radiomics features for predicting LVI. In the clinical model, the maximum tumor thickness based on CECT (cThick) in patients with LVI was significantly greater than that in patients without LVI (P<0.001). Patients with LVI had higher clinical N stage based on CECT (cN stage) than patients without LVI (P<0.001). The ROC analysis showed that both the radiomics model (AUC values were 0.847 and 0.826 in the training and testing cohort, respectively) and the combined model (0.876 and 0.867, respectively) performed better than the clinical model (0.775 and 0.798, respectively), with the combined model exhibiting the best performance.

Conclusions

The combined model incorporating radiomics features and clinical CT predictors may potentially predict the LVI status in ESCC and provide support for clinical treatment decisions.

A Nomogram for Predicting Lymphovascular Invasion in Superficial Esophageal Squamous Cell Carcinoma

The lymphovascular invasion (LVI) status facilitates the determination of the optimal therapeutic strategy for superficial esophageal squamous cell carcinoma (SESCC), but in clinical practice, LVI must be confirmed by postoperative pathology. However, studies of the risk factors for LVI in SESCC are limited. Consequently, this study aimed to identify the risk factors for LVI and use these factors to establish a prediction model. The data of 516 patients who underwent radical esophagectomy between January 2007 and September 2019 were retrospectively collected (training set, n=361, January 2007 to May 2015; validation set, n=155, June 2015 to September 2019). In the training set, least absolute shrinkage and selection operator (LASSO) regression and multivariate analyses were utilized to identify predictive factors for LVI in patients with SESCC. A nomogram was then developed using these predictors. The area under the curve (AUC), calibration curve, and decision curve were used to evaluate the efficiency, accuracy, and clinical utility of the model. LASSO regression indicated that the tumor size, depth of invasion, tumor differentiation, lymph node metastasis (LNM), sex, circumferential extension, the presence of multiple lesions, and the resection margin were correlated with LVI. However, multivariate analysis revealed that only the tumor size, depth of invasion, tumor differentiation, and LNM were independent risk factors for LVI. Incorporating these four variables, model 1 achieved an AUC of 0.817 in predicting LVI. Adding circumferential extension to model 1 did not appreciably change the AUC and integrated discrimination improvement, but led to a significant increase in the net reclassification improvement (p=0.011). A final nomogram was constructed by incorporating tumor size, depth of invasion, tumor differentiation, LNM, and circumferential extension and showed good discrimination (training set, AUC=0.833; validation set, AUC=0.819) and good calibration in the training and validation sets. Decision curve analysis demonstrated that the nomogram was clinically useful in both sets. Thus, it is possible to predict the status of LVI using this nomogram scoring system, which can aid the selection of an appropriate treatment plan.

Gastric poorly cohesive carcinoma: differentiation from tubular adenocarcinoma using nomograms based on CT findings in the 40 s late arterial phase

OBJECTIVES

To summarise the CT findings of gastric poorly cohesive carcinoma (PCC) in the 40 s late arterial phase and differentiate it from tubular adenocarcinoma (TAC) using an integrative nomogram.

METHODS

A total of 241 patients including 59 PCCs, 109 TACs, and 73 other type gastric cancers were enrolled. Thirteen CT morphological characteristics of each lesion in the late arterial phase were evaluated. In addition, CT value-related parameters were extracted from ROIs encompassing the area of greatest enhancement on four-phase CT images. Nomograms based on regression models were built to discriminate PCCs from TACs and from non-PCCs. ROC curve analysis was performed to assess the diagnostic efficiency.

RESULTS

Six morphological characteristics, 10 CT value-related parameters, and the enhanced curve types differed significantly among the above three groups in the primary cohort (all p < 0.05). The paired comparison revealed that 10 CT value-related parameters differed significantly between PCCs and TACs (all p < 0.05). The AUC of the nomogram based on the multivariate model for discriminating PCCs from TACs was 0.954, which was confirmed in the validation cohort (AUC = 0.895). The AUC of another nomogram for discriminating PCCs from non-PCCs was 0.938, which was confirmed in the validation cohort (AUC = 0.880).

CONCLUSIONS

In the 40 s late arterial phase, the morphological characteristics and CT value-related parameters were significantly different among PCCs, TACs, and other types. PCCs were prone to manifest mucosal line interruption, diffuse thickening, infiltrative growth, and slow-rising enhanced curve (Type A). Furthermore, multivariate models were useful in discriminating PCCs from TACs and other types.

KEY POINTS

• Multiple morphological characteristics and CT value-related parameters differed significantly between gastric PCCs and TACs in the 40 s late arterial phase. • The nomogram integrating morphological characteristics and CT value-related parameters in the 40 s late arterial phase had favourable performance in discriminating PCCs from TACs. • More useful information can be derived from 40 s late arterial phase CT images; thus, a more accurate evaluation can be made in clinical practice.

Machine Learning-Based Computational Models Derived From Large-Scale Radiographic-Radiomic Images Can Help Predict Adverse Histopathological Status of Gastric Cancer

INTRODUCTION

Adverse histopathological status (AHS) decreases outcomes of gastric cancer (GC). With the lack of a single factor with great reliability to preoperatively predict AHS, we developed a computational approach by integrating large-scale imaging factors, especially radiomic features at contrast-enhanced computed tomography, to predict AHS and clinical outcomes of patients with GC.

METHODS

Five hundred fifty-four patients with GC (370 training and 184 test) undergoing gastrectomy were retrospectively included. Six radiomic scores (R-scores) related to pT stage, pN stage, Lauren & Borrmann (L&B) classification, World Health Organization grade, lymphatic vascular infiltration, and an overall histopathologic score (H-score) were, respectively, built from 7,000+ radiomic features. R-scores and radiographic factors were then integrated into prediction models to assess AHS. The developed AHS-based Cox model was compared with the American Joint Committee on Cancer (AJCC) eighth stage model for predicting survival outcomes.

RESULTS

Radiomics related to tumor gray-level intensity, size, and inhomogeneity were top-ranked features for AHS. R-scores constructed from those features reflected significant difference between AHS-absent and AHS-present groups (P < 0.001). Regression analysis identified 5 independent predictors for pT and pN stages, 2 predictors for Lauren & Borrmann classification, World Health Organization grade, and lymphatic vascular infiltration, and 3 predictors for H-score, respectively. Area under the curve of models using those predictors was training/test 0.93/0.94, 0.85/0.83, 0.63/0.59, 0.66/0.63, 0.71/0.69, and 0.84/0.77, respectively. The AHS-based Cox model produced higher area under the curve than the eighth AJCC staging model for predicting survival outcomes. Furthermore, adding AHS-based scores to the eighth AJCC staging model enabled better net benefits for disease outcome stratification.

DISCUSSION

The developed computational approach demonstrates good performance for successfully decoding AHS of GC and preoperatively predicting disease clinical outcomes.

Radiomics analysis of contrast-enhanced CT predicts lymphovascular invasion and disease outcome in gastric cancer: a preliminary study

BACKGROUND

To determine whether radiomics features based on contrast-enhanced CT (CECT) can preoperatively predict lymphovascular invasion (LVI) and clinical outcome in gastric cancer (GC) patients.

METHODS

In total, 160 surgically resected patients were retrospectively analyzed, and seven predictive models were constructed. Three radiomics predictive models were built from radiomics features based on arterial (A), venous (V) and combination of two phase (A + V) images. Then, three Radscores (A-Radscore, V-Radscore and A + V-Radscore) were obtained. Another four predictive models were constructed by the three Radscores and clinical risk factors through multivariate logistic regression. A nomogram was developed to predict LVI by incorporating A + V-Radscore and clinical risk factors. Kaplan-Meier curve and log-rank test were utilized to analyze the outcome of LVI.

RESULTS

Radiomics related to tumor size and intratumoral inhomogeneity were the top-ranked LVI predicting features. The related Radscores showed significant differences according to LVI status (P < 0.01). Univariate logistic analysis identified three clinical features (T stage, N stage and AJCC stage) and three Radscores as LVI predictive factors. The Clinical-Radscore (namely, A + V + C) model that used all these factors showed a higher performance (AUC = 0.856) than the clinical (namely, C, including T stage, N stage and AJCC stage) model (AUC = 0.810) and the A + V-Radscore model (AUC = 0.795) in the train cohort. For patients without LVI and with LVI, the median progression-free survival (PFS) was 11.5 and 8.0 months (P < 0.001),and the median OS was 20.2 and 17.0 months (P = 0.3), respectively. In the Clinical-Radscore-predicted LVI absent and LVI present groups, the median PFS was 11.0 and 8.0 months (P = 0.03), and the median OS was 20.0 and 18.0 months (P = 0.05), respectively. N stage, LVI status and Clinical-Radscore-predicted LVI status were associated with disease-specific recurrence or mortality.

CONCLUSIONS

Radiomics features based on CECT may serve as potential markers to successfully predict LVI and PFS, but no evidence was found that these features were related to OS. Considering that it is a single central study, multi-center validation studies will be required in the future to verify its clinical feasibility.

Computed tomography texture analysis in patients with gastric cancer: a quantitative imaging biomarker for preoperative evaluation before neoadjuvant chemotherapy treatment

PURPOSE

The aim of the study is to explore the role of computed tomography texture analysis (CT-TA) for predicting clinical T and N stages and tumor grade before neoadjuvant chemotherapy treatment in gastric cancer (GC) patients during the preoperative period.

MATERIALS AND METHODS

CT images of 114 patients with GC were included in this retrospective study. Following pre-processing steps, textural features were extracted using MaZda software in the portal venous phase. We evaluated and analyzed texture features of six principal categories for differentiating between T stages (T1,2 vs T3,4), N stages (N+ vs N-) and grades (low-intermediate vs. high). Classification was performed based on texture parameters with high model coefficients in linear discriminant analysis (LDA).

RESULTS

Dimension-reduction steps yielded five textural features for T stage, three for N stage and two for tumor grade. The discriminatory capacities of T stage, N stage and tumor grade were 90.4%, 81.6% and 64.5%, respectively, when LDA algorithm was employed.

CONCLUSION

CT-TA yields potentially useful imaging biomarkers for predicting the T and N stages of patients with GC and can be used for preoperative evaluation before neoadjuvant treatment planning.

Influential factors and prognostic analysis of blood vessel invasion in advanced gastric cancer

The purpose of this study was to analyze the influencing factors of BVI in advanced gastric cancer and explore the factors affecting the prognosis of advanced gastric cancer, so as to accurately evaluate the disease status and enable patients to receive effective treatment. We retrospectively analyzed 622 cases with complete data and successful follow-up. BVI was found in 144 of the 622 patients with advanced gastric cancer, with a detection rate of 23.15%. BVI was closely related to the differentiation degree, infiltration depth and lymph node metastasis of advanced gastric cancer, (P <  0.05). Gender, age, tumor location, tumor size, Lauren classification, tumor M stage, and clinical TNM stage were not the influencing factors of BVI in patients with advanced gastric cancer (P >  0.05). The 5-year survival rate of patients in the positive group of BVI was 34.72%. The 5-year survival rate of patients with advanced gastric cancer was correlated with BVI, Lauren classification, depth of invasion, lymph node metastasis, and clinical TNM staging, (P <  0.05). The 5-year survival rate was independent of gender, age, tumor location, tumor size, tumor tissue differentiation, and M stage (P >  0.05). The results of multi-factor analysis showed that BVI, N stage and clinical TNM stage were independent predictors of prognosis in patients with advanced radical gastric cancer. By analyzing the stage and related prognostic factors of resectable advanced gastric cancer, we found that BVI was not only closely related to lymph node metastasis, but also an independent predictor of prognosis of advanced gastric cancer. As this study was only a single-center retrospective study, there may be a selective bias in clinical data. So large-scale and multi-center collaboration is needed to further explore the influencing factors of BVI in the progression of gastric cancer.

Gastric heterotopic pancreas and stromal tumors smaller than 3 cm in diameter: clinical and computed tomography findings

BACKGROUND

Identifying gastric heterotopic pancreas and stromal tumors is difficult. Few studies have reported computed tomography (CT) findings for differentiating lesions less than 3 cm in diameter. In this study, we aimed to identify clinical characteristics and CT findings that can differentiate gastric heterotopic pancreatic lesions from stromal tumors less than 3 cm in diameter.

METHODS

A total of 132 patients with pathologically confirmed gastric heterotopic pancreas (n = 66) and stromal tumors (n = 66) were included. Each group was divided into primary (n = 50) and validation cohort (n = 16). Clinical characteristics and CT findings were retrospectively reviewed. CT findings included location, border, contour, growth pattern, enhancement pattern and grade, the enhancement value of tumor, enhancement ratio of tumor, and enhancement ratio of tumor to pancreas in venous phase. The findings in the two groups were compared using the Pearson χ² test or Student t-test. Receiver operating characteristic curves were used to determine areas under the curve and optimal cut-offs.

RESULTS

Significant differences were observed between heterotopic pancreas and stromal tumors in the distribution of tumor location, border, contour (all P < 0.001), enhancement values (P < 0.001), enhancement ratios of tumors (P < 0.001), and enhancement ratios of tumors to pancreas (P < 0.001). No significant differences existed in growth pattern (P = 0.203). The area under the curve differed significantly between enhancement ratio of tumor to pancreas and enhancement ratio (P = 0.030). There were significant differences in above characteristics between two groups in validation cohort.

CONCLUSIONS

Heterotopic pancreas has characteristic CT features differentiating it from stromal tumors.

Application of CT texture analysis in predicting histopathological characteristics of gastric cancers

OBJECTIVES

To explore the application of computed tomography (CT) texture analysis in predicting histopathological features of gastric cancers.

METHODS

Preoperative contrast-enhanced CT images and postoperative histopathological features of 107 patients (82 men, 25 women) with gastric cancers were retrospectively reviewed. CT texture analysis generated: (1) mean attenuation, (2) standard deviation, (3) max frequency, (4) mode, (5) minimum attenuation, (6) maximum attenuation, (7) the fifth, 10th, 25th, 50th, 75th and 90th percentiles, and (8) entropy. Correlations between CT texture parameters and histopathological features were analysed.

RESULTS

Mean attenuation, maximum attenuation, all percentiles and mode derived from portal venous CT images correlated significantly with differentiation degree and Lauren classification of gastric cancers (r, -0.231 ~ -0.324, 0.228 ~ 0.321, respectively). Standard deviation and entropy derived from arterial CT images also correlated significantly with Lauren classification of gastric cancers (r = -0.265, -0.222, respectively). In arterial phase analysis, standard deviation and entropy were significantly lower in gastric cancers with than those without vascular invasion; however, minimum attenuation was significantly higher in gastric cancers with than those without vascular invasion.

CONCLUSION

CT texture analysis held great potential in predicting differentiation degree, Lauren classification and vascular invasion status of gastric cancers.

KEY POINTS

• CT texture analysis is noninvasive and effective for gastric cancer. • Portal venous CT images correlated significantly with differentiation degree and Lauren classification. • Standard deviation, entropy and minimum attenuation in arterial phase reflect vascular invasion.