Prognostic aspects of lymphovascular invasion in localized gastric cancer: new insights into the radiomics and deep transfer learning from contrast-enhanced CT imaging

Prediction of lymphovascular invasion of gastric cancer based on contrast-enhanced computed tomography radiomics

Background

Lymphovascular invasion (LVI) is a significant risk factor for lymph node metastasis in gastric cancer (GC) and is closely related to the prognosis and recurrence of GC. This study aimed to establish clinical models, radiomics models and combination models for the diagnosis of GC vascular invasion.

Methods

This study enrolled 146 patients with GC proved by pathology and who underwent radical resection of GC. The patients were assigned to the training and validation cohorts. A total of 1,702 radiomic features were extracted from contrast-enhanced computed tomography images of GC. Logistic regression analyses were performed to establish a clinical model, a radiomics model and a combined model. The performance of the predictive models was measured by the receiver operating characteristic (ROC) curve.

Results

In the training cohort, the age of LVI negative (-) patients and LVI positive (+) patients were 62.41 ± 8.41 and 63.76 ± 10.08 years, respectively, and there were more male (n = 63) than female (n = 19) patients in the LVI (+) group. Diameter and differentiation were the independent risk factors for determining LVI (-) and (+). A combined model was found to be relatively highly discriminative based on the area under the ROC curve for both the training (0.853, 95% CI: 0.784-0.920, sensitivity: 0.650 and specificity: 0.907) and the validation cohorts (0.742, 95% CI: 0.559-0.925, sensitivity: 0.736 and specificity: 0.700).

Conclusions

The combined model had the highest diagnostic effectiveness, and the nomogram established by this model had good performance. It can provide a reliable prediction method for individual treatment of LVI in GC before surgery.

Radiomics analysis in predicting vascular invasion in gastric cancer based on enhanced CT: a preliminary study

BACKGROUND

Vascular invasion (VI) is closely related to the metastasis, recurrence, prognosis, and treatment of gastric cancer. Currently, predicting VI preoperatively using traditional clinical examinations alone remains challenging. This study aims to explore the value of radiomics analysis based on preoperative enhanced CT images in predicting VI in gastric cancer.

METHODS

We retrospectively analyzed 194 patients with gastric adenocarcinoma who underwent enhanced CT examination. Based on pathology analysis, patients were divided into the VI group (n = 43) and the non-VI group (n = 151). Radiomics features were extracted from arterial phase (AP) and portal venous phase (PP) CT images. The radiomics score (Rad-score) was then calculated. Prediction models based on image features, clinical factors, and a combination of both were constructed. The diagnostic efficiency and clinical usefulness of the models were evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA).

RESULTS

The combined prediction model included the Rad-score of AP, the Rad-score of PP, Ki-67, and Lauren classification. In the training group, the area under the curve (AUC) of the combined prediction model was 0.83 (95% CI 0.76-0.89), with a sensitivity of 64.52% and a specificity of 92.45%. In the validation group, the AUC was 0.80 (95% CI 0.67-0.89), with a sensitivity of 66.67% and a specificity of 88.89%. DCA indicated that the combined prediction model might have a greater net clinical benefit than the clinical model alone.

CONCLUSION

The integrated models, incorporating enhanced CT radiomics features, Ki-67, and clinical factors, demonstrate significant predictive capability for VI. Moreover, the radiomics model has the potential to optimize personalized clinical treatment selection and patient prognosis assessment.

Radiomics in Oesogastric Cancer: Staging and Prediction of Preoperative Treatment Response: A Narrative Review and the Results of Personal Experience

BACKGROUND

Oesophageal, gastroesophageal, and gastric malignancies are often diagnosed at locally advanced stage and multimodal therapy is recommended to increase the chances of survival. However, given the significant variation in treatment response, there is a clear imperative to refine patient stratification. The aim of this narrative review was to explore the existing evidence and the potential of radiomics to improve staging and prediction of treatment response of oesogastric cancers.

METHODS

The references for this review article were identified via MEDLINE (PubMed) and Scopus searches with the terms "radiomics", "texture analysis", "oesophageal cancer", "gastroesophageal junction cancer", "oesophagogastric junction cancer", "gastric cancer", "stomach cancer", "staging", and "treatment response" until May 2024.

RESULTS

Radiomics proved to be effective in improving disease staging and prediction of treatment response for both oesophageal and gastric cancer with all imaging modalities (TC, MRI, and 18F-FDG PET/CT). The literature data on the application of radiomics to gastroesophageal junction cancer are very scarce. Radiomics models perform better when integrating different imaging modalities compared to a single radiology method and when combining clinical to radiomics features compared to only a radiomics signature.

CONCLUSIONS

Radiomics shows potential in noninvasive staging and predicting response to preoperative therapy among patients with locally advanced oesogastric cancer. As a future perspective, the incorporation of molecular subgroup analysis to clinical and radiomic features may even increase the effectiveness of these predictive and prognostic models.

Impact of Neoadjuvant Treatment on Body Composition in Patients with Locally Advanced Gastric Cancer

Neoadjuvant chemotherapy (NT) followed by radical surgery is the standard treatment for locally advanced gastric cancer (GC). The incidence of sarcopenia in upper gastrointestinal tract malignancies is very high, and it may be increased after NT. This study aimed to evaluate the impact of NT on body composition. A retrospective study of patients with locally advanced GC undergoing gastrectomy who had received NT in a tertiary hospital between 2012 and 2019 was conducted. CT measured the skeletal muscle index, total psoas area, and visceral and subcutaneous adipose tissue before and after NT. Of the 180 gastrectomies for GC, 61 patients received NT. During NT, changes in body composition were observed with a decrease in the skeletal muscle mass index (SMMI -2.5%; p < 0.001), and these changes were significantly greater in men (SMMI -10.55%). Before surgery, patients who received NT presented 15% more sarcopenia than those without NT (p = 0.048). In conclusion, patients with locally advanced gastric cancer who receive NT have significant changes in body composition during chemotherapy. These changes, which are at the expense of a loss of muscle mass, lead to an increased incidence of pre-surgical sarcopenia.

Preoperative Risk Stratification for Gastric Cancer: The Establishment of Dual-Energy CT-Based Radiomics Using Prospective Datasets at Two Centers

RATIONALE AND OBJECTIVES

To evaluate the performance of dual-energy CT (DECT)-based radiomics models for identifying high-risk histopathologic phenotypes-serosal invasion (pT4a), lymph node metastasis (LNM), lymphovascular invasion (LVI) and perineural invasion (PNI) in gastric cancer.

MATERIAL AND METHODS

This prospective bi-center study recruited histologically confirmed gastric adenocarcinoma patients who underwent triple-phase enhanced DECT before gastrectomy between January 2021 and July 2023. Radiomics features were extracted from polychromatic/monochromatic (40 keV, 100 keV)/iodine images at arterial/venous/delay phase, respectively. Predictive features were selected in the training dataset using logistic regression classifier, and trained models were applied to the external validation dataset. Performances of clinical models, conventional contrast enhanced CT (CECT) models and DECT models were evaluated using areas under the receiver operating characteristic curve (AUCs).

RESULTS

In total, 503 patients were recruited: 396 at training dataset (60.1 ± 10.8 years, 110 females, 286 males) and 107 at validation dataset (61.4 ± 9.5 years, 29 females, 78 males). DECT models dichotomizing pT4a, LNM, LVI, and PNI achieved AUCs of 0.891, 0.817, 0.834, and 0.889, respectively, in the validation dataset, similar with the CECT models. In the training dataset, compared to the CECT model, the DECT model provided increased performance for identifying pT4a, LNM, LVI (all P＜0.05), and similar performance for stratifying PNI (P = 0.104). The DECT models was associated with patient disease-free survival (all P＜0.05).

CONCLUSION

DECT radiomics can stratify patients preoperatively according to high-risk histopathologic phenotypes for gastric cancer and are associated with patient disease-free survival in the training dataset.

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.

Comparison of MRI and CT-Based Radiomics and Their Combination for Early Identification of Pathological Response to Neoadjuvant Chemotherapy in Locally Advanced Gastric Cancer

BACKGROUND

Current radiomics for treatment response assessment in gastric cancer (GC) have focused solely on Computed tomography (CT). The importance of multi-parametric magnetic resonance imaging (mp-MRI) radiomics in GC is less clear.

PURPOSE

To compare and combine CT and mp-MRI radiomics for pretreatment identification of pathological response to neoadjuvant chemotherapy in GC.

STUDY TYPE

Retrospective.

POPULATION

Two hundred twenty-five GC patients were recruited and split into training (157) and validation dataset (68) in the ratio of 7:3 randomly.

FIELD/SEQUENCE

T2-weighted fast spin echo (fat suppressed T2-weighted imaging [fs-T2WI]), diffusion weighted echo planar imaging (DWI), and fast gradient echo (dynamic contrast enhanced [DCE]) sequences at 3.0T.

ASSESSMENT

Apparent diffusion coefficient (ADC) maps were generated from DWI. CT, fs-T2WI, ADC, DCE, and mp-MRI Radiomics score (Radscores) were compared between responders and non-responders. A multimodal nomogram combining CT and mp-MRI Radscores was developed. Patients were followed up for 3-65 months (median 19) after surgery, the overall survival (OS) and progression free survival (PFS) were calculated.

STATISTICAL TESTS

A logistic regression classifier was applied to construct the five models. Each model's performance was evaluated using a receiver operating characteristic curve. The association of the nomogram with OS/PFS was evaluated by Kaplan-Meier survival analysis and C-index. A P value <0.05 was considered statistically significant.

RESULTS

CT Radscore, mp-MRI Radscore and nomogram were significantly associated with tumor regression grading. The nomogram achieved the highest area under the curves (AUCs) of 0.893 (0.834-0.937) and 0.871 (0.767-0.940) in training and validation datasets, respectively. The C-index was 0.589 for OS and 0.601 for PFS. The AUCs of the mp-MRI model were not significantly different to that of the CT model in training (0.831 vs. 0.770, P = 0.267) and validation dataset (0.797 vs. 0.746, P = 0.137).

DATA CONCLUSIONS

mp-MRI radiomics provides similar results to CT radiomics for early identification of pathologic response to neoadjuvant chemotherapy. The multimodal radiomics nomogram further improved the capability.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: 2.

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.

Multiparametric MRI-based radiomics nomogram for early prediction of pathological response to neoadjuvant chemotherapy in locally advanced gastric cancer

OBJECTIVES

To build and validate a multi-parametric MRI (mpMRI)-based radiomics nomogram for early prediction of treatment response to neoadjuvant chemotherapy (NAC) in locally advanced gastric cancer.

METHODS

Baseline MRI were retrospectively enrolled from 141 patients with gastric adenocarcinoma who received NAC followed by radical gastrectomy. According to pathologic response of tumor regression grading (TRG), patients were labeled as responders (TRG = 0 + 1) and non-responders (TRG = 2 + 3) and further divided into a training (n = 85) and validation dataset (n = 56). Radiomics score (Radscore) were built from T2WI, ADC, and venous phase of dynamic-contrasted-enhanced MR imaging. Clinical information, laboratory indicators, MRI parameters, and follow-up data were also recorded. According to multivariable regression analysis, an mpMRI radiomics nomogram was built and its predictive ability was evaluated by ROC analysis. Decision curve analysis was applied to evaluate the clinical usefulness. Kaplan-Meier survival curves based on the nomogram were used to estimate the progression-free survival (PFS) and overall survival (OS) in the validation dataset.

RESULTS

Both single sequence-based Radscores and mpMRI radiomics nomogram were associated with pathologic response (p < 0.001). The nomogram achieved the highest diagnostic ability with area under ROC curve of 0.844 (95% CI, 0.749-0.914) and 0.820 (95% CI, 0.695-0.910) in the training and validation datasets. The hazard ratio of the nomogram for PFS and OS prediction was 2.597 (95% CI: 1.046-6.451, log-rank p = 0.023) and 2.570 (95% CI: 1.166-5.666, log-rank p = 0.011).

CONCLUSIONS

The mpMRI-based radiomics nomogram showed preferable performance in predicting pathologic response to NAC in LAGC.

KEY POINTS

• This study investigated the value of multi-parametric MRI-based radiomics in predicting pathologic response to neoadjuvant chemotherapy in locally advanced gastric cancer. • The nomogram incorporating T2WI Radscore, ADC Radscore, and DCE Radscore as well as Borrmann classification outperformed the single sequence-based Radscore. • The nomogram also exhibited a promising prognostic ability for patient survival and enriched radiomics studies in gastric cancer.

Deep learning based radiomics for gastrointestinal cancer diagnosis and treatment: A minireview

Gastrointestinal (GI) cancers are the major cause of cancer-related mortality globally. Medical imaging is an important auxiliary means for the diagnosis, assessment and prognostic prediction of GI cancers. Radiomics is an emerging and effective technology to decipher the encoded information within medical images, and traditional machine learning is the most commonly used tool. Recent advances in deep learning technology have further promoted the development of radiomics. In the field of GI cancer, although there are several surveys on radiomics, there is no specific review on the application of deep-learning-based radiomics (DLR). In this review, a search was conducted on Web of Science, PubMed, and Google Scholar with an emphasis on the application of DLR for GI cancers, including esophageal, gastric, liver, pancreatic, and colorectal cancers. Besides, the challenges and recommendations based on the findings of the review are comprehensively analyzed to advance DLR.

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.