Texture analysis of computed tomography data using morphologic and metabolic delineation of esophageal cancer-relation to tumor type and neoadjuvant therapy response

18Fluorodeoxyglucose positron emission tomography (18F-FDG PET)-derived tumoral and peritumoral radiomic parameters can predict pathological subtype and survival in esophageal carcinoma

AIM

The aim of this study is to investigate the importance of the quantitative parameters of the tumoral and peritumoral regions in prediction of pathological subtypes and 1-year survival in patients with esophageal carcinoma.

MATERIALS AND METHODS

A total of 103 patients with esophageal squamous cell carcinoma (SCC) and adenocarcinoma (AC) and in whom 18fluorodeoxyglucose positron emission tomography/computerized tomography (18F-FDG PET/CT) was performed were included in the study. One-year progression-free survival (PFS) and overall survival times of all patients were noted. Primary tumor and peritumoral area were drawn with manual segmentation on the 18F-FDG PET images. Seventy-three quantitative parameters were extracted from tumoral and peritumoral volumes of interest by using software. The differences of parameters of tumoral and peritumoral regions were determined statistically between pathological subtypes and between 1-year survivors and non-survivors.

RESULTS

Diagnostic models were created with the statistically significant parameters. The model that consists of a tumoral and a peritumoral parameter could classify the pathological subtypes in 61% of the patients correctly (area under the curve [AUC]: 0.706, 61.2% accuracy, 53.7% sensitivity, and 75% specificity). The model that was created with 2 tumoral parameters could classify the 1-year survival in 66% of the patients correctly (AUC: 0.695, 66% accuracy, 73.6% sensitivity, and 56.1% specificity). The model consisting of a tumoral and a peritumoral parameter detected 1-year PFS in 66% of the patients accurately (AUC: 0.687, 66% accuracy, 72.4% sensitivity, and 55.6% specificity).

CONCLUSION

The quantitative parameters obtained from tumoral and peritumoral regions can provide information about pathological subtypes and 1-year survival in esophageal carcinoma.

Multicentre validation of CT grey-level co-occurrence matrix features for overall survival in primary oesophageal adenocarcinoma

BACKGROUND

Personalising management of primary oesophageal adenocarcinoma requires better risk stratification. Lack of independent validation of proposed imaging biomarkers has hampered clinical translation. We aimed to prospectively validate previously identified prognostic grey-level co-occurrence matrix (GLCM) CT features for 3-year overall survival.

METHODS

Following ethical approval, clinical and contrast-enhanced CT data were acquired from participants from five institutions. Data from three institutions were used for training and two for testing. Survival classifiers were modelled on prespecified variables ('Clinical' model: age, clinical T-stage, clinical N-stage; 'ClinVol' model: clinical features + CT tumour volume; 'ClinRad' model: ClinVol features + GLCM_Correlation and GLCM_Contrast). To reflect current clinical practice, baseline stage was also modelled as a univariate predictor ('Stage'). Discrimination was assessed by area under the receiver operating curve (AUC) analysis; calibration by Brier scores; and clinical relevance by thresholding risk scores to achieve 90% sensitivity for 3-year mortality.

RESULTS

A total of 162 participants were included (144 male; median 67 years [IQR 59, 72]; training, 95 participants; testing, 67 participants). Median survival was 998 days [IQR 486, 1594]. The ClinRad model yielded the greatest test discrimination (AUC, 0.68 [95% CI 0.54, 0.81]) that outperformed Stage (ΔAUC, 0.12 [95% CI 0.01, 0.23]; p = .04). The Clinical and ClinVol models yielded comparable test discrimination (AUC, 0.66 [95% CI 0.51, 0.80] vs. 0.65 [95% CI 0.50, 0.79]; p > .05). Test sensitivity of 90% was achieved by ClinRad and Stage models only.

CONCLUSIONS

Compared to Stage, multivariable models of prespecified clinical and radiomic variables yielded improved prediction of 3-year overall survival.

CLINICAL RELEVANCE STATEMENT

Previously identified radiomic features are prognostic but may not substantially improve risk stratification on their own.

KEY POINTS

• Better risk stratification is needed in primary oesophageal cancer to personalise management. • Previously identified CT features-GLCM_Correlation and GLCM_Contrast-contain incremental prognostic information to age and clinical stage. • Compared to staging, multivariable clinicoradiomic models improve discrimination of 3-year overall survival.

Correlation of primary tumor volume and histopathologic response following neoadjuvant treatment of esophageal adenocarcinoma

INTRODUCTION

In esophageal cancer, histopathologic response following neoadjuvant therapy and transthoracic esophagectomy is a strong predictor of long-term survival. At the present, it is not known whether the initial tumor volume quantified by computed tomography (CT) correlates with the degree of pathologic regression.

METHODS

In a retrospective analysis of a consecutive patient cohort with esophageal adenocarcinoma, tumor volume in CT prior to chemoradiotherapy or chemotherapy alone was quantified using manual segmentation. Primary tumor volume was correlated to the histomorphological regression based on vital residual tumor cells (VRTC) (Cologne regression scale, CRS: grade I, >50% VRTC; grade II, 10-50% VRTC; grade III, <10% VRTC and grade IV, complete response without VRTC).

RESULTS

A total of 287 patients, 165 with neoadjuvant chemoradiotherapy according to the CROSS protocol and 122 with chemotherapy according to the FLOT regimen, were included. The initial tumor volume for patients following CROSS and FLOT therapy was measured (CROSS: median 24.8 ml, IQR 13.1-41.1 ml, FLOT: 23.4 ml, IQR 10.6-37.3 ml). All patients underwent an Ivor-Lewis esophagectomy. 180 patients (62.7 %) were classified as minor (CRS I/II) and 107 patients (37.3 %) as major or complete responder (CRS III/IV). The median tumor volume was calculated as 24.2 ml (IQR 11.9-40.3 ml). Ordered logistic regression revealed no significant dependence of CRS from tumor volume (OR = 0.99, p-value = 0.99) irrespective of the type of multimodal treatment.

CONCLUSION

The initial tumor volume on diagnostic CT does not aid to differentiate between potential histopathological responders and non-responders to neoadjuvant therapy in esophageal cancer patients. The results emphasize the need to establish other biological markers of prediction.

Radiomics model based on contrast-enhanced CT texture features for pretreatment prediction of overall survival in esophageal neuroendocrine carcinoma

Background

Limited studies have observed the prognostic value of CT images for esophageal neuroendocrine carcinoma (NEC) due to rare incidence and low treatment experience in clinical. In this study, the pretreatment enhanced CT texture features and clinical characteristics were investigated to predict the overall survival of esophageal NEC.

Methods

This retrospective study included 89 patients with esophageal NEC. The training and testing cohorts comprised 61 (70%) and 28 (30%) patients, respectively. A total of 402 radiomics features were extracted from the tumor region that segmented pretreatment venous phase CT images. The least absolute shrinkage and selection operator (LASSO) Cox regression was applied to feature dimension reduction, feature selection, and radiomics signature construction. A radiomics nomogram was constructed based on the radiomics signature and clinical risk factors using a multivariable Cox proportional regression. The performance of the nomogram for the pretreatment prediction of overall survival (OS) was evaluated for discrimination and calibration.

Results

Only the enhancement degree was an independent factor in clinical variable influenced OS. The radiomics signatures demonstrated good predictability for prognostic status discrimination. The radiomics nomogram integrating texture signatures was slightly superior to the nomogram derived from the combined model with a C-index of 0.844 (95%CI: 0.783-0.905) and 0.847 (95% CI: 0.782-0.912) in the training set, and 0.805 (95%CI: 0.707-0.903) and 0.745 (95% CI: 0.639-0.851) in the testing set, respectively.

Conclusion

The radiomics nomogram based on pretreatment CT radiomics signature had better prognostic power and predictability of the overall survival in patients with esophageal NEC than the model using combined variables.

Prognostic value of pre-therapeutic FDG-PET radiomic analysis in gastro-esophageal junction cancer

The main aim of this study was to evaluate the prognostic value of radiomic approach in pre-therapeutic ¹⁸F-fluorodeoxyglucose positron-emission tomography (FDG-PET/CT) in a large cohort of patients with gastro-esophageal junction cancer (GEJC). This was a retrospective monocenter study including 97 consecutive patients with GEJC who underwent a pre-therapeutic FDG-PET and were followed up for 3 years. Standard first-order radiomic PET indices including SUV_max, SUV_mean, SUV_peak, MTV and TLG and 32 textural features (TFs) were calculated using LIFEx software on PET imaging. Prognostic significance of these parameters was assessed in univariate and multivariate analysis. Relapse-free survival (RFS) and overall survival (OS) were respectively chosen as primary and secondary endpoints. An internal validation cohort was used by randomly drawing one-third of included patients. The main characteristics of this cohort were: median age of 65 years [41-88], sex ratio H/F = 83/14, 81.5% of patients with a histopathology of adenocarcinoma and 43.3% with a stage IV disease. The median follow-up was 28.5 months [4.2-108.5]. Seventy-seven (79.4%) patients had locoregional or distant progression or recurrence and 71 (73.2%) died. In univariate analysis, SUV_mean, Histogram-Entropy and 2 TFs (GLCM-Homogeneity and GLCM-Energy) were significantly correlated with RFS and OS, as well as 2 others TFs (GLRLM-LRE and GLRLM-GLNU) with OS only. In multivariate analysis, Histogram-Entropy remained an independent prognostic factor of both RFS and OS whereas SUV_mean was an independent prognostic factor of OS only. These results were partially confirmed in our internal validation cohort of 33 patients. Our results suggest that radiomic approach reveals independent prognostic factors for survival in patients with GEJC.

Change in Density Not Size of Esophageal Adenocarcinoma During Neoadjuvant Chemotherapy Is Associated with Improved Survival Outcomes

BACKGROUND

Changes in the size and density of esophageal malignancy during neoadjuvant chemotherapy (NCT) may be useful in predicting overall survival (OS). The aim of this study was to explore this relationship in patients with adenocarcinoma.

METHODS

A retrospective single-centre cohort study was performed. Consecutive patients with esophageal adenocarcinoma who received NCT followed by en bloc resection with curative intent were identified. Pre- and post-NCT computed tomography scans were reviewed. The percentage difference between the greatest tumor diameter, esophageal wall thickness and tumor density was calculated. Multivariate Cox regression analysis identified variables independently associated with OS. A ROC analysis was performed on radiological markers to identify optimal cut-off points with Kaplan-Meier plots subsequently created.

RESULTS

Of the 167 identified, 88 (51.5%) had disease of the gastro-esophageal junction and 149 (89.2%) were clinical T3. In total, 122 (73.1%) had node-positive disease. Increased tumor density (HR 1.01 per % change, 95% CI 1.00-1.02, p = 0.007), lymphovascular invasion (HR 3.23, 95% CI 1.34-7.52, p = 0.006) and perineural invasion (HR 2.51, 95% CI 1.03-6.08, p = 0.048) were independently associated with a decrease in OS. Patients who had a decrease in their tumor density during the time they received NCT of ≥ 20% in Hounsfield units had significantly longer OS than those who did not (75.5 months versus 34.4 months, 95% CI 38.83-105.13/18.63-35.07, p = 0.025).

CONCLUSIONS

Interval changes in the density, not size, of esophageal adenocarcinoma during the time that NCT are independently associated with OS.

Volumetric Evaluation of Staging 18F-FDG PET/CT Images in Patients with Esophageal Cancer

Objectives

The aim of this study was to evaluate the metastatic potential of primary tumor and survival in esophageal cancer (EC) patients by using metabolic tumor volume (MTV) and total lesion glycolysis (TLG) from the staging 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) images. Another aim is to determine a tumor volume-based cut-off value to predict long-term survival.

Methods

Medical records of EC patients were retrospectively evaluated. Sixty-two patients with staging 18F-FDG PET/CT and at least five years of follow-up were included in the study. The region of interest to the primary tumor and all metastatic sites was created and MTV and TLG values of the primary tumor (MTVp, TLGp) and total tumor volume (MTVt and TLGt) values were obtained. The relationship between the obtained MTV and TLG values and short-time (one-year) and long time (five-year) survival was investigated.

Results

Significant factors on survival were determined as lymph node or distant metastasis (p=0.024, 0.008, respectively) at the staging PET/CT. A significant relationship between volumetric parameters of the primary tumor and total tumor burden (MTVp, TLGp, MTVwb and TLGwb) between survivors and non-survivors for one-year and five-year was detected. In receiver operating characteristics analysis, the most significant volumetric parameter was MTVwb, with area under curve 0.771 in estimated five-year survival. The best cut-off value was detected as 36.1 mL with 78% sensitivity and 75% specificity for MTVwb in determining long-term survivors.

Conclusion

Tumor burden in 18F-FDG PET/CT images at the time of staging of patients with EC will contribute to the prediction of long-term survivors.

Radiomic assessment of oesophageal adenocarcinoma: a critical review of 18F-FDG PET/CT, PET/MRI and CT

OBJECTIVES

Radiomic models present an avenue to improve oesophageal adenocarcinoma assessment through quantitative medical image analysis. However, model selection is complicated by the abundance of available predictors and the uncertainty of their relevance and reproducibility. This analysis reviews recent research to facilitate precedent-based model selection for prospective validation studies.

METHODS

This analysis reviews research on 18F-FDG PET/CT, PET/MRI and CT radiomics in oesophageal adenocarcinoma between 2016 and 2021. Model design, testing and reporting are evaluated according to the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) score and Radiomics Quality Score (RQS). Key results and limitations are analysed to identify opportunities for future research in the area.

RESULTS

Radiomic models of stage and therapeutic response demonstrated discriminative capacity, though clinical applications require greater sensitivity. Although radiomic models predict survival within institutions, generalisability is limited. Few radiomic features have been recommended independently by multiple studies.

CONCLUSIONS

Future research must prioritise prospective validation of previously proposed models to further clinical translation.

MRI-based radiomics and ADC values are related to recurrence of endometrial carcinoma: a preliminary analysis

Background

To identify predictive value of apparent diffusion coefficient (ADC) values and magnetic resonance imaging (MRI)-based radiomics for all recurrences in patients with endometrial carcinoma (EC).

Methods

One hundred and seventy-four EC patients who were treated with operation and followed up in our institution were retrospectively reviewed, and the patients were divided into training and test group. Baseline clinicopathological features and mean ADC (ADC_mean), minimum ADC (ADC_min), and maximum ADC (ADC_max) were analyzed. Radiomic parameters were extracted on T2 weighted images and screened by logistic regression, and then a radiomics signature was developed to calculate the radiomic score (radscore). In training group, Kaplan–Meier analysis was performed and a Cox regression model was used to evaluate the correlation between clinicopathological features, ADC values and radscore with recurrence, and verified in the test group.

Results

ADC_mean showed inverse correlation with recurrence, while radscore was positively associated with recurrence. In univariate analyses, FIGO stage, pathological types, myometrial invasion, ADC_mean, ADC_min and radscore were associated with recurrence. In the training group, multivariate Cox analysis showed that pathological types, ADC_mean and radscore were independent risk factors for recurrence, which were verified in the test group.

Conclusions

ADC_mean value and radscore were independent predictors of recurrence of EC, which can supplement prognostic information in addition to clinicopathological information and provide basis for individualized treatment and follow-up plan.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-021-08988-x.

Evaluating the effect of Neoadjuvant chemotherapy for esophageal Cancer using the RECIST system with shorter-axis measurements: a retrospective multicenter study

Background

Evaluating the effect on primary lesions is important in determining treatment strategies for esophageal cancer. The Response Evaluation Criteria in Solid Tumors system, which employs the longest diameter for measuring tumors, is commonly used for evaluating treatment effects. However, the usefulness of these criteria in assessing primary esophageal tumors remains controversial. Thus, we evaluated this issue by measuring not only the longest diameter but also the shorter axis of the tumor.

Methods

We retrospectively reviewed data from 313 patients with esophageal cancer treated with neoadjuvant chemotherapy followed by esophagectomy at three major high-volume centers in Japan. All patients underwent contrast-enhanced computed tomography before and after chemotherapy. The longest and shortest tumor diameters were measured in each case. Treatment effects were adapted to the Response Evaluation Criteria in Solid Tumors system. Correlations between pathological and survival data were also analyzed.

Results

Inter-observer discrepancies were examined for changes in the longest diameter and shorter axis of the tumor (the intraclass correlation coefficients were 0.550 and 0.624, respectively). The shorter axis was correlated with the pathological response in the multivariate analysis (p < 0.001). The shorter axis was significantly associated with overall survival and disease-free survival (both p < 0.001), whereas this association was not observed for the longest tumor diameter.

Conclusions

This multicenter study demonstrated that the Response Evaluation Criteria in Solid Tumors system is useful for predicting pathological response and survival by incorporating the shorter axis of the primary esophageal tumor.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-021-08747-y.

A different overview of staging PET/CT images in patients with esophageal cancer: the role of textural analysis with machine learning methods

OBJECTIVE

This study evaluates the ability of several machine learning (ML) algorithms, developed using volumetric and texture data extracted from baseline 18F-FDG PET/CT studies performed initial staging of patient with esophageal cancer (EC), to predict survival and histopathology.

METHODS

The initial staging 18F-FDG PET/CT images obtained on newly diagnosed EC patients between January 2008 and June 2019 were evaluated using LIFEx software. A region of interest (ROI) of the primary tumor was created and volumetric and textural features were obtained. A significant relationship between these features and pathological subtypes, 1-year, and 5-year survival was investigated. Due to the nonhomogeneity of the data, nonparametric test (The Mann-Whitney U test) was used for each feature, in pairwise comparisons of independent variables. A p value of < 0.05 was considered significant. Receiver operating curve (ROC) analysis was performed for features with p < 0.05. Correlation between the significant features was evaluated with Spearman correlation test; features with correlation coefficient < 0.8 were evaluated with several ML algorithms.

RESULTS

In predicting survival in a 1-year follow-up J48 was obtained as the most successful algorithm (AUC: 0.581, PRC: 0.565, MCC: 0.258, acc: 64.29%). 5-year survival results were more promising than 1-year survival results with (AUC: 0.820, PRC: 0.860, MCC: 271, acc: 81.36%) by logistic regression. It is revealed that the most successful algorithm was naive bayes (AUC: 0.680 PRC: 0.776, MCC: 0.298, acc: 82.66%) in the histopathological discrimination.

CONCLUSION

Texture analysis with ML algorithms could be predictive of overall survival and discriminating histopathological subtypes of EC.

Computed tomography volumetry of esophageal cancer - the role of semiautomatic assessment

Background

The clinical and research value of Computed Tomography (CT) volumetry of esophageal cancer tumor size remains controversial. Development in CT technique and image analysis has made CT volumetry less cumbersome and it has gained renewed attention. The aim of this study was to assess esophageal tumor volume by semi-automatic measurements as compared to manual.

Methods

A total of 23 esophageal cancer patients (median age 65, range 51–71), undergoing CT in the portal-venous phase for tumor staging, were retrospectively included between 2007 and 2012. One radiology resident and one consultant radiologist measured the tumor volume by semiautomatic segmentation and manual segmentation. Reproducibility of the respective measurements was assessed by intraclass correlation coefficients (ICC) and by average deviation from mean.

Results

Mean tumor volume was 46 ml (range 5-137 ml) using manual segmentation and 42 ml (range 3-111 ml) using semiautomatic segmentation. Semiautomatic measurement provided better inter-observer agreement than traditional manual segmentation. The ICC was significantly higher for semiautomatic segmentation in comparison to manual segmentation (0.86, 0.56, p < 0.01). The average absolute percentage difference from mean was reduced from 24 to 14% (p < 0.001) when using semiautomatic segmentation.

Conclusions

Semiautomatic analysis outperforms manual analysis for assessment of esophageal tumor volume, improving reproducibility.