Development and validation of a nomogram based on CT images and 3D texture analysis for preoperative prediction of the malignant potential in gastrointestinal stromal tumors

Preoperative CT-based radiomics and deep learning model for predicting risk stratification of gastric gastrointestinal stromal tumors

BACKGROUND

Gastrointestinal stromal tumors (GISTs) are clinically heterogeneous with various malignant potential in different individuals. It is crucial to explore a reliable method for preoperative risk stratification of gastric GISTs noninvasively.

PURPOSE

To establish and evaluate a machine learning model using the combination of computed tomography (CT) morphology, radiomics, and deep learning features to predict the risk stratification of primary gastric GISTs preoperatively.

METHODS

The 193 gastric GISTs lesions were randomly divided into training set, validation set, and test set in a ratio of 6:2:2. The qualitative and quantitative CT morphological features were assessed by two radiologists. The tumors were segmented manually, and then radiomic features were extracted using PyRadiomics and the deep learning features were extracted using pre-trained Resnet50 from arterial phase and venous phase CT images, respectively. Pearson correlation analysis and recursive feature elimination were used for feature selection. Support vector machines were employed to build a classifier for predicting the risk stratification of GISTs. This study compared the performance of models using different pre-trained convolutional neural networks (CNNs) to extract deep features for classification, as well as the performance of modeling features from single-phase and dual-phase images. The arterial phase, venous phase and dual-phase machine learning models were built, respectively, and the morphological features were added to the dual-phase machine learning model to construct a combined model. Receiver operating characteristic (ROC) curves were used to evaluate the efficacy of each model. The clinical application value of the combined model was determined through the decision curve analysis (DCA) and the net reclassification index (NRI) was analyzed.

RESULTS

The area under the curve (AUC) of the dual-phase machine learning model was 0.876, which was higher than that of the arterial phase model or venous phase model (0.813, 0.838, respectively). The combined model had best predictive performance than the above models with an AUC of 0.941 (95% CI: 0.887-0.974) (p = 0.012, Delong test). DCA demonstrated that the combined model had good clinical application value with an NRI of 0.575 (95% CI: 0.357-0.891).

CONCLUSION

In this study, we established a combined model that incorporated dual-phase morphology, radiomics, and deep learning characteristics, which can be used to predict the preoperative risk stratification of gastric GISTs.

Sub-regional CT Radiomics for the Prediction of Ki-67 Proliferation Index in Gastrointestinal Stromal Tumors: A Multi-center Study

RATIONALE AND OBJECTIVES

The objective was to assess and examine radiomics models derived from contrast-enhanced CT for their predictive capacity using the sub-regional radiomics regarding the Ki-67 proliferation index (PI) in patients with pathologically confirmed gastrointestinal stromal tumors (GIST).

METHODS

In this retrospective study, a total of 412 GIST patients across three institutions (223 from center 1, 106 from center 2, and 83 from center 3) was enrolled. Radiomic features were derived from various sub-regions of the tumor region of interest employing the K-means approach. The Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed to identify features correlated with Ki-67 PI level in GIST patients. A support vector machine (SVM) model was then constructed to predict the high level of Ki-67 (Ki-67 index >8%), drawing on the radiomics features from each sub-region within the training cohort.

RESULTS

After features selection process, 6, 9, 9, 7 features were obtained to construct SVM models based on sub-region 1, 2, 3 and the entire tumor, respectively. Among different models, the model developed by the sub-region 1 achieved an area under the receiver operating characteristic curve (AUC) of 0.880 (95% confidence interval [CI]: 0.830 to 0.919), 0.852 (95% CI: 0.770-0.914), 0.799 (95% CI: 0.697-0.879) in the training, external test set 1, and 2, respectively.

CONCLUSION

The results of the present study suggested that SVM model based on the sub-regional radiomics features had the potential of predicting Ki-67 PI level in patients with GIST.

Preliminary study on diagnosis of gallbladder neoplastic polyps based on contrast-enhanced ultrasound and grey scale ultrasound radiomics

Objective

Neoplastic gallbladder polyps (GPs), including adenomas and adenocarcinomas, are considered absolute indications for surgery; however, the distinction of neoplastic from non-neoplastic GPs on imaging is often challenging. This study thereby aimed to develop a CEUS radiomics nomogram, and evaluate the role of a combined grey-scale ultrasound and CEUS model for the prediction and diagnosis of neoplastic GPs.

Methods

Patients with GPs of ≥ 1 cm who underwent CEUS between January 2017 and May 2022 were retrospectively enrolled. Grey-scale ultrasound and arterial phase CEUS images of the largest section of the GPs were used for radiomics feature extraction. Features with good reproducibility in terms of intraclass correlation coefficient were selected. Grey-scale ultrasound and CEUS Rad-score models were first constructed using the Mann-Whitney U and LASSO regression test, and were subsequently included in the multivariable logistic regression analysis as independent factors for construction of the combined model.

Results

A total of 229 patients were included in our study. Among them, 118 cholesterol polyps, 68 adenomas, 33 adenocarcinomas, 6 adenomyomatoses, and 4 inflammatory polyps were recorded. A total of 851 features were extracted from each patient. Following screening, 21 and 15 features were retained in the grey-scale and CEUS models, respectively. The combined model demonstrated AUCs of 0.88 (95% CI: 0.83 - 0.93) and 0.84 (95% CI: 0.74 - 0.93) in the training and testing set, respectively. When applied to the whole dataset, the combined model detected 111 of the 128 non-neoplastic GPs, decreasing the resection rate of non-neoplastic GPs to 13.3%.

Conclusion

Our proposed combined model based on grey-scale ultrasound and CEUS radiomics features carries the potential as a non-invasive, radiation-free, and reproducible tool for the prediction and identification of neoplastic GPs. Our model may not only guide the treatment selection for GPs, but may also reduce the surgical burden of such patients.

CT and MRI of abdominal cancers: current trends and perspectives in the era of radiomics and artificial intelligence

Abdominal cancers continue to pose daily challenges to clinicians, radiologists and researchers. These challenges are faced at each stage of abdominal cancer management, including early detection, accurate characterization, precise assessment of tumor spread, preoperative planning when surgery is anticipated, prediction of tumor aggressiveness, response to therapy, and detection of recurrence. Technical advances in medical imaging, often in combination with imaging biomarkers, show great promise in addressing such challenges. Information extracted from imaging datasets owing to the application of radiomics can be used to further improve the diagnostic capabilities of imaging. However, the analysis of the huge amount of data provided by these advances is a difficult task in daily practice. Artificial intelligence has the potential to help radiologists in all these challenges. Notably, the applications of AI in the field of abdominal cancers are expanding and now include diverse approaches for cancer detection, diagnosis and classification, genomics and detection of genetic alterations, analysis of tumor microenvironment, identification of predictive biomarkers and follow-up. However, AI currently has some limitations that need further refinement for implementation in the clinical setting. This review article sums up recent advances in imaging of abdominal cancers in the field of image/data acquisition, tumor detection, tumor characterization, prognosis, and treatment response evaluation.

CT and MRI of Gastrointestinal Stromal Tumors: New Trends and Perspectives

Gastrointestinal stromal tumors (GISTs) are defined as mesenchymal tumors of the gastrointestinal tract that express positivity for CD117, which is a c-KIT proto-oncogene antigen. Expression of the c-KIT protein, a tyrosine kinase growth factor receptor, allows the distinction between GISTs and other mesenchymal tumors such as leiomyoma, leiomyosarcoma, schwannoma and neurofibroma. GISTs can develop anywhere in the gastrointestinal tract, as well as in the mesentery and omentum. Over the years, the management of GISTs has improved due to a better knowledge of their behaviors and risk or recurrence, the identification of specific mutations and the use of targeted therapies. This has resulted in a better prognosis for patients with GISTs. In parallel, imaging of GISTs has been revolutionized by tremendous progress in the field of detection, characterization, survival prediction and monitoring during therapy. Recently, a particular attention has been given to radiomics for the characterization of GISTs using analysis of quantitative imaging features. In addition, radiomics has currently many applications that are developed in conjunction with artificial intelligence with the aim of better characterizing GISTs and providing a more precise assessment of tumor burden. This article sums up recent advances in computed tomography and magnetic resonance imaging of GISTs in the field of image/data acquisition, tumor detection, tumor characterization, treatment response evaluation, and preoperative planning.

Comparing endoscopic ultrasonography and double contrast-enhanced ultrasonography in the preoperative diagnosis of gastric stromal tumor

BACKGROUND

This study was designed to perform a comparative analysis between endoscopic ultrasonography (EUS) and double contrast-enhanced ultrasonography (DCEUS) for the preoperative diagnosis of gastric stromal tumors (GSTs).

METHODS

A retrospective study was conducted involving 139 patients with histologically confirmed GSTs. All patients preoperatively underwent DCEUS and EUS. The pathology reports were treated as the baseline and were retrospectively compared with the findings of EUS and DCEUS.

RESULTS

Of the 139 lesions, 120 and 113 were correctly identified by DCEUS and EUS, respectively, with an accuracy of 86.3% and 81.3%. The results revealed an insignificant difference between these two methods (p = 0.189).

CONCLUSIONS

DCEUS can display not only the locations, sizes, shapes, borders, internal echoes, but also show the blood perfusion patterns of GSTs. It is a highly accurate, noninvasive, and convenient method to be used at the pre-treatment stage.

Computed tomography texture-based models for predicting KIT exon 11 mutation of gastrointestinal stromal tumors

Background

KIT exon 11 mutation in gastrointestinal stromal tumors (GISTs) is associated with treatment strategies. However, few studies have shown the role of imaging-based texture analysis in KIT exon 11 mutation in GISTs. In this study, we aimed to show the association between computed tomography (CT)-based texture features and KIT exon 11 mutation.

Methods

Ninety-five GISTs confirmed by surgery and identified with mutational genotype of KIT were included in this study. By amplifying the samples using over-sampling technique, a total of 183 region of interest (ROI) segments were extracted from 63 patients as training cohort. The 63 new ROI segments were extracted from the 63 patients as internal validation cohort. Thirty-two patients who underwent KIT exon 11 mutation test during 2021-2023 was selected as external validation cohort. The textural parameters were evaluated both in training cohort and validation cohort. Least absolute shrinkage and selection operator (LASSO) algorithms and logistic regression analysis were used to select the discriminant features.

Results

Three of textural features were obtained using LASSO analysis. Logistic regression analysis showed that patients' age, tumor location and radiomics features were significantly associated with KIT exon 11 mutation (p < 0.05). A nomogram was developed based on the associated factors. The area under the curve (AUC) of clinical features, radiomics features and their combination in training cohort was 0.687 (95 % CI: 0.604-0.771), 0.829 (95 % CI: 0.768-0.890) and 0.874 (95 % CI: 0.822-0.926), respectively. The AUC of radiomics features in internal validation cohort and external cohort was 0.880 (95 % CI: 0.796-0.964) and 0.827 (95%CI: 0.667-0.987), respectively.

Conclusion

The CT texture-based model can be used to predict KIT exon 11 mutation in GISTs.

Computerized Tomography Texture Analysis in the Differential Diagnosis of Intracranial Epidermoid and Arachnoid Cysts

PURPOSE

This study evaluated the differences between arachnoid and epidermoid cysts in computerized tomography (CT) texture analysis (TA).

MATERIAL AND METHODS

The study included 12 patients with intracranial epidermoid cysts and 26 patients with intracranial arachnoid cysts who were diagnosed with diffusion-weighted magnetic resonance imaging (DW-MRI) and who had undergone an unenhanced CT examination before treatment. The LIFEx application software was used to obtain texture features. Eighty-two texture features from 38 lesions were automatically calculated for each lesion. The Shapiro-Wilk test was used to test the normality of the scores, and the Mann-Whitney U Test was used to test the difference between the groups. Receiver operating characteristic (ROC) curves and multivariate logistic regression modeling examined the parameters' diagnostic performances.

RESULTS

The median age of the patients was 53 years (range: 19-88 years). Eighty-two texture parameters were evaluated in the first order: gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), neighbor gray-tone difference matrix (NGTDM), and gray-level size zone matrix (GLSZM) groups. There was a statistically significant difference between the arachnoid cyst and the epidermoid cyst in the variables of compacity, compactness 1, compactness 2, sphericity, asphericity, sum average, coarseness, and low gray-level zone (p<0.05). According to the multiple logistic regression model, it was determined that the sum average in the GLCM group (B=-0.11; p=0.015), coarseness (B= 869.5; p=0.044) in the NGTDM group, and morphological sphericity (B=24.18; p=0.047) were the radiomics variables that increased the probability of epidermoid diagnosis. According to the classification table of the model, the sensitivity rate was found to be 83%, and the specificity rate was found to be 96%. Therefore, the probability of accurate model classification was 92%.

CONCLUSION

CT TA is a method that can be applied with high diagnostic accuracy in the differential diagnosis of intracranial epidermoid and arachnoid cysts, especially in patients who cannot undergo an MRI examination.

Use of a Convolutional Neural Network to Predict the Malignant Potential of Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Images: Visualization of the Focus of the Prediction Model

OBJECTIVE

We established a deep convolutional neural network (CNN) model based on ultrasound images (US-CNN) for predicting the malignant potential of gastrointestinal stromal tumors (GISTs).

METHODS

A total of 980 ultrasound images from 245 pathology-confirmed GIST patients after surgical operation were retrospectively collected and divided into a low (very-low-risk, low-risk) and a high (medium-risk, high-risk) malignant potential group. Eight pre-trained CNN models were used to extract the features. The CNN model with the highest accuracy in the test set was selected. The model's performance was evaluated by calculating accuracy, sensitivity, specificity, positive-predictive value (PPV), negative-predictive value (NPV) and the F1 score. Three radiologists with different experience levels also predicted the malignant potential of GISTs in the same test set. US-CNN and human assessments were compared. Subsequently, gradient-weighted class activation diagrams (Grad-CAMs) were used to visualize the model's final classification decisions.

RESULTS

Among the eight transfer learning-based CNNs, ResNet18 performed best. The accuracy, sensitivity, specificity, PPV, NPV and F1 score were 0.88, 0.86, 0.89, 0.82, 0.92 and 0.90, respectively, which were significantly better than those achieved by radiologists (resident doctor: 0.66, 0.55, 0.79, 0.74, 0.62 and 0.69; attending doctor: 0.68, 0.59, 0.78, 0.70, 0.69 and 0.73; professor: 0.69, 0.63, 0.72, 0.51, 0.80 and 0.76). Model interpretation with Grad-CAMs revealed that the activated areas mainly focused on cystic necrosis and margins.

CONCLUSION

The US-CNN model predicts GIST malignant potential well, which can assist in clinical treatment decision-making.

Risk stratification for 1- to 2-cm gastric gastrointestinal stromal tumors: visual assessment of CT and EUS high-risk features versus CT radiomics analysis

OBJECTIVES

To investigate the ability of CT and endoscopic sonography (EUS) in predicting the malignant risk of 1-2-cm gastric gastrointestinal stromal tumors (gGISTs) and to clarify whether radiomics could be applied for risk stratification.

METHODS

A total of 151 pathologically confirmed 1-2-cm gGISTs from seven institutions were identified by contrast-enhanced CT scans between January 2010 and March 2021. A detailed description of EUS morphological features was available for 73 gGISTs. The association between EUS or CT high-risk features and pathological malignant potential was evaluated. gGISTs were randomly divided into three groups to build the radiomics model, including 74 in the training cohort, 37 in validation cohort, and 40 in testing cohort. The ROIs covering the whole tumor volume were delineated on the CT images of the portal venous phase. The Pearson test and least absolute shrinkage and selection operator (LASSO) algorithm were used for feature selection, and the ROC curves were used to evaluate the model performance.

RESULTS

The presence of EUS- and CT-based morphological high-risk features, including calcification, necrosis, intratumoral heterogeneity, irregular border, or surface ulceration, did not differ between very-low and intermediate risk 1-2-cm gGISTs (p > 0.05). The radiomics model consisting of five radiomics features showed favorable performance in discrimination of malignant 1-2-cm gGISTs, with the AUC of the training, validation, and testing cohort as 0.866, 0.812, and 0.766, respectively.

CONCLUSIONS

Instead of CT- and EUS-based morphological high-risk features, the CT radiomics model could potentially be applied for preoperative risk stratification of 1-2-cm gGISTs.

KEY POINTS

• The presence of EUS- and CT-based morphological high-risk factors, including calcification, necrosis, intratumoral heterogeneity, irregular border, or surface ulceration, did not correlate with the pathological malignant potential of 1-2-cm gGISTs. • The CT radiomics model could potentially be applied for preoperative risk stratification of 1-2-cm gGISTs.

Application of radiomics in predicting the preoperative risk stratification of gastric stromal tumors

PURPOSE The stomach is the most common site of gastrointestinal stromal tumors (GISTs). In this study, clinical model, radiomics models, and nomogram were constructed to compare and assess the clinical value of each model in predicting the preoperative risk stratification of gastric stromal tumors (GSTs). METHODS In total, 180 patients with GSTs confirmed postoperatively pathologically were included. 70% was randomly selected from each category as the training group (n = 126), and the remaining 30% was stratified as the testing group (n = 54). The image features and texture characteristics of each patient were analyzed, and predictive model were constructed. The image features and the rad-score of the optimal radiomics model were used to establish the nomogram. The clinical application value of these models was assessed by the receiver operating characteristic (ROC) curve and decision curve analysis (DCA). The calibration of each model was evaluated by the calibration curve. RESULTS The Area Under the Curve (AUC) value of the nomogram was 0.930 (95% confidence interval [CI]: 0.886- 0.973) in the training group and 0.931 (95% CI: 0.869-0.993) in the testing group. The AUC values of the training group and the testing group calculated by the radiomics model were 0.874 (95% CI: 0.814-0.935) and 0.863 (95% CI: 0.76 5-0.960), respectively; the AUC values calculated by the clinical model were 0.871 (95% CI: 0.811-0.931) and 0.854 (95% CI: 0.76 0-0.947). CONCLUSION The proposed nomogram can accurately predict the malignant potential of GSTs and can be used as repeatable imaging markers for decision support to predict the risk stratification of GSTs before surgery noninvasively and effectively.

Building contrast-enhanced CT-based models for preoperatively predicting malignant potential and Ki67 expression of small intestine gastrointestinal stromal tumors (GISTs)

PURPOSE

To assess contrast-enhanced computed tomography (CE-CT) features for predicting malignant potential and Ki67 in small intestinal gastrointestinal stromal tumors (GISTs) and the correlation between them.

METHODS

We retrospectively analyzed the pathological and imaging data for 123 patients (55 male/68 female, mean age: 57.2 years) with a histopathological diagnosis of small intestine GISTs who received CE-CT followed by curative surgery from May 2009 to August 2019. According to postoperatively pathological and immunohistochemical results, patients were categorized by malignant potential and the Ki67 index, respectively. CT features were analyzed to be associated with malignant potential or the Ki67 index using univariate analysis, logistic regression and receiver operating curve analysis. Then, we explored the correlation between the Ki67 index and malignant potential by using the Spearman rank correlation.

RESULTS

Based on univariate and multivariate analysis, a predictive model of malignant potential of small intestine GISTs, consisting of tumor size (p < 0.001) and presence of necrosis (p = 0.033), was developed with the area under the receiver operating curve (AUC) of 0.965 (95% CI, 0.915-0.990; p < 0.001), with 91.53% sensitivity, 96.87% specificity, 96.43% PPV, 92.54% NPV, 94.31% diagnostic accuracy. For high Ki67 expression, a model made up of tumor size (p = 0.051), presence of ulceration (p = 0.054) and metastasis (p = 0.001) may be the best predictive combination with an AUC of 0.785 (95% CI, 0.702-0.854; p < 0.001), 63.33% sensitivity, 76.34% specificity, 46.34% PPV, 86.59% NPV, 73.17% diagnostic accuracy. Ki67 index showed a moderate positive correlation with mitotic count (r = 0.578, p < 0.001), a weak positive correlation with tumor size (r = 0.339, p < 0.001) and with risk stratification (r = 0.364, p < 0.001).

CONCLUSION

Features on CE-CT could preoperatively predict malignant potential and high Ki67 expression of small intestine GISTs, and Ki67 index may be a promising prognostic factor in predicting the prognosis of small intestine GISTs, independent of the risk stratification system.

Ultrasound radiomics model-based nomogram for predicting the risk Stratification of gastrointestinal stromal tumors

This study aimed to develop and evaluate a nomogram based on an ultrasound radiomics model to predict the risk grade of gastrointestinal stromal tumors (GISTs). 216 GIST patients pathologically diagnosed between December 2016 and December 2021 were reviewed and divided into a training cohort (n = 163) and a validation cohort (n = 53) in a ratio of 3:1. The tumor region of interest was depicted on each patient’s ultrasound image using ITK-SNAP, and the radiomics features were extracted. By filtering unstable features and using Spearman’s correlation analysis, and the least absolute shrinkage and selection operator algorithm, a radiomics score was derived to predict the malignant potential of GISTs. a radiomics nomogram that combines the radiomics score and clinical ultrasound predictors was constructed and assessed in terms of calibration, discrimination, and clinical usefulness. The radiomics score from ultrasound images was significantly associated with the malignant potential of GISTs. The radiomics nomogram was superior to the clinical ultrasound nomogram and the radiomics score, and it achieved an AUC of 0.90 in the validation cohort. Based on the decision curve analysis, the radiomics nomogram was found to be more clinically significant and useful. A nomogram consisting of radiomics score and the maximum tumor diameter demonstrated the highest accuracy in the prediction of risk grade in GISTs. The outcomes of our study provide vital insights for important preoperative clinical decisions.

Radiomics Nomogram Based on Contrast-enhanced CT to Predict the Malignant Potential of Gastrointestinal Stromal Tumor: A Two-center Study

RATIONALE AND OBJECTIVES

Contrast-enhanced computed tomography (CE-CT) was used to establish radiomics nomogram to evaluate the malignant potential of gastrointestinal stromal tumors (GISTs).

MATERIALS AND METHODS

A total of 500 GIST patients were enrolled in this study and divided into training cohort (n = 346, our center) and validation cohort (n = 154, another center). Minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) algorithms were used to select the feature subset with the best discriminant features from the three phases image, and five classifiers were used to establish four radiomics signatures. Preoperative radiomics nomogram was constructed by adding the clinical features determined by multivariate logistic regression analysis. The performance of radiomics signatures and nomogram were evaluated by area under the curve (AUC) of the receiver operating characteristic (ROC). The calibration of nomogram was appraised by calibration curve.

RESULTS

A total of 13 radiomic features were extracted from tri-phase combined CE-CT images. Tri-phase combined CE-CT features + Support Vector Machine (SVM) was the best combination at predicting the malignant potential of GIST, with an AUC of 0.895 (95% CI 0.858-0.931) in the training cohort and 0.847 (95% CI 0.778-0.917) in the validation cohort. The nomogram also had good calibration. In the training cohort and the validation cohort, preoperative radiomics nomogram reached AUCs of 0.927 and 0.905, respectively, which were higher than clinical.

CONCLUSION

The radiomics nomogram had a good predictive effect and generalization on the malignant potential of GIST, which could effectively help guide preoperative clinical decision.

Mesenchymal tumors of the stomach: radiologic and pathologic correlation

Mesenchymal tumors of the stomach are uncommon, with gastrointestinal stromal tumor (GIST) being the most common among them. Majority of the tumors may arise from cells of Cajal, smooth muscle cells, neural cells, totipotent stem cells, adipocytes or fibroblasts. Imaging plays an important role not only in staging but also in characterizing these tumors. Many of these tumors have characteristic imaging features. GISTs usually present as large cavitating and necrotic tumors with exophytic component. Presence of fat tissue within the tumor suggests a lipoma or a teratoma, early phase hyperenhancement indicates glomus tumor and hemangioma, and delayed contrast enhancement is seen in schwannoma. Their differentiation from epithelial tumors like carcinoma and neuroendocrine tumors is often possible based on the location (mesenchymal tumors are intramural), spread, morphological appearance and enhancement patterns. However, overlapping features exist between these tumors with imaging often being only suggestive. A biopsy is necessary for a definitive diagnosis in many cases.

Preoperative prediction of malignant potential of 2-5 cm gastric gastrointestinal stromal tumors by computerized tomography-based radiomics

BACKGROUND

The use of endoscopic surgery for treating gastrointestinal stromal tumors (GISTs) between 2 and 5 cm remains controversial considering the potential risk of metastasis and recurrence. Also, surgeons are facing great difficulties and challenges in assessing the malignant potential of 2-5 cm gastric GISTs.

AIM

To develop and evaluate computerized tomography (CT)-based radiomics for predicting the malignant potential of primary 2-5 cm gastric GISTs.

METHODS

A total of 103 patients with pathologically confirmed gastric GISTs between 2 and 5 cm were enrolled. The malignant potential was categorized into low grade and high grade according to postoperative pathology results. Preoperative CT images were reviewed by two radiologists. A radiological model was constructed by CT findings and clinical characteristics using logistic regression. Radiomic features were extracted from preoperative contrast-enhanced CT images in the arterial phase. The XGboost method was used to construct a radiomics model for the prediction of malignant potential. Nomogram was established by combing the radiomics score with CT findings. All of the models were developed in a training group (n = 69) and evaluated in a test group (n = 34).

RESULTS

The area under the curve (AUC) value of the radiological, radiomics, and nomogram models was 0.753 (95% confidence interval [CI]: 0.597-0.909), 0.919 (95%CI: 0.828-1.000), and 0.916 (95%CI: 0.801-1.000) in the training group vs 0.642 (95%CI: 0.379-0.870), 0.881 (95%CI: 0.772-0.990), and 0.894 (95%CI: 0.773-1.000) in the test group, respectively. The AUC of the nomogram model was significantly larger than that of the radiological model in both the training group (Z = 2.795, P = 0.0052) and test group (Z = 2.785, P = 0.0054). The decision curve of analysis showed that the nomogram model produced increased benefit across the entire risk threshold range.

CONCLUSION

Radiomics may be an effective tool to predict the malignant potential of 2-5 cm gastric GISTs and assist preoperative clinical decision making.

Computed tomography in the size measurement of gastric gastrointestinal stromal tumors: Implication to risk stratification and "wait-and-see" tactics

INTRODUCTION

This study aimed to compare the radiologic size of gastric gastrointestinal stromal tumors (GISTs) on computed tomography (CT) with the pathologic size in a Chinese population, and elucidate the potential significance of the CT size in the preoperative risk stratification.

MATERIALS AND METHODS

The study enrolled 314 patients treated by endoscopic/surgical resection of gastric lesions that proved postoperatively to be GISTs. Bland-Altman analysis and intraclass correlation coefficient (ICC) were adopted to assess the size agreement between CT and pathology. Independent predictors of risk category underestimation and the optimal cut-off value of CT size were determined by logistic regression analysis and the receiver operating characteristic (ROC) curve.

RESULTS

CT underestimated gastric GISTs size by 0.30 cm [95% confidence interval (CI): (-0.42, - 0.19); p < 0.001]. In the subgroup analysis, the size underestimation was 0.10 cm in GISTs ≤ 5 cm [95% CI: (-0.19, -0.01); p = 0.024]; and 0.75 cm in GISTs >5 cm [95% CI: (-1.05, 0.45), p < 0.001]. Though ICC values showed well reliability for the corresponding pathologic size, with 0.95 in all size, 0.86 in size ≤ 5 cm, and 0.92 in size >5 cm respectively. Risk underestimation by CT imaging mainly occurred in gastric GISTs with smaller size (≤5 cm; p = 0.010) and lower mitotic index (≤5 per 50 high-power fields; p = 0.011). CT size of 3.65 cm was defined as an absolute cut-off to differentiate intermediate/high-risk patients from low-risk group, with 87.5% sensitivity at a specificity of 57.8%.

CONCLUSION

Preoperative CT underestimated the mean size by 0.30 cm in gastric GISTs. A CT size of 3.65 cm would facilitate the selection of potential intermediate/high-risk patients, instant intervention should be encouraged in the absence of contraindications.

Building Radiomics Models Based on Triple-Phase CT Images Combining Clinical Features for Discriminating the Risk Rating in Gastrointestinal Stromal Tumors

We aimed to build radiomics models based on triple-phase CT images combining clinical features to predict the risk rating of gastrointestinal stromal tumors (GISTs). A total of 231 patients with pathologically diagnosed GISTs from July 2012 to July 2020 were categorized into a training data set (82 patients with high risk, 80 patients with low risk) and a validation data set (35 patients with high risk, 34 patients with low risk) with a ratio of 7:3. Four diagnostic models were constructed by assessing 20 clinical characteristics and 18 radiomic features that were extracted from a lesion mask based on triple-phase CT images. The receiver operating characteristic (ROC) curves were applied to calculate the diagnostic performance of these models, and ROC curves of these models were compared using Delong test in different data sets. The results of ROC analyses showed that areas under ROC curves (AUC) of model 4 [Clinic + CT value of unenhanced (CTU) + CT value of arterial phase (CTA) + value of venous phase (CTV)], model 1 (Clinic + CTU), model 2 (Clinic + CTA), and model 3 (Clinic + CTV) were 0.925, 0.894, 0.909, and 0.914 in the training set and 0.897, 0.866, 0,892, and 0.892 in the validation set, respectively. Model 4, model 1, model 2, and model 3 yielded an accuracy of 88.3%, 85.8%, 86.4%, and 84.6%, a sensitivity of 85.4%, 84.2%, 76.8%, and 78.0%, and a specificity of 91.2%, 87.5%, 96.2%, and 91.2% in the training set and an accuracy of 88.4%, 84.1%, 82.6%, and 82.6%, a sensitivity of 88.6%, 77.1%, 74.3%, and 85.7%, and a specificity of 88.2%, 91.2%, 91.2%, and 79.4% in the validation set, respectively. There was a significant difference between model 4 and model 1 in discriminating the risk rating in gastrointestinal stromal tumors in the training data set (Delong test, p < 0.05). The radiomic models based on clinical features and triple-phase CT images manifested excellent accuracy for the discrimination of risk rating of GISTs.

Preoperative CT-Based Deep Learning Model for Predicting Risk Stratification in Patients With Gastrointestinal Stromal Tumors

Objective

To develop and evaluate a deep learning model (DLM) for predicting the risk stratification of gastrointestinal stromal tumors (GISTs).

Methods

Preoperative contrast-enhanced CT images of 733 patients with GISTs were retrospectively obtained from two centers between January 2011 and June 2020. The datasets were split into training (n = 241), testing (n = 104), and external validation cohorts (n = 388). A DLM for predicting the risk stratification of GISTs was developed using a convolutional neural network and evaluated in the testing and external validation cohorts. The performance of the DLM was compared with that of radiomics model by using the area under the receiver operating characteristic curves (AUROCs) and the Obuchowski index. The attention area of the DLM was visualized as a heatmap by gradient-weighted class activation mapping.

Results

In the testing cohort, the DLM had AUROCs of 0.90 (95% confidence interval [CI]: 0.84, 0.96), 0.80 (95% CI: 0.72, 0.88), and 0.89 (95% CI: 0.83, 0.95) for low-malignant, intermediate-malignant, and high-malignant GISTs, respectively. In the external validation cohort, the AUROCs of the DLM were 0.87 (95% CI: 0.83, 0.91), 0.64 (95% CI: 0.60, 0.68), and 0.85 (95% CI: 0.81, 0.89) for low-malignant, intermediate-malignant, and high-malignant GISTs, respectively. The DLM (Obuchowski index: training, 0.84; external validation, 0.79) outperformed the radiomics model (Obuchowski index: training, 0.77; external validation, 0.77) for predicting risk stratification of GISTs. The relevant subregions were successfully highlighted with attention heatmap on the CT images for further clinical review.

Conclusion

The DLM showed good performance for predicting the risk stratification of GISTs using CT images and achieved better performance than that of radiomics model.

CT Radiomics Model for Discriminating the Risk Stratification of Gastrointestinal Stromal Tumors: A Multi-Class Classification and Multi-Center Study

Objective

To establish and verify a computed tomography (CT)-based multi-class prediction model for discriminating the risk stratification of gastrointestinal stromal tumors (GISTs).

Materials and Methods

A total of 381 patients with GISTs were confirmed by surgery and pathology. Information on 213 patients were obtained from one hospital and used as training cohort, whereas the details of 168 patients were collected from two other hospitals and used as independent validation cohort. Regions of interest on CT images of arterial and venous phases were drawn, radiomics features were extracted, and dimensionality reduction processing was performed. Using a one-vs-rest method, a Random Forest-based GISTs risk three-class prediction model was established, and the receiver operating characteristic curve (ROC) was used to evaluate the performance of the multi-class classification model, and the generalization ability was verified using external data.

Results

The training cohort included 96 very low-risk and low-risk, 60 intermediate-risk and 57 high-risk patients. External validation cohort included 82 very low-risk and low-risk, 48 intermediate-risk and 38 high-risk patients. The GISTs risk three-class radiomics model had a macro/micro average area under the curve (AUC) of 0.84 and an accuracy of 0.78 in the training cohort. It had a stable performance in the external validation cohort, with a macro/micro average AUC of 0.83 and an accuracy of 0.80.

Conclusion

CT radiomics can discriminate GISTs risk stratification. The performance of the three-class radiomics prediction model is good, and its generalization ability has also been verified in the external validation cohort, indicating its potential to assist stratified and accurate treatment of GISTs in the clinic.

Value of radiomics model based on enhanced computed tomography in risk grade prediction of gastrointestinal stromal tumors

To explore the application of computed tomography (CT)-enhanced radiomics for the risk-grade prediction of gastrointestinal stromal tumors (GIST). GIST patients (n = 292) confirmed by surgery or endoscopic pathology during June 2013–2019 were reviewed and categorized into low-grade (very low to low risk) and high-grade (medium to high risk) groups. The tumor region of interest (ROI) was depicted layer by layer on each patient’s enhanced CT venous phase images using the ITK-SNAP. The texture features were extracted using the Analysis Kit (AK) and then randomly divided into the training (n = 205) and test (n = 87) groups in a ratio of 7:3. After dimension reduction by the least absolute shrinkage and the selection operator algorithm (LASSO), a prediction model was constructed using the logistic regression method. The clinical data of the two groups were statistically analyzed, and the multivariate regression prediction model was constructed by using statistically significant features. The ROC curve was applied to evaluate the prediction performance of the proposed model. A radiomics-prediction model was constructed based on 10 characteristic parameters selected from 396 quantitative feature parameters extracted from the CT images. The proposed radiomics model exhibited effective risk-grade prediction of GIST. For the training group, the area under curve (AUC), sensitivity, specificity, and accuracy rate were 0.793 (95%CI: 0.733–0.854), 83.3%, 64.3%, and 72.7%, respectively; the corresponding values for the test group were 0.791 (95%CI: 0.696–0.886), 84.2%, 69.3%, and 75.9%, respectively. There were significant differences in age (t value: − 3.133, P = 0.008), maximum tumor diameter (Z value: − 12.163, P = 0.000) and tumor morphology (χ² value:10.409, P = 0.001) between the two groups, which were used to establish a clinical prediction model. The area under the receiver operating characteristic curve of the clinical model was 0.718 (95%CI: 0.659–0.776). The proposed CT-enhanced radiomics model exhibited better accuracy and effective performance than the clinical model, which can be used for the assessment of risk grades of GIST.

Radiomics in Oncology, Part 1: Technical Principles and Gastrointestinal Application in CT and MRI

Simple Summary

Part I is an overview aimed to investigate some technical principles and the main fields of radiomic application in gastrointestinal oncologic imaging (CT and MRI) with a focus on diagnosis, prediction prognosis, and assessment of response to therapy in gastrointestinal cancers, describing mostly the results for each pre-eminent tumor. In particular, this paper provides a general description of the main radiomic drawbacks and future challenges, which limit radiomic application in clinical setting as routine. Further investigations need to standardize and validate the Radiomics as a helpful tool in management of oncologic patients. In that context, Radiomics has been playing a relevant role and could be considered as a future imaging landscape.

Abstract

Radiomics has been playing a pivotal role in oncological translational imaging, particularly in cancer diagnosis, prediction prognosis, and therapy response assessment. Recently, promising results were achieved in management of cancer patients by extracting mineable high-dimensional data from medical images, supporting clinicians in decision-making process in the new era of target therapy and personalized medicine. Radiomics could provide quantitative data, extracted from medical images, that could reflect microenvironmental tumor heterogeneity, which might be a useful information for treatment tailoring. Thus, it could be helpful to overcome the main limitations of traditional tumor biopsy, often affected by bias in tumor sampling, lack of repeatability and possible procedure complications. This quantitative approach has been widely investigated as a non-invasive and an objective imaging biomarker in cancer patients; however, it is not applied as a clinical routine due to several limitations related to lack of standardization and validation of images acquisition protocols, features segmentation, extraction, processing, and data analysis. This field is in continuous evolution in each type of cancer, and results support the idea that in the future Radiomics might be a reliable application in oncologic imaging. The first part of this review aimed to describe some radiomic technical principles and clinical applications to gastrointestinal oncologic imaging (CT and MRI) with a focus on diagnosis, prediction prognosis, and assessment of response to therapy.

MRI-Based Radiomics Models for Predicting Risk Classification of Gastrointestinal Stromal Tumors

Background

We conduct a study in developing and validating four MRI-based radiomics models to preoperatively predict the risk classification of gastrointestinal stromal tumors (GISTs).

Methods

Forty-one patients (low-risk = 17, intermediate-risk = 13, high-risk = 11) underwent MRI before surgery between September 2013 and March 2019 in this retrospective study. The Kruskal–Wallis test with Bonferonni correction and variance threshold was used to select appropriate features, and the Random Forest model (three classification model) was used to select features among the high-risk, intermediate-risk, and low-risk of GISTs. The predictive performance of the models built by the Random Forest was estimated by a 5-fold cross validation (5FCV). Their performance was estimated using the receiver operating characteristic (ROC) curve, summarized as the area under the ROC curve (AUC). Area under the curve (AUC), accuracy, sensitivity, and specificity for risk classification were reported. Linear discriminant analysis (LDA) was used to assess the discriminative ability of these radiomics models.

Results

The high-risk, intermediate-risk, and low-risk of GISTs were well classified by radiomics models, the micro-average of ROC curves was 0.85, 0.81, 0.87 and 0.94 for T1WI, T2WI, ADC and combined three MR sequences. And ROC curves achieved excellent AUCs for T1WI (0.85, 0.75 and 0.82), T2WI (0.69, 0.78 and 0.78), ADC (0.85, 0.77 and 0.80) and combined three MR sequences (0.96, 0.92, 0.81) for the diagnosis of high-risk, intermediate-risk, and low-risk of GISTs, respectively. In addition, LDA demonstrated the different risk of GISTs were correctly classified by radiomics analysis (61.0% for T1WI, 70.7% for T2WI, 83.3% for ADC, and 78.9% for the combined three MR sequences).

Conclusions

Radiomics models based on a single sequence and combined three MR sequences can be a noninvasive method to evaluate the risk classification of GISTs, which may help the treatment of GISTs patients in the future.

Computed-Tomography-Based Radiomics Model for Predicting the Malignant Potential of Gastrointestinal Stromal Tumors Preoperatively: A Multi-Classifier and Multicenter Study

Background: Our goal was to establish and verify a radiomics risk grading model for gastrointestinal stromal tumors (GISTs) and to identify the optimal algorithm for risk stratification. Methods: We conducted a retrospective analysis of 324 patients with GISTs, the presence of which was confirmed by surgical pathology. Patients were treated at three different hospitals. A training cohort of 180 patients was collected from the largest center, while an external validation cohort of 144 patients was collected from the other two centers. To extract radiomics features, regions of interest (ROIs) were outlined layer by layer along the edge of the tumor contour on CT images of the arterial and portal venous phases. The dimensionality of radiomic features was reduced, and the top 10 features with importance value above 5 were selected before modeling. The training cohort used three classifiers [logistic regression, support vector machine (SVM), and random forest] to establish three GIST risk stratification prediction models. The receiver operating characteristic curve (ROC) was used to compare model performance, which was validated by external data. Results: In the training cohort, the average area under the curve (AUC) was 0.84 ± 0.07 of the logistic regression, 0.88 ± 0.06 of the random forest, and 0.81 ± 0.08 of the SVM. In the external validation cohort, the AUC was 0.85 of the logistic regression, 0.90 of the random forest, and 0.80 of the SVM. The random forest model performed the best in both the training and the external validation cohorts and could be generalized. Conclusion: Based on CT radiomics, there are multiple machine-learning models that can predict the risk of GISTs. Among them, the random forest algorithm had the highest prediction efficiency and could be readily generalizable. Through external validation data, we assume that the random forest model may be used as an effective tool to guide preoperative clinical decision-making.

A multi-class scoring system based on CT features for preoperative prediction in gastric gastrointestinal stromal tumors

Our study aimed to establish and validate a multi-class scoring system for preoperative gastric gastrointestinal stromal tumors (GISTs) risk stratifications based on CT features. 150 gastric GIST patients who underwent contrast-enhanced CT examination and surgical resection from hospital 1 were retrospectively analyzed as the training cohort, and 61 patients from hospitals 2 and 3 were included as the validation cohort. A model was established by logistic regression analysis and weighted to be a scoring model. A calibration test, area under the receiver operating characteristic (ROC) curve (AUC), and cutoff points were determined for the score model. The model was also divided into three score ranges for convenient clinical evaluation. Five CT features were included in the score model, including tumor size (4 points), ill-defined margin (6 points), intratumoral enlarged vessels (5 points), heterogeneous enhancement pattern (4 points), and exophytic or mixed growth pattern (2 points). Then, based on the calibration results, performance was merely assessed as very low and high* risk. The AUCs of the score model for very low risk and high* risk were 0.973 and 0.977, and the cutoff points were 3 points (97.30%, 93.81%) and 7 points (92.19%, 94.19%), respectively. In the validation cohort, the AUCs were 0.912 and 0.972, and the cutoff values were 3 points (92.31%, 85.42%) and 5 points (100%, 87.88%), respectively. The model was stratified into 3 ranges: 0-3 points for very low risk, 4-8 points for low risk, and 9-21 points for high* risk. A concise and practical score system for gastric GISTs risk stratification was proposed.

Preoperative CT feature of incomplete overlying enhancing mucosa as a high-risk predictor in gastrointestinal stromal tumors of the stomach

OBJECTIVES

To determine whether the CT finding of overlying enhancing gastric mucosa (OEGM) can be used to predict risk stratifications by observing CT features of gastrointestinal stromal tumors (GISTs) of the stomach.

METHODS

Clinical characteristics and CT features within pathologically demonstrated GISTs were retrospectively reviewed. Risk stratifications were classified into non-high group and high-risk group according to the modified National Institutes of Health criteria. Univariate analysis and multivariate logistic regression analysis were performed in order to determine significant predictors for high-risk stratification. Receiver operating characteristic (ROC) curve analysis, subgroup analysis, and pathologic-radiologic correlation analysis were all executed.

RESULTS

A total of 147 patients were finally enrolled as test subjects. Within the univariate analysis, high-risk tumors tended to have a larger diameter, irregular shape, exophytic growth pattern, present necrosis, incomplete OEGM, tumor vessels, heterogeneous enhancement, and present rupture. According to ROC curve analysis, incomplete OEGM showed the largest area under curve values for diagnosing lesions (0.835; 95% CI, 0.766-0.904; p < 0.001). Multivariate analysis showed that the incomplete OEGM was the strongest independent predictor for high-risk stratification of gastric GISTs (OR = 21.944; 95% CI, 4.344-110.863; p < 0.001). Within the subgroup analysis, incomplete OEGM was more frequently associated with tumors size > 10 cm, irregular shape, exophytic growth pattern, high mitotic count, and disrupted mucosa on pathology.

CONCLUSIONS

The CT feature of incomplete OEGM is an independent predictive factor for high-risk stratification of gastric GISTs and strongly correlated with pathological mucosal changes.

KEY POINTS

• Preoperative CT features can be helpful in assessment of risk stratifications of gastric GISTs. • OEGM is an independent predictor for high-risk stratification of gastric GISTs. • Incomplete OEGM likely indicates high-risk stratification of gastric GISTs.

New advances in radiomics of gastrointestinal stromal tumors

Gastrointestinal stromal tumors (GISTs) are uncommon neoplasms of the gastrointestinal tract with peculiar clinical, genetic, and imaging characteristics. Preoperative knowledge of risk stratification and mutational status is crucial to guide the appropriate patients’ treatment. Predicting the clinical behavior and biological aggressiveness of GISTs based on conventional computed tomography (CT) and magnetic resonance imaging (MRI) evaluation is challenging, unless the lesions have already metastasized at the time of diagnosis. Radiomics is emerging as a promising tool for the quantification of lesion heterogeneity on radiological images, extracting additional data that cannot be assessed by visual analysis. Radiomics applications have been explored for the differential diagnosis of GISTs from other gastrointestinal neoplasms, risk stratification and prediction of prognosis after surgical resection, and evaluation of mutational status in GISTs. The published researches on GISTs radiomics have obtained excellent performance of derived radiomics models on CT and MRI. However, lack of standardization and differences in study methodology challenge the application of radiomics in clinical practice. The purpose of this review is to describe the new advances of radiomics applied to CT and MRI for the evaluation of gastrointestinal stromal tumors, discuss the potential clinical applications that may impact patients’ management, report limitations of current radiomics studies, and future directions.

Difference of computed tomographic characteristic findings between gastric and intestinal gastrointestinal stromal tumors

PURPOSE

We aimed to compare the computed tomography (CT) imaging differences between gastric and intestinal gastrointestinal stromal tumors (GISTs).

MATERIALS AND METHODS

Thirty-eight patients with 38 gastric GISTs and 27 with 31 intestinal GISTs were enrolled. Tumors were classified as small (< 5 cm) or large (≥ 5 cm). Qualitative and quantitative CT imaging characteristics on non-contrast and contrast-enhanced CT were evaluated by two radiologists independently and statistically compared.

RESULTS

Early venous return and higher CT number of the draining vein in the arterial phase were more frequent in small-sized intestinal GISTs than in small-sized gastric GISTs (p < 0.001). Small-sized intestinal GISTs demonstrated a wash-out pattern, whereas small-sized gastric GISTs showed a plateau pattern. Contrast enhancement was higher in small-sized intestinal GISTs than in small-sized gastric GISTs (p < 0.001). CT number was inversely proportional to the diameter of intestinal GISTs in both arterial and venous phases but not to that of gastric GISTs.

CONCLUSION

Strong enhancement with wash-out pattern and early venous return are characteristic findings of small-sized intestinal GISTs. Radiologists should be aware that CT findings of GISTs have a wide spectrum and may differ according to size and site of origin.