Preoperative prediction of gastrointestinal stromal tumors with high Ki-67 proliferation index based on CT features

Prediction of Ki-67 expression in gastric gastrointestinal stromal tumors using histogram analysis of monochromatic and iodine images derived from spectral CT

PURPOSE

To assess and compare the diagnostic efficiency of histogram analysis of monochromatic and iodine images derived from spectral CT in predicting Ki-67 expression in gastric gastrointestinal stromal tumors (gGIST).

METHODS

Sixty-five patients with gGIST who underwent spectral CT were divided into a low-level Ki-67 expression group (LEG, Ki-67 < 10%, n = 33) and a high-level Ki-67 expression group (HEG, Ki-67 ≥ 10%, n = 32). Conventional CT features were extracted and compared. Histogram parameters were extracted from monochromatic and iodine images, respectively. The diagnostic efficiency of the histogram parameters from monochromatic and iodine images was assessed and compared between the two groups. Spearman's correlation analysis was used to correlate histogram parameters with Ki-67 expression.

RESULTS

The HEG was more likely to present with an irregular shape and a larger size than the LEG (all p < 0.05). Regarding histogram parameters, the HEG showed higher maximum, mean, Perc.10, Perc.25, Perc.50, Perc.75, Perc.90, Perc.99, SD, variance, and CV of monochromatic images; higher maximum, Perc.99, and entropy of iodine images, compared with the LEG (all p < 0.003125). ROC analysis showed that significant histogram parameters of monochromatic and iodine images allowed for effective differentiation between LEG and HEG. DeLong's test showed that the diagnostic efficiency of histogram parameters in monochromatic images (Perc.90) was superior to that of iodine images (maximum) (p = 0.010). A positive correlation was observed between the significant histogram parameters and Ki-67 expression (all p < 0.05).

CONCLUSION

Both histogram analysis of monochromatic and iodine images derived from spectral CT can predict Ki-67 expression in gGIST, and the diagnostic efficacy of monochromatic images is superior to iodine images.

Interpretable machine learning model based on CT semantic features and radiomics features to preoperatively predict Ki-67 expression in gastrointestinal stromal tumors

To develop and validate a machine learning (ML) model which combined computed tomography (CT) semantic and radiomics features to preoperatively predict Ki-67 expression in gastrointestinal stromal tumors (GISTs) patients. We retrospectively collected the clinical, imaging and pathological data of 149 GISTs patients. We randomly assigned the patients in a ratio of 7:3 to a training set (104 cases) and a validation (45 cases) set. We divided the patients into low and high Ki-67 expression group according to postoperative pathology. CT semantic features were analyzed from preoperative enhancement CT images and radiomics features were extracted from venous phase-enhanced images. We used intraclass correlation coefficient, maximal relevance and minimal redundancy and least absolute shrinkage and selection operator method to screen radiomics features and build radiomics label. 6 ML models were used for model construction. Receiver operating characteristic curves were used to evaluate the predictive efficiency of ML models. SHAP analysis was used to explain the contribution of different variables and their risk threshold. AUC of radscores in predicting Ki-67 expression of GIST patients were 0.749 and 0.729 in training and validation set. Among the 6 ML models, SVM exhibited best prediction accuracy. AUC of SVM model in predicting Ki-67 expression of GIST patients were 0.840, 0.767 and 0.832 in training, validation and test set. SHAP analysis showed that radscores and tumor diameter had highly positive contribution to the model. Therefore, the interpretable SVM model can predict Ki-67 expression of GISTs patients individually before surgery, which can provide reliable imaging biomarkers for clinical treatment decisions.

Performance of radiomics in preoperative determination of malignant potential and Ki-67 expression levels in gastrointestinal stromal tumors: a systematic review and meta-analysis

Empirical evidence for radiomics predicting the malignant potential and Ki-67 expression in gastrointestinal stromal tumors (GISTs) is lacking. The aim of this review article was to explore the preoperative discriminative performance of radiomics in assessing the malignant potential, mitotic index, and Ki-67 expression levels of GISTs. We systematically searched PubMed, EMBASE, Web of Science, and the Cochrane Library. The search was conducted up to 30 September 2023. Quality assessment was performed using the Radiomics Quality Score (RQS). A total of 35 original studies were included in the analysis. Among them, 26 studies focused on determining malignant potential, three studies on mitotic index discrimination, and six studies on Ki-67 discrimination. In the validation set, the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of radiomics in the determination of high malignant potential were 0.74 (95% CI=0.69-0.78), 0.90 (95% CI=0.83-0.94), and 0.81 (95% CI=0.14-0.99), respectively. For moderately to highly malignant potential, the sensitivity, specificity, and AUC were 0.86 (95% CI=0.83-0.88), 0.73 (95% CI=0.67-0.78), and 0.88 (95% CI=0.27-0.99), respectively. Regarding the determination of high mitotic index, the sensitivity, specificity, and AUC of radiomics were 0.86 (95% CI=0.83-0.88), 0.73 (95% CI=0.67-0.78), and 0.88 (95% CI=0.27-0.99), respectively. When determining high Ki-67 expression, the combined sensitivity, specificity, and AUC were 0.74 (95% CI=0.65-0.81), 0.81 (95% CI=0.74-0.86), and 0.84 (95% CI=0.61-0.95), respectively. Radiomics demonstrates promising discriminative performance in the preoperative assessment of malignant potential, mitotic index, and Ki-67 expression levels in GISTs.

Erratum to preoperative prediction of gastrointestinal stromal tumors with high Ki-67 proliferation index based on CT features

[This corrects the article DOI: 10.21037/atm-21-4669.].

Selenylated Imidazo [1,2-a]pyridine Induces Apoptosis and Oxidative Stress in 2D and 3D Models of Colon Cancer Cells

Colon cancer incidence rates are increasing annually, a scenario aggravated by genetic and epigenetic alterations that promote drug resistance. Recent studies showed that novel synthetic selenium compounds are more efficient and less toxic than conventional drugs, demonstrating biocompatibility and pro-oxidant effects on tumor cells. This study aimed to investigate the cytotoxic effect of MRK-107, an imidazo [1,2- a]pyridine derivative, in 2D and 3D cell culture models of colon cancer (Caco-2 and HT-29). Sulforhodamine B results revealed a GI50 of 2.4 µM for Caco-2, 1.1 µM for HT-29, and 22.19 µM for NIH/3T3 in 2D cultures after 48 h of treatment. Cell recovery, migration, clonogenic, and Ki-67 results corroborated that MRK-107 inhibits cell proliferation and prevents cell regeneration and metastatic transition by selectively reducing migratory and clonogenic capacity; non-tumor cells (NIH/3T3) re-established proliferation in less than 18 h. The oxidative stress markers DCFH-DA and TBARS revealed increased ROS generation and oxidative damage. Caspases-3/7 are activated and induce apoptosis as the main mode of cell death in both cell models, as assessed by annexin V-FITC and acridine orange/ethidium bromide staining. MRK-107 is a selective, redox-active compound with pro-oxidant and pro-apoptotic properties and the capacity to activate antiproliferative pathways, showing promise in anticancer drug research.

Radiomics signatures based on contrast-enhanced CT for preoperative prediction of the Ki-67 proliferation state in gastrointestinal stromal tumors

PURPOSE

This study aimed to evaluate the Ki-67 proliferation state in patients with gastrointestinal stromal tumors (GISTs) using radiomics prediction signatures based on contrast-enhanced computed tomography (CE-CT).

MATERIALS AND METHODS

This single-center, retrospective study involved 103 patients (48 men and 55 women, mean age 61.1 ± 10.6 years) who had pathologically confirmed GISTs after curative resection, including 63 with low Ki-67 proliferation level (Ki-67 labeling index ≤ 6%) and 40 with high Ki-67 proliferation level (Ki-67 labeling index > 6%). Radiomics features of the delineated lesions were preoperatively extracted from three-phase CE-CT images, including the arterial, venous, and delayed phases. The most relevant features were selected to construct the radiomics signatures using a logistic regression algorithm. Significant demographic characteristics and semantic features on CT were selected to develop a nomogram along with the optimal radiomics feature. We calculated the sensitivity, specificity, accuracy, F1 score, and area under the receiver operating characteristic (ROC) curve to evaluate the predictive performance of radiomics signatures.

RESULTS

Ten quantitative radiomics features (two first-order and eight texture features) were selected to construct radiomics signatures. The radiomics signature based on the three-phase CE-CT images showed better predictive performance than that based on the single-phase CE-CT images, with an area under the curve (AUC) of 0.83 (95% CI 0.73-0.92) and F1 score of 82% in the training dataset and an AUC of 0.80 (95% CI 0.63-0.95) and F1 score of 75% in the testing dataset. The nomogram showed good calibration.

CONCLUSION

Radiomics signatures using CE-CT images are generalizable and could be used in clinical practice to determine the proliferation state of Ki-67 in GISTs.

Early Prediction and Monitoring of Treatment Response in Gastrointestinal Stromal Tumors by Means of Imaging: A Systematic Review

Gastrointestinal stromal tumors (GISTs) are rare mesenchymal neoplasms. Tyrosine kinase inhibitor (TKI) therapy is currently part of routine clinical practice for unresectable and metastatic disease. It is important to assess the efficacy of TKI treatment at an early stage to optimize therapy strategies and eliminate futile ineffective treatment, side effects and unnecessary costs. This systematic review provides an overview of the imaging features obtained from contrast-enhanced (CE)-CT and 2-deoxy-2-[18F]fluoro-D-glucose ([18F]FDG) PET/CT to predict and monitor TKI treatment response in GIST patients. PubMed, Web of Science, the Cochrane Library and Embase were systematically screened. Articles were considered eligible if quantitative outcome measures (area under the curve (AUC), correlations, sensitivity, specificity, accuracy) were used to evaluate the efficacy of imaging features for predicting and monitoring treatment response to various TKI treatments. The methodological quality of all articles was assessed using the Quality Assessment of Diagnostic Accuracy Studies, v2 (QUADAS-2) tool and modified versions of the Radiomics Quality Score (RQS). A total of 90 articles were included, of which 66 articles used baseline [18F]FDG-PET and CE-CT imaging features for response prediction. Generally, the presence of heterogeneous enhancement on baseline CE-CT imaging was considered predictive for high-risk GISTs, related to underlying neovascularization and necrosis of the tumor. The remaining articles discussed therapy monitoring. Clinically established imaging features, including changes in tumor size and density, were considered unfavorable monitoring criteria, leading to under- and overestimation of response. Furthermore, changes in glucose metabolism, as reflected by [18F]FDG-PET imaging features, preceded changes in tumor size and were more strongly correlated with tumor response. Although CE-CT and [18F]FDG-PET can aid in the prediction and monitoring in GIST patients, further research on cost-effectiveness is recommended.