Incidence and predictors of synchronous liver metastases in patients with gastrointestinal stromal tumors (GISTs)

Automated machine learning for predicting liver metastasis in patients with gastrointestinal stromal tumor: a SEER-based analysis

Gastrointestinal stromal tumors (GISTs) are a rare type of tumor that can develop liver metastasis (LIM), significantly impacting the patient's prognosis. This study aimed to predict LIM in GIST patients by constructing machine learning (ML) algorithms to assist clinicians in the decision-making process for treatment. Retrospective analysis was performed using the Surveillance, Epidemiology, and End Results (SEER) database, and cases from 2010 to 2015 were assigned to the developing sets, while cases from 2016 to 2017 were assigned to the testing set. Missing values were addressed using the multiple imputation technique. Four algorithms were utilized to construct the models, comprising traditional logistic regression (LR) and automated machine learning (AutoML) analysis such as gradient boost machine (GBM), deep neural net (DL), and generalized linear model (GLM). We evaluated the models' performance using LR-based metrics, including the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA), as well as AutoML-based metrics, such as feature importance, SHapley Additive exPlanation (SHAP) Plots, and Local Interpretable Model Agnostic Explanation (LIME). A total of 6207 patients were included in this study, with 2683, 1780, and 1744 patients allocated to the training, validation, and test sets, respectively. Among the different models evaluated, the GBM model demonstrated the highest performance in the training, validation, and test cohorts, with respective AUC values of 0.805, 0.780, and 0.795. Furthermore, the GBM model outperformed other AutoML models in terms of accuracy, achieving 0.747, 0.700, and 0.706 in the training, validation, and test cohorts, respectively. Additionally, the study revealed that tumor size and tumor location were the most significant predictors influencing the AutoML model's ability to accurately predict LIM. The AutoML model utilizing the GBM algorithm for GIST patients can effectively predict the risk of LIM and provide clinicians with a reference for developing individualized treatment plans.

A nomogram for predicting liver metastasis in patients with gastric gastrointestinal stromal tumor

BACKGROUND

Liver metastasis (LIM) is an important factor in the diagnosis, treatment, follow-up, and prognosis of patients with gastric gastrointestinal stromal tumor (GIST). There is no simple tool to assess the risk of LIM in patients with gastric GIST. Our aim was to develop and validate a nomogram to identify patients with gastric GIST at high risk of LIM.

METHODS

Patient data diagnosed as having gastric GIST between 2010 and 2019 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database and randomly divided into training cohort and internal validation cohort in a 7:3 ratio. For external validation, retrospective data collection was performed on patients diagnosed as having gastric GIST at Yunnan Cancer Center (YNCC) between January 2015 and May 2023. Univariate and multivariate logistic regression analyses were used to identify independent risk factors associated with LIM in patients with gastric GIST. An individualized LIM nomogram specific for gastric GIST was formulated based on the multivariate logistic model; its discriminative performance, calibration, and clinical utility were evaluated.

RESULTS

In the SEER database, a cohort of 2341 patients with gastric GIST was analyzed, of which 173 cases (7.39%) were found to have LIM; 239 patients with gastric GIST from the YNCC database were included, of which 25 (10.46%) had LIM. Multivariate analysis showed tumor size, tumor site, and sex were independent risk factors for LIM (P < .05). The nomogram based on the basic clinical characteristics of tumor size, tumor site, sex, and age demonstrated significant discrimination, with an area under the curve of 0.753 (95% CI, 0.692-0.814) and 0.836 (95% CI, 0.743-0.930) in the internal and external validation cohort, respectively. The Hosmer-Lemeshow test showed that the nomogram was well calibrated, whereas the decision curve analysis and the clinical impact plot demonstrated its clinical utility.

CONCLUSION

Tumor size, tumor subsite, and sex were significantly correlated with the risk of LIM in gastric GIST. The nomogram for patients with GIST can effectively predict the individualized risk of LIM and contribute to the planning and decision making related to metastasis management in clinical practice.

Prognostic factors for liver metastasis in patients with small intestinal stromal tumor: A retrospective analysis of surveillance, epidemiology, and end results

BACKGROUND

Liver metastasis (LIM) is the most common distant site of metastasis in small intestinal stromal tumors (SISTs). The aim of this study was to determine the risk and prognostic factors associated with LIM in patients with SISTs.

METHODS

Patients diagnosed with gastrointestinal stromal tumors between 2010 and 2019 were selected from the Surveillance, Epidemiology, and End Results (SEER) database. Univariate and multivariate logistic regression models, as well as a Cox regression model were used to explore the risk factors associated with the development and prognosis of LIM. Additionally, the overall survival (OS) of patients with LIM was analyzed using the Kaplan-Meier method. Furthermore, a predictive nomogram was constructed, and the model's performance was evaluated using receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA).

RESULTS

A total of 1582 eligible patients with SISTs were included, among whom 146 (9.2%) were diagnosed with LIM. Poor tumor grade, absence of surgery, later T-stage, and no chemotherapy were associated with an increased risk of developing LIM. The nomogram prediction model achieved an AUC of 0.810, 95% Confidence Interval (CI) 0.773-0.846, indicating good performance, and the calibration curve showed excellent accuracy in predicting LIM. The OS rate of patients with LIM was significantly lower than that of patients without LIM (p < 0.001).

CONCLUSIONS

Patients with SISTs who are at high risk of developing LIM deserve more attention during follow-up, as LIM can significantly affect patient prognosis. The nomogram demonstrated good calibration and discrimination for predicting LIM.

Multiple Metastatic Extra-gastrointestinal Stromal Tumors with Plasmoid Differentiation: A Case Report and Review of Literature

Extra-gastrointestinal stromal tumors (EGISTs) are rare mesenchymal tumors that arise from the abdominal, pelvic or retroperitoneal region, unrelated to the gastrointestinal tract. However, cases with a plasmoid morphology are extremely rare. we hererin report a 49-year-old man with abdominal pain who underwent magnetic resonance imaging that revealed an irregular tumor (103×71 mm) in size, in the space between stomach and pancreas, diagnosed as an EGISIT, we also reviewed the clinicopathological characteristics and immunohistochemical characteristics, molecular genetic features and differential diagnoses previously reported in the literature.

High-frame-rate contrast-enhanced ultrasound findings of liver metastasis of duodenal gastrointestinal stromal tumor: A case report and literature review

BACKGROUND

Liver metastasis of duodenal gastrointestinal stromal tumor (GIST) is rare. Most reports mainly focus on its treatment and approaches to surgical resection, while details on its contrast-enhanced ultrasound (CEUS) findings are lacking. The diagnosis and imaging modalities for this condition remain challenging.

CASE SUMMARY

A 53-year-old Chinese man presented with mild signs and symptoms of the digestive tract. He underwent routine examinations after GIST surgery. Magnetic resonance imaging showed a 2.3 cm hepatic space-occupying lesion. All the laboratory test results were within normal limits. For further diagnostic confirmation, we conducted high frame rate CEUS (H-CEUS) and found a malignant perfusion pattern. Heterogeneous concentric hyper-enhancement, earlier wash-in than the liver parenchyma, and two irregular vessel columns could be observed at the periphery of the lesion during the arterial phase. Ultrasound-guided puncture biopsy was used to confirm the diagnosis of the lesion as liver metastasis of duodenal GIST. Imatinib was prescribed after biopsy, and the patient’s clinical course was monitored.

CONCLUSION

H-CEUS is useful for detecting microcirculation differences, wash-in patterns, and vascular morphogenesis and diagnosing liver metastasis of duodenal GIST.

Learning Curve for Metastatic Liver Tumor Open Resection in Patients with Primary Colorectal Cancer: Use of the Cumulative Sum Method

Background: Liver resections have become the first-line treatment for primary and metastatic tumors and, therefore, are considered a core aspect of surgical training. This study aims to evaluate the learning curve of the extent and safety of liver resection procedures for patients with metastatic colorectal cancer. Methods: This single tertiary center retrospective analysis includes 158 consecutive cases of small liver resection (SLR) (n = 107) and major liver resection (MLR) (n = 58) procedures. A cumulative sum control chart (CUSUM) method was used to investigate the learning curve. Results: The operative time, total blood loss level, and incidence of adverse effects showed a learning curve. For SLRs, the CUSUM curve for operative time and blood loss level peaked at the 19th and 17th case, respectively, while for MLRs, these curves peaked at the 28th and 24th case, respectively. The CUSUM curve for minor adverse effects (MAEs) and severe adverse effects (SAEs) showed a downward slope after the 16th and 68th procedures in the SLRs group and after the 29th and 39th procedures in the MLRs cohort; however, it remained within the acceptable range throughout the entire study. Conclusion: SLR procedures were performed faster with less intraoperative blood loss and shorter postoperative stays than MLRs, and a higher number of completed procedures was required to gain stabilization and repeatability in the operating time and intraoperative blood loss level. In MLR procedures, the reduction of SAEs was accomplished significantly later than the stabilization of the operative time and intraoperative blood loss level.

Combined model based on enhanced CT texture features in liver metastasis prediction of high-risk gastrointestinal stromal tumors

PURPOSE

To investigate the use of the combined model based on clinical and enhanced CT texture features for predicting the liver metastasis of high-risk gastrointestinal stromal tumors (GISTs).

METHODS

This retrospective study was conducted including 204 patients with pathologically confirmed high-risk GISTs from the Zhejiang Cancer Hospital from January 2015 to June 2021, and 76 cases of them were diagnosed with simultaneous liver metastasis. We randomly divided the cohort into a training cohort (n = 142) and a validation cohort (n = 62) with a ratio of 7:3. All volumes of interest (VOIs) of the high-risk GISTs were manually segmented on the portal venous phase CT images using the ITK-SNAP software. The least absolute shrinkage and selection operator (Lasso) algorithm was performed to determine the most valuable features from a total of 110 texture features extracted by the A-K software to reflect the texture information of the given VOIs. Texture-based predictive model was built from the selected texture features. Independent clinical risk factors were identified through univariate logistic analysis. Then, the texture-based model incorporated the clinical predictors to develop a combined model by multivariate logistic regression. Receiver operating characteristic curve, calibration curve, and decision curve analysis were utilized to analyze the discrimination capacity and clinical application value of the predictive models.

RESULTS

The nine optimal texture features were remained after the reduction of dimension using Lasso method. Another four clinical parameters (BMI, location, gastrointestinal bleeding, and CA125 level) were included in the clinical-based predictive model. Finally, with the combination of remaining texture and clinical features, a multivariate logistic regression classifier was built to predict the liver metastasis potential of high-risk GISTs. The remarkable classification performance of the combined model for the prediction of liver metastasis in the subjects with high-risk GISTs was obtained with area under curve (AUC) = 0.919, sensitivity = 83.9%, specificity = 89.7%, and accuracy = 84.9% in our validation group.

CONCLUSION

The texture-based radiomic signature derived from the portal venous phase CT images could predict liver metastasis of high-risk GISTs in a non-invasive way. Integrating additional clinical variables into the model further leads to an improvement of liver metastasis risk prediction.

Skeletal muscle metastasis from a gastrointestinal stromal tumor: A case report

RATIONALE

Gastrointestinal stromal tumors (GISTs) are the most common mesenchymal tumors of the gastrointestinal tract. Common sites for metastasis are the liver and peritoneum, whereas skeletal muscle metastases are rare.

PATIENT CONCERNS

A 59-year-old man with skeletal muscle metastasis was diagnosed during a period of adjuvant imatinib therapy following the recurrence of GIST of the small intestine.

DIAGNOSIS

The patient was diagnosed with skeletal muscle metastasis of GIST based on immunohistochemistry and molecular pathology analysis results.

INTERVENTION

Extensive resection of the left thigh tumor was performed. The patient underwent whole-exome sequencing of tissue examination. The results suggest that resistance to imatinib may have been developed, and the patient was therefore administered sunitinib instead.

OUTCOMES

Complete remission was observed following sunitinib therapy.

LESSONS

In cases of skeletal muscle metastasis diagnosed during a period of adjuvant imatinib therapy following the recurrence of a GIST of the small intestine, whole exome sequencing may be used to discover more gene variations.

Near-infrared fluorescence-guided metastasectomy for hepatic gastrointestinal stromal tumor metastases using indocyanine green: A case report

•

Near-infrared fluorescence imaging should be considered as an additional imaging technique to intraoperative ultrasound during surgery for hepatic metastasis.

•

Near-infrared fluorescence imaging can aid surgeons in the identification of preoperatively identified liver metastases from primary GIST.

•

For the detection of additional superficially located liver metastases from primary GIST near-infrared fluorescence imaging can be used.

•

Real-time evaluation of resection margins with NIRF imaging may lead to a lower number of R1 resections.

Introduction and importance

Gastrointestinal stromal tumors are the most prevalent mesenchymal tumors of the gastrointestinal tract. Distant metastases are most often found in the liver or peritoneum with surgery being the preferred treatment option. In our center, fluorescence-guided surgery with indocyanine green is used as standard-of-care for hepatic metastases in colorectal cancer. This case report describes fluorescence-guided metastasectomy for a hepatic gastrointestinal stromal tumor in two patients undergoing open liver resection and radiofrequency ablation.

Case presentation

A 69-year old women was seen during follow-up after laparoscopic resection of a GIST in the lesser curvature of the stomach. Contrast-enhanced computed tomography imaging showed two suspicious lesions in liver segment VI and VIII. Intraoperative near-infrared fluorescence imaging of the liver clearly revealed the lesion in segment VIII, and an additional lesion in segment V – which was not seen on preoperative CT-imaging, neither on intraoperative ultrasonography. The lesion in segment VI was not seen with NIRF imaging due to its deeper location in the liver parenchyma. The second case is an 82-year old man who was also diagnosed with liver metastases from a GIST in the stomach and was scheduled for near-infrared fluorescence-guided liver resection and radio frequency ablation.

Clinical discussion

In this case report we demonstrated the feasibility of fluorescence-guided surgery in detection of liver metastases and treatment planning of two patients with hepatic GIST metastases using indocyanine green.

Conclusion

NIRF-imaging with ICG is useful for identification of preoperatively discovered lesions, surgical resection planning and margin evaluation, and for detection of additional hepatic GIST metastases.

Hepatic nodules with arterial phase hyperenhancement and washout on enhanced computed tomography/magnetic resonance imaging: how to avoid pitfalls

This essay aimed to illustrate the various hepatic nodules that may exhibit arterial phase hyperenhancement and washout on computed tomography/magnetic resonance imaging (CT/MRI). Hepatic nodules with arterial phase hyperenhancement and washout on CT/MRI include hepatocellular carcinoma, focal nodular hyperplasia-like nodules, serum amyloid A-positive hepatocellular neoplasms, intrahepatic cholangiocarcinoma, intrahepatic bile duct adenoma, hepatoblastoma, hepatocellular adenoma, hepatic epithelioid angiomyolipoma, and metastasis including neuroendocrine and gastrointestinal stromal tumors. Understanding the imaging findings is important to ensure correct diagnosis.

Differential diagnosis of liver metastases of gastrointestinal stromal tumors from colorectal cancer based on combined tumor biomarker with features of conventional ultrasound and contrast-enhanced ultrasound

PURPOSE

To explore the value of tumor marker CA125 and CEA linked with conventional ultrasound (US) and contrast-enhanced ultrasound (CEUS) features in differentiating gastrointestinal stromal tumors liver metastases (GISTLM) from colorectal cancer liver metastases (CRCLM).

MATERIALS AND METHODS

From December 2005 to February 2019, eighty patients with pathologically proven GISTLM together with 80 CRCLM patients were retrospectively evaluated with contrast-enhanced ultrasound (CEUS). Clinical characteristics such as CA125 and CEA were documented to compare the difference between GISTLM and CRCLM. Univariate analysis was performed to determine significant features in ultrasound and then these features were entered into multivariate logistic regression model to determine diagnostic criteria. By analyzing the tumor marker and imaging features, diagnostic performance was evaluated via receiver-operating characteristic (ROC) analysis. The sensitivity, specificity and accuracy were calculated for the diagnosis of GISTLM.

RESULTS

Multiple logistic regression analysis showed that increased CA125 and normal CEA were the independent variables of GISTLM. On conventional US, the features of hypo- or mix-echogenicity and anechoic area were associated with GISTLM. On CEUS, capsule enhancement, starting time of washout > 40 s and proportion of non-enhancement area > 20% were the features indicating GISTLM. All of the p values were < 0.05. When linking tumor marker with imaging features, the diagnostic sensitivity improved from 36.3-57.5% to 70.0%, and the area under the ROC (AUROC) curve improved from 0.681-0.750 to 0.838, with a specificity of 97.5%.

CONCLUSIONS

Combining the imaging features of conventional US and CEUS with serum tumor markers provides a potentially effective diagnostic method in differentiation of GISTLM and CRCLM.

Clinicopathologic and Surgical Characteristics Study of 151 Cases of GIST

BACKGROUND

Gastrointestinal stromal tumor (GIST) is the most appearing mesenchymal tumor of the gastrointestinal system. In this study, we are aiming to share the most up to date knowledge about diagnosis and treatment of these tumors by transferring our clinical experience about GISTs.

METHODS

The 151 patients who were operated between 2006-2020 and whose pathological examination was reported as GIST were analyzed retrospectively. Demographic, clinical, and pathological features and treatment methods of patients were evaluated.

RESULTS

Seeventy-six of the patients were women and 75 of them were men whose age averages were 66.1 (31-86). The most common location was the stomach (55.6%), followed by the small intestine, retroperitoneal, large intestine, rectum, esophagus, and another organ. With surgical intervention, 139 of them had been cured. Twelve of cases were accepted as inoperable. The diameter of tumors in our cases were between 0.4 cm and 35 cm. Determined mitotic activity was ≤ 5 in 71 patients and 5 < in 80 patients. In 8 of 12 unresectable cases, it has been seen that partial remission after the treatment of 12-month tyrosine kinase inhibitors, C-KIT, was positive in 96.7% of our cases. CD34 and Ki-67 was analyzed in patients. CD34 was found positive in 98 (64.9%) of them, Ki-67 was positive in 82 (54.3%) patients. Patients had been observed for 40 months.

CONCLUSION

Despite GISTs are not appearing frequently, nowadays they have started to be seen more frequently than before with the growing present-day diagnostic methods. The ideal treatment is performing radical resection without leaving any tumor cells behind. Tyrosine kinase inhibitors have an important place in unresectable cases.

Establishment and Verification of Synchronous Metastatic Nomogram for Gastrointestinal Stromal Tumors (GISTs): A Population-Based Analysis

Aim

Assess the risk of synchronous metastasis and establish a nomogram in patients with GISTs.

Methods

Surveillance, Epidemiology and End Results database (2004-2014) was accessed. With the logistic regression model as the basis, a nomogram was constructed.

Results

7,256 target patients were contained in our study. The nomogram discrimination for mGIST prediction revealed that tumor size contributed most to synchronous metastasis, followed by lymph nodes, extension, pathologic grade, tumor location, and mitotic count. C-index values of predictions were 0.821 (95% CI, 0.805-0.836) and 0.815 (95% CI, 0.800-0.831), and Brier score were 0.109 and 0.112 in training and validation group, respectively. The value of area under the ROCs were 0.813 (p < 0.001) in the primary cohort and 0.819 (p < 0.001) in the validation cohort. Through the calibration curves (as seen in the figures), nomogram prediction proved to have excellent agreement with actual metastatic diseases.

Conclusion

A new nomogram was created that can evaluate synchronous metastatic diseases in patients with GISTs.

Metastatic pattern and prognosis of gastrointestinal stromal tumor (GIST): a SEER-based analysis

PURPOSE

This SEER-based study aimed to explore and analyze the relationship of metastasis of liver, lung and bone of GIST patients and their prognosis.

METHODS

The data of GIST patients were from Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2015 and all the statistical analyses were conducted by statistical software package SPSS (Version 22.0).

RESULTS

A total of 4224 GIST patients were identified, of which 388 (9.19%) patients with liver metastasis, 20 (0.47%) patients with bone metastasis and 32 (0.76%) patients with lung metastasis. There was no significant difference of risk of bone or lung metastasis between patients with and without liver metastasis (P = 0.935). The median overall survival of patients with liver, bone, or lung metastasis was, respectively, 49 months, 18 months, and 20 months, which were all shorter than that of patients without metastasis. The overall survival of patients with both liver and bone metastasis and those with metastasis of all three sites was not significantly different from that of patients with only liver metastasis. The multivariate analysis showed age of less than 65 years, female patients, married status and receiving surgery were all the beneficial factors for prognosis of GIST patients with liver metastasis.

CONCLUSIONS

Patients with metastasis had a poorer prognosis than those without. Liver metastasis might have no relationship with bone or lung metastasis and liver might play a more dominant role than the other two sites in the prognosis of GIST patients with metastasis. So, more attention should be paid to liver status in diagnosis and treatment of GIST patients.

Gigantic GIST: A Case of the Largest Gastrointestinal Stromal Tumor Found to Date

Gastrointestinal stromal tumors are uncommon when compared to all gastrointestinal neoplasms but are the most common mesenchymal tumors of the gastrointestinal tract. The largest gastrointestinal stromal tumor ever recorded in literature weighed approximately 6.1 kg and measured 39 cm × 27 cm × 14 cm. About two-thirds of GISTs are malignant. The tumor size, mitotic rate, cellularity, and nuclear pleomorphism are the most important parameters when considering prognosis and recurrence. The definitive treatment for these tumors is resection. In the year 2000, the first patient was treated with the tyrosine kinase inhibitor imatinib and since then, gastrointestinal stromal tumors with high-risk features have been treated successfully with tyrosine kinase inhibitors. We present the largest gastrointestinal stromal tumor recorded in medical literature measuring 42.0 cm × 31.0 cm × 23.0 cm in maximum dimensions and weighing in at approximately 18.5 kg in a 65-year-old African-American male who presented with increased abdominal distention. The mass was successfully excised, and the patient was treated with imatinib without local or distant recurrence 1.5 years postoperatively.