GEIS guidelines for gastrointestinal sarcomas (GIST)

Understanding Gastric GIST: From Pathophysiology to Personalized Treatment

Background: Gastric gastrointestinal stromal tumors (GISTs) represent a subset of gastrointestinal tumors predominantly found in the stomach. Despite their rarity, these tumors carry significant implications for patient health and management. GISTs are potentially malignant tumors with unpredictable progression. They originate from the interstitial cells of Cajal, which are positioned between the intramural neurons and the smooth muscle cells of the digestive tract. These tumors are characterized primarily by mutations in the c-Kit gene, as well as other mutations such as those in the platelet-derived growth factor receptor alpha (PDGFRA) gene. Methods: Our comprehensive search across five databases initially yielded 2976 articles. After eliminating 197 duplicates, we screened the titles and abstracts of 2779 articles, excluding 2692 for not meeting the inclusion criteria. During the full-text screening, 16 more articles were excluded. Ultimately, 71 papers met the inclusion criteria and were included in our analysis. Results: Due to differences in study designs, inclusion criteria for patients, and reported outcomes, a meta-analysis was not conducted. The accurate diagnosis of GIST is established through histopathological examination and immunohistochemistry. Histopathologically, GISTs are classified into three main types: spindle cell, epithelioid, and mixed. The therapeutic management of GIST involves surgery, endoscopic treatment, and chemotherapy. Conclusions: The prognosis for GIST patients depends on various factors, including risk category, disease stage, applied treatments, and recurrence post-treatment. A significant recent advancement comes from artificial intelligence, which can be increasingly involved in both the diagnosis and treatment of this tumor.

Electrospun nanofibrous mats loaded with gemcitabine and cisplatin suppress bladder tumor growth by improving the tumor immune microenvironment

The perplexing issues related to positive surgical margins and the considerable negative consequences associated with systemic chemotherapy have posed ongoing challenges for clinicians, especially when it comes to addressing bladder cancer treatment. The current investigation describes the production of nanocomposites loaded with gemcitabine (GEM) and cisplatin (CDDP) through the utilization of electrospinning technology. In vitro and in vivo studies have provided evidence of the strong effectiveness in suppressing tumor advancement while simultaneously reducing the accumulation of chemotherapy drugs within liver and kidney tissues. Mechanically, the GEM and CDDP-loaded electrospun nanocomposites could effectively eliminate myeloid-derived suppressor cells (MDSCs) in tumor tissues, and recruit CD8+ T cells and NKp46+ NK cells to kill tumor cells, which can also effectively inhibit tumor microvascular formation. Our investigation into the impact of localized administration of chemotherapy through GEM and CDDP-loaded electrospun nanocomposites on the tumor microenvironment will offer novel insights for tackling tumors.

The development of a prediction model based on deep learning for prognosis prediction of gastrointestinal stromal tumor: a SEER-based study

Accurately predicting the prognosis of Gastrointestinal stromal tumor (GIST) patients is an important task. The goal of this study was to create and assess models for GIST patients' survival patients using the Surveillance, Epidemiology, and End Results Program (SEER) database based on the three different deep learning models. Four thousand five hundred thirty-eight patients were enrolled in this study and divided into training and test cohorts with a 7:3 ratio; the training cohort was used to develop three different models, including Cox regression, RSF, and DeepSurv model. Test cohort was used to evaluate model performance using c-index, Brier scores, calibration, and the area under the curve (AUC). The net benefits at risk score stratification of GIST patients based on the optimal model was compared with the traditional AJCC staging system using decision curve analysis (DCA). The clinical usefulness of risk score stratification compared to AJCC tumor staging was further assessed using the Net Reclassification Index (NRI) and Integrated Discrimination Improvement (IDI). The DeepSurv model predicted cancer-specific survival (CSS) in GIST patients showed a higher c-index (0.825), lower Brier scores (0.142), and greater AUC of receiver operating characteristic (ROC) analysis (1-year ROC:0.898; 3-year:0.853, and 5-year ROC: 0.856). The calibration plots demonstrated good agreement between the DeepSurv model's forecast and actual results. The NRI values ( training cohort: 0.425 for 1-year, 0.329 for 3-year and 0.264 for 5-year CSS prediction; test cohort:0.552 for 1-year,0.309 for 3-year and 0.255 for 5-year CSS prediction) and IDI (training cohort: 0.130 for 1-year,0.141 for 5-year and 0.155 for 10-year CSS prediction; test cohort: 0.154 for 1-year,0.159 for 3-year and 0.159 for 5-year CSS prediction) indicated that the risk score stratification performed significantly better than the AJCC staging alone (P < 0.001). DCA demonstrated the risk score stratification as more clinically beneficial and discriminatory than AJCC staging. Finally, an interactive native web-based prediction tool was constructed for the survival prediction of GIST patients. This study established a high-performance prediction model for projecting GIST patients based on deep learning, which has advantages in predicting each person's prognosis and risk stratification.

Deciphering the tumor immune microenvironment of imatinib-resistance in advanced gastrointestinal stromal tumors at single-cell resolution

The heterogeneous nature of tumors presents a considerable obstacle in addressing imatinib resistance in advanced cases of gastrointestinal stromal tumors (GIST). To address this issue, we conducted single-cell RNA-sequencing in primary tumors as well as peritoneal and liver metastases from patients diagnosed with locally advanced or advanced GIST. Single-cell transcriptomic signatures of tumor microenvironment (TME) were analyzed. Immunohistochemistry and multiplex immunofluorescence staining were used to further validate it. This analysis revealed unique tumor evolutionary patterns, transcriptome features, dynamic cell-state changes, and different metabolic reprogramming. The findings indicate that in imatinib-resistant TME, tumor cells with activated immune and cytokine-mediated immune responses interacted with a higher proportion of Treg cells via the TIGIT-NECTIN2 axis. Future immunotherapeutic strategies targeting Treg may provide new directions for the treatment of imatinib-resistant patients. In addition, IDO1+ dendritic cells (DC) were highly enriched in imatinib-resistant TME, interacting with various myeloid cells via the BTLA-TNFRSF14 axis, while the interaction was not significant in imatinib-sensitive TME. Our study highlights the transcriptional heterogeneity and distinct immunosuppressive microenvironment of advanced GIST, which provides novel therapeutic strategies and innovative immunotherapeutic agents for imatinib resistance.

TRIM21/USP15 balances ACSL4 stability and the imatinib resistance of gastrointestinal stromal tumors

BACKGROUND

Imatinib has become an exceptionally effective targeted drug for treating gastrointestinal stromal tumors (GISTs). Despite its efficacy, the resistance to imatinib is common in GIST patients, posing a significant challenge to the effective treatment.

METHODS

The expression profiling of TRIM21, USP15, and ACSL4 in GIST patients was evaluated using Western blot and immunohistochemistry. To silence gene expression, shRNA was utilized. Biological function of TRIM21, USP15, and ACSL4 was examined through various methods, including resistance index calculation, colony formation, shRNA interference, and xenograft mouse model. The molecular mechanism of TRIM21 and USP15 in GIST was determined by conducting Western blot, co-immunoprecipitation, and quantitative real-time PCR (qPCR) analyses.

RESULTS

Here we demonstrated that downregulation of ACSL4 is associated with imatinib (IM) resistance in GIST. Moreover, clinical data showed that higher levels of ACSL4 expression are positively correlated with favorable clinical outcomes. Mechanistic investigations further indicated that the reduced expression of ACSL4 in GIST is attributed to excessive protein degradation mediated by the E3 ligase TRIM21 and the deubiquitinase USP15.

CONCLUSION

These findings demonstrate that the TRIM21 and USP15 control ACSL4 stability to maintain the IM sensitive/resistant status of GIST.

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.

KIT mutations and expression: current knowledge and new insights for overcoming IM resistance in GIST

Gastrointestinal stromal tumor (GIST) is the most common sarcoma located in gastrointestinal tract and derived from the interstitial cell of Cajal (ICC) lineage. Both ICC and GIST cells highly rely on KIT signal pathway. Clinically, about 80-90% of treatment-naive GIST patients harbor primary KIT mutations, and special KIT-targeted TKI, imatinib (IM) showing dramatic efficacy but resistance invariably occur, 90% of them was due to the second resistance mutations emerging within the KIT gene. Although there are multiple variants of KIT mutant which did not show complete uniform biologic characteristics, most of them have high KIT expression level. Notably, the high expression level of KIT gene is not correlated to its gene amplification. Recently, accumulating evidences strongly indicated that the gene coding, epigenetic regulation, and pre- or post- protein translation of KIT mutants in GIST were quite different from that of wild type (WT) KIT. In this review, we elucidate the biologic mechanism of KIT variants and update the underlying mechanism of the expression of KIT gene, which are exclusively regulated in GIST, providing a promising yet evidence-based therapeutic landscape and possible target for the conquer of IM resistance. Video Abstract.

Fragment-based investigation of thiourea derivatives as VEGFR-2 inhibitors: a cross-validated approach of ligand-based and structure-based molecular modeling studies

Angiogenesis is mediated by the vascular endothelial growth factor (VEGF) that plays a key role in the modulation of progression, invasion and metastasis, related to solid tumors and hematological malignancies. Several small-molecule VEGFR-2 inhibitors are marketed, but their usage is restricted to specific cancers due to severe toxicities. Therefore, cost-effective novel small molecule VEGFR-2 inhibitors may be an alternative to overcome these adverse effects. Here, a set of thiourea-based VEGFR-2 inhibitors were considered for a combined fragment-based QSAR technique, structure-based molecular docking followed by molecular dynamics simulation studies to acquire insights into the key structural attributes and the binding pattern of enzyme-ligand interactions. Noticeably, amine-substituted quinazoline phenyl ring and a higher number of nitrogen atoms, and the hydrazide function in the molecular structure are crucial for VEGFR-2 inhibition whereas methoxy groups are detrimental to VEGFR-2 inhibition. The MD simulation study of sorafenib and thiourea derivatives explored the significance of urea and thiourea moiety binding at VEGFR-2 active site that can be utilized further in the future to design molecules for greater binding stability and better VEGFR-2 selectivity. Therefore, such findings can be beneficial for the development of newer VEGFR-2 inhibitors for further refinement to acquire better therapeutic efficacy.Communicated by Ramaswamy H. Sarma.

Radiomics in gastrointestinal stromal tumours: an up-to-date review

Gastrointestinal stromal tumours are rare mesenchymal neoplasms originating from the Cajal cells and represent the most common sarcomas in the gastroenteric tract. Symptoms may be absent or non-specific, ranging from fatigue and weight loss to acute abdomen. Nowadays endoscopy, echoendoscopy, contrast-enhanced computed tomography, magnetic resonance imaging and positron emission tomography are the main methods for diagnosis. Because of their rarity, these neoplasms may not be included immediately in the differential diagnosis of a solitary abdominal mass. Radiomics is an emerging technique that can extract medical imaging information, not visible to the human eye, transforming it into quantitative data. The purpose of this review is to demonstrate how radiomics can improve the already known imaging techniques by providing useful tools for the diagnosis, treatment, and prognosis of these tumours.

Large-Scale, Multicenter, Prospective Registry Study of Ripretinib in Advanced GIST: A Real-World Study from China

INTRODUCTION

Tyrosine-kinase inhibitors (TKIs) have become the standard treatment for patients with advanced gastrointestinal stromal tumor (GIST); however, secondary mutations can still drive disease progression. Studies have shown that ripretinib, a novel switch-control TKI, inhibits various primary and secondary drug-resistant mutations. There is a paucity of data on the effectiveness and safety of ripretinib in a real-world setting. This prospective, large-scale, real-world registry study aimed to evaluate the effectiveness and safety of ripretinib as a fourth-line treatment in Chinese patients with advanced GIST.

METHODS

Patients ≥ 18 years of age having recurrent/metastatic GIST were enrolled. Key endpoints were median progression-free survival (mPFS), median overall survival (mOS), and adverse events (AEs) incidence. Univariate and multivariate analyses were conducted to identify various parameters associated with PFS.

RESULTS

A total of 240 patients were enrolled. After a median follow-up period of 6.5 months, the mPFS [95% confidence interval (CI)] was 7.70 (6.60, 8.60) months and the mOS was not reached. Multivariate analysis revealed association of Eastern Cooperative Oncology Group (ECOG) performance status score with PFS and superior benefits for non-gastric was observed as compared to gastric GISTs [hazard ratio (HR) 0.58, 95% CI (0.39-0.86)]. Disease control rate and tumor shrinkage (any magnitude) was 73% and 43%, respectively. Ripretinib was also effective in the subgroup of patients with different gene mutations. The toxicities were tolerable, and most reported AEs were alopecia (17.1%) and hand-foot syndrome (15.4%).

CONCLUSION

Ripretinib demonstrated effectiveness and a tolerable safety profile, making it a viable option as a fourth- or later-line treatment in Chinese patients with advanced GISTs, especially for non-gastric GISTs.

TRIAL REGISTRATION

ClinicalTrials.gov identifier, NCT05697107.

Differential impacts of initial treatment status on long-term survival in patients with sarcomas treated in a referral center according to histologic type and anatomic site

OBJECTIVE

The aim of this work was to estimate the magnitude of the differential impacts of initial treatment status relative to the impact of classic clinicopathologic factors on the long-term overall survival (OS) of sarcoma patients in a referral cancer center.

METHODS

From the institutional database, we identified 2185 patients who presented to the institutional multidisciplinary team (MDT) prior to (N = 717, 32.8%) or after (N = 1468, 67.2%) initial treatment, with a first diagnosis of sarcoma from January 1999 to December 2018. Descriptive, univariate and multivariate analyses were applied to identify the factors related to OS. By performing propensity score matching of each completely MDT-treated patient to a referral patient with similar characteristics, the differential impacts of the identified risk and prognostic factors on OS in the 2 groups were estimated by the Kaplan‒Meier survival curves, log-rank test and Cox proportional hazard regression; the results were compared using calibrated nomograph models and forest plots.

RESULTS

Adjusted for the clinicopathologic factors of patient age, sex, primary site, tumor grade, tumor size, resection margin and histology, hazard ratio-based modeling analysis indicated that the initial treatment status was an independent but intermediate prognostic factor associated with long-term OS. The major impacts of the initial and comprehensive MDT-based management on significant improvement of the 20-year OS of sarcomas were reflected in the subgroup of patients with stromal, undifferentiated pleomorphic, fibromatous, fibroepithelial, or synovial neoplasms and tumors in the breast, gastrointestinal tract, or soft tissues of limb and trunk.

CONCLUSIONS

This retrospective study supports early referral of patients with soft tissue masses of unknown identity to a specialized MDT before biopsy and initial resection to reduce the risk of death but highlights an unmet need for a greater understanding of some of the most difficult sarcoma subtypes and subsites and their management.

2023 GEIS Guidelines for gastrointestinal stromal tumors

Gastrointestinal stromal tumor (GIST) is the most common malignant neoplasm of mesenchymal origin. GIST spans a wide clinical spectrum that ranges from tumors with essentially no metastatic potential to malignant and life-threatening spread diseases. Gain-of-function mutations in KIT or PDGFRA receptor tyrosine kinases are the crucial drivers of most GISTs, responsible for tumor initiation and evolution throughout the entire course of the disease. The introduction of tyrosine kinase inhibitors targeting these receptors has substantially improved the outcomes in this formerly chemoresistant cancer. As of today, five agents hold regulatory approval for the treatment of GIST: imatinib, sunitinib, regorafenib, ripretinib, and avapritinib. This, in turn, represents a success for a rare neoplasm. During the past two decades, GIST has become a paradigmatic model in cancer for multidisciplinary work, given the disease-specific particularities regarding tumor biology and tumor evolution. Herein, we review currently available evidence for the management of GIST. This clinical practice guideline has been developed by a multidisciplinary expert panel (oncologist, pathologist, surgeon, molecular biologist, radiologist, and representative of patients' advocacy groups) from the Spanish Group for Sarcoma Research, and it is conceived to provide, from a critical perspective, the standard approach for diagnosis, treatment, and follow-up.

Therapeutic Targets of Monoclonal Antibodies Used in the Treatment of Cancer: Current and Emerging

Cancer is one of the leading global causes of death and disease, and treatment options are constantly evolving. In this sense, the use of monoclonal antibodies (mAbs) in immunotherapy has been considered a fundamental aspect of modern cancer therapy. In order to avoid collateral damage, it is indispensable to identify specific molecular targets or biomarkers of therapy and/or diagnosis (theragnostic) when designing an appropriate immunotherapeutic regimen for any type of cancer. Furthermore, it is important to understand the currently employed mAbs in immunotherapy and their mechanisms of action in combating cancer. To achieve this, a comprehensive understanding of the biology of cancer cell antigens, domains, and functions is necessary, including both those presently utilized and those emerging as potential targets for the design of new mAbs in cancer treatment. This review aims to provide a description of the therapeutic targets utilized in cancer immunotherapy over the past 5 years, as well as emerging targets that hold promise as potential therapeutic options in the application of mAbs for immunotherapy. Additionally, the review explores the mechanisms of actin of the currently employed mAbs in immunotherapy.

Microvessel density in patients with gastrointestinal stromal tumors: A systematic review and meta-analysis

BACKGROUND

Gastrointestinal stromal tumors (GISTs) are considered the most common mesenchymal tumors of the gastrointestinal tract. Microvessel density (MVD) constitutes a direct method of vascularity quantification and has been associated with survival rates in multiple malignancies.

AIM

To appraise the effect of MVD on the survival of patients with GIST.

METHODS

This study adhered to Systematic reviews and Meta-Analyses guidelines and the Cochrane Handbook for Systematic Reviews of Interventions. Electronic scholar databases and grey literature repositories were systematically screened. The Fixed Effects or Random Effects models were used according to the Cochran Q test.

RESULTS

In total, 6 eligible studies were identified. The pooled hazard ratio (HR) for disease free survival (DFS) was 8.52 (95%CI: 1.69-42.84, P = 0.009). The odds ratios of disease-free survival between high and low MVD groups at 12 and 60 mo did not reach statistical significance. Significant superiority of the low MVD group in terms of DFS was documented at 36 and 120 mo (OR: 8.46, P < 0.0001 and OR: 22.71, P = 0.0003, respectively) as well as at metastases rate (OR: 0.11, P = 0.0003).

CONCLUSION

MVD significantly correlates with the HR of DFS and overall survival rates at 36 and 120 mo. Further prospective studies of higher methodological quality are required.

A novel technique for endoscope progression in gastroscopy resection: forward-return way for dissection of stromal tumor in the muscularis propria of the gastric fundus

Background

The fundus of the stomach is a challenging region for endoscopic resection of gastrointestinal stromal tumors (GISTs), especially in the anterior wall of the fornix at the side of the greater curvature. This study aimed to introduce the Forward-Return Way (FRW) technique in gastric fundus operations and provide evidence of its advantages. The FRW technique allows the gastroscope to access the stomach fornix without entering the gastric antrum after passing through the gastric cardia. Using FRW, the gastroscope body makes a forward return along the wall of the posterior wall of the upper gastric body and the wall of the greater curvature.

Methods

The clinical data of patients with stromal tumors in muscularis propria at the gastric fundus (STMF) at the Fourth Hospital of China Medical University between May 2020- March 2021 were reviewed. The novel FRW technique was used in the procedures, and the beneficial effects, suitability, applicable lesion site, and success rates of FRW were analyzed.

Results

A total of 10 cases were reviewed, and the FRW technique was successfully performed in 7 cases (70%). The gastroscope's tip reached the area just below the gastric cardia, allowing endoscopists to successfully access all angles and sites of the stomach's fundus in all seven patients. The lesion was easily accessed, and the gastroscope was stable with good left-right and forward-backwards movements.

Conclusion

The FRW technique significantly facilitates the resection of the GISTs by aligning the endoscopy body movement direction with the observation direction. Gastrointestinal Stromal Tumor; forward-return of gastroscopy along the gastric body wall; muscularis propria; gastric fundus.

An ileal gastrointestinal stromal tumor misdiagnosed as pelvic metastases from rectal cancer: a case report

With the advancement of imaging and pathological diagnostic methods, it is not uncommon to see synchronous gastrointestinal stromal tumors (GIST) and other primary cancers, the most common of which are synchronous gastric cancer and gastric GIST. However, synchronous advanced rectal cancer and high-risk GIST in the terminal ileum are extremely rare, and they are easily misdiagnosed as rectal cancer with pelvic metastases due to their special location near iliac vessels. Herein, we report a 55-year-old Chinese woman with rectal cancer. Preoperative imaging revealed a middle and lower rectal lesion with a right pelvic mass (considered possible metastasis from rectal cancer). Through multidisciplinary discussions, we suspected the possibility of rectal cancer synchronous with a GIST in the terminal ileum. Intraoperative exploration by laparoscopy revealed a terminal ileal mass with pelvic adhesion, a rectal mass with plasma membrane depression, and no abdominal or liver metastases. Laparoscopic radical proctectomy (DIXON) plus partial small bowel resection plus prophylactic loop ileostomy was performed, and the pathological report confirmed the coexistence of advanced rectal cancer and a high-risk ileal GIST. The patient was treated with the chemotherapy (CAPEOX regimen) plus targeted therapy(imatinib) after surgery, and no abnormalities were observed on the follow-up examination. Synchronous rectal cancer and ileal GIST are rare and easily misdiagnosed as a rectal cancer with pelvic metastases, and careful preoperative imaging analysis and prompt laparoscopic exploration are required to determine the diagnosis and prolong patient survival.

Advances in immunology and immunotherapy for mesenchymal gastrointestinal cancers

Mesenchymal gastrointestinal cancers are represented by the gastrointestinal stromal tumors (GISTs) which occur throughout the whole gastrointestinal tract, and affect human health and economy globally. Curative surgical resections and tyrosine kinase inhibitors (TKIs) are the main managements for localized GISTs and recurrent/metastatic GISTs, respectively. Despite multi-lines of TKIs treatments prolonged the survival time of recurrent/metastatic GISTs by delaying the relapse and metastasis of the tumor, drug resistance developed quickly and inevitably, and became the huge obstacle for stopping disease progression. Immunotherapy, which is typically represented by immune checkpoint inhibitors (ICIs), has achieved great success in several solid tumors by reactivating the host immune system, and been proposed as an alternative choice for GIST treatment. Substantial efforts have been devoted to the research of immunology and immunotherapy for GIST, and great achievements have been made. Generally, the intratumoral immune cell level and the immune-related gene expressions are influenced by metastasis status, anatomical locations, driver gene mutations of the tumor, and modulated by imatinib therapy. Systemic inflammatory biomarkers are regarded as prognostic indicators of GIST and closely associated with its clinicopathological features. The efficacy of immunotherapy strategies for GIST has been widely explored in pre-clinical cell and mouse models and clinical experiments in human, and some patients did benefit from ICIs. This review comprehensively summarizes the up-to-date advancements of immunology, immunotherapy and research models for GIST, and provides new insights and perspectives for future studies.

Deubiquitylation of Rab35 by USP32 promotes the transmission of imatinib resistance by enhancing exosome secretion in gastrointestinal stromal tumours

Imatinib is a tyrosine kinase inhibitor that is widely used to combat gastrointestinal stromal tumours (GISTs). However, secondary resistance to imatinib is an important challenge in GIST treatment. Recent studies have demonstrated that cancer-derived nanosized exosomes play a key role in intercellular communication, but little is known about the roles of exosomes in imatinib-resistant GISTs. Here, we reveal that exosomes released from imatinib-resistant GISTs transmit drug resistance to imatinib-sensitive tumours. By using iTRAQ technology, we demonstrate that Ras-related protein Rab-35 (Rab35) is upregulated differentially in imatinib-resistant GISTs. Loss of Rab35 decreases exosome secretion, thereby hampering the transmission of imatinib resistance to sensitive tumours. Mechanistically, we showed that the ubiquitin‒proteasome system is involved in elevated Rab35 expression and that ubiquitin-specific protease 32 (USP32), a deubiquitylating enzyme, is bound to Rab35. Further experiments demonstrate that this protease protects Rab35 from proteasomal degradation by reducing Lys48 (K48)-ubiquitination. Additionally, we found that the transcription factor ETV1, which is a lineage survival factor in GISTs, promotes USP32 expression. Collectively, our results reveal that exosomes transmit imatinib resistance in GISTs and that deubiquitylation plays a key role in regulating the transmission process. The USP32-Rab35 axis provides a potential target for interventions to reduce the occurrence of imatinib resistance in GISTs.

Counting mitoses in gastrointestinal stromal tumours (GISTs): variable practices in the real-world setting and their clinical implications

Mitotic count (MC) is an important prognostic indicator in gastrointestinal stromal tumours (GISTs). Though MC evaluation was initially proposed in 50 HPFs, recent international guidelines recommend that MC be performed on 5 mm² because HPFs may have different areas depending on the ocular field number (FN) of the utilized light microscope. Performing MC on different areas leads to a non-standardized evaluation and erroneous risk stratification. The aim of the study was to audit real-life MC practices with special emphasis on possible risk stratification errors. A survey was administered to Italian pathologists to evaluate the following: method used for MC (5 mm² versus 50 HPF); FN of the light microscope; prognostic scheme for risk stratification. Based on the results of the survey, 100 GISTs (25/risk class using Miettinen prognostic scheme) were retrieved and MC performed using 5 mm² versus the corresponding mm² area sizes of 50 HPFs with variable FNs (18, 20, 22). The survey demonstrated that the majority of pathologists (64.5%) use 50 HPFs with various FNs leading to excessive area size. The most frequently used prognostic scheme is that by Miettinen. Using this prognostic scheme and counting mitoses in 5 mm² versus 50 HPFs with FNs 18, 20 and 22, a change in risk class was identified ranging from 10 to 41%, depending on FN. In conclusion, this study demonstrates that MC is still frequently performed on 50 HPF, with area sizes exceeding the specified 5 mm² by far.

[Use of genome-wide testing in oncology: French expert opinion based on the Delphi methodology]

In oncology, genome-wide testing is a major element in facilitating the implementation of precision medicine. However, current recommendations do not always specify the indication and utility of these tests according to the type of cancer. A national consensus approach based on a modified Delphi methodology was set up to provide expert opinion on the use of genome-wide testing in clinical practice in France. Four groups of experts - 4 each representing the following topics of interest - were defined: non-small cell lung cancer (NSCLC), breast cancer, melanoma, and cancer of unknown primary (CUP). In each group, assertions were formulated by a lead expert (8, 5, 7 and 6, respectively) and rated by five panellists involved in the management of these cancers, on a scale from 1 (strongly disagree) to 9 (strongly agree). Consensus was reached when 75% of the scores were above 7. In case of disagreement, the panellists were asked to justify their rate. In total, 24 statements reached consensus after two to four rounds of rating, depending on the group. While the experts advocated the routine use of genome-wide testing in the diagnostic management of NSCLC and CUP, they did not recommend the systematisation of these tests for breast cancer and melanoma. Nevertheless, access to innovation in France could soon remove certain barriers and allow greater standardisation of broad molecular screening in oncology.

Surgical and oncological results after surgical treatment of patients diagnosed with sarcoma liver metastases

INTRODUCTION

The presence of liver metastases in sarcomatous tumors is associated with poor prognosis. However, in selected patients, surgical resection has been suggested as a tool to improve survival rates. The aim of our study is to describe postoperative and oncological outcomes after liver resection.

METHODS

A retrospective unicentric study was conducted including patients diagnosed with hepatic metastases from soft tissue sarcoma who underwent hepatic resection between 2003-2019. The inclusion criteria were the presence of resectable disease, including synchronic and metachronic lesions. The presence of extra-hepatic controlled disease was not considered unresectable.

RESULTS

Nineteen patients underwent liver resection for liver metastasis of 7 different sarcomatous subtypes. Median age was 58-years. Liver metastases were diagnosed a median 25 months after primary tumor diagnosis. Six patients (32%) suffered of synchronic metastases and 12 (63%) were affected of extrahepatic disease. Major hepatectomy was done in 5 (26 %) patients, 8 (42%) minor complications were described. Median follow-up was 33 months. Survival analysis was performed independently for, GIST tumors and non-GIST sarcomas. One, three and five-year survival rate was 100%, 85.7% and 42.9% in non-GIST sarcomas, while Five and ten-year survival rate was 100% and 40% in GIST, respectively.

CONCLUSION

Surgical approach of liver metastases of sarcomatous tumors seems to be useful in order to improve survival in selected patients, while been associated to low complications rate. In our cohort, extrahepatic disease rate is high in comparison with series published before, nevertheless survival is comparable. These results support performing surgical resection in selected patients with stable extrahepatic disease.

Chinese Pedigree with Hereditary Gastrointestinal Stromal Tumors: A Case Report and Literature Review

Familial gastrointestinal stromal tumor (GIST) is a rare autosomal dominant genetic disorder with only a few affected families reported to date. Here, we report a case of familial GISTs harboring a novel germline mutation within exon 18 of KIT. A 58-year-old male patient presented with gastric subepithelial lesions accompanied by cutaneous hyperpigmentation, which were subsequently diagnosed as multinodular GISTs. Endoscopic surgery was initially conducted to remove the larger lesions, and pathological examinations were then conducted for the diagnosis of GISTs. Family history revealed that some other family members had similar cutaneous pigmentations. Whole-exome sequencing was used to search for potential driver mutations, and Sanger sequencing was used for mutation validation. A novel primary driver mutation of KIT (c.G2485C, p.A829P) was detected in these hereditary GISTs, which has been reported in some targeted chemotherapy-resistant GISTs. Cell models were subsequently established for the rapid screening of candidate drugs and exploring potential mechanisms. This mutation could lead to cell proliferation and imatinib resistance by ligand-independent activation of KIT; however, ripretinib administration was identified as an applicable targeted therapy for this mutation. The mutation activated the JAK/STAT3 and MAPK/ERK pathways, which could be inhibited by ripretinib administration. To the best of our knowledge, this is the first report of the KIT-A829P mutation in familial GISTs, complementing the pathogenesis of familial GISTs and providing valuable information for the precision treatment of this disease.

Molecular Mechanisms of Tyrosine Kinase Inhibitor Resistance in Chronic Myeloid Leukemia

The hematopoietic neoplasm chronic myeloid leukemia (CML) is a rare disease caused by chromosomal reciprocal translocation t(9;22)(q34:q11) with subsequent formation of the BCR-ABL1 fusion gene. This fusion gene encodes a constitutively active tyrosine kinase, which results in malignant transformation of the cells. Since 2001, CML can be effectively treated using tyrosine kinase inhibitors (TKIs) such as imatinib, which prevent phosphorylation of downstream targets by blockade of the BCR-ABL kinase. Due to its tremendous success, this treatment became the role model of targeted therapy in precision oncology. Here, we review the mechanisms of TKI resistance focusing on BCR-ABL1-dependent and -independent mechanisms. These include the genomics of the BCR-ABL1, TKI metabolism and transport and alternative signaling pathways.

Transcriptomic study of gastrointestinal stromal tumors with liver metastasis

Introduction: GIST (gastrointestinal stromal tumor) is the most prominent mesenchymal neoplasms of the gastrointestinal tract, and liver is the most common metastasis site for GIST. The molecular mechanism leading to liver metastasis of GIST is currently unclear. Methods: With the goal of revealing the underlying mechanism, we performed whole-genome gene expression profiling on 18 pairs of RNA samples comprised of GIST tissues (with liver metastasis) and corresponding non-tumor tissues. After identifying differentially expressed gene, functional annotation and signal pathway analyses were conducted. GSE13861, datasets that compare GIST (without liver metastasis) with adjacent tissues, served as a comparison. Results: A total of 492 up-regulated genes and 629 down-regulated genes were identified as differentially expressed genes between liver metastasis tissues and non-tumor tissues. We characterized expression patterns of DEGs identified from our cohort and GSE13861 that show signatures of enrichment for functionality. In subsequent gene set enrichment analysis, differentially expressed genes were mainly enriched in Epithelial Mesenchymal Transition in both datasets. 493 genes were overlapped among our whole-genome gene expression profiling results and GSE13861, consisting 188 up-regulated genes and 305 down-regulated genes. By using CytoHubba plugin of Cytoscape, CDH1, CD34, KIT, PROM1, SOX9, FGF2, CD24, ALDH1A1, JAG1 and NES were identified as top ten hub genes in tumorigenesis and liver metastasis of GIST. higher expression levels of FGF2, JAG1, CD34, ALDH1A1 and the lower expression level of CDH1 were respectively associated with unfavorable overall survival. Meanwhile higher expression levels of CD34, FGF2, KIT, JAG1, ALDH1A were correlated with worse disease-free survival. Discussion: The present study may help to provide candidate pathways and targets for treatment of GIST and prevention methods to liver metastasis.

SH3BP2 Silencing Increases miRNAs Targeting ETV1 and Microphthalmia-Associated Transcription Factor, Decreasing the Proliferation of Gastrointestinal Stromal Tumors

Gastrointestinal stromal tumors (GISTs) are the most common mesenchymal tumors of the gastrointestinal tract. Gain of function in receptor tyrosine kinases type III, KIT, or PDGFRA drives the majority of GIST. Previously, our group reported that silencing of the adaptor molecule SH3 Binding Protein 2 (SH3BP2) downregulated KIT and PDGFRA and microphthalmia-associated transcription factor (MITF) levels and reduced tumor growth. This study shows that SH3BP2 silencing also decreases levels of ETV1, a required factor for GIST growth. To dissect the SH3BP2 pathway in GIST cells, we performed a miRNA array in SH3BP2-silenced GIST cell lines. Among the most up-regulated miRNAs, we found miR-1246 and miR-5100 to be predicted to target MITF and ETV1. Overexpression of these miRNAs led to a decrease in MITF and ETV1 levels. In this context, cell viability and cell cycle progression were affected, and a reduction in BCL2 and CDK2 was observed. Interestingly, overexpression of MITF enhanced cell proliferation and significantly rescued the viability of miRNA-transduced cells. Altogether, the KIT-SH3BP2-MITF/ETV1 pathway deserves to be considered in GIST cell survival and proliferation.

Small Gastric Stromal Tumors: An Underestimated Risk

BACKGROUND AND OBJECTIVES

Small gastrointestinal stromal tumors (GISTs) are defined as tumors less than 2 cm in diameter, which are often found incidentally during gastroscopy. There is controversy regarding the management of small GISTs, and a certain percentage of small GISTs become malignant during follow-up. Previous studies which used Sanger targeted sequencing have shown that the mutation rate of small GISTs is significantly lower than that of large tumors. The aim of this study was to investigate the overall mutational profile of small GISTs, including those of wild-type tumors, using whole-exome sequencing (WES) and Sanger sequencing.

METHODS

Thirty-six paired small GIST specimens, which were resected by endoscopy, were analyzed by WES. Somatic mutations identified by WES were confirmed by Sanger sequencing. Sanger sequencing was performed in an additional 38 small gastric stromal tumor samples for examining hotspot mutations in KIT, PDGFRA, and BRAF.

RESULTS

Somatic C-KIT/PDGFRA mutations accounted for 81% of the mutations, including three novel mutation sites in C-KIT at exon 11, across the entire small gastric stromal tumor cohort (n = 74). In addition, 15% of small GISTs harbored previously undescribed BRAF-V600E hotspot mutations. No significant correlation was observed among the genotype, pathological features, and clinical classification.

CONCLUSIONS

Our data revealed a high overall mutation rate (~96%) in small GISTs, indicating that genetic alterations are common events in early GIST generation. We also identified a high frequency of oncogenic BRAF-V600E mutations (15%) in small GISTs, which has not been previously reported.

Deep learning and radiomics to predict the mitotic index of gastrointestinal stromal tumors based on multiparametric MRI

Introduction

Preoperative evaluation of the mitotic index (MI) of gastrointestinal stromal tumors (GISTs) represents the basis of individualized treatment of patients. However, the accuracy of conventional preoperative imaging methods is limited. The aim of this study was to develop a predictive model based on multiparametric MRI for preoperative MI prediction.

Methods

A total of 112 patients who were pathologically diagnosed with GIST were enrolled in this study. The dataset was subdivided into the development (n = 81) and test (n = 31) sets based on the time of diagnosis. With the use of T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) map, a convolutional neural network (CNN)-based classifier was developed for MI prediction, which used a hybrid approach based on 2D tumor images and radiomics features from 3D tumor shape. The trained model was tested on an internal test set. Then, the hybrid model was comprehensively tested and compared with the conventional ResNet, shape radiomics classifier, and age plus diameter classifier.

Results

The hybrid model showed good MI prediction ability at the image level; the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and accuracy in the test set were 0.947 (95% confidence interval [CI]: 0.927-0.968), 0.964 (95% CI: 0.930-0.978), and 90.8 (95% CI: 88.0-93.0), respectively. With the average probabilities from multiple samples per patient, good performance was also achieved at the patient level, with AUROC, AUPRC, and accuracy of 0.930 (95% CI: 0.828-1.000), 0.941 (95% CI: 0.792-1.000), and 93.6% (95% CI: 79.3-98.2) in the test set, respectively.

Discussion

The deep learning-based hybrid model demonstrated the potential to be a good tool for the operative and non-invasive prediction of MI in GIST patients.

The immune subtypes and landscape of sarcomas

Background

Considering the molecular heterogeneity of sarcomas and their immunologically quiet character, immunotherapy (e.g., immune checkpoint inhibitors) plays a viable role in only a subset of these tumors. This study aimed to determine the immune subtypes (IMSs) of sarcomas for selecting suitable patients from an extremely heterogeneous population.

Results

By performing consensus clustering analysis of the gene expression profiles of 538 patients with sarcomas in online databases, we stratified sarcomas into three IMSs characterized by different immune cell features, tumor mutational burdens (TMBs), gene mutations, and clinical outcomes. IMS1 showed an immune “hot” and immunosuppressive phenotype, the highest frequencies of CSMD3 mutation but the lowest frequencies of HMCN1 and LAMA2 mutations; these patients had the worst progression-free survival (PFS). IMS2 was defined by a high TMB and more gene mutations, but had the lowest frequency of MND1 mutations. IMS3 displayed the highest MDN1 expression level and an immune “cold” phenotype, these patients had the worst PFS. Each subtype was associated with different expression levels of immunogenic cell death modulators and immune checkpoints. Moreover, we applied graph learning-based dimensionality reduction to the immune landscape and identified significant intra-cluster heterogeneity within each IMS. Finally, we developed and validated an immune gene signature with good prognostic performance.

Conclusions

Our results provide a conceptual framework for understanding the immunological heterogeneity of sarcomas. The identification of immune-related subtypes may facilitate optimal selection of sarcoma patients who will respond to appropriate therapeutic strategies.

Patient-Derived Organoid Facilitating Personalized Medicine in Gastrointestinal Stromal Tumor With Liver Metastasis: A Case Report

The gastrointestinal stromal tumors (GIST) are a rare gastrointestinal tract malignancy. The two primary mutation sites are found in KIT and platelet-derived growth factor receptor-α (PDGFR-α) genes. The current study reports on a point mutation within the exon 11 of KIT, named KIT p.V560E. Patient-derived organoids (PDOs) are potential 3D in vitro models of tissues that can be used to identify sensitivity toward specific targets in patients with tumors and allow for personalized medicine when drugs specific for newly identified genetic locus mutations are not yet available. This study describes a 68-year-old patient who complained of diffused abdominal pain and intermittent melena lasting more than 10 days. He has no other gastrointestinal abnormalities, prior abdominal surgery, or related family history. Surgery was conducted first to remove the lesions and ascertain the disease through histology and immunohistochemical stains of the mass. Immunohistochemistry revealed that the tumor was positive for CD117 and Dog-1. Based on the above findings, he was diagnosed with GISTs. Gene detection analysis and organoid culture were then performed to verify clinical decisions. KIT p.V560E and the reduced number of RB1 copies were identified as two obvious mutations, so the patient was administrated first-line treatment of imatinib 400 mg/d. However, progressive disease prompted us to switch to sunitinib, and his condition gradually improved. Meanwhile, organoid culture showed sensitivity to sunitinib and tolerance to imatinib with half-maximal inhibitory concentration (IC50) values of 0.89 and >20, respectively. In summary, to the best of our knowledge, this is the first time that the established organoid culture indicated that the GISTs organoid could identify the sensitivity to target therapies and facilitate individual-based treatment.

A case of jejunal GIST revealed by hematemesis: Unusual situation

Introduction

Gastrointestinal stromal tumors (GISTs) are rare tumors of the gastrointestinal (GI) tract, which can occur in majorly stomach, and rarely in the small intestine, rectum, and large intestine. We report a jejunal GIST presented with massive hematemesis in the current study.

Case presentation

A 39-years-old male, without any underlying history, was presented to our center with the complaint of massive hematemesis. Given the unstable hemodynamics of the patient, an upper GI endoscopy was requested, associated with a large amount of blood in the duodenal bulb without any sign of bleeding. The patient was sent to the operation room, and after laparotomy, a mass was seen in the jejunum, revealed as GIST after pathological study.

Discussion

Small-intestine-related etiologies are rare conditions related to upper GI bleeding (UGIB). Jejunal GIST usually manifests as asymptomatic subepithelial mass and is associated with abdominal discomfort or GI bleeding. Sudden unset bleeding is a rare manifestation of jejunal GIST, but it can be associated with the emergency outcome and may need emergency intervention.

Conclusion

UGIB can occur in jejunal GIST, which should be considered in the management of UGIB.

•

Gastrointestinal stromal tumors (GISTs) are rare tumors of the gastrointestinal (GI) tract.

•

GISTs are rarely found in the small intestine, compatible with abdominal discomfort.

•

Jejunal GISTs usually manifest as intestinal obstruction and abdominal pain.

•

Massive hematemesis is rare in jejunal GISTs and should be consider in the management of upper GI bleeding.

Mutation of KIT in cellular extraskeletal myxoid chondrosarcoma: a case report and literature review

BACKGROUND

Extraskeletal myxoid chondrosarcomas (EMCs) are solid tumors that have been genetically and biologically characterized. Only a few studies have discussed the role of the KIT gene or CD117 expression in EMCs, identified by immunohistochemical (IHC) staining. Herein, we present a novel case of cellular EMC exhibiting an EWSR1-NR4A3 fusion, KIT exon 13 mutations and strong diffuse expression of CD117.

CASE PRESENTATION

A 69-year-old man presented with a fist-sized tumor on his left shoulder. CT revealed a tumor in the left thoracic and dorsal muscle space. The tumor was completely resected. Histologically, the tumor cells had a nodular structure and infiltrated the peripheral fat and muscle tissues. The tumor cells were uniform in size with round nuclei, well-defined nucleoli and eosinophilic cytoplasm. Immunohistochemically, the tumor cells were positive for CD117, vimentin, CD56 and NSE and focally expressed desmin; the cells were negative for myogenin, S-100, SYN, INSM1, CD34, STAT6, INI-1, Brachyury, ERG, TLE1, AE1/AE3, WT-1, CD99 and SMA. NGS revealed an EWSR1-NR4A3 fusion and KIT exon 13 mutations. The patient had no further treatment after surgery, and no recurrence or metastasis occurred during the ~ 10 month follow-up period.

CONCLUSIONS

Molecular detection is an indispensable technique for diagnosing cellular EMCs. The KIT mutations noted in this case report may offer fresh insights into EMCs treatment options.

Value of 18F-FDG PET/CT for differentiating diagnosis between malignant and benign primary gastric gastrointestinal mesenchymal tumors: a single-center retrospective study

BACKGROUND

Malignant primary gastric gastrointestinal stromal tumors (gGISTs) without treatment with imatinib are prone to bleeding and peritoneum implantation during operation. Therefore, preoperative assessment of the malignant potential of gGIST is essential. The use of 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) combined with computed tomography (PET/CT) as a non-invasive tool for diagnosis, staging and prognosis evaluation in oncology, may also be useful for gGISTs. In the present study, we analyzed the value of 18F-FDG PET-CT in assessing the malignant potential of gGISTs before treatment.

METHODS

Patients who were diagnosed with gGIST by pathology and underwent 18F-FDG PET/CT at the same time were collected. The clinicopathological features of 26 patients with gGISTs were retrospectively analyzed at last. The gGIST risk classification was graded according to the US National Institutes of Health (NIH) GIST risk classification criteria [2008]. Lesions were classified as malignant group (moderate- or high-risk category) and benign group (low- or very low-risk category) according to pathology. The relationship between the maximal standard uptake value (SUVmax) and GIST risk category, tumor diameter, Ki-67 index, and mitotic count was analyzed. The cut-off level of SUVmax for the diagnosis of malignant gGIST with the highest sensitivity was calculated based on the receiver-operating characteristic (ROC) curve.

RESULTS

The SUVmax, tumor diameter, Ki-67 index, and mitotic count of the 26 gGIST patients were 5.90±4.49, 7.40±4.92 cm, 7.62%±11.76%, (5.96±3.19)/50 high-power field (HPF), respectively. SUVmax was significantly correlated with GIST risk category, Ki-67 index, and mitotic count (r=0.855, 0.860, and 0.690, all P<0.01) but not with tumor diameter (r=0.383, P=0.054). The SUVmax of gGIST was 7.00±4.57 in the malignant group (moderate or high NIH risk category in 20 patients), which was significantly different from that (2.25±0.77) in the benign group (low or extremely low NIH risk category in 6 patients) (t=4.566, P<0.01). ROC curve analysis showed that a SUVmax cut-off of 2.60 was most sensitive for predicting malignant gGIST. When the area under the curve was 0.967, the sensitivity was 100% and the specificity was 83.3%.

CONCLUSIONS

SUVmax may be used as a complementary indicator for predicting the malignant potential of gGISTs before treatment.

Combined Positive Score for Programmed Death Ligand-1 Expression and Inflammatory Microenvironment in Gastrointestinal Stromal Tumors

Background and Objectives: GISTs are the most frequent type of mesenchymal neoplasm of the digestive tract. The prognosis is mainly determined by tumor dimensions, mitotic rate and location, but other less well-documented factors can influence evolution and survival. The immune microenvironment and checkpoint molecule expression were proven to impact the prognosis in different types of cancer. The aim of this study was to determine PD-L1 expression in GISTs and to evaluate the level of intratumoral immune infiltration in relation to prognostic variables and survival. Materials and Methods: Sixty-five GISTs diagnosed in the same institution between 2015 and 2018 were immunohistochemically tested for PD-L1 and evaluated using CPS. Immune cells were emphasized, with CD3, CD4, CD8, CD20 and CD68 antibodies and quantified. All data were processed using statistical tools. Results: The median age was 61 years (range, 28–78) and 36 patients (55.4%) were males. The location of the tumors was predominantly gastric (46%), followed by the small bowel (17%) and colorectal (6%). In addition, 11% were EGISTs and 20% were secondary tumors (11% metastases and 9% local recurrences). PD-L1 had a variable expression in tumor and inflammatory cells, with a CPS ranging from 0 to 100. Moreover, 64.6% of cases were PD-L1 positive with no significant differences among categories of variables, such as the age and the sex of the patient, tumor location, the primary or secondary character of the tumor, dimensions, mitotic rate, the risk of disease progression and tumor cell type. Immune cells had a variable distribution throughout the tumors. CD3+ lymphocytes were the most frequent type. CD20+ cells were identified in a larger number in tumors ≤5 cm (p = 0.038). PD-L1-positive tumors had a higher number of immune cells, particularly CD3+, CD20+ and CD68+, in comparison to PD-L1-negative ones (p = 0.032, p = 0.051, p = 0.008). Epithelioid and mixed cell-type tumors had a higher number of CD68+ cells. Survival was not influenced by PD-L1 expression; instead, it was decreased in multifocal tumors (p = 0.0001) and in cases with Ki67 ≥ 50% (p = 0.008). Conclusions: PD-L1-positive expression and the presence of different immune cell types, in variable quantities, can contribute to a better understanding of the complex interactions between tumor cells and the microenvironment, with a possible therapeutic role in GISTs.

OUP accepted manuscript

We performed the accurate diagnosis and complete surgical resection of a gastrointestinal stromal tumor at the mesentery of the small bowel. Computed tomography (CT) in a 62-year-old man at 2 years after gastrectomy for gastric cancer showed a mesenteric tumor, with no other tumors noted. Positron emission tomography-computed tomography (PET-CT) showed a maximum standardized uptake value (SUV max) of 2.9 at the tumor. The presence of a single and low SUV max tumor allowed us to perform laparoscopic surgery. Partial resection of the tumor with an adequate margin was performed. The pathological findings showed c-kit positivity and a low Ki-67 proliferation index (<5%). In the present case, PET-CT and laparoscopic assessments were useful for accurately evaluating the surgical resectability of the mesenteric tumor after distal gastrectomy for gastric cancer. The low SUV max and laparoscopic findings led to complete surgical resection of a mesenteric tumor.

Development and validation of a novel diagnostic model for initially clinical diagnosed gastrointestinal stromal tumors using an extreme gradient-boosting machine

Introduction

Gastrointestinal stromal tumor (GIST) is the most common gastrointestinal soft tissue tumor. Clinical diagnosis mainly relies on enhanced CT, endoscopy and endoscopic ultrasound (EUS), but the misdiagnosis rate is still high without fine needle aspiration biopsy. We aim to develop a novel diagnostic model by analyzing the preoperative data of the patients.

Methods

We used the data of patients who were initially diagnosed as gastric GIST and underwent partial gastrectomy. The patients were randomly divided into training dataset and test dataset at a ratio of 3 to 1. After pre-experimental screening, max depth = 2, eta = 0.1, gamma = 0.5, and nrounds = 200 were defined as the best parameters, and in this way we developed the initial extreme gradient-boosting (XGBoost) model. Based on the importance of the features in the initial model, we improved the model by excluding the hematological features. In this way we obtained the final XGBoost model and underwent validation using the test dataset.

Results

In the initial XGBoost model, we found that the hematological indicators (including inflammation and nutritional indicators) examined before the surgery had little effect on the outcome, so we subsequently excluded the hematological indicators. Similarly, we also screened the features from enhanced CT and ultrasound gastroscopy, and finally determined the 6 most important predictors for GIST diagnosis, including the ratio of long and short diameter under CT, the CT value of the tumor, the enhancement of the tumor in arterial period and venous period, existence of liquid area and calcific area inside the tumor under EUS. Round or round-like tumors with a CT value of around 30 (25–37) and delayed enhancement, as well as liquid but not calcific area inside the tumor best indicate the diagnosis of GIST.

Conclusions

We developed a model to further differential diagnose GIST from other tumors in initially clinical diagnosed gastric GIST patients by analyzing the results of clinical examinations that most patients should have completed before surgical resection.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12876-021-02048-1.

Gastric Mass: Intramural Hematoma

Gastric masses can be challenging to diagnose pre-operatively due to their heterogeneity in presentation and work-up. One must be cautious that a seemingly benign mass may be malignant and vice versa. Some of the more common gastric masses include peptic ulcer, adenocarcinoma, and gastrointestinal stromal tumour. These diagnoses have vastly different management strategies despite similar presentations. The case presented here is an example of this management, highlighting a patient with a gastric bleeding mass initially thought to be a gastrointestinal stromal tumour. However, on final pathology, the mass was determined to be benign, an ulcerated hematoma.

Robotic-assisted Resection of a Diaphragmatic Metastasis of a Gastrointestinal Stromal Tumor

Gastrointestinal stromal tumors (GISTs) are relatively rare mesenchymal tumors. The treatment of these tumors has drastically changed based on molecular treatment methods, namely tyrosine kinase inhibitors, which have led to impressive survival benefits. While medical management has enhanced patient outcomes, surgery is still the standard of care for stable, completely resectable primary tumors or metastases that are >2 cm. This case presents the resection of a diaphragmatic metastasis of a tyrosine kinase inhibitor-controlled GIST in a 51-year-old male. The surgery was collaboratively approached from both the thoracic and abdominal cavities, utilizing the da Vinci robotic system. Prior data is limited regarding patient outcomes after robotic-assisted resection of GISTs. However, small case series have shown it to be a safe and effective surgical option. Our patient's quick recovery and return to normal function demonstrate the successful use of robotic-assisted surgery for GIST resection.

Gastrointestinal Stromal Tumor (GIST) from esophagus to anorectum - diagnosis, response evaluation and surveillance on computed tomography (CT) scan

Gastrointestinal stromal tumor (GIST) are the most common non epithelial tumor of the gastrointestinal (GI) tract. They arise from interstitial cells of Cajal present in the myenteric plexus. They can also arise outside the GI tract from mesentery, retro peritoneum and omentum. With the advent of new targeted molecular therapy c- tyrosine kinase inhibitor (Imatinib), it has become important to differentiate between response and pseudo-progression of the disease as response evaluation criteria for GIST are different from Response Evaluation Criteria in Solid Tumors (RECIST). Purpose of this pictorial essay is to enumerate the characteristic CT features of GIST, and discuss atypical features and response evaluation criteria.

Pharmacogenomics of Impaired Tyrosine Kinase Inhibitor Response: Lessons Learned From Chronic Myelogenous Leukemia

The use of small molecules became one key cornerstone of targeted anti-cancer therapy. Among them, tyrosine kinase inhibitors (TKIs) are especially important, as they were the first molecules to proof the concept of targeted anti-cancer treatment. Since 2001, TKIs can be successfully used to treat chronic myelogenous leukemia (CML). CML is a hematologic neoplasm, predominantly caused by reciprocal translocation t(9;22)(q34;q11) leading to formation of the so-called BCR-ABL1 fusion gene. By binding to the BCR-ABL1 kinase and inhibition of downstream target phosphorylation, TKIs, such as imatinib or nilotinib, can be used as single agents to treat CML patients resulting in 80 % 10-year survival rates. However, treatment failure can be observed in 20-25 % of CML patients occurring either dependent or independent from the BCR-ABL1 kinase. Here, we review approved TKIs that are indicated for the treatment of CML, their side effects and limitations. We point out mechanisms of TKI resistance focusing either on BCR-ABL1-dependent mechanisms by summarizing the clinically observed BCR-ABL1-mutations and their implications on TKI binding, as well as on BCR-ABL1-independent mechanisms of resistances. For the latter, we discuss potential mechanisms, among them cytochrome P450 implications, drug efflux transporter variants and expression, microRNA deregulation, as well as the role of alternative signaling pathways. Further, we give insights on how TKI resistance could be analyzed and what could be learned from studying TKI resistance in CML in vitro.

Multimodal functional imaging for early response assessment in patients with gastrointestinal stromal tumor treated with tyrosine kinase inhibitors

BACKGROUND

Several imaging modalities are used in the early work-up of patients with gastrointestinal stromal tumor (GIST) receiving tyrosine kinase inhibitor (TKI) treatment and there is a need to establish whether they provide similar or complimentary information.

PURPOSE

To compare 18F-fluorodeoxyglucose positron emission tomography (FDG PET), computed tomography (CT) and magnetic resonance imaging (MRI) as early predictors of three-month outcomes for patients with GIST receiving TKI treatment.

MATERIAL AND METHODS

Thirty-five patients with advanced GIST were prospectively included between February 2011 and June 2017. FDG PET, contrast-enhanced CT (CECT), and MRI were performed before and early after onset of TKI treatment (range 8-18 days). Early response was categorized according to mRECIST (CT), the Choi criteria (CECT), and PERCIST (FDG PET/CT). For MRI, volumetry from T2-weighted images and change in apparent diffusion coefficient (ADC) from diffusion-weighted imaging was used. The reference standard for early assessment was the three-month mRECIST evaluation based on CT. At three months, both stable disease (SD) and partial response (PR) were categorized as response. Clinical usefulness was defined as agreement between early and three-month assessment.

RESULTS

At the three-month assessment, 91% (32/35) were responders, 37% (13/35) PR, 54% (19/35) SD, and 9% (3/35) had progressive disease (PD). Early assessment correctly predicted three-month response in 93% (27/29) for MRI, 80% (28/35) for PERCIST, 74% (26/35) for Choi, and 23% (8/35) for mRECIST. Six patients had non-FDG-avid tumors. For the FDG-avid tumors, PET/CT correctly predicted three-month response in 97% (28/29).

CONCLUSION

MRI was superior to CECT for early assessment of TKI-treatment response in GIST. If the tumor was FDG-avid, PET and MRI were equally good. Changes in functional parameters were superior to changes in longest tumor diameter (mRECIST).

Gastric and Small Intestine Gist: Results of 156 Cases in 20 Years

PURPOSE

Gastric and small intestine are the most common gastrointestinal stromal tumors (GISTs). There are few studies of patients who underwent surgical treatment with disparate findings. We aimed to evaluate the differences between groups and the risk factors for recurrence and mortality.

METHODS

A retrospective study of 96 gastric and 60 small intestine GIST was performed between 1995 and 2015. Both groups were compared in terms of clinicopathologic features, morbidity, recurrence, and mortality. Statistical analysis was performed with SPSS®.

RESULTS

Eighty-one gastric GISTs and 56 small intestine GISTs underwent surgical treatment. Gastrointestinal bleeding was the most common cause of emergency surgery being more frequent in gastric GIST (P = 0.009); however, emergency surgery was indicated more frequently in the small intestinal GIST (P = 0.004) and was mostly due to perforation (P = 0.009). With a median follow-up of 66.9 (39.7-94.8) months, 28 (20.4%) patients had recurrence. A mitotic index > 5 (P ≤ 0.001) and the intestinal location (P = 0.012) were significantly associated to recurrence. Tumor size > 15 cm (P = 0.001) and an age of ≥ 75 years (P = 0.014) were associated to mortality. On univariate analysis, higher mean values of Ki-67 were associated to higher mortality (P = 0.0032). Small intestine GIST presented lower disease-free survival (DFS) than that of gastric GIST (65.7% vs 90.8%) with P = 0.003. The overall survival (OS) of gastric and small intestine GIST was 74.7% and 71.6%, respectively (P = 0.68).

CONCLUSION

Small intestine GIST received emergency surgery more frequently showing lower DFS and same OS than that of gastric GIST. We found that Ki-67 could be a prognostic factor. Further studies are necessary to assess whether Ki-67 is a prognostic risk factor for GISTs.

Ripretinib for the treatment of advanced gastrointestinal stromal tumor

Gastrointestinal stromal tumors (GISTs) are rare tumors of the gastrointestinal (GI) tract yet represent the most common GI sarcomas. Most GISTs are driven by activating mutations of the KIT and/or PDGFRA genes. Prior to the development of tyrosine kinase inhibitors (TKIs), GISTs were associated with a poor prognosis because conventional cytotoxic chemotherapy was relatively ineffective. However, TKIs that inhibit the most common driver mutations in KIT or PDGFRA have revolutionized the treatment of GISTs over the past two decades. Notwithstanding, ongoing management challenges relate to the development of secondary mutations in these genes, resulting in tumor progression. Due to both the intra- and inter-patient heterogeneity of these secondary mutations in GISTs, optimal treatment requires an agent that blocks as many mutant genes as possible. Ripretinib - a novel switch-control TKI - inhibits many of the most common primary and secondary activating KIT and PDGFRA mutants involved in GIST progression through a dual mechanism of action. In the pivotal INVICTUS phase III trial, patients with advanced GIST that had progressed on at least imatinib, sunitinib, and regorafenib and who received ripretinib experienced significantly longer progression-free survival (primary endpoint) as well as prolongation of overall survival, compared with those receiving placebo. Treatment with ripretinib was associated with durable improvements in quality-of-life indices and a manageable toxicity profile. The most frequent side effects were common to the class of TKIs used in the management of GIST. These results led to the approval of ripretinib for treatment of advanced GIST in adults who have received three or more TKIs, including imatinib. Ripretinib is also under investigation in the second-line treatment of advanced GIST in a phase III trial (INTRIGUE) comparing ripretinib with sunitinib in patients with advanced GIST after treatment with imatinib.

PLAIN LANGUAGE SUMMARY

Use of ripretinib for the treatment of gastrointestinal stromal tumors (GISTs) Gastrointestinal stromal tumors (GISTs) are a rare type of tumor most commonly located in the stomach and small intestine but can develop anywhere throughout the gastrointestinal tract. The symptoms of GISTs vary in extent depending on location of the primary tumor and include a feeling of fullness, abdominal pain, intestinal bleeding, and fatigue. Since these symptoms are nonspecific, making a diagnosis can be challenging. Most GISTs carry initial mutations in genes that control specific enzymes called tyrosine kinases. Historically, treatment of GISTs was limited because traditional chemotherapy is ineffective against these tumors. However, with the introduction of drugs that inhibit tyrosine kinases [i.e., tyrosine kinase inhibitors (TKIs)], survival has been extended substantially. However, many GISTs go on to develop secondary mutations that render them resistant to a given TKI. Prior to the approval of ripretinib, four TKIs were available for the treatment of GIST: imatinib; sunitinib; regorafenib; and, recently, avapritinib. Each drug is used until resistance develops or patients are unable to tolerate the side effects of treatment, after which the next drug is started. Ripretinib was recently approved by the FDA as the fourth drug in the usual treatment sequence recommended for patients with advanced GIST who have progressed (or are treatment intolerant) after receiving three or more TKIs, including imatinib. Approval of ripretinib was based on the results of the INVICTUS trial, which demonstrated that the drug significantly improves the time patients have without progression of the disease or death compared with placebo. The most common side effects related to ripretinib were hair loss, muscle pain, nausea, fatigue, hand-foot syndrome, and diarrhea, although most events were not very severe. Ripretinib is being further studied as the second TKI used in patients with GIST who have progressed on or could not tolerate first-line treatment with imatinib.

LncRNA-HOTAIR activates autophagy and promotes the imatinib resistance of gastrointestinal stromal tumor cells through a mechanism involving the miR-130a/ATG2B pathway

Gastrointestinal stromal tumors (GISTs) are common neoplasms of the gastrointestinal tract that can be treated successfully using C-kit target therapy and surgery; however, imatinib chemoresistance is a major barrier to success in therapy. The present study aimed to discover alternative pathways in imatinib-resistant GISTs. Long noncoding RNAs (lncRNAs) are newly discovered regulators of chemoresistance. Previously, we showed that the lncRNA HOTAIR was upregulated in recurrent GISTs. In this study, we analyzed differentially expressed lncRNAs after imatinib treatment and found that HOTAIR displayed the largest increase. The distribution of HOTAIR in GISTs was shifted from nucleus to cytoplasm after imatinib treatments. The expression of HOTAIR was validated as related to drug sensitivity through Cell Counting Kit-8 assays. Moreover, HOTAIR was associated strongly with cell autophagy and regulated drug sensitivity via autophagy. Mechanistically, HOTAIR correlated negatively with miRNA-130a in GISTs. The downregulation of miRNA-130a reversed HOTAIR-small interfering RNA-induced suppression of autophagy and imatinib sensitivity. We identified autophagy-related protein 2 homolog B (ATG2B) as a downstream target of miR-130a and HOTAIR. ATG2B downregulation reversed the effect of pEX-3-HOTAIR/miR-130a inhibitor on imatinib sensitivity. Finally, HOTAIR was shown to influence the autophagy and imatinib sensitivity of GIST cells in mouse tumor models. Our results suggested that HOTAIR targets the ATG2B inhibitor miR-130a to upregulate the level of cell autophagy so that promotes the imatinib resistance in GISTs.

Gastrointestinal stromal tumors: relationship between preoperative CT features and pathologic risk stratification

OBJECTIVE

To investigate a relationship between contrast-enhanced computed tomography (CECT) features of gastrointestinal stromal tumors (GISTs) and risk of relapse according to Miettinen stratified risk classifications.

METHODS

After ethical committee approval, a retrospective analysis was conducted on the preoperative CECT of patients with pathologically proven GIST undergoing surgery between June 2009 and December 2019. Chi-square analysis was used to evaluate the correlation between Miettinen stratified risk categories and the following imaging features: tumor size and location, growth pattern, margins, type and degree of contrast enhancement, presence of calcifications, necrosis, signs of ulceration/fistulation, internal hemorrhagic foci, enlarged feeding or draining vessels (EFDV), ascites, peritoneal implants, lymphadenopathy, or metastasis.

RESULTS

A total of 54 patients (mean age 65 ± 11, 29 men) were included in the study with a total of 56 GISTs. Necrosis, ulceration/fistulation, hemorrhage, margins, enlarged vessels, type of contrast enhancement, and metastasis turned out to be associated with Miettinen risk categories (p < 0.005). Logistic regression analysis identified the presence of necrosis and EFDV as predictors of pathologic risk of relapse (overall accuracy of 89.3%).

CONCLUSION

Preoperative CECT may be helpful in predicting pathologic risk categories of GISTs, as determined by the Miettinen classification system.

Novel Prognostic Nomogram for Recurrence-Free Survival of Patients With Primary Gastrointestinal Stromal Tumors After Surgical Resection: Combination of Prognostic Nutritional Index and Basic Variables

Background

Gastrointestinal stromal tumor (GIST) is the most common type of mesenchymal tumors in the digestive tract, often recrudescing even after R0 resection. Adjuvant tyrosine kinase inhibitor therapy prolonged recurrence-free survival (RFS). This study aimed to develop a novel nomogram for predicting the RFS of patients following surgical resection of GISTs.

Methods

Clinicopathologic data of patients with GISTs at Tianjin Medical University General Hospital (Tianjin, China) from January 2000 to October 2019 were retrospectively reviewed. Univariate and multivariate Cox regression analyses were used to select the suitable variables from the training cohort to construct a nomogram for 2- and 5-year RFS. The 1,000 bootstrap samples and calibration curves were used to validate the discrimination of the nomogram. The receiver operating characteristic analysis(ROC) was used to compare the predictive ability of the nomogram and present four commonly used risk stratification systems: National Institutes of Health (NIH)–Fletcher staging system; NIH–Miettinen criteria; Modified NIH criteria; and Air Forces Institute of Pathology risk criteria (AFIP).

Results

Univariate and multivariate analyses showed that the tumor site, tumor size, mitotic index, tumor rupture, and prognostic nutritional index were significant factors associated with RFS. These variables were selected to create the nomogram for 2- and 5-year RFS (all P<0.05). The 2- and 5-year the ROC of the nomogram were 0.821 (95% confidence interval [CI]: 0.740–0.903) and 0.798 (95% CI: 0.739–0.903); NIH–Fletcher criteria were 0.757 (95% CI: 0.667–0.846) and 0.683 (95% CI: 0.613–0.753); NIH–Miettinen criteria were 0.762 (95% CI: 0.678–0.845) and 0.718 (95% CI: 0.653–0.783); Modified NIH criteria were 0.750 (95% CI: 0.661–0.838) and 0.689 (95% CI: 0.619–0.760); and AFIP were 0.777 (95% CI: 0.685–0.869) and 0.708 (95% CI: 0.636–0.780). Hence, the predictive probabilities of our nomogram are better than those of other GIST risk stratification systems.

Conclusion

This nomogram, combining tumor site, tumor size, mitotic index, tumor rupture, and prognostic nutritional index, may assist physicians in providing individualized treatment and surveillance protocols for patients with GISTs following surgical resection.

Efficacy evaluation of nilotinib treatment in different genomic subtypes of gastrointestinal stromal tumors: A meta-analysis and systematic review

Nilotinib has been used as a third-line drug for gastrointestinal stromal tumors (GISTs) after a failure of sunitinib. In this study, we aimed to evaluate the efficacy of nilotinib in different genomic subtypes of GISTs. We searched the English articles through EMBASE, Cochrane Library and PubMed Database regarding to the use of nilotinib on GISTs, which published up to February 15, 2019. Inclusion criteria were: GISTs patients received nilotinib in a clinical trial and had detailed genetic subtype records (such as KIT exon 9, KIT exon 11, or PDGFRA mutations, or wild-type). The clinical benefit rate was used to assess the efficacy of nilotinib. A total of 3 studies involving 218 GISTs were included in this meta-analysis. The overall OR (KIT group vs WT group) was 3.26 (95% CI: 1.14-9.28; P = 0.027, P_{heterogeneity} = 0.613). The overall OR in KIT exon 11 group vs WT group was 5.30 (95% CI: 1.79-15.68; P = 0.003, P_{heterogeneity} = 0.409). The overall OR in KIT exon 9 group vs WT group was 0.13 (95% CI: 0.02-0.86; P = 0.035, P_{heterogeneity} = 0.229). The overall OR in KIT exon 11 group vs exon 9 group was 9.96 (95% CI: 0.39-254.66; P < 0.0001, P_{heterogeneity} = 0.024). Different genotypes of GISTs showed different responses to nilotinib, and KIT exon 11-mutant GISTs mostly benefited from nilotinib, followed by KIT exon 9-mutant or WT one.

Case report: multiple gastrointestinal stroma tumors in the background of neurofibromatosis type 1

Gastrointestinal stromal tumors (GISTs) are the most common mesenchymal malignancies of the gastrointestinal tract. GISTs can occur in the background of neurofibromatosis 1 (NF-1), where chemotherapeutic treatment is not optimal and surgical intervention is the only management option. In this case report, we present a case involving a 61-year-old gentleman with NF-1. The patient presented with acute blood loss anemia that was initially controlled with embolization of a hyper-vascular mass abutting the distal jejunum. The patient was taken to the operating room for excision of the mass. All macroscopic disease was excised and the pathology noted GISTs. Surgical decision making is not clearly delineated in the literature for GISTs in patients with NF-1, where targeted therapy is not a treatment option. Resection of all disease should be considered, since NF-1 associated GISTs generally do not have harbor mutations that can be targeted.

Metachronous extragastrointestinal stromal tumor (EGIST) in utero: Report of an unusual case

INTRODUCTION

The gastrointestinal stromal tumor (GIST) is the most common mesenchymal tumor in the digestive tract. Currently, GIST is the name given to CD117 positive mesenchymal tumors, primary of the digestive tract, mesentery, and retroperitoneum. Nevertheless, they have been reported in the mesentery, omentum, gallbladder, bladder wall, and few cases in the uterus; known as extragastrointestinal stromal tumors (EGIST).

PRESENTATION OF CASE

Seventy-six-year-old woman with a history of the third recurrence of pelvic tumor located in the uterus initially diagnosed as uterine leiomyosarcoma. CT and MRI showed a tumor in the uterine corpus of approximately 10 cm. It was decided to perform the surgical rescue. The immunohistochemistry and anatomic pathology report revealed a tumor compatible with a uterine EGIST. It was decided to perform adjuvant treatment with imatinib. Currently, the patient continues to be disease-free 20 months after the surgery.

DISCUSSION

For years, GIST has often been confused with leiomyosarcoma, given that they are histologically almost indistinguishable. The IHC analysis for KIT (CD117) has become essential in the GIST diagnosis. On the other hand, stromal tumors arising outside the gastrointestinal tract are rare (5%), which have a histological and biological behavior similar to that of GISTs.

CONCLUSION

EGISTs are extremely rare and often incidentally detected. Currently, evidence about this location is scarce. According to the literature, this is the first case of uterine EGIST with a metachronous presentation.

Development of a Malignancy Potential Binary Prediction Model Based on Deep Learning for the Mitotic Count of Local Primary Gastrointestinal Stromal Tumors

Objective

The mitotic count of gastrointestinal stromal tumors (GIST) is closely associated with the risk of planting and metastasis. The purpose of this study was to develop a predictive model for the mitotic index of local primary GIST, based on deep learning algorithm.

Materials and Methods

Abdominal contrast-enhanced CT images of 148 pathologically confirmed GIST cases were retrospectively collected for the development of a deep learning classification algorithm. The areas of GIST masses on the CT images were retrospectively labelled by an experienced radiologist. The postoperative pathological mitotic count was considered as the gold standard (high mitotic count, > 5/50 high-power fields [HPFs]; low mitotic count, ≤ 5/50 HPFs). A binary classification model was trained on the basis of the VGG16 convolutional neural network, using the CT images with the training set (n = 108), validation set (n = 20), and the test set (n = 20). The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated at both, the image level and the patient level. The receiver operating characteristic curves were generated on the basis of the model prediction results and the area under curves (AUCs) were calculated. The risk categories of the tumors were predicted according to the Armed Forces Institute of Pathology criteria.

Results

At the image level, the classification prediction results of the mitotic counts in the test cohort were as follows: sensitivity 85.7% (95% confidence interval [CI]: 0.834–0.877), specificity 67.5% (95% CI: 0.636–0.712), PPV 82.1% (95% CI: 0.797–0.843), NPV 73.0% (95% CI: 0.691–0.766), and AUC 0.771 (95% CI: 0.750–0.791). At the patient level, the classification prediction results in the test cohort were as follows: sensitivity 90.0% (95% CI: 0.541–0.995), specificity 70.0% (95% CI: 0.354–0.919), PPV 75.0% (95% CI: 0.428–0.933), NPV 87.5% (95% CI: 0.467–0.993), and AUC 0.800 (95% CI: 0.563–0.943).

Conclusion

We developed and preliminarily verified the GIST mitotic count binary prediction model, based on the VGG convolutional neural network. The model displayed a good predictive performance.