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

2021 ◽  
Vol 11 ◽  
Author(s):  
Haijia Mao ◽  
Bingqian Zhang ◽  
Mingyue Zou ◽  
Yanan Huang ◽  
Liming Yang ◽  
...  
Keyword(s):  
High Risk ◽  
Random Forest ◽  
Gastrointestinal Stromal Tumors ◽  
Roc Curves ◽  
Risk Classification ◽  
Low Risk ◽  
Intermediate Risk ◽  
Stromal Tumors ◽  
Mr Sequences

BackgroundWe conduct a study in developing and validating four MRI-based radiomics models to preoperatively predict the risk classification of gastrointestinal stromal tumors (GISTs).MethodsForty-one patients (low-risk = 17, intermediate-risk = 13, high-risk = 11) underwent MRI before surgery between September 2013 and March 2019 in this retrospective study. The Kruskal–Wallis test with Bonferonni correction and variance threshold was used to select appropriate features, and the Random Forest model (three classification model) was used to select features among the high-risk, intermediate-risk, and low-risk of GISTs. The predictive performance of the models built by the Random Forest was estimated by a 5-fold cross validation (5FCV). Their performance was estimated using the receiver operating characteristic (ROC) curve, summarized as the area under the ROC curve (AUC). Area under the curve (AUC), accuracy, sensitivity, and specificity for risk classification were reported. Linear discriminant analysis (LDA) was used to assess the discriminative ability of these radiomics models.ResultsThe high-risk, intermediate-risk, and low-risk of GISTs were well classified by radiomics models, the micro-average of ROC curves was 0.85, 0.81, 0.87 and 0.94 for T1WI, T2WI, ADC and combined three MR sequences. And ROC curves achieved excellent AUCs for T1WI (0.85, 0.75 and 0.82), T2WI (0.69, 0.78 and 0.78), ADC (0.85, 0.77 and 0.80) and combined three MR sequences (0.96, 0.92, 0.81) for the diagnosis of high-risk, intermediate-risk, and low-risk of GISTs, respectively. In addition, LDA demonstrated the different risk of GISTs were correctly classified by radiomics analysis (61.0% for T1WI, 70.7% for T2WI, 83.3% for ADC, and 78.9% for the combined three MR sequences).ConclusionsRadiomics models based on a single sequence and combined three MR sequences can be a noninvasive method to evaluate the risk classification of GISTs, which may help the treatment of GISTs patients in the future.

The Relationship Between CT Signs of Computed Tomography and Risk Classification of Gastric Stromal Tumors

2021 ◽  
Vol 11 (2) ◽  
pp. 642-647
Author(s):  
Wang Chen ◽  
Rong Guo ◽  
WeiGao Sun ◽  
DingYou Lu
Keyword(s):  
High Risk ◽  
Risk Group ◽  
High Risk Group ◽  
Risk Classification ◽  
Low Risk ◽  
Stromal Tumors ◽  
Medium Risk ◽  
Solid Part ◽  
The Relationship

Objective: The study aims to explore the role of computed tomography (CT) in clinical diagnosis, thus having a preliminary understanding of the relationship between CT signs and the risk of gastric stromal tumors (GSTs). Methods: In this study, 213 patients with GST with complete preoperative CT and postoperative pathological results in Yancheng No. 1 People's Hospital from January 2016 to August 2019 are selected as research objects. The patient's basic information is collected. CT machine (Toshiba 320 row CT and Siemens dualsource CT (Somatom Definition Flash)) is used to examine all patients. The obtained image data are evaluated. Patients are divided into low-risk group, medium risk group and high-risk group according to the risk classification standard of GST. The data collected are analyzed statistically. Results: After risk classification of all patients, 87 patients in low-risk group, 74 in medium-risk group and 52 in high-risk group are found. After further analysis of the risk classification, it is found that there is no significant difference in GST risk classification between the tumor sites (P > 0.05). In the GST risk classification, the smaller the tumor, the more the low-risk group, the larger the tumor, the more the high-risk group, the difference is statistically significant (P < 0.05). In the observation of the relationship between tumor growth pattern and risk classification, it is found that the number of intraluminal growth is the most, while mixed growth is the least (P < 0.05). Further analysis of tumor density, solid part enhancement, distant metastasis and risk grade show that there are significant differences (P < 0.05). Conclusion: As an auxiliary diagnostic method in clinic, CT signs can be used to analyze the relationship with risk grade from tumor location, tumor size, tumor growth mode, tumor density, solid part enhancement degree and tumor distant metastasis, so as to have a more accurate understanding of patients' situation, and provide experimental basis for the later application of CT signs in tumor and auxiliary diagnosis.

A Novel Risk Classification Model Predicts Overall Survival and Locoregional Surgery Benefit in Colorectal Patients with Distant Metastasis at the Initial Diagnosis

2020 ◽  
Author(s):  
Mo Chen ◽  
Tian-en Li ◽  
Pei-zhun Du ◽  
Junjie Pan ◽  
Zheng Wang ◽  
...  
Keyword(s):  
Overall Survival ◽  
High Risk ◽  
Distant Metastasis ◽  
Cox Regression ◽  
Risk Group ◽  
Risk Groups ◽  
Risk Classification ◽  
Low Risk ◽  
Classification Model ◽  
Intermediate Risk

Abstract Background and aims: In this research, we aimed to construct a risk classification model to predict overall survival (OS) and locoregional surgery benefit in colorectal cancer (CRC) patients with distant metastasis.Methods: We selected a cohort consisting of 12741 CRC patients diagnosed with distant metastasis between 2010 and 2014, from the Surveillance, Epidemiology and End Results (SEER) database. Patients were randomly assigned into training group and validation group at the ratio of 2:1. Univariable and multivariable Cox regression models were applied to screen independent prognostic factors. A nomogram was constructed and assessed by the Harrell’s concordance index (C-index) and calibration plots. A novel risk classification model was further established based on the nomogram.Results: Ultimately 12 independent risk factors including race, age, marriage, tumor site, tumor size, grade, T stage, N stage, bone metastasis, brain metastasis, lung metastasis and liver metastasis were identified and adopted in the nomogram. The C-indexes of training and validation groups were 0.77 (95% confidence interval [CI] 0.73-0.81) and 0.75 (95% CI 0.72-0.78), respectively. The risk classification model stratified patients into three risk groups (low-, intermediate- and high-risk) with divergent median OS (low-risk: 36.0 months, 95% CI 34.1-37.9; intermediate-risk: 18.0 months, 95% CI 17.4-18.6; high-risk: 6.0 months, 95% CI 5.3-6.7). Locoregional therapies including surgery and radiotherapy could prognostically benefit patients in the low-risk group (surgery: hazard ratio [HR] 0.59, 95% CI 0.50-0.71; radiotherapy: HR 0.84, 95% CI 0.72-0.98) and intermediate risk group (surgery: HR 0.61, 95% CI 0.54-0.68; radiotherapy: HR 0.86, 95% CI 0.77-0.95), but not in the high-risk group (surgery: HR 1.03, 95% CI 0.82-1.29; radiotherapy: HR 1.03, 95% CI 0.81-1.31). And all risk groups could benefit from systemic therapy (low-risk: HR 0.68, 95% CI 0.58-0.80; intermediate-risk: HR 0.50, 95% CI 0.47-0.54; high-risk: HR 0.46, 95% CI 0.40-0.53).Conclusion: A novel risk classification model predicting prognosis and locoregional surgery benefit of CRC patients with distant metastasis was established and validated. This predictive model could be further utilized by physicians and be of great significance for medical practice.

scholarly journals Endoscopic Removal of Gastrointestinal Stromal Tumors in the Stomach: A Single-Center Experience

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Yingjie Guo ◽  
Xue Jing ◽  
Jian Zhang ◽  
Xueli Ding ◽  
Xiaoyu Li ◽  
...  
Keyword(s):  
Tumor Size ◽  
Gastrointestinal Stromal Tumors ◽  
Average Length ◽  
Risk Classification ◽  
Low Risk ◽  
Efficacy And Safety ◽  
Endoscopic Removal ◽  
Moderate Risk ◽  
Stromal Tumors ◽  
Gastric Gists

Background and Aims. Endoscopic removal of GISTs (gastrointestinal stromal tumors) is recently recognized, but less is known about its efficacy and safety. This study is aimed at assessing the feasibility, clinical efficacy, and safety of the endoscopic removal of gastric GISTs. Patients and Methods. Endoscopic removal (ER) of GISTs was performed in 134 patients at our hospital between January 2015 and January 2019. The clinical features, surgical outcomes, complications, pathological diagnosis, and risk classification were evaluated retrospectively. Results. ER was successful in 131 cases (98%), including 58 by ESD (endoscopic submucosal dissection), 43 by ESE (endoscopic submucosal excavation), 25 by EFTR (endoscopic full-thickness resection), and 5 by STER (submucosal tunneling endoscopic resection). In addition, GISTs of two cases were resected using LECS (laparoscopic and luminal endoscopic cooperative surgery) for the extraluminal and intraluminal growth pattern. The average tumor size was 1.89±1.25 cm (range: 0.5-6.0 cm). Of these patients, 26 cases had a large tumor size (range: 2.0-6.0 cm), and endoscopic removal was successful in all of them. During the procedure, endoclips were used to close the perforation in all cases, without conversion to open surgery. The average length of hospital stay was 5.50±2.15 days (range: 3-10 days). In the risk classification, 106 (79.7%) were of a very low risk, 25 (18.8%) of a low risk, and 2 (1.5%) of a moderate risk. The moderate-risk cases were treated with imatinib mesylate after ER. No recurrence or metastasis was observed during the follow-up period of 23±8 months (range: 3-48 months). Conclusions. The endoscopic treatment is feasible, effective, and safe for gastric GISTs, and individualized choice of approaches is recommended for GISTs.

Biological and clinical significance of cytogenetic abnormalities in low-risk and high-risk gastrointestinal stromal tumors

2002 ◽  
Vol 33 (3) ◽  
pp. 316-321 ◽  
Author(s):  
Bastian Gunawan ◽  
Frank Bergmann ◽  
Jörg Höer ◽  
Claus Langer ◽  
Volker Schumpelick ◽  
...  
Keyword(s):  
High Risk ◽  
Clinical Significance ◽  
Gastrointestinal Stromal Tumors ◽  
Low Risk ◽  
Cytogenetic Abnormalities ◽  
Stromal Tumors

scholarly journals Serbian lymphoma study group: Demografic characteristics of 257 patients with follicular lymphoma

2015 ◽  
Vol 72 (6) ◽  
pp. 483-488
Author(s):  
Olivera Simonovic ◽  
Lana Macukanovic-Golubovic ◽  
Bosko Andjelic ◽  
Darko Antic ◽  
Biljana Mihaljevic
Keyword(s):  
High Risk ◽  
Follicular Lymphoma ◽  
International Prognostic Index ◽  
Prognostic Index ◽  
Treatment Decision ◽  
Risk Groups ◽  
Low Risk ◽  
Intermediate Risk ◽  
Prognostic Groups

Background/Aim. Follicular lymphoma (FL) is a B-cell tumor usually with indolent clinical course, yet in some cases the course of the disease can be very aggressive. The aim of the re-search was to determine distribution of patients into prognostic groups based on the International Prognostic Index (IPI) and Folicular Lymphoma International Prognostic Index (FLIPI) criteria, as well as to determine the importance of classifying patients into the prognostic groups, since this could potentially have the influence on selection of the treatment modality. Methods. The retrospective study was performed on 257 patients with follicular lymphoma diagnosed between January 2000 and April 2011. Results. Based on the IPI score, 153 (59.53%) patients had low risk, 57 (22.18%) low intermediate risk, 15 (5.84%) high intermediate risk, 9 (3.50%) high risk, whereas the classification of 23 patients diagnosed with FL remained with unknown risk according to the IPI. Based on the FLIPI prognostic index, 113 (43.97%) patients had low risk, 70 (27.24%) intermediate risk and 51 (19.84%) high risk, whereas the classification of 23 (8.95%) patients remained unknown. On the basis of the FLIPI 2 prognostic index, 48 (18.68%) patients had low risk, 145 (56.42%) intermediate risk and 41 (15.95%) high risk. The classification into prognostic groups for 23 (8.95%) patients remained unknown. According to the IPI, FLIPI and FLIPI 2 there were the patients that required treatment in all the risk groups. Conclusion. The FLIPI and FLIPI 2 effectively identify patients at high risk, thus helping in treatment decision for each single patient.

scholarly journals Comparison of different risk classification systems in patients with high risk gastrointestinal stromal tumors

2018 ◽  
Vol 29 ◽  
pp. v33
Author(s):  
Y. Yin ◽  
Z. Cai ◽  
B. Zhang ◽  
C. Shen
Keyword(s):  
High Risk ◽  
Gastrointestinal Stromal Tumors ◽  
Risk Classification ◽  
Classification Systems ◽  
Stromal Tumors

scholarly journals Histopathological Characteristics of Gastrointestinal Stromal Tumors in a Cohort of Vietnamese Patients

2020 ◽  
Vol 13 ◽  
pp. 2632010X2097240
Author(s):  
Pham Nguyen Cuong ◽  
Nguyen Thanh Xuan ◽  
Tran Xuan Tien ◽  
Pham Nhu Huy ◽  
Pham Nguyen Tuong
Keyword(s):  
High Risk ◽  
Gastrointestinal Stromal Tumors ◽  
Histopathological Examination ◽  
Armed Forces ◽  
Risk Groups ◽  
Low Risk ◽  
Stromal Tumors ◽  
Primary Gist ◽  
Mesenchymal Neoplasms ◽  
The Relationship

Introduction: Gastrointestinal stromal tumors (GISTs) are the most common mesenchymal neoplasms of the gastrointestinal system. Histopathological examination takes an important part in confirming the subtypes of GISTs, to choose appropriate therapeutics for patients. This study aims to explore the histopathological characteristics and evaluate the relationship between malignant risk classification (according to Armed Forces Institute of Pathology criteria) and the histopathological features of GISTs in a cohort of Vietnamese patients. Methods: We reviewed 89 patients with primary GIST who underwent surgery between 2014 and 2019 at Hue Central Hospital, Vietnam. We investigated histopathological characteristics and immunohistochemical findings of all patients. Results: The average age was 55.9 ± 11.9 years. A tumor size of 2-5 cm accounted for 64.1%. The most common position was at the stomach which accounted for 48.5%. Among the subtypes of GIST, spindle cells were seen in 85.9% of patients; epithelial form 10.9%; multi-morphology (3.2%). 97.4% of the samples were positive for CD117, 61.5% of cases were positive for CD34; and no case was positive for Desmin. The rate of high-risk GIST was dominant (46.9%) as compared to the intermediate-risk (28.1%), low-risk (0.3%-2%), and very low-risk groups (4.7%). Conclusions: This study demonstrates the histopathological characteristics of GIST and emphasizes the significant rate of high-risk GIST.

Clinicopathological Features and Clinical Outcomes of Primary Hepatic Gastrointestinal Stromal Tumors: Evaluation of a Pooled Case Series

2020 ◽  
Author(s):  
Xing Xu ◽  
Guoliang Zheng ◽  
Zhichao Zheng
Keyword(s):  
High Risk ◽  
Mitotic Index ◽  
Tumor Size ◽  
Gastrointestinal Stromal Tumors ◽  
Multivariable Analysis ◽  
Case Series ◽  
Risk Classification ◽  
Clinicopathological Features ◽  
Stromal Tumors ◽  
Gastric Gists

Abstract Background: Due to the extremely rare incidence, data of clinicopathological features and prognosis of primary hepatic gastrointestinal stromal tumors (GISTs) is limited. Methods: 36 cases of hepatic GISTs were from the literature, PUBMED, EMBASE, China National Knowledge Infrastructure and WANFANG DATA, and 1 case came from our center. Clinicopathological features and outcomes were analyzed between 37 hepatic GISTs and 254 gastric GISTs from our center. Results: A majority of hepatic GISTs exceeded 5 cm (83.7%), displayed mixed density (69.4%) and spindle morphology (74.2%) and were classified as high risk (91.4%). Larger tumors of hepatic GISTs were likely to display mixed lesion and tumors with mixed lesion were prone to be classified as high risk. In comparisons to gastric GISTs, hepatic GISTs differed from gastric GISTs in tumor size, main symptoms, histologic type, mitotic index, CD34 expression, NIH risk classification. In patients with hepatic GISTs, 5-year DFS and DSS rates were 19.4% and 53.7%, which were worse than that of gastric GISTs (P＜ 0.001), especially for those with tumor size exceeding 5 cm or mitotic indices exceeding 5/50 HPF (P < 0.001). Multivariable analysis showed location and NIH risk classification were independent prognostic factors for DFS in patients with GISTs, and size and location were significantly associated with DSS. Conclusions: Hepatic GISTs distinguished from gastric GISTs in respect to clinicopathological features and outcomes. Mitotic index exceeding 5/50 HPF or tumor size exceeding 5 cm may be important factor to distinguish hepatic GISTs from gastric GISTs in DFS and DSS.

MRI Texture‐Based Models for Predicting Mitotic Index and Risk Classification of Gastrointestinal Stromal Tumors

2020 ◽  
Author(s):  
Linsha Yang ◽  
Tao Zheng ◽  
Yanchao Dong ◽  
Zhanqiu Wang ◽  
Defeng Liu ◽  
...  
Keyword(s):  
Mitotic Index ◽  
Gastrointestinal Stromal Tumors ◽  
Risk Classification ◽  
Stromal Tumors

scholarly journals Gastrointestinal stromal tumor of rectum

2019 ◽  
Vol 19 (2) ◽  
pp. 85-88
Author(s):  
Md Rayhanur Rahman ◽  
Md Shahadot Hossain Sheikh ◽  
Ismat Jahan Lima ◽  
Most Bilkis Fatema ◽  
Md Ariful Alam ◽  
...  
Keyword(s):  
Gastrointestinal Tract ◽  
High Risk ◽  
Gastrointestinal Stromal Tumor ◽  
Surgical Resection ◽  
Gastrointestinal Stromal Tumors ◽  
Stromal Tumor ◽  
Intermediate Risk ◽  
Stromal Tumors ◽  
Rectal Gist ◽  
Complete Surgical Resection

Although gastrointestinal stromal tumors (GISTs) frequently occur in the gastrointestinal tract, they are relatively rare in the rectum. Biopsy of the lesion and immunohistochemistry (IHC) confirm the diagnosis. Complete surgical resection is the principal curative procedure. In combination with surgery, immunotherapy with Imatinib shows cure in intermediate risk and improvement in high risk rectal GIST. We report a case of a 45-yearold female who  presented with constipation and generalized weakness, ultimately diagnosed to have rectal GIST. Journal of Surgical Sciences (2015) Vol. 19 (2) : 85-88

Sign in / Sign up

Export Citation Format

Share Document