Dataset Information

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

ABSTRACT:

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.

SUBMITTER: Yang J

PROVIDER: S-EPMC7909867 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Yang Jiejin J Chen Zeyang Z Liu Weipeng W Wang Xiangpeng X Ma Shuai S Jin Feifei F Wang Xiaoying X

Korean journal of radiology 20201021 3

<h4>Objective</h4>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.<h4>Materials and methods</h4>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 ...[more]

PMID: 33169545

Similar Datasets

Project description:This work seeks the development and validation of radiomics signatures from nonenhanced computed tomography (CT, NE-RS) to preoperatively predict the malignancy degree of gastrointestinal stromal tumors (GISTs) and the comparison of these signatures with those from contrast-enhanced CT. A dataset for 370 GIST patients was collected from four centers. This dataset was divided into cohorts for training, as well as internal and external validation. The minimum-redundancy maximum-relevance algorithm and the least absolute shrinkage and selection operator (LASSO) algorithm were used to filter unstable features. (a) NE-RS and radiomics signature from contrast-enhanced CT (CE-RS) were built and compared for the prediction of malignancy potential of GIST based on the area under the receiver operating characteristic curve (AUC). (b) The radiomics model was also developed with both the tumor size and NE-RS. The AUC values were comparable between NE-RS and CE-RS in the training (.965 vs .936; P = .251), internal validation (.967 vs .960; P = .801), and external validation (.941 vs .899; P = .173) cohorts in diagnosis of high malignancy potential of GISTs. We next focused on the NE-RS. With 0.185 selected as the cutoff of NE-RS for diagnosis of the malignancy potential of GISTs, accuracy, sensitivity, and specificity for diagnosis high-malignancy potential GIST was 90.0%, 88.2%, and 92.3%, respectively, in the training cohort. For the internal validation set, the corresponding metrics are 89.1%, 94.9%, and 80.0%, respectively. The corresponding metrics for the external cohort are 84.6%, 76.1%, and 91.0%, respectively. Compared with only NE-RS, the radiomics model increased the sensitivity in the diagnosis of GIST with high-malignancy potential by 5.9% (P = .025), 2.5% (P = .317), 10.5% (P = .008) for the training set, internal validation set, and external validation set, respectively. The NE-RS had comparable prediction efficiency in the diagnosis of high-risk GISTs to CE-RS. The NE-RS and radiomics model both had excellent accuracy in predicting malignancy potential of GISTs.

Project description:Gastrointestinal stromal tumors (GIST) are rare mesenchymal smooth muscle sarcomas that can arise anywhere within the gastrointestinal tract. Sporadic mutations within the tyrosine kinase receptors of the interstitial cells of Cajal have been identified as the key molecular step in GIST carcinogenesis. Although many patients are asymptomatic, the most common associated symptoms include: abdominal pain, dyspepsia, gastric outlet obstruction, and anorexia. Rarely, GIST can perforate causing life-threatening hemoperitoneum. Most are ultimately diagnosed on cross-sectional imaging studies (i.e., computed tomography and/or magnetic resonance imaging in combination with upper endoscopy. Endoscopic ultrasonographic localization of these tumors within the smooth muscle layer and acquisition of neoplastic spindle cells harboring mutations in the c-KIT gene is pathognomonic. Curative treatment requires a complete gross resection of the tumor. Both open and minimally invasive operations have been shown to reduce recurrence rates and improve long-term survival. While there is considerable debate over whether GIST can be benign neoplasms, we believe that all GIST have malignant potential, but vary in their propensity to recur after resection and metastasize to distant organ sites. Prognostic factors include location, size (i.e., > 5 cm), grade (> 5-10 mitoses per 50 high power fields and specific mutational events that are still being defined. Adjuvant therapy with tyrosine kinase inhibitors, such as imatinib mesylate, has been shown to reduce the risk of recurrence after one year of therapy. Treatment of locally-advanced or borderline resectable gastric GIST with neoadjuvant imatinib has been shown to induce regression in a minority of patients and stabilization in the majority of cases. This treatment strategy potentially reduces the need for more extensive surgical resections and increases the number of patients eligible for curative therapy. The modern surgical treatment of gastric GIST combines the novel use of targeted therapy and aggressive minimally invasive surgical procedures to provide effective treatment for this lethal, but rare gastrointestinal malignancy.

Dataset Information

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

Objective

Materials and methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets