Possibility of Using Conventional Computed Tomography Features and Histogram Texture Analysis Parameters as Imaging Biomarkers for Preoperative Prediction of High-Risk Gastrointestinal Stromal Tumors of the Stomach
Background: The objective of this study is to determine the morphological computed tomography features of the tumor and texture analysis parameters, which may be a useful diagnostic tool for the preoperative prediction of high-risk gastrointestinal stromal tumors (HR GISTs). Methods: This is a prosp...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/15/24/5840 |
| _version_ | 1797381662946885632 |
|---|---|
| author | Milica Mitrovic Jovanovic Aleksandra Djuric Stefanovic Dimitrije Sarac Jelena Kovac Aleksandra Jankovic Dusan J. Saponjski Boris Tadic Milena Kostadinovic Milan Veselinovic Vladimir Sljukic Ognjan Skrobic Marjan Micev Dragan Masulovic Predrag Pesko Keramatollah Ebrahimi |
| author_facet | Milica Mitrovic Jovanovic Aleksandra Djuric Stefanovic Dimitrije Sarac Jelena Kovac Aleksandra Jankovic Dusan J. Saponjski Boris Tadic Milena Kostadinovic Milan Veselinovic Vladimir Sljukic Ognjan Skrobic Marjan Micev Dragan Masulovic Predrag Pesko Keramatollah Ebrahimi |
| author_sort | Milica Mitrovic Jovanovic |
| collection | DOAJ |
| description | Background: The objective of this study is to determine the morphological computed tomography features of the tumor and texture analysis parameters, which may be a useful diagnostic tool for the preoperative prediction of high-risk gastrointestinal stromal tumors (HR GISTs). Methods: This is a prospective cohort study that was carried out in the period from 2019 to 2022. The study included 79 patients who underwent CT examination, texture analysis, surgical resection of a lesion that was suspicious for GIST as well as pathohistological and immunohistochemical analysis. Results: Textural analysis pointed out min norm (<i>p</i> = 0.032) as a histogram parameter that significantly differed between HR and LR GISTs, while min norm (<i>p</i> = 0.007), skewness (<i>p</i> = 0.035) and kurtosis (<i>p</i> = 0.003) showed significant differences between high-grade and low-grade tumors. Univariate regression analysis identified tumor diameter, margin appearance, growth pattern, lesion shape, structure, mucosal continuity, enlarged peri- and intra-tumoral feeding or draining vessel (EFDV) and max norm as significant predictive factors for HR GISTs. Interrupted mucosa (<i>p</i> < 0.001) and presence of EFDV (<i>p</i> < 0.001) were obtained by multivariate regression analysis as independent predictive factors of high-risk GISTs with an AUC of 0.878 (CI: 0.797–0.959), sensitivity of 94%, specificity of 77% and accuracy of 88%. Conclusion: This result shows that morphological CT features of GIST are of great importance in the prediction of non-invasive preoperative metastatic risk. The incorporation of texture analysis into basic imaging protocols may further improve the preoperative assessment of risk stratification. |
| first_indexed | 2024-03-08T20:55:41Z |
| format | Article |
| id | doaj.art-544123083b57416aa4652c4839ea592f |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-08T20:55:41Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-544123083b57416aa4652c4839ea592f2023-12-22T13:59:02ZengMDPI AGCancers2072-66942023-12-011524584010.3390/cancers15245840Possibility of Using Conventional Computed Tomography Features and Histogram Texture Analysis Parameters as Imaging Biomarkers for Preoperative Prediction of High-Risk Gastrointestinal Stromal Tumors of the StomachMilica Mitrovic Jovanovic0Aleksandra Djuric Stefanovic1Dimitrije Sarac2Jelena Kovac3Aleksandra Jankovic4Dusan J. Saponjski5Boris Tadic6Milena Kostadinovic7Milan Veselinovic8Vladimir Sljukic9Ognjan Skrobic10Marjan Micev11Dragan Masulovic12Predrag Pesko13Keramatollah Ebrahimi14Center for Radiology and Magnetic Resonance Imaging, University Clinical Centre of Serbia, Pasterova No. 2, 11000 Belgrade, SerbiaCenter for Radiology and Magnetic Resonance Imaging, University Clinical Centre of Serbia, Pasterova No. 2, 11000 Belgrade, SerbiaCenter for Radiology and Magnetic Resonance Imaging, University Clinical Centre of Serbia, Pasterova No. 2, 11000 Belgrade, SerbiaCenter for Radiology and Magnetic Resonance Imaging, University Clinical Centre of Serbia, Pasterova No. 2, 11000 Belgrade, SerbiaCenter for Radiology and Magnetic Resonance Imaging, University Clinical Centre of Serbia, Pasterova No. 2, 11000 Belgrade, SerbiaCenter for Radiology and Magnetic Resonance Imaging, University Clinical Centre of Serbia, Pasterova No. 2, 11000 Belgrade, SerbiaDepartment for HBP Surgery, Clinic for Digestive Surgery, University Clinical Centre of Serbia, Koste Todorovica Street, No. 6, 11000 Belgrade, SerbiaCenter for Physical Medicine and Rehabilitation, University Clinical Centre of Serbia, Pasterova Street, No. 2, 11000 Beograd, SerbiaDepartment for Surgery, Faculty of Medicine, University of Belgrade, Dr Subotica No. 8, 11000 Belgrade, SerbiaDepartment for Surgery, Faculty of Medicine, University of Belgrade, Dr Subotica No. 8, 11000 Belgrade, SerbiaDepartment for Surgery, Faculty of Medicine, University of Belgrade, Dr Subotica No. 8, 11000 Belgrade, SerbiaDepartment for Pathology, Clinic for Digestive Surgery, University Clinical Centre of Serbia, Koste Todorovica Street, No. 6, 11000 Belgrade, SerbiaCenter for Radiology and Magnetic Resonance Imaging, University Clinical Centre of Serbia, Pasterova No. 2, 11000 Belgrade, SerbiaDepartment for Surgery, Faculty of Medicine, University of Belgrade, Dr Subotica No. 8, 11000 Belgrade, SerbiaDepartment for Surgery, Faculty of Medicine, University of Belgrade, Dr Subotica No. 8, 11000 Belgrade, SerbiaBackground: The objective of this study is to determine the morphological computed tomography features of the tumor and texture analysis parameters, which may be a useful diagnostic tool for the preoperative prediction of high-risk gastrointestinal stromal tumors (HR GISTs). Methods: This is a prospective cohort study that was carried out in the period from 2019 to 2022. The study included 79 patients who underwent CT examination, texture analysis, surgical resection of a lesion that was suspicious for GIST as well as pathohistological and immunohistochemical analysis. Results: Textural analysis pointed out min norm (<i>p</i> = 0.032) as a histogram parameter that significantly differed between HR and LR GISTs, while min norm (<i>p</i> = 0.007), skewness (<i>p</i> = 0.035) and kurtosis (<i>p</i> = 0.003) showed significant differences between high-grade and low-grade tumors. Univariate regression analysis identified tumor diameter, margin appearance, growth pattern, lesion shape, structure, mucosal continuity, enlarged peri- and intra-tumoral feeding or draining vessel (EFDV) and max norm as significant predictive factors for HR GISTs. Interrupted mucosa (<i>p</i> < 0.001) and presence of EFDV (<i>p</i> < 0.001) were obtained by multivariate regression analysis as independent predictive factors of high-risk GISTs with an AUC of 0.878 (CI: 0.797–0.959), sensitivity of 94%, specificity of 77% and accuracy of 88%. Conclusion: This result shows that morphological CT features of GIST are of great importance in the prediction of non-invasive preoperative metastatic risk. The incorporation of texture analysis into basic imaging protocols may further improve the preoperative assessment of risk stratification.https://www.mdpi.com/2072-6694/15/24/5840gastrointestinal stromal tumor (GIST)multidetector computed tomography (MDCT)texture analysismetastatic risk |
| spellingShingle | Milica Mitrovic Jovanovic Aleksandra Djuric Stefanovic Dimitrije Sarac Jelena Kovac Aleksandra Jankovic Dusan J. Saponjski Boris Tadic Milena Kostadinovic Milan Veselinovic Vladimir Sljukic Ognjan Skrobic Marjan Micev Dragan Masulovic Predrag Pesko Keramatollah Ebrahimi Possibility of Using Conventional Computed Tomography Features and Histogram Texture Analysis Parameters as Imaging Biomarkers for Preoperative Prediction of High-Risk Gastrointestinal Stromal Tumors of the Stomach Cancers gastrointestinal stromal tumor (GIST) multidetector computed tomography (MDCT) texture analysis metastatic risk |
| title | Possibility of Using Conventional Computed Tomography Features and Histogram Texture Analysis Parameters as Imaging Biomarkers for Preoperative Prediction of High-Risk Gastrointestinal Stromal Tumors of the Stomach |
| title_full | Possibility of Using Conventional Computed Tomography Features and Histogram Texture Analysis Parameters as Imaging Biomarkers for Preoperative Prediction of High-Risk Gastrointestinal Stromal Tumors of the Stomach |
| title_fullStr | Possibility of Using Conventional Computed Tomography Features and Histogram Texture Analysis Parameters as Imaging Biomarkers for Preoperative Prediction of High-Risk Gastrointestinal Stromal Tumors of the Stomach |
| title_full_unstemmed | Possibility of Using Conventional Computed Tomography Features and Histogram Texture Analysis Parameters as Imaging Biomarkers for Preoperative Prediction of High-Risk Gastrointestinal Stromal Tumors of the Stomach |
| title_short | Possibility of Using Conventional Computed Tomography Features and Histogram Texture Analysis Parameters as Imaging Biomarkers for Preoperative Prediction of High-Risk Gastrointestinal Stromal Tumors of the Stomach |
| title_sort | possibility of using conventional computed tomography features and histogram texture analysis parameters as imaging biomarkers for preoperative prediction of high risk gastrointestinal stromal tumors of the stomach |
| topic | gastrointestinal stromal tumor (GIST) multidetector computed tomography (MDCT) texture analysis metastatic risk |
| url | https://www.mdpi.com/2072-6694/15/24/5840 |
| work_keys_str_mv | AT milicamitrovicjovanovic possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT aleksandradjuricstefanovic possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT dimitrijesarac possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT jelenakovac possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT aleksandrajankovic possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT dusanjsaponjski possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT boristadic possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT milenakostadinovic possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT milanveselinovic possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT vladimirsljukic possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT ognjanskrobic possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT marjanmicev possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT draganmasulovic possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT predragpesko possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach AT keramatollahebrahimi possibilityofusingconventionalcomputedtomographyfeaturesandhistogramtextureanalysisparametersasimagingbiomarkersforpreoperativepredictionofhighriskgastrointestinalstromaltumorsofthestomach |