A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interest
Abstract Background Prostate cancer (PCa) is one of the most common cancers in men worldwide, and its timely diagnosis and treatment are becoming increasingly important. MRI is in increasing use to diagnose cancer and to distinguish between non-clinically significant and clinically significant PCa,...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-12-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-023-01167-3 |
| _version_ | 1797397661809115136 |
|---|---|
| author | Haoming Zhuang Aritrick Chatterjee Xiaobing Fan Shouliang Qi Wei Qian Dianning He |
| author_facet | Haoming Zhuang Aritrick Chatterjee Xiaobing Fan Shouliang Qi Wei Qian Dianning He |
| author_sort | Haoming Zhuang |
| collection | DOAJ |
| description | Abstract Background Prostate cancer (PCa) is one of the most common cancers in men worldwide, and its timely diagnosis and treatment are becoming increasingly important. MRI is in increasing use to diagnose cancer and to distinguish between non-clinically significant and clinically significant PCa, leading to more precise diagnosis and treatment. The purpose of this study is to present a radiomics-based method for determining the Gleason score (GS) for PCa using tumour heterogeneity on multiparametric MRI (mp-MRI). Methods Twenty-six patients with biopsy-proven PCa were included in this study. The quantitative T2 values, apparent diffusion coefficient (ADC) and signal enhancement rates (α) were calculated using multi-echo T2 images, diffusion-weighted imaging (DWI) and dynamic contrast-enhanced MRI (DCE-MRI), for the annotated region of interests (ROI). After texture feature analysis, ROI range expansion and feature filtering was performed. Then obtained data were put into support vector machine (SVM), K-Nearest Neighbor (KNN) and other classifiers for binary classification. Results The highest classification accuracy was 73.96% for distinguishing between clinically significant (Gleason 3 + 4 and above) and non-significant cancers (Gleason 3 + 3) and 83.72% for distinguishing between Gleason 3 + 4 from Gleason 4 + 3 and above, which was achieved using initial ROIs drawn by the radiologists. The accuracy improved when using expanded ROIs to 80.67% using SVM and 88.42% using Bayesian classification for distinguishing between clinically significant and non-significant cancers and Gleason 3 + 4 from Gleason 4 + 3 and above, respectively. Conclusions Our results indicate the research significance and value of this study for determining the GS for prostate cancer using the expansion of the ROI region. |
| first_indexed | 2024-03-09T01:13:24Z |
| format | Article |
| id | doaj.art-1d22c0586b6844edb89badcc97a075cb |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-03-09T01:13:24Z |
| publishDate | 2023-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-1d22c0586b6844edb89badcc97a075cb2023-12-10T12:36:02ZengBMCBMC Medical Imaging1471-23422023-12-0123111110.1186/s12880-023-01167-3A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interestHaoming Zhuang0Aritrick Chatterjee1Xiaobing Fan2Shouliang Qi3Wei Qian4Dianning He5College of Medicine and Biological Information Engineering, Northeastern UniversityDepartment of Radiology, University of ChicagoDepartment of Radiology, University of ChicagoCollege of Medicine and Biological Information Engineering, Northeastern UniversityCollege of Medicine and Biological Information Engineering, Northeastern UniversityCollege of Medicine and Biological Information Engineering, Northeastern UniversityAbstract Background Prostate cancer (PCa) is one of the most common cancers in men worldwide, and its timely diagnosis and treatment are becoming increasingly important. MRI is in increasing use to diagnose cancer and to distinguish between non-clinically significant and clinically significant PCa, leading to more precise diagnosis and treatment. The purpose of this study is to present a radiomics-based method for determining the Gleason score (GS) for PCa using tumour heterogeneity on multiparametric MRI (mp-MRI). Methods Twenty-six patients with biopsy-proven PCa were included in this study. The quantitative T2 values, apparent diffusion coefficient (ADC) and signal enhancement rates (α) were calculated using multi-echo T2 images, diffusion-weighted imaging (DWI) and dynamic contrast-enhanced MRI (DCE-MRI), for the annotated region of interests (ROI). After texture feature analysis, ROI range expansion and feature filtering was performed. Then obtained data were put into support vector machine (SVM), K-Nearest Neighbor (KNN) and other classifiers for binary classification. Results The highest classification accuracy was 73.96% for distinguishing between clinically significant (Gleason 3 + 4 and above) and non-significant cancers (Gleason 3 + 3) and 83.72% for distinguishing between Gleason 3 + 4 from Gleason 4 + 3 and above, which was achieved using initial ROIs drawn by the radiologists. The accuracy improved when using expanded ROIs to 80.67% using SVM and 88.42% using Bayesian classification for distinguishing between clinically significant and non-significant cancers and Gleason 3 + 4 from Gleason 4 + 3 and above, respectively. Conclusions Our results indicate the research significance and value of this study for determining the GS for prostate cancer using the expansion of the ROI region.https://doi.org/10.1186/s12880-023-01167-3Multiparametric MRIGleason scoreTexture featureMachine learningProstate cancer |
| spellingShingle | Haoming Zhuang Aritrick Chatterjee Xiaobing Fan Shouliang Qi Wei Qian Dianning He A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interest BMC Medical Imaging Multiparametric MRI Gleason score Texture feature Machine learning Prostate cancer |
| title | A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interest |
| title_full | A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interest |
| title_fullStr | A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interest |
| title_full_unstemmed | A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interest |
| title_short | A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interest |
| title_sort | radiomics based method for prediction of prostate cancer gleason score using enlarged region of interest |
| topic | Multiparametric MRI Gleason score Texture feature Machine learning Prostate cancer |
| url | https://doi.org/10.1186/s12880-023-01167-3 |
| work_keys_str_mv | AT haomingzhuang aradiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT aritrickchatterjee aradiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT xiaobingfan aradiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT shouliangqi aradiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT weiqian aradiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT dianninghe aradiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT haomingzhuang radiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT aritrickchatterjee radiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT xiaobingfan radiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT shouliangqi radiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT weiqian radiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest AT dianninghe radiomicsbasedmethodforpredictionofprostatecancergleasonscoreusingenlargedregionofinterest |