Proficiency evaluation of shape and WPT radiomics based on machine learning for CT lung cancer prognosis
Abstract Background Lung cancer is a fatal disease which has high occurrence and mortality rates, worldwide. Computed tomography imaging is being widely used by clinicians for detection of lung cancer. Radiomics extracted from medical images together with machine learning platform has enabled automa...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-03-01
|
| Series: | The Egyptian Journal of Radiology and Nuclear Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s43055-024-01223-0 |
| _version_ | 1797275383302717440 |
|---|---|
| author | Arooj Nissar A. H. Mir |
| author_facet | Arooj Nissar A. H. Mir |
| author_sort | Arooj Nissar |
| collection | DOAJ |
| description | Abstract Background Lung cancer is a fatal disease which has high occurrence and mortality rates, worldwide. Computed tomography imaging is being widely used by clinicians for detection of lung cancer. Radiomics extracted from medical images together with machine learning platform has enabled automated lung cancer diagnosis. Therefore, this study is proposed with the aim to efficiently apply radiomics and ML techniques to classify pulmonary nodules in CT images. Lung Image Data Consortium is utilized which contains 1018 CT lung cancer cases. Results Radiomics are extracted using Shape, Gray Level Co-occurrence Method, Gray Level Difference Method, and Gray Level Run Length Matrix along with Wavelet Packet Transform. To select a relevant set of features two techniques, Analysis of variance and Chi-square test, are applied. The classification of nodule into benign or malignant is evaluated by using state-of-art models: Support vector machine, Decision Trees, Ensemble Trees (BOCET, BACET, RUSBOCET), Ensemble Subspace KNN and Ensemble Subspace Discriminant. The results show that, BACET gives best AUROC (92.9%), MGSVM gives best accuracy (90.4%), FGSVM yields the best sensitivity (97.8%), MGSVM gives best precision (94.1%) and RUSBOCET gives best specificity (84%). Conclusions The results show that the proposed methodology can be successfully used for the classification of pulmonary nodules based on CT images. The outcome thus can help clinicians to reach better decision, treatments and early diagnosis. |
| first_indexed | 2024-03-07T15:13:34Z |
| format | Article |
| id | doaj.art-ef9172f4bb004760a65daf6b1cc90594 |
| institution | Directory Open Access Journal |
| issn | 2090-4762 |
| language | English |
| last_indexed | 2024-03-07T15:13:34Z |
| publishDate | 2024-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | The Egyptian Journal of Radiology and Nuclear Medicine |
| spelling | doaj.art-ef9172f4bb004760a65daf6b1cc905942024-03-05T18:03:48ZengSpringerOpenThe Egyptian Journal of Radiology and Nuclear Medicine2090-47622024-03-0155111310.1186/s43055-024-01223-0Proficiency evaluation of shape and WPT radiomics based on machine learning for CT lung cancer prognosisArooj Nissar0A. H. Mir1Department of Information Technology, National Institute of Technology SrinagarDepartment of Electronics and Communication, National Institute of Technology SrinagarAbstract Background Lung cancer is a fatal disease which has high occurrence and mortality rates, worldwide. Computed tomography imaging is being widely used by clinicians for detection of lung cancer. Radiomics extracted from medical images together with machine learning platform has enabled automated lung cancer diagnosis. Therefore, this study is proposed with the aim to efficiently apply radiomics and ML techniques to classify pulmonary nodules in CT images. Lung Image Data Consortium is utilized which contains 1018 CT lung cancer cases. Results Radiomics are extracted using Shape, Gray Level Co-occurrence Method, Gray Level Difference Method, and Gray Level Run Length Matrix along with Wavelet Packet Transform. To select a relevant set of features two techniques, Analysis of variance and Chi-square test, are applied. The classification of nodule into benign or malignant is evaluated by using state-of-art models: Support vector machine, Decision Trees, Ensemble Trees (BOCET, BACET, RUSBOCET), Ensemble Subspace KNN and Ensemble Subspace Discriminant. The results show that, BACET gives best AUROC (92.9%), MGSVM gives best accuracy (90.4%), FGSVM yields the best sensitivity (97.8%), MGSVM gives best precision (94.1%) and RUSBOCET gives best specificity (84%). Conclusions The results show that the proposed methodology can be successfully used for the classification of pulmonary nodules based on CT images. The outcome thus can help clinicians to reach better decision, treatments and early diagnosis.https://doi.org/10.1186/s43055-024-01223-0Lung cancerLIDCRadiomicsWPTSVMFeature selection |
| spellingShingle | Arooj Nissar A. H. Mir Proficiency evaluation of shape and WPT radiomics based on machine learning for CT lung cancer prognosis The Egyptian Journal of Radiology and Nuclear Medicine Lung cancer LIDC Radiomics WPT SVM Feature selection |
| title | Proficiency evaluation of shape and WPT radiomics based on machine learning for CT lung cancer prognosis |
| title_full | Proficiency evaluation of shape and WPT radiomics based on machine learning for CT lung cancer prognosis |
| title_fullStr | Proficiency evaluation of shape and WPT radiomics based on machine learning for CT lung cancer prognosis |
| title_full_unstemmed | Proficiency evaluation of shape and WPT radiomics based on machine learning for CT lung cancer prognosis |
| title_short | Proficiency evaluation of shape and WPT radiomics based on machine learning for CT lung cancer prognosis |
| title_sort | proficiency evaluation of shape and wpt radiomics based on machine learning for ct lung cancer prognosis |
| topic | Lung cancer LIDC Radiomics WPT SVM Feature selection |
| url | https://doi.org/10.1186/s43055-024-01223-0 |
| work_keys_str_mv | AT aroojnissar proficiencyevaluationofshapeandwptradiomicsbasedonmachinelearningforctlungcancerprognosis AT ahmir proficiencyevaluationofshapeandwptradiomicsbasedonmachinelearningforctlungcancerprognosis |