Identification and validation of radiomic features from computed tomography for preoperative classification of neuroblastic tumors in children
Abstract Background To identify radiomic features that can predict the pathological type of neuroblastic tumor in children. Methods Data on neuroblastic tumors in 104 children were retrospectively analyzed. There were 14 cases of ganglioneuroma, 24 cases of ganglioneuroblastoma, and 65 cases of neur...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-05-01
|
| Series: | BMC Pediatrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12887-023-04057-3 |
| _version_ | 1827939698101714944 |
|---|---|
| author | Lian Zhao Liting Shi Shun-gen Huang Tian-na Cai Wan-liang Guo Xin Gao Jian Wang |
| author_facet | Lian Zhao Liting Shi Shun-gen Huang Tian-na Cai Wan-liang Guo Xin Gao Jian Wang |
| author_sort | Lian Zhao |
| collection | DOAJ |
| description | Abstract Background To identify radiomic features that can predict the pathological type of neuroblastic tumor in children. Methods Data on neuroblastic tumors in 104 children were retrospectively analyzed. There were 14 cases of ganglioneuroma, 24 cases of ganglioneuroblastoma, and 65 cases of neuroblastoma. Stratified sampling was used to randomly allocate the cases into the training and validation sets in a ratio of 3:1. The maximum relevance–minimum redundancy algorithm was used to identify the top 10 of two clinical features and 851 radiomic features in portal venous–phase contrast-enhanced computed tomography images. Least absolute shrinkage and selection operator regression was used to classify tumors in two binary steps: first as ganglioneuroma compared to the other two types, then as ganglioneuroblastoma compared to neuroblastoma. Results Based on 10 clinical-radiomic features, the classifier identified ganglioneuroma compared to the other two tumor types in the validation dataset with sensitivity of 100.0%, specificity of 81.8%, and an area under the receiver operating characteristic curve (AUC) of 0.875. The classifier identified ganglioneuroblastoma versus neuroblastoma with a sensitivity of 83.3%, a specificity of 87.5%, and an AUC of 0.854. The overall accuracy of the classifier across all three types of tumors was 80.8%. Conclusion Radiomic features can help predict the pathological type of neuroblastic tumors in children. |
| first_indexed | 2024-03-13T08:58:17Z |
| format | Article |
| id | doaj.art-432c13eb57da4cbab8a89e991a252d10 |
| institution | Directory Open Access Journal |
| issn | 1471-2431 |
| language | English |
| last_indexed | 2024-03-13T08:58:17Z |
| publishDate | 2023-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Pediatrics |
| spelling | doaj.art-432c13eb57da4cbab8a89e991a252d102023-05-28T11:27:49ZengBMCBMC Pediatrics1471-24312023-05-012311910.1186/s12887-023-04057-3Identification and validation of radiomic features from computed tomography for preoperative classification of neuroblastic tumors in childrenLian Zhao0Liting Shi1Shun-gen Huang2Tian-na Cai3Wan-liang Guo4Xin Gao5Jian Wang6Radiology Department, Children’s Hospital of Soochow UniversityDivision of Life Sciences and Medicine, School of Biomedical Engineering (Suzhou), University of Science and Technology of ChinaPediatric Surgery Department, Children’s Hospital of Soochow UniversityRadiology Department, Children’s Hospital of Soochow UniversityRadiology Department, Children’s Hospital of Soochow UniversitySuzhou Institute of Biomedical Engineering and Technology, Chinese Academy of SciencesPediatric Surgery Department, Children’s Hospital of Soochow UniversityAbstract Background To identify radiomic features that can predict the pathological type of neuroblastic tumor in children. Methods Data on neuroblastic tumors in 104 children were retrospectively analyzed. There were 14 cases of ganglioneuroma, 24 cases of ganglioneuroblastoma, and 65 cases of neuroblastoma. Stratified sampling was used to randomly allocate the cases into the training and validation sets in a ratio of 3:1. The maximum relevance–minimum redundancy algorithm was used to identify the top 10 of two clinical features and 851 radiomic features in portal venous–phase contrast-enhanced computed tomography images. Least absolute shrinkage and selection operator regression was used to classify tumors in two binary steps: first as ganglioneuroma compared to the other two types, then as ganglioneuroblastoma compared to neuroblastoma. Results Based on 10 clinical-radiomic features, the classifier identified ganglioneuroma compared to the other two tumor types in the validation dataset with sensitivity of 100.0%, specificity of 81.8%, and an area under the receiver operating characteristic curve (AUC) of 0.875. The classifier identified ganglioneuroblastoma versus neuroblastoma with a sensitivity of 83.3%, a specificity of 87.5%, and an AUC of 0.854. The overall accuracy of the classifier across all three types of tumors was 80.8%. Conclusion Radiomic features can help predict the pathological type of neuroblastic tumors in children.https://doi.org/10.1186/s12887-023-04057-3Neuroblastic tumorsRadiomicsComputed tomographyGanglioneuromaGanglioneuroblastomaNeuroblastoma |
| spellingShingle | Lian Zhao Liting Shi Shun-gen Huang Tian-na Cai Wan-liang Guo Xin Gao Jian Wang Identification and validation of radiomic features from computed tomography for preoperative classification of neuroblastic tumors in children BMC Pediatrics Neuroblastic tumors Radiomics Computed tomography Ganglioneuroma Ganglioneuroblastoma Neuroblastoma |
| title | Identification and validation of radiomic features from computed tomography for preoperative classification of neuroblastic tumors in children |
| title_full | Identification and validation of radiomic features from computed tomography for preoperative classification of neuroblastic tumors in children |
| title_fullStr | Identification and validation of radiomic features from computed tomography for preoperative classification of neuroblastic tumors in children |
| title_full_unstemmed | Identification and validation of radiomic features from computed tomography for preoperative classification of neuroblastic tumors in children |
| title_short | Identification and validation of radiomic features from computed tomography for preoperative classification of neuroblastic tumors in children |
| title_sort | identification and validation of radiomic features from computed tomography for preoperative classification of neuroblastic tumors in children |
| topic | Neuroblastic tumors Radiomics Computed tomography Ganglioneuroma Ganglioneuroblastoma Neuroblastoma |
| url | https://doi.org/10.1186/s12887-023-04057-3 |
| work_keys_str_mv | AT lianzhao identificationandvalidationofradiomicfeaturesfromcomputedtomographyforpreoperativeclassificationofneuroblastictumorsinchildren AT litingshi identificationandvalidationofradiomicfeaturesfromcomputedtomographyforpreoperativeclassificationofneuroblastictumorsinchildren AT shungenhuang identificationandvalidationofradiomicfeaturesfromcomputedtomographyforpreoperativeclassificationofneuroblastictumorsinchildren AT tiannacai identificationandvalidationofradiomicfeaturesfromcomputedtomographyforpreoperativeclassificationofneuroblastictumorsinchildren AT wanliangguo identificationandvalidationofradiomicfeaturesfromcomputedtomographyforpreoperativeclassificationofneuroblastictumorsinchildren AT xingao identificationandvalidationofradiomicfeaturesfromcomputedtomographyforpreoperativeclassificationofneuroblastictumorsinchildren AT jianwang identificationandvalidationofradiomicfeaturesfromcomputedtomographyforpreoperativeclassificationofneuroblastictumorsinchildren |