Multi-Height Extraction of Clinical Parameters Improves Classification of Craniosynostosis
Introduction: 3D surface scan-based diagnosis of craniosynostosis is a promising radiation-free alternative to traditional diagnosis using computed tomography. The cranial index (CI) and the cranial vault asymmetry index (CVAI) are well-established clinical parameters that are widely used. However,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2023-09-01
|
| Series: | Current Directions in Biomedical Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/cdbme-2023-1050 |
| _version_ | 1827780165852200960 |
|---|---|
| author | Becker Anna Maria Schaufelberger Matthias Kühle Reinald Peter Freudlsperger Christian Nahm Werner |
| author_facet | Becker Anna Maria Schaufelberger Matthias Kühle Reinald Peter Freudlsperger Christian Nahm Werner |
| author_sort | Becker Anna Maria |
| collection | DOAJ |
| description | Introduction: 3D surface scan-based diagnosis of craniosynostosis is a promising radiation-free alternative to traditional diagnosis using computed tomography. The cranial index (CI) and the cranial vault asymmetry index (CVAI) are well-established clinical parameters that are widely used. However, they also have the benefit of being easily adaptable for automatic diagnosis without the need of extensive preprocessing. Methods: We propose a multi-height-based classification approach that uses CI and CVAI in different height layers and compare it to the initial approach using only one layer. We use ten-fold cross-validation and test seven different classifiers. The dataset of 504 patients consists of three types of craniosynostosis and a control group consisting of healthy and non-synostotic subjects. Results: The multi-height-based approach improved classification for all classifiers. The k-nearest neighbors classifier scored best with a mean accuracy of 89% and a mean F1-score of 0.75. Conclusion: Taking height into account is beneficial for the classification. Based on accepted and widely used clinical parameters, this might be a step towards an easy-to-understand and transparent classification approach for both physicians and patients. |
| first_indexed | 2024-03-11T15:00:48Z |
| format | Article |
| id | doaj.art-787a1f60d33d41bfba964843cba0fb9a |
| institution | Directory Open Access Journal |
| issn | 2364-5504 |
| language | English |
| last_indexed | 2024-03-11T15:00:48Z |
| publishDate | 2023-09-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Current Directions in Biomedical Engineering |
| spelling | doaj.art-787a1f60d33d41bfba964843cba0fb9a2023-10-30T07:58:11ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042023-09-019119820110.1515/cdbme-2023-1050Multi-Height Extraction of Clinical Parameters Improves Classification of CraniosynostosisBecker Anna Maria0Schaufelberger Matthias1Kühle Reinald Peter2Freudlsperger Christian3Nahm Werner4Institute of Biomedical Engineering, Karlsruhe Institute of Technology, Kaiserstr. 12, Karlsruhe, GermanyInstitute of Biomedical Engineering, Karlsruhe Institute of Technology, Kaiserstr. 12, Karlsruhe, GermanyDepartment of Oral and Maxillofacial Surgery, Heidelberg University Hospital, Im Neuenheimer Feld 400, Heidelberg, GermanyDepartment of Oral and Maxillofacial Surgery, Heidelberg University Hospital, Im Neuenheimer Feld 400, Heidelberg, GermanyInstitute of Biomedical Engineering, Karlsruhe Institute of Technology, Kaiserstr. 12, Karlsruhe, GermanyIntroduction: 3D surface scan-based diagnosis of craniosynostosis is a promising radiation-free alternative to traditional diagnosis using computed tomography. The cranial index (CI) and the cranial vault asymmetry index (CVAI) are well-established clinical parameters that are widely used. However, they also have the benefit of being easily adaptable for automatic diagnosis without the need of extensive preprocessing. Methods: We propose a multi-height-based classification approach that uses CI and CVAI in different height layers and compare it to the initial approach using only one layer. We use ten-fold cross-validation and test seven different classifiers. The dataset of 504 patients consists of three types of craniosynostosis and a control group consisting of healthy and non-synostotic subjects. Results: The multi-height-based approach improved classification for all classifiers. The k-nearest neighbors classifier scored best with a mean accuracy of 89% and a mean F1-score of 0.75. Conclusion: Taking height into account is beneficial for the classification. Based on accepted and widely used clinical parameters, this might be a step towards an easy-to-understand and transparent classification approach for both physicians and patients.https://doi.org/10.1515/cdbme-2023-1050craniosynostosisclassificationclinical parameterscranial indexcranial vault asymmetry index |
| spellingShingle | Becker Anna Maria Schaufelberger Matthias Kühle Reinald Peter Freudlsperger Christian Nahm Werner Multi-Height Extraction of Clinical Parameters Improves Classification of Craniosynostosis Current Directions in Biomedical Engineering craniosynostosis classification clinical parameters cranial index cranial vault asymmetry index |
| title | Multi-Height Extraction of Clinical Parameters Improves Classification of Craniosynostosis |
| title_full | Multi-Height Extraction of Clinical Parameters Improves Classification of Craniosynostosis |
| title_fullStr | Multi-Height Extraction of Clinical Parameters Improves Classification of Craniosynostosis |
| title_full_unstemmed | Multi-Height Extraction of Clinical Parameters Improves Classification of Craniosynostosis |
| title_short | Multi-Height Extraction of Clinical Parameters Improves Classification of Craniosynostosis |
| title_sort | multi height extraction of clinical parameters improves classification of craniosynostosis |
| topic | craniosynostosis classification clinical parameters cranial index cranial vault asymmetry index |
| url | https://doi.org/10.1515/cdbme-2023-1050 |
| work_keys_str_mv | AT beckerannamaria multiheightextractionofclinicalparametersimprovesclassificationofcraniosynostosis AT schaufelbergermatthias multiheightextractionofclinicalparametersimprovesclassificationofcraniosynostosis AT kuhlereinaldpeter multiheightextractionofclinicalparametersimprovesclassificationofcraniosynostosis AT freudlspergerchristian multiheightextractionofclinicalparametersimprovesclassificationofcraniosynostosis AT nahmwerner multiheightextractionofclinicalparametersimprovesclassificationofcraniosynostosis |