Sex estimation with parameters of the facial canal by computed tomography using machine learning algorithms and artificial neural networks
Abstract Background The skull is highly durable and plays a significant role in sex determination as one of the most dimorphic bones. The facial canal (FC), a clinically significant canal within the temporal bone, houses the facial nerve. This study aims to estimate sex using morphometric measuremen...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-07-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-025-01834-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849341972549992448 |
|---|---|
| author | Yusuf Secgin Seren Kaya Oğuzhan Harmandaoğlu Oğuzhan Öztürk Deniz Senol Ömer Önbaş Nihat Yılmaz |
| author_facet | Yusuf Secgin Seren Kaya Oğuzhan Harmandaoğlu Oğuzhan Öztürk Deniz Senol Ömer Önbaş Nihat Yılmaz |
| author_sort | Yusuf Secgin |
| collection | DOAJ |
| description | Abstract Background The skull is highly durable and plays a significant role in sex determination as one of the most dimorphic bones. The facial canal (FC), a clinically significant canal within the temporal bone, houses the facial nerve. This study aims to estimate sex using morphometric measurements from the FC through machine learning (ML) and artificial neural networks (ANNs). Materials and methods The study utilized Computed Tomography (CT) images of 200 individuals (100 females, 100 males) aged 19–65 years. These images were retrospectively retrieved from the Picture Archiving and Communication Systems (PACS) at Düzce University Faculty of Medicine, Department of Radiology, covering 2021–2024. Bilateral measurements of nine temporal bone parameters were performed in axial, coronal, and sagittal planes. ML algorithms including Quadratic Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), Decision Tree (DT), Extra Tree Classifier (ETC), Random Forest (RF), Logistic Regression (LR), Gaussian Naive Bayes (GaussianNB), and k-Nearest Neighbors (k-NN) were used, alongside a multilayer perceptron classifier (MLPC) from ANN algorithms. Results Except for QDA (Acc 0.93), all algorithms achieved an accuracy rate of 0.97. SHapley Additive exPlanations (SHAP) analysis revealed the five most impactful parameters: right SGAs, left SGAs, right TSWs, left TSWs and, the inner mouth width of the left FN, respectively. Conclusions FN-centered morphometric measurements show high accuracy in sex determination and may aid in understanding FN positioning across sexes and populations. These findings may support rapid and reliable sex estimation in forensic investigations—especially in cases with fragmented craniofacial remains—and provide auxiliary diagnostic data for preoperative planning in otologic and skull base surgeries. They are thus relevant for surgeons, anthropologists, and forensic experts. Clinical trial number Not applicable. |
| format | Article |
| id | doaj-art-2872742e67124f28be4dcac676abb582 |
| institution | Kabale University |
| issn | 1471-2342 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj-art-2872742e67124f28be4dcac676abb5822025-08-20T03:43:31ZengBMCBMC Medical Imaging1471-23422025-07-0125111310.1186/s12880-025-01834-7Sex estimation with parameters of the facial canal by computed tomography using machine learning algorithms and artificial neural networksYusuf Secgin0Seren Kaya1Oğuzhan Harmandaoğlu2Oğuzhan Öztürk3Deniz Senol4Ömer Önbaş5Nihat Yılmaz6Department of Anatomy, Faculty of Medicine, Karabük UniversityDepartment of Anatomy, Faculty of Medicine, Düzce UniversityDepartment of Therapy and Rehabilitation, Çatalzeytin Vocational School, Kastamonu UniversityDepartment of Therapy and Rehabilitation, Çatalzeytin Vocational School, Kastamonu UniversityDepartment of Anatomy, Faculty of Medicine, Düzce UniversityDepartment of Radiology, Faculty of Medicine, Düzce UniversityDepartment of Otorhinolaryngology, Faculty of Medicine, Karabük UniversityAbstract Background The skull is highly durable and plays a significant role in sex determination as one of the most dimorphic bones. The facial canal (FC), a clinically significant canal within the temporal bone, houses the facial nerve. This study aims to estimate sex using morphometric measurements from the FC through machine learning (ML) and artificial neural networks (ANNs). Materials and methods The study utilized Computed Tomography (CT) images of 200 individuals (100 females, 100 males) aged 19–65 years. These images were retrospectively retrieved from the Picture Archiving and Communication Systems (PACS) at Düzce University Faculty of Medicine, Department of Radiology, covering 2021–2024. Bilateral measurements of nine temporal bone parameters were performed in axial, coronal, and sagittal planes. ML algorithms including Quadratic Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), Decision Tree (DT), Extra Tree Classifier (ETC), Random Forest (RF), Logistic Regression (LR), Gaussian Naive Bayes (GaussianNB), and k-Nearest Neighbors (k-NN) were used, alongside a multilayer perceptron classifier (MLPC) from ANN algorithms. Results Except for QDA (Acc 0.93), all algorithms achieved an accuracy rate of 0.97. SHapley Additive exPlanations (SHAP) analysis revealed the five most impactful parameters: right SGAs, left SGAs, right TSWs, left TSWs and, the inner mouth width of the left FN, respectively. Conclusions FN-centered morphometric measurements show high accuracy in sex determination and may aid in understanding FN positioning across sexes and populations. These findings may support rapid and reliable sex estimation in forensic investigations—especially in cases with fragmented craniofacial remains—and provide auxiliary diagnostic data for preoperative planning in otologic and skull base surgeries. They are thus relevant for surgeons, anthropologists, and forensic experts. Clinical trial number Not applicable.https://doi.org/10.1186/s12880-025-01834-7Sex estimationMachine learningArtificial neural networkFacial canalFallopian canal |
| spellingShingle | Yusuf Secgin Seren Kaya Oğuzhan Harmandaoğlu Oğuzhan Öztürk Deniz Senol Ömer Önbaş Nihat Yılmaz Sex estimation with parameters of the facial canal by computed tomography using machine learning algorithms and artificial neural networks BMC Medical Imaging Sex estimation Machine learning Artificial neural network Facial canal Fallopian canal |
| title | Sex estimation with parameters of the facial canal by computed tomography using machine learning algorithms and artificial neural networks |
| title_full | Sex estimation with parameters of the facial canal by computed tomography using machine learning algorithms and artificial neural networks |
| title_fullStr | Sex estimation with parameters of the facial canal by computed tomography using machine learning algorithms and artificial neural networks |
| title_full_unstemmed | Sex estimation with parameters of the facial canal by computed tomography using machine learning algorithms and artificial neural networks |
| title_short | Sex estimation with parameters of the facial canal by computed tomography using machine learning algorithms and artificial neural networks |
| title_sort | sex estimation with parameters of the facial canal by computed tomography using machine learning algorithms and artificial neural networks |
| topic | Sex estimation Machine learning Artificial neural network Facial canal Fallopian canal |
| url | https://doi.org/10.1186/s12880-025-01834-7 |
| work_keys_str_mv | AT yusufsecgin sexestimationwithparametersofthefacialcanalbycomputedtomographyusingmachinelearningalgorithmsandartificialneuralnetworks AT serenkaya sexestimationwithparametersofthefacialcanalbycomputedtomographyusingmachinelearningalgorithmsandartificialneuralnetworks AT oguzhanharmandaoglu sexestimationwithparametersofthefacialcanalbycomputedtomographyusingmachinelearningalgorithmsandartificialneuralnetworks AT oguzhanozturk sexestimationwithparametersofthefacialcanalbycomputedtomographyusingmachinelearningalgorithmsandartificialneuralnetworks AT denizsenol sexestimationwithparametersofthefacialcanalbycomputedtomographyusingmachinelearningalgorithmsandartificialneuralnetworks AT omeronbas sexestimationwithparametersofthefacialcanalbycomputedtomographyusingmachinelearningalgorithmsandartificialneuralnetworks AT nihatyılmaz sexestimationwithparametersofthefacialcanalbycomputedtomographyusingmachinelearningalgorithmsandartificialneuralnetworks |