Modeling Uncertainty in Fracture Age Estimation from Pediatric Wrist Radiographs
In clinical practice, fracture age estimation is commonly required, particularly in children with suspected non-accidental injuries. It is usually done by radiologically examining the injured body part and analyzing several indicators of fracture healing such as osteopenia, periosteal reaction, and...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/9/24/3227 |
| _version_ | 1797502646196633600 |
|---|---|
| author | Franko Hržić Michael Janisch Ivan Štajduhar Jonatan Lerga Erich Sorantin Sebastian Tschauner |
| author_facet | Franko Hržić Michael Janisch Ivan Štajduhar Jonatan Lerga Erich Sorantin Sebastian Tschauner |
| author_sort | Franko Hržić |
| collection | DOAJ |
| description | In clinical practice, fracture age estimation is commonly required, particularly in children with suspected non-accidental injuries. It is usually done by radiologically examining the injured body part and analyzing several indicators of fracture healing such as osteopenia, periosteal reaction, and fracture gap width. However, age-related changes in healing timeframes, inter-individual variabilities in bone density, and significant intra- and inter-operator subjectivity all limit the validity of these radiological clues. To address these issues, for the first time, we suggest an automated neural network-based system for determining the age of a pediatric wrist fracture. In this study, we propose and evaluate a deep learning approach for automatically estimating fracture age. Our dataset included 3570 medical cases with a skewed distribution toward initial consultations. Each medical case includes a lateral and anteroposterior projection of a wrist fracture, as well as patients’ age, and gender. We propose a neural network-based system with Monte-Carlo dropout-based uncertainty estimation to address dataset skewness. Furthermore, this research examines how each component of the system contributes to the final forecast and provides an interpretation of different scenarios in system predictions in terms of their uncertainty. The examination of the proposed systems’ components showed that the feature-fusion of all available data is necessary to obtain good results. Also, proposing uncertainty estimation in the system increased accuracy and F1-score to a final <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.906</mn><mo>±</mo><mn>0.011</mn></mrow></semantics></math></inline-formula> on a given task. |
| first_indexed | 2024-03-10T03:38:05Z |
| format | Article |
| id | doaj.art-62ee1e6f70044859ab4f8a62d6056d72 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T03:38:05Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-62ee1e6f70044859ab4f8a62d6056d722023-11-23T09:26:04ZengMDPI AGMathematics2227-73902021-12-01924322710.3390/math9243227Modeling Uncertainty in Fracture Age Estimation from Pediatric Wrist RadiographsFranko Hržić0Michael Janisch1Ivan Štajduhar2Jonatan Lerga3Erich Sorantin4Sebastian Tschauner5Department of Computer Engineering, Faculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka 51000, CroatiaDivision of General Radiology, Department of Radiology, Medical University of Graz, 8036 Graz, AustriaDepartment of Computer Engineering, Faculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka 51000, CroatiaDepartment of Computer Engineering, Faculty of Engineering, University of Rijeka, Vukovarska 58, Rijeka 51000, CroatiaDivision of Pediatric Radiology, Department of Radiology, Medical University of Graz, 8036 Graz, AustriaDivision of Pediatric Radiology, Department of Radiology, Medical University of Graz, 8036 Graz, AustriaIn clinical practice, fracture age estimation is commonly required, particularly in children with suspected non-accidental injuries. It is usually done by radiologically examining the injured body part and analyzing several indicators of fracture healing such as osteopenia, periosteal reaction, and fracture gap width. However, age-related changes in healing timeframes, inter-individual variabilities in bone density, and significant intra- and inter-operator subjectivity all limit the validity of these radiological clues. To address these issues, for the first time, we suggest an automated neural network-based system for determining the age of a pediatric wrist fracture. In this study, we propose and evaluate a deep learning approach for automatically estimating fracture age. Our dataset included 3570 medical cases with a skewed distribution toward initial consultations. Each medical case includes a lateral and anteroposterior projection of a wrist fracture, as well as patients’ age, and gender. We propose a neural network-based system with Monte-Carlo dropout-based uncertainty estimation to address dataset skewness. Furthermore, this research examines how each component of the system contributes to the final forecast and provides an interpretation of different scenarios in system predictions in terms of their uncertainty. The examination of the proposed systems’ components showed that the feature-fusion of all available data is necessary to obtain good results. Also, proposing uncertainty estimation in the system increased accuracy and F1-score to a final <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.906</mn><mo>±</mo><mn>0.011</mn></mrow></semantics></math></inline-formula> on a given task.https://www.mdpi.com/2227-7390/9/24/3227fracture ageforensicdeep learninguncertainty estimationGaussian processX-ray |
| spellingShingle | Franko Hržić Michael Janisch Ivan Štajduhar Jonatan Lerga Erich Sorantin Sebastian Tschauner Modeling Uncertainty in Fracture Age Estimation from Pediatric Wrist Radiographs Mathematics fracture age forensic deep learning uncertainty estimation Gaussian process X-ray |
| title | Modeling Uncertainty in Fracture Age Estimation from Pediatric Wrist Radiographs |
| title_full | Modeling Uncertainty in Fracture Age Estimation from Pediatric Wrist Radiographs |
| title_fullStr | Modeling Uncertainty in Fracture Age Estimation from Pediatric Wrist Radiographs |
| title_full_unstemmed | Modeling Uncertainty in Fracture Age Estimation from Pediatric Wrist Radiographs |
| title_short | Modeling Uncertainty in Fracture Age Estimation from Pediatric Wrist Radiographs |
| title_sort | modeling uncertainty in fracture age estimation from pediatric wrist radiographs |
| topic | fracture age forensic deep learning uncertainty estimation Gaussian process X-ray |
| url | https://www.mdpi.com/2227-7390/9/24/3227 |
| work_keys_str_mv | AT frankohrzic modelinguncertaintyinfractureageestimationfrompediatricwristradiographs AT michaeljanisch modelinguncertaintyinfractureageestimationfrompediatricwristradiographs AT ivanstajduhar modelinguncertaintyinfractureageestimationfrompediatricwristradiographs AT jonatanlerga modelinguncertaintyinfractureageestimationfrompediatricwristradiographs AT erichsorantin modelinguncertaintyinfractureageestimationfrompediatricwristradiographs AT sebastiantschauner modelinguncertaintyinfractureageestimationfrompediatricwristradiographs |