Automated Spleen Injury Detection Using 3D Active Contours and Machine Learning
The spleen is one of the most frequently injured organs in blunt abdominal trauma. Computed tomography (CT) is the imaging modality of choice to assess patients with blunt spleen trauma, which may include lacerations, subcapsular or parenchymal hematomas, active hemorrhage, and vascular injuries. Wh...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/4/382 |
| _version_ | 1797540266302767104 |
|---|---|
| author | Julie Wang Alexander Wood Chao Gao Kayvan Najarian Jonathan Gryak |
| author_facet | Julie Wang Alexander Wood Chao Gao Kayvan Najarian Jonathan Gryak |
| author_sort | Julie Wang |
| collection | DOAJ |
| description | The spleen is one of the most frequently injured organs in blunt abdominal trauma. Computed tomography (CT) is the imaging modality of choice to assess patients with blunt spleen trauma, which may include lacerations, subcapsular or parenchymal hematomas, active hemorrhage, and vascular injuries. While computer-assisted diagnosis systems exist for other conditions assessed using CT scans, the current method to detect spleen injuries involves the manual review of scans by radiologists, which is a time-consuming and repetitive process. In this study, we propose an automated spleen injury detection method using machine learning. CT scans from patients experiencing traumatic injuries were collected from Michigan Medicine and the Crash Injury Research Engineering Network (CIREN) dataset. Ninety-nine scans of healthy and lacerated spleens were split into disjoint training and test sets, with random forest (RF), naive Bayes, SVM, <i>k</i>-nearest neighbors (<i>k</i>-NN) ensemble, and subspace discriminant ensemble models trained via 5-fold cross validation. Of these models, random forest performed the best, achieving an Area Under the receiver operating characteristic Curve (AUC) of 0.91 and an F1 score of 0.80 on the test set. These results suggest that an automated, quantitative assessment of traumatic spleen injury has the potential to enable faster triage and improve patient outcomes. |
| first_indexed | 2024-03-10T12:58:37Z |
| format | Article |
| id | doaj.art-feff4fa8c6c94ca881b9d0eb944b4ae2 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T12:58:37Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-feff4fa8c6c94ca881b9d0eb944b4ae22023-11-21T11:45:43ZengMDPI AGEntropy1099-43002021-03-0123438210.3390/e23040382Automated Spleen Injury Detection Using 3D Active Contours and Machine LearningJulie Wang0Alexander Wood1Chao Gao2Kayvan Najarian3Jonathan Gryak4Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI 48109, USADepartment of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USADepartment of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USADepartment of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI 48109, USADepartment of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USAThe spleen is one of the most frequently injured organs in blunt abdominal trauma. Computed tomography (CT) is the imaging modality of choice to assess patients with blunt spleen trauma, which may include lacerations, subcapsular or parenchymal hematomas, active hemorrhage, and vascular injuries. While computer-assisted diagnosis systems exist for other conditions assessed using CT scans, the current method to detect spleen injuries involves the manual review of scans by radiologists, which is a time-consuming and repetitive process. In this study, we propose an automated spleen injury detection method using machine learning. CT scans from patients experiencing traumatic injuries were collected from Michigan Medicine and the Crash Injury Research Engineering Network (CIREN) dataset. Ninety-nine scans of healthy and lacerated spleens were split into disjoint training and test sets, with random forest (RF), naive Bayes, SVM, <i>k</i>-nearest neighbors (<i>k</i>-NN) ensemble, and subspace discriminant ensemble models trained via 5-fold cross validation. Of these models, random forest performed the best, achieving an Area Under the receiver operating characteristic Curve (AUC) of 0.91 and an F1 score of 0.80 on the test set. These results suggest that an automated, quantitative assessment of traumatic spleen injury has the potential to enable faster triage and improve patient outcomes.https://www.mdpi.com/1099-4300/23/4/382image segmentationcomputer-assisted diagnosismachine learningspleen injury detection |
| spellingShingle | Julie Wang Alexander Wood Chao Gao Kayvan Najarian Jonathan Gryak Automated Spleen Injury Detection Using 3D Active Contours and Machine Learning Entropy image segmentation computer-assisted diagnosis machine learning spleen injury detection |
| title | Automated Spleen Injury Detection Using 3D Active Contours and Machine Learning |
| title_full | Automated Spleen Injury Detection Using 3D Active Contours and Machine Learning |
| title_fullStr | Automated Spleen Injury Detection Using 3D Active Contours and Machine Learning |
| title_full_unstemmed | Automated Spleen Injury Detection Using 3D Active Contours and Machine Learning |
| title_short | Automated Spleen Injury Detection Using 3D Active Contours and Machine Learning |
| title_sort | automated spleen injury detection using 3d active contours and machine learning |
| topic | image segmentation computer-assisted diagnosis machine learning spleen injury detection |
| url | https://www.mdpi.com/1099-4300/23/4/382 |
| work_keys_str_mv | AT juliewang automatedspleeninjurydetectionusing3dactivecontoursandmachinelearning AT alexanderwood automatedspleeninjurydetectionusing3dactivecontoursandmachinelearning AT chaogao automatedspleeninjurydetectionusing3dactivecontoursandmachinelearning AT kayvannajarian automatedspleeninjurydetectionusing3dactivecontoursandmachinelearning AT jonathangryak automatedspleeninjurydetectionusing3dactivecontoursandmachinelearning |