Unsupervised abnormality detection in neonatal MRI brain scans using deep learning
Abstract Analysis of 3D medical imaging data has been a large topic of focus in the area of Machine Learning/Artificial Intelligence, though little work has been done in algorithmic (particularly unsupervised) analysis of neonatal brain MRI’s. A myriad of conditions can manifest at an early age, inc...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-38430-0 |
| _version_ | 1827895173575606272 |
|---|---|
| author | Jad Dino Raad Ratna Babu Chinnam Suzan Arslanturk Sidhartha Tan Jeong-Won Jeong Swati Mody |
| author_facet | Jad Dino Raad Ratna Babu Chinnam Suzan Arslanturk Sidhartha Tan Jeong-Won Jeong Swati Mody |
| author_sort | Jad Dino Raad |
| collection | DOAJ |
| description | Abstract Analysis of 3D medical imaging data has been a large topic of focus in the area of Machine Learning/Artificial Intelligence, though little work has been done in algorithmic (particularly unsupervised) analysis of neonatal brain MRI’s. A myriad of conditions can manifest at an early age, including neonatal encephalopathy (NE), which can result in lifelong physical consequences. As such, there is a dire need for better biomarkers of NE and other conditions. The objective of the study is to improve identification of anomalies and prognostication of neonatal MRI brain scans. We introduce a framework designed to support the analysis and assessment of neonatal MRI brain scans, the results of which can be used as an aid to neuroradiologists. We explored the efficacy of the framework through iterations of several deep convolutional Autoencoder (AE) unsupervised modeling architectures designed to learn normalcy of the neonatal brain structure. We tested this framework on the developing human connectome project (dHCP) dataset with 97 patients that were previously categorized by severity. Our framework demonstrated the model’s ability to identify and distinguish subtle morphological signatures present in brain structures. Normal and abnormal neonatal brain scans can be distinguished with reasonable accuracy, correctly categorizing them in up to 83% of cases. Most critically, new brain anomalies originally missed during the radiological reading were identified and corroborated by a neuroradiologist. This framework and our modeling approach demonstrate an ability to improve prognostication of neonatal brain conditions and are able to localize new anomalies. |
| first_indexed | 2024-03-12T22:17:44Z |
| format | Article |
| id | doaj.art-4b10ce0033304d329675b7922be57d06 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-12T22:17:44Z |
| publishDate | 2023-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-4b10ce0033304d329675b7922be57d062023-07-23T11:14:08ZengNature PortfolioScientific Reports2045-23222023-07-0113111010.1038/s41598-023-38430-0Unsupervised abnormality detection in neonatal MRI brain scans using deep learningJad Dino Raad0Ratna Babu Chinnam1Suzan Arslanturk2Sidhartha Tan3Jeong-Won Jeong4Swati Mody5Industrial and Systems Engineering Department, Wayne State UniversityIndustrial and Systems Engineering Department, Wayne State UniversityComputer Science Department, Wayne State UniversityDepartment of Pediatrics, Wayne State UniversityDepartment of Pediatrics, Wayne State UniversityDivision of Pediatric Radiology, University of MichiganAbstract Analysis of 3D medical imaging data has been a large topic of focus in the area of Machine Learning/Artificial Intelligence, though little work has been done in algorithmic (particularly unsupervised) analysis of neonatal brain MRI’s. A myriad of conditions can manifest at an early age, including neonatal encephalopathy (NE), which can result in lifelong physical consequences. As such, there is a dire need for better biomarkers of NE and other conditions. The objective of the study is to improve identification of anomalies and prognostication of neonatal MRI brain scans. We introduce a framework designed to support the analysis and assessment of neonatal MRI brain scans, the results of which can be used as an aid to neuroradiologists. We explored the efficacy of the framework through iterations of several deep convolutional Autoencoder (AE) unsupervised modeling architectures designed to learn normalcy of the neonatal brain structure. We tested this framework on the developing human connectome project (dHCP) dataset with 97 patients that were previously categorized by severity. Our framework demonstrated the model’s ability to identify and distinguish subtle morphological signatures present in brain structures. Normal and abnormal neonatal brain scans can be distinguished with reasonable accuracy, correctly categorizing them in up to 83% of cases. Most critically, new brain anomalies originally missed during the radiological reading were identified and corroborated by a neuroradiologist. This framework and our modeling approach demonstrate an ability to improve prognostication of neonatal brain conditions and are able to localize new anomalies.https://doi.org/10.1038/s41598-023-38430-0 |
| spellingShingle | Jad Dino Raad Ratna Babu Chinnam Suzan Arslanturk Sidhartha Tan Jeong-Won Jeong Swati Mody Unsupervised abnormality detection in neonatal MRI brain scans using deep learning Scientific Reports |
| title | Unsupervised abnormality detection in neonatal MRI brain scans using deep learning |
| title_full | Unsupervised abnormality detection in neonatal MRI brain scans using deep learning |
| title_fullStr | Unsupervised abnormality detection in neonatal MRI brain scans using deep learning |
| title_full_unstemmed | Unsupervised abnormality detection in neonatal MRI brain scans using deep learning |
| title_short | Unsupervised abnormality detection in neonatal MRI brain scans using deep learning |
| title_sort | unsupervised abnormality detection in neonatal mri brain scans using deep learning |
| url | https://doi.org/10.1038/s41598-023-38430-0 |
| work_keys_str_mv | AT jaddinoraad unsupervisedabnormalitydetectioninneonatalmribrainscansusingdeeplearning AT ratnababuchinnam unsupervisedabnormalitydetectioninneonatalmribrainscansusingdeeplearning AT suzanarslanturk unsupervisedabnormalitydetectioninneonatalmribrainscansusingdeeplearning AT sidharthatan unsupervisedabnormalitydetectioninneonatalmribrainscansusingdeeplearning AT jeongwonjeong unsupervisedabnormalitydetectioninneonatalmribrainscansusingdeeplearning AT swatimody unsupervisedabnormalitydetectioninneonatalmribrainscansusingdeeplearning |