A deep learning model for diagnosing dystrophinopathies on thigh muscle MRI images
Abstract Background Dystrophinopathies are the most common type of inherited muscular diseases. Muscle biopsy and genetic tests are effective to diagnose the disease but cost much more than primary hospitals can reach. The more available muscle MRI is promising but its diagnostic results highly depe...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-01-01
|
| Series: | BMC Neurology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12883-020-02036-0 |
| _version_ | 1811270792958181376 |
|---|---|
| author | Mei Yang Yiming Zheng Zhiying Xie Zhaoxia Wang Jiangxi Xiao Jue Zhang Yun Yuan |
| author_facet | Mei Yang Yiming Zheng Zhiying Xie Zhaoxia Wang Jiangxi Xiao Jue Zhang Yun Yuan |
| author_sort | Mei Yang |
| collection | DOAJ |
| description | Abstract Background Dystrophinopathies are the most common type of inherited muscular diseases. Muscle biopsy and genetic tests are effective to diagnose the disease but cost much more than primary hospitals can reach. The more available muscle MRI is promising but its diagnostic results highly depends on doctors’ experiences. This study intends to explore a way of deploying a deep learning model for muscle MRI images to diagnose dystrophinopathies. Methods This study collected 2536 T1WI images from 432 cases who had been diagnosed by genetic analysis and/or muscle biopsy, including 148 cases with dystrophinopathies and 284 cases with other diseases. The data was randomly divided into three sets: the data from 233 cases were used to train the CNN model, the data from 97 cases for the validation experiments, and the data from 102 cases for the test experiments. We also validated our models expertise at diagnosing by comparing the model’s results on the 102 cases with those of three skilled radiologists. Results The proposed model achieved 91% (95% CI: 0.88, 0.93) accuracy on the test set, higher than the best accuracy of 84% in radiologists. It also performed better than the skilled radiologists in sensitivity : sensitivities of the models and the doctors were 0.89 (95% CI: 0.85 0.93) versus 0.79 (95% CI:0.73, 0.84; p = 0.190). Conclusions The deep model achieved excellent accuracy and sensitivity in identifying cases with dystrophinopathies. The comparable performance of the model and skilled radiologists demonstrates the potential application of the model in diagnosing dystrophinopathies through MRI images. |
| first_indexed | 2024-04-12T22:08:27Z |
| format | Article |
| id | doaj.art-3eac1ccf74114849b84525b1cf36af53 |
| institution | Directory Open Access Journal |
| issn | 1471-2377 |
| language | English |
| last_indexed | 2024-04-12T22:08:27Z |
| publishDate | 2021-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Neurology |
| spelling | doaj.art-3eac1ccf74114849b84525b1cf36af532022-12-22T03:14:50ZengBMCBMC Neurology1471-23772021-01-012111910.1186/s12883-020-02036-0A deep learning model for diagnosing dystrophinopathies on thigh muscle MRI imagesMei Yang0Yiming Zheng1Zhiying Xie2Zhaoxia Wang3Jiangxi Xiao4Jue Zhang5Yun Yuan6Department of Neurology, Peking University First HospitalDepartment of Neurology, Peking University First HospitalDepartment of Neurology, Peking University First HospitalDepartment of Neurology, Peking University First HospitalDepartment of Radiology, Peking University First HospitalAcademy for Advanced Interdisciplinary Studies, Peking UniversityDepartment of Neurology, Peking University First HospitalAbstract Background Dystrophinopathies are the most common type of inherited muscular diseases. Muscle biopsy and genetic tests are effective to diagnose the disease but cost much more than primary hospitals can reach. The more available muscle MRI is promising but its diagnostic results highly depends on doctors’ experiences. This study intends to explore a way of deploying a deep learning model for muscle MRI images to diagnose dystrophinopathies. Methods This study collected 2536 T1WI images from 432 cases who had been diagnosed by genetic analysis and/or muscle biopsy, including 148 cases with dystrophinopathies and 284 cases with other diseases. The data was randomly divided into three sets: the data from 233 cases were used to train the CNN model, the data from 97 cases for the validation experiments, and the data from 102 cases for the test experiments. We also validated our models expertise at diagnosing by comparing the model’s results on the 102 cases with those of three skilled radiologists. Results The proposed model achieved 91% (95% CI: 0.88, 0.93) accuracy on the test set, higher than the best accuracy of 84% in radiologists. It also performed better than the skilled radiologists in sensitivity : sensitivities of the models and the doctors were 0.89 (95% CI: 0.85 0.93) versus 0.79 (95% CI:0.73, 0.84; p = 0.190). Conclusions The deep model achieved excellent accuracy and sensitivity in identifying cases with dystrophinopathies. The comparable performance of the model and skilled radiologists demonstrates the potential application of the model in diagnosing dystrophinopathies through MRI images.https://doi.org/10.1186/s12883-020-02036-0Magnetic Resonance ImagingMuscular DiseasesDeep LearningComputer-Assisted Diagnosis |
| spellingShingle | Mei Yang Yiming Zheng Zhiying Xie Zhaoxia Wang Jiangxi Xiao Jue Zhang Yun Yuan A deep learning model for diagnosing dystrophinopathies on thigh muscle MRI images BMC Neurology Magnetic Resonance Imaging Muscular Diseases Deep Learning Computer-Assisted Diagnosis |
| title | A deep learning model for diagnosing dystrophinopathies on thigh muscle MRI images |
| title_full | A deep learning model for diagnosing dystrophinopathies on thigh muscle MRI images |
| title_fullStr | A deep learning model for diagnosing dystrophinopathies on thigh muscle MRI images |
| title_full_unstemmed | A deep learning model for diagnosing dystrophinopathies on thigh muscle MRI images |
| title_short | A deep learning model for diagnosing dystrophinopathies on thigh muscle MRI images |
| title_sort | deep learning model for diagnosing dystrophinopathies on thigh muscle mri images |
| topic | Magnetic Resonance Imaging Muscular Diseases Deep Learning Computer-Assisted Diagnosis |
| url | https://doi.org/10.1186/s12883-020-02036-0 |
| work_keys_str_mv | AT meiyang adeeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT yimingzheng adeeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT zhiyingxie adeeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT zhaoxiawang adeeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT jiangxixiao adeeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT juezhang adeeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT yunyuan adeeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT meiyang deeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT yimingzheng deeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT zhiyingxie deeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT zhaoxiawang deeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT jiangxixiao deeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT juezhang deeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages AT yunyuan deeplearningmodelfordiagnosingdystrophinopathiesonthighmusclemriimages |