Parameter settings.
<div><p>This study aims at the limitations of traditional methods in the evaluation of stroke sequelae and rehabilitation effect monitoring, especially for the accurate identification and tracking of brain injury areas. To overcome these challenges, we introduce an advanced neuroimaging...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852022509912719360 |
|---|---|
| author | Xueliang Guo (4797057) |
| author2 | Lin Sun (105539) |
| author2_role | author |
| author_facet | Xueliang Guo (4797057) Lin Sun (105539) |
| author_role | author |
| dc.creator.none.fl_str_mv | Xueliang Guo (4797057) Lin Sun (105539) |
| dc.date.none.fl_str_mv | 2025-02-24T18:27:48Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0317193.t003 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/Parameter_settings_/28474350 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified receiver operating characteristic multimodal mri scans employing skip connections cbam attention module autonomously delineate areas adam optimization algorithm 3d spatial characteristics novel machine learning analyze tumor progression rec ), precision models &# 8217 brain injury areas model &# 8217 local receptive field rehabilitation effect monitoring model effectively integrates brain tumor distributions stroke injury area 3d cnn encoder segmentation accuracy comparable ml models indicated rehabilitation effect brain tumor stroke sequelae effectively identify deep learning cnn encoder tumor core enhancing tumor segmentation maps rehabilitation process manual segmentation ml models miou ), knn ), adaboost ), unet model model make xlink "> traditional methods thereby increasing testing phases subtle changes study introduces study aims statistical metrics shift mechanism scientific basis sampling features results showed resolution features refine features random forest processing capabilities particularly suitable neuroimaging technique net architecture nearest neighbor kappa coefficient jump connection including recall hausdorff distance handle long finely capture existing research et ). efficient tool distance dependencies computational efficiency comprehensive array clinical settings bra2020 dataset auc ). annotation maps also provided |
| dc.title.none.fl_str_mv | Parameter settings. |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <div><p>This study aims at the limitations of traditional methods in the evaluation of stroke sequelae and rehabilitation effect monitoring, especially for the accurate identification and tracking of brain injury areas. To overcome these challenges, we introduce an advanced neuroimaging technology based on deep learning, the SWI-BITR-UNet model. This model, introduced as novel Machine Learning (ML) model, combines the SWIN Transformer’s local receptive field and shift mechanism, and the effective feature fusion strategy in the U-Net architecture, aiming to improve the accuracy of brain lesion region segmentation in multimodal MRI scans. Through the application of a 3-D CNN encoder and decoder, as well as the integration of the CBAM attention module and jump connection, the model can finely capture and refine features, to achieve a level of segmentation accuracy comparable to that of manual segmentation by experts. This study introduces a 3D CNN encoder-decoder architecture specifically designed to enhance the processing capabilities of 3D medical imaging data. The development of the 3D CNN model utilizes the ADAM optimization algorithm to facilitate the training process. The Bra2020 dataset is utilized to assess the accuracy of the proposed deep learning neural network. By employing skip connections, the model effectively integrates the high-resolution features from the encoder with the up-sampling features from the decoder, thereby increasing the model’s sensitivity to 3D spatial characteristics. To assess both the training and testing phases, the SWI-BITR-Unet model is trained using reliable datasets and evaluated through a comprehensive array of statistical metrics, including Recall (Rec), Precision (Pre), F1 test score, Kappa Coefficient (KC), mean Intersection over Union (mIoU), and Receiver Operating Characteristic-Area Under Curve (ROC-AUC). Furthermore, various machine learning models, such as Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Adaptive Boosting (AdaBoost), and K-Nearest Neighbor (KNN), have been employed to analyze tumor progression in the brain, with performance characterized by Hausdorff distance. In From the performance of ML models, the SWI-BITR-Unet model was more accurate than other models. Subsequently, regarding DICE coefficient values, the segmentation maps (annotation maps of brain tumor distributions) generated by the ML models indicated the models’s capability to autonomously delineate areas such as the tumor core (TC) and the enhancing tumor (ET). Moreover, the efficacy of the proposed machine learning models demonstrated superiority over existing research in the field. The computational efficiency and the ability to handle long-distance dependencies of the model make it particularly suitable for applications in clinical Settings. The results showed that the SNA-BITR-UNet model can not only effectively identify and monitor the subtle changes in the stroke injury area, but also provided a new and efficient tool in the rehabilitation process, providing a scientific basis for developing personalized rehabilitation plans.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_a243aa3cd338b8a4f7dd934bf85fcfe6 |
| identifier_str_mv | 10.1371/journal.pone.0317193.t003 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28474350 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Parameter settings.Xueliang Guo (4797057)Lin Sun (105539)Science PolicyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedreceiver operating characteristicmultimodal mri scansemploying skip connectionscbam attention moduleautonomously delineate areasadam optimization algorithm3d spatial characteristicsnovel machine learninganalyze tumor progressionrec ), precisionmodels &# 8217brain injury areasmodel &# 8217local receptive fieldrehabilitation effect monitoringmodel effectively integratesbrain tumor distributionsstroke injury area3d cnn encodersegmentation accuracy comparableml models indicatedrehabilitation effectbrain tumorstroke sequelaeeffectively identifydeep learningcnn encodertumor coreenhancing tumorsegmentation mapsrehabilitation processmanual segmentationml modelsmiou ),knn ),adaboost ),unet modelmodel makexlink ">traditional methodsthereby increasingtesting phasessubtle changesstudy introducesstudy aimsstatistical metricsshift mechanismscientific basissampling featuresresults showedresolution featuresrefine featuresrandom forestprocessing capabilitiesparticularly suitableneuroimaging techniquenet architecturenearest neighborkappa coefficientjump connectionincluding recallhausdorff distancehandle longfinely captureexisting researchet ).efficient tooldistance dependenciescomputational efficiencycomprehensive arrayclinical settingsbra2020 datasetauc ).annotation mapsalso provided<div><p>This study aims at the limitations of traditional methods in the evaluation of stroke sequelae and rehabilitation effect monitoring, especially for the accurate identification and tracking of brain injury areas. To overcome these challenges, we introduce an advanced neuroimaging technology based on deep learning, the SWI-BITR-UNet model. This model, introduced as novel Machine Learning (ML) model, combines the SWIN Transformer’s local receptive field and shift mechanism, and the effective feature fusion strategy in the U-Net architecture, aiming to improve the accuracy of brain lesion region segmentation in multimodal MRI scans. Through the application of a 3-D CNN encoder and decoder, as well as the integration of the CBAM attention module and jump connection, the model can finely capture and refine features, to achieve a level of segmentation accuracy comparable to that of manual segmentation by experts. This study introduces a 3D CNN encoder-decoder architecture specifically designed to enhance the processing capabilities of 3D medical imaging data. The development of the 3D CNN model utilizes the ADAM optimization algorithm to facilitate the training process. The Bra2020 dataset is utilized to assess the accuracy of the proposed deep learning neural network. By employing skip connections, the model effectively integrates the high-resolution features from the encoder with the up-sampling features from the decoder, thereby increasing the model’s sensitivity to 3D spatial characteristics. To assess both the training and testing phases, the SWI-BITR-Unet model is trained using reliable datasets and evaluated through a comprehensive array of statistical metrics, including Recall (Rec), Precision (Pre), F1 test score, Kappa Coefficient (KC), mean Intersection over Union (mIoU), and Receiver Operating Characteristic-Area Under Curve (ROC-AUC). Furthermore, various machine learning models, such as Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Adaptive Boosting (AdaBoost), and K-Nearest Neighbor (KNN), have been employed to analyze tumor progression in the brain, with performance characterized by Hausdorff distance. In From the performance of ML models, the SWI-BITR-Unet model was more accurate than other models. Subsequently, regarding DICE coefficient values, the segmentation maps (annotation maps of brain tumor distributions) generated by the ML models indicated the models’s capability to autonomously delineate areas such as the tumor core (TC) and the enhancing tumor (ET). Moreover, the efficacy of the proposed machine learning models demonstrated superiority over existing research in the field. The computational efficiency and the ability to handle long-distance dependencies of the model make it particularly suitable for applications in clinical Settings. The results showed that the SNA-BITR-UNet model can not only effectively identify and monitor the subtle changes in the stroke injury area, but also provided a new and efficient tool in the rehabilitation process, providing a scientific basis for developing personalized rehabilitation plans.</p></div>2025-02-24T18:27:48ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0317193.t003https://figshare.com/articles/dataset/Parameter_settings_/28474350CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/284743502025-02-24T18:27:48Z |
| spellingShingle | Parameter settings. Xueliang Guo (4797057) Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified receiver operating characteristic multimodal mri scans employing skip connections cbam attention module autonomously delineate areas adam optimization algorithm 3d spatial characteristics novel machine learning analyze tumor progression rec ), precision models &# 8217 brain injury areas model &# 8217 local receptive field rehabilitation effect monitoring model effectively integrates brain tumor distributions stroke injury area 3d cnn encoder segmentation accuracy comparable ml models indicated rehabilitation effect brain tumor stroke sequelae effectively identify deep learning cnn encoder tumor core enhancing tumor segmentation maps rehabilitation process manual segmentation ml models miou ), knn ), adaboost ), unet model model make xlink "> traditional methods thereby increasing testing phases subtle changes study introduces study aims statistical metrics shift mechanism scientific basis sampling features results showed resolution features refine features random forest processing capabilities particularly suitable neuroimaging technique net architecture nearest neighbor kappa coefficient jump connection including recall hausdorff distance handle long finely capture existing research et ). efficient tool distance dependencies computational efficiency comprehensive array clinical settings bra2020 dataset auc ). annotation maps also provided |
| status_str | publishedVersion |
| title | Parameter settings. |
| title_full | Parameter settings. |
| title_fullStr | Parameter settings. |
| title_full_unstemmed | Parameter settings. |
| title_short | Parameter settings. |
| title_sort | Parameter settings. |
| topic | Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified receiver operating characteristic multimodal mri scans employing skip connections cbam attention module autonomously delineate areas adam optimization algorithm 3d spatial characteristics novel machine learning analyze tumor progression rec ), precision models &# 8217 brain injury areas model &# 8217 local receptive field rehabilitation effect monitoring model effectively integrates brain tumor distributions stroke injury area 3d cnn encoder segmentation accuracy comparable ml models indicated rehabilitation effect brain tumor stroke sequelae effectively identify deep learning cnn encoder tumor core enhancing tumor segmentation maps rehabilitation process manual segmentation ml models miou ), knn ), adaboost ), unet model model make xlink "> traditional methods thereby increasing testing phases subtle changes study introduces study aims statistical metrics shift mechanism scientific basis sampling features results showed resolution features refine features random forest processing capabilities particularly suitable neuroimaging technique net architecture nearest neighbor kappa coefficient jump connection including recall hausdorff distance handle long finely capture existing research et ). efficient tool distance dependencies computational efficiency comprehensive array clinical settings bra2020 dataset auc ). annotation maps also provided |