Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages
Abstract Cerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/21eb399e283e4d58af842595fa6c735c |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:21eb399e283e4d58af842595fa6c735c |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:21eb399e283e4d58af842595fa6c735c2021-12-02T15:45:21ZSpectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages10.1038/s41598-021-88236-12045-2322https://doaj.org/article/21eb399e283e4d58af842595fa6c735c2021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88236-1https://doaj.org/toc/2045-2322Abstract Cerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.Christian CrouzetGwangjin JeongRachel H. ChaeKrystal T. LoPrestiCody E. DunnDanny F. XieChiagoziem AguChuo FangAne C. F. NunesWei Ling LauSehwan KimDavid H. CribbsMark FisherBernard ChoiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Christian Crouzet Gwangjin Jeong Rachel H. Chae Krystal T. LoPresti Cody E. Dunn Danny F. Xie Chiagoziem Agu Chuo Fang Ane C. F. Nunes Wei Ling Lau Sehwan Kim David H. Cribbs Mark Fisher Bernard Choi Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages |
| description |
Abstract Cerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy. |
| format |
article |
| author |
Christian Crouzet Gwangjin Jeong Rachel H. Chae Krystal T. LoPresti Cody E. Dunn Danny F. Xie Chiagoziem Agu Chuo Fang Ane C. F. Nunes Wei Ling Lau Sehwan Kim David H. Cribbs Mark Fisher Bernard Choi |
| author_facet |
Christian Crouzet Gwangjin Jeong Rachel H. Chae Krystal T. LoPresti Cody E. Dunn Danny F. Xie Chiagoziem Agu Chuo Fang Ane C. F. Nunes Wei Ling Lau Sehwan Kim David H. Cribbs Mark Fisher Bernard Choi |
| author_sort |
Christian Crouzet |
| title |
Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages |
| title_short |
Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages |
| title_full |
Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages |
| title_fullStr |
Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages |
| title_full_unstemmed |
Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages |
| title_sort |
spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/21eb399e283e4d58af842595fa6c735c |
| work_keys_str_mv |
AT christiancrouzet spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT gwangjinjeong spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT rachelhchae spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT krystaltlopresti spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT codyedunn spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT dannyfxie spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT chiagoziemagu spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT chuofang spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT anecfnunes spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT weilinglau spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT sehwankim spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT davidhcribbs spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT markfisher spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages AT bernardchoi spectroscopicanddeeplearningbasedapproachestoidentifyandquantifycerebralmicrohemorrhages |
| _version_ |
1718385736665792512 |