Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation
Abstract Background Tumour vascular density assessed from CD-31 immunohistochemistry (IHC) images has previously been shown to have prognostic value in breast cancer. Current methods to measure vascular density, however, are time-consuming, suffer from high inter-observer variability and are limited...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | Breast Cancer Research |
| Online Access: | https://doi.org/10.1186/s13058-024-01950-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861468635856896 |
|---|---|
| author | Tristan Whitmarsh Wei Cope Julia Carmona-Bozo Roido Manavaki Stephen-John Sammut Ramona Woitek Elena Provenzano Emma L. Brown Sarah E. Bohndiek Ferdia A. Gallagher Carlos Caldas Fiona J. Gilbert Florian Markowetz |
| author_facet | Tristan Whitmarsh Wei Cope Julia Carmona-Bozo Roido Manavaki Stephen-John Sammut Ramona Woitek Elena Provenzano Emma L. Brown Sarah E. Bohndiek Ferdia A. Gallagher Carlos Caldas Fiona J. Gilbert Florian Markowetz |
| author_sort | Tristan Whitmarsh |
| collection | DOAJ |
| description | Abstract Background Tumour vascular density assessed from CD-31 immunohistochemistry (IHC) images has previously been shown to have prognostic value in breast cancer. Current methods to measure vascular density, however, are time-consuming, suffer from high inter-observer variability and are limited in describing the complex tumour vasculature morphometry. Methods We propose a method for automatically measuring a range of vascular parameters from CD-31 IHC images, which together provide a detailed description of the vasculature morphology. We first used a U-Net based convolutional neural network, trained and validated using 36 partially annotated whole slide images from 27 patients, to segment vessel structures and tumour regions from which the measurements are taken. The model also segments the vascular smooth muscle, benign epithelium, adipose tissue, stroma, lymphocyte clusters, nerves and CD-31 positive leukocytes, and we applied it to an additional 21 images from 15 patients. Using these segmentations, we investigated the relationship between the various tissue types and the vasculature and studied the relationship of various vascular parameters with clinical parameters. We also performed a 3D histology analysis on a separate tumour sample as a proof of principle, providing a more comprehensive visualization of vasculature morphology compared to the standard 2D cross-section of a tissue sample. Results Using two-way cross-validation, we show that vessels were accurately segmented, with Dice scores of 0.875 and 0.856, and were accurately identified, with F1 scores of 0.777 and 0.748. All vascular parameters exhibit strong ( $$r>0.7$$ r > 0.7 ) and significant (p<0.001) correlations with measurements taken from the manual ground truth vessel segmentations. A significant relationship between the major/minor axis ratio, a measure of elongation, and the tumour grade was found. Conclusion Our proposed method shows promise as a tool for studying the tumour vasculature and its relationship with surrounding cells and tissue types. Furthermore, the correlation with tumour grade highlights the clinical relevance of our approach. These findings suggest that our method could have substantial implications for improving prognostic assessments and personalizing therapeutic strategies in breast cancer treatment. |
| format | Article |
| id | doaj-art-59f3099e8df441218f880e51acde565b |
| institution | Kabale University |
| issn | 1465-542X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | Breast Cancer Research |
| spelling | doaj-art-59f3099e8df441218f880e51acde565b2025-02-09T13:00:44ZengBMCBreast Cancer Research1465-542X2025-02-0127111310.1186/s13058-024-01950-2Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentationTristan Whitmarsh0Wei Cope1Julia Carmona-Bozo2Roido Manavaki3Stephen-John Sammut4Ramona Woitek5Elena Provenzano6Emma L. Brown7Sarah E. Bohndiek8Ferdia A. Gallagher9Carlos Caldas10Fiona J. Gilbert11Florian Markowetz12Institute of Astronomy, University of CambridgeCambridge University Hospitals NHS Foundation TrustSchool of Medicine, University of California San FranciscoDepartment of Radiology, University of CambridgeBreast Cancer Now Toby Robins Research Centre, The Institute of Cancer ResearchDepartment of Radiology, University of CambridgeCambridge University Hospitals NHS Foundation TrustCancer Research UK Beatson Institute, University of GlasgowCancer Research UK Cambridge Institute, University of CambridgeDepartment of Radiology, University of CambridgeDepartment of Clinical Biochemistry, University of CambridgeDepartment of Radiology, University of CambridgeCancer Research UK Cambridge Institute, University of CambridgeAbstract Background Tumour vascular density assessed from CD-31 immunohistochemistry (IHC) images has previously been shown to have prognostic value in breast cancer. Current methods to measure vascular density, however, are time-consuming, suffer from high inter-observer variability and are limited in describing the complex tumour vasculature morphometry. Methods We propose a method for automatically measuring a range of vascular parameters from CD-31 IHC images, which together provide a detailed description of the vasculature morphology. We first used a U-Net based convolutional neural network, trained and validated using 36 partially annotated whole slide images from 27 patients, to segment vessel structures and tumour regions from which the measurements are taken. The model also segments the vascular smooth muscle, benign epithelium, adipose tissue, stroma, lymphocyte clusters, nerves and CD-31 positive leukocytes, and we applied it to an additional 21 images from 15 patients. Using these segmentations, we investigated the relationship between the various tissue types and the vasculature and studied the relationship of various vascular parameters with clinical parameters. We also performed a 3D histology analysis on a separate tumour sample as a proof of principle, providing a more comprehensive visualization of vasculature morphology compared to the standard 2D cross-section of a tissue sample. Results Using two-way cross-validation, we show that vessels were accurately segmented, with Dice scores of 0.875 and 0.856, and were accurately identified, with F1 scores of 0.777 and 0.748. All vascular parameters exhibit strong ( $$r>0.7$$ r > 0.7 ) and significant (p<0.001) correlations with measurements taken from the manual ground truth vessel segmentations. A significant relationship between the major/minor axis ratio, a measure of elongation, and the tumour grade was found. Conclusion Our proposed method shows promise as a tool for studying the tumour vasculature and its relationship with surrounding cells and tissue types. Furthermore, the correlation with tumour grade highlights the clinical relevance of our approach. These findings suggest that our method could have substantial implications for improving prognostic assessments and personalizing therapeutic strategies in breast cancer treatment.https://doi.org/10.1186/s13058-024-01950-2 |
| spellingShingle | Tristan Whitmarsh Wei Cope Julia Carmona-Bozo Roido Manavaki Stephen-John Sammut Ramona Woitek Elena Provenzano Emma L. Brown Sarah E. Bohndiek Ferdia A. Gallagher Carlos Caldas Fiona J. Gilbert Florian Markowetz Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation Breast Cancer Research |
| title | Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation |
| title_full | Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation |
| title_fullStr | Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation |
| title_full_unstemmed | Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation |
| title_short | Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation |
| title_sort | quantifying the tumour vasculature environment from cd 31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation |
| url | https://doi.org/10.1186/s13058-024-01950-2 |
| work_keys_str_mv | AT tristanwhitmarsh quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT weicope quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT juliacarmonabozo quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT roidomanavaki quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT stephenjohnsammut quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT ramonawoitek quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT elenaprovenzano quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT emmalbrown quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT sarahebohndiek quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT ferdiaagallagher quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT carloscaldas quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT fionajgilbert quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation AT florianmarkowetz quantifyingthetumourvasculatureenvironmentfromcd31immunohistochemistryimagesofbreastcancerusingdeeplearningbasedsemanticsegmentation |