Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide Images
Ki67 hot-spot detection and its evaluation in invasive breast cancer regions play a significant role in routine medical practice. The quantification of cellular proliferation assessed by Ki67 immunohistochemistry is an established prognostic and predictive biomarker that determines the choice of the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/21/7761 |
| _version_ | 1797549045572435968 |
|---|---|
| author | Zaneta Swiderska-Chadaj Jaime Gallego Lucia Gonzalez-Lopez Gloria Bueno |
| author_facet | Zaneta Swiderska-Chadaj Jaime Gallego Lucia Gonzalez-Lopez Gloria Bueno |
| author_sort | Zaneta Swiderska-Chadaj |
| collection | DOAJ |
| description | Ki67 hot-spot detection and its evaluation in invasive breast cancer regions play a significant role in routine medical practice. The quantification of cellular proliferation assessed by Ki67 immunohistochemistry is an established prognostic and predictive biomarker that determines the choice of therapeutic protocols. In this paper, we present three deep learning-based approaches to automatically detect and quantify Ki67 hot-spot areas by means of the Ki67 labeling index. To this end, a dataset composed of 100 whole slide images (WSIs) belonging to 50 breast cancer cases (Ki67 and H&E WSI pairs) was used. Three methods based on CNN classification were proposed and compared to create the tumor proliferation map. The best results were obtained by applying the CNN to the mutual information acquired from the color deconvolution of both the Ki67 marker and the H&E WSIs. The overall accuracy of this approach was 95%. The agreement between the automatic Ki67 scoring and the manual analysis is promising with a Spearman’s <inline-formula><math display="inline"><semantics><mi>ρ</mi></semantics></math></inline-formula> correlation of 0.92. The results illustrate the suitability of this CNN-based approach for detecting hot-spots areas of invasive breast cancer in WSI. |
| first_indexed | 2024-03-10T15:08:06Z |
| format | Article |
| id | doaj.art-764b6b6af7694a9fb81355a07234a8c4 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:08:06Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-764b6b6af7694a9fb81355a07234a8c42023-11-20T19:32:42ZengMDPI AGApplied Sciences2076-34172020-11-011021776110.3390/app10217761Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide ImagesZaneta Swiderska-Chadaj0Jaime Gallego1Lucia Gonzalez-Lopez2Gloria Bueno3Faculty of Electrical Engineering, Warsaw University of Technology, 00-662 Warsaw, PolandVISILAB, University of Castilla-La Mancha, Av. Camilo José Cela s/n, 13071 Ciudad Real, SpainHospital General Universitario de Ciudad Real, 13005 Ciudad Real, SpainVISILAB, University of Castilla-La Mancha, Av. Camilo José Cela s/n, 13071 Ciudad Real, SpainKi67 hot-spot detection and its evaluation in invasive breast cancer regions play a significant role in routine medical practice. The quantification of cellular proliferation assessed by Ki67 immunohistochemistry is an established prognostic and predictive biomarker that determines the choice of therapeutic protocols. In this paper, we present three deep learning-based approaches to automatically detect and quantify Ki67 hot-spot areas by means of the Ki67 labeling index. To this end, a dataset composed of 100 whole slide images (WSIs) belonging to 50 breast cancer cases (Ki67 and H&E WSI pairs) was used. Three methods based on CNN classification were proposed and compared to create the tumor proliferation map. The best results were obtained by applying the CNN to the mutual information acquired from the color deconvolution of both the Ki67 marker and the H&E WSIs. The overall accuracy of this approach was 95%. The agreement between the automatic Ki67 scoring and the manual analysis is promising with a Spearman’s <inline-formula><math display="inline"><semantics><mi>ρ</mi></semantics></math></inline-formula> correlation of 0.92. The results illustrate the suitability of this CNN-based approach for detecting hot-spots areas of invasive breast cancer in WSI.https://www.mdpi.com/2076-3417/10/21/7761Ki67 hot-spot detectionKi67 labeling indexproliferation indexCNNscolor deconvolutionWSI |
| spellingShingle | Zaneta Swiderska-Chadaj Jaime Gallego Lucia Gonzalez-Lopez Gloria Bueno Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide Images Applied Sciences Ki67 hot-spot detection Ki67 labeling index proliferation index CNNs color deconvolution WSI |
| title | Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide Images |
| title_full | Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide Images |
| title_fullStr | Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide Images |
| title_full_unstemmed | Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide Images |
| title_short | Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide Images |
| title_sort | detection of ki67 hot spots of invasive breast cancer based on convolutional neural networks applied to mutual information of h e and ki67 whole slide images |
| topic | Ki67 hot-spot detection Ki67 labeling index proliferation index CNNs color deconvolution WSI |
| url | https://www.mdpi.com/2076-3417/10/21/7761 |
| work_keys_str_mv | AT zanetaswiderskachadaj detectionofki67hotspotsofinvasivebreastcancerbasedonconvolutionalneuralnetworksappliedtomutualinformationofheandki67wholeslideimages AT jaimegallego detectionofki67hotspotsofinvasivebreastcancerbasedonconvolutionalneuralnetworksappliedtomutualinformationofheandki67wholeslideimages AT luciagonzalezlopez detectionofki67hotspotsofinvasivebreastcancerbasedonconvolutionalneuralnetworksappliedtomutualinformationofheandki67wholeslideimages AT gloriabueno detectionofki67hotspotsofinvasivebreastcancerbasedonconvolutionalneuralnetworksappliedtomutualinformationofheandki67wholeslideimages |