Deep Neural Networks for HER2 Grading of Whole Slide Images with Subclasses Levels
HER2 overexpression is a prognostic and predictive factor observed in about 15% to 20% of breast cancer cases. The assessment of its expression directly affects the selection of treatment and prognosis. The measurement of HER2 status is performed by an expert pathologist who assigns a score of 0, 1,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/17/3/97 |
| _version_ | 1797242344704049152 |
|---|---|
| author | Anibal Pedraza Lucia Gonzalez Oscar Deniz Gloria Bueno |
| author_facet | Anibal Pedraza Lucia Gonzalez Oscar Deniz Gloria Bueno |
| author_sort | Anibal Pedraza |
| collection | DOAJ |
| description | HER2 overexpression is a prognostic and predictive factor observed in about 15% to 20% of breast cancer cases. The assessment of its expression directly affects the selection of treatment and prognosis. The measurement of HER2 status is performed by an expert pathologist who assigns a score of 0, 1, 2+, or 3+ based on the gene expression. There is a high probability of interobserver variability in this evaluation, especially when it comes to class 2+. This is reasonable as the primary cause of error in multiclass classification problems typically arises in the intermediate classes. This work proposes a novel approach to expand the decision limit and divide it into two additional classes, that is 1.5+ and 2.5+. This subdivision facilitates both feature learning and pathology assessment. The method was evaluated using various neural networks models capable of performing patch-wise grading of HER2 whole slide images (WSI). Then, the outcomes of the 7-class classification were merged back into 5 classes in accordance with the pathologists’ criteria and to compare the results with the initial 5-class model. Optimal outcomes were achieved by employing colour transfer for data augmentation, and the ResNet-101 architecture with 7 classes. A sensitivity of 0.91 was achieved for class 2+ and 0.97 for 3+. Furthermore, this model offers the highest level of confidence, ranging from 92% to 94% for 2+ and 96% to 97% for 3+. In contrast, a dataset containing only 5 classes demonstrates a sensitivity performance that is 5% lower for the same network. |
| first_indexed | 2024-04-24T18:37:44Z |
| format | Article |
| id | doaj.art-6e0e74c891a340359652c1b4e0c21a12 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-04-24T18:37:44Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-6e0e74c891a340359652c1b4e0c21a122024-03-27T13:17:14ZengMDPI AGAlgorithms1999-48932024-02-011739710.3390/a17030097Deep Neural Networks for HER2 Grading of Whole Slide Images with Subclasses LevelsAnibal Pedraza0Lucia Gonzalez1Oscar Deniz2Gloria Bueno3VISILAB Group (Vision and Artificial Intelligence Group), Universidad de Castilla-La Mancha, ETSII, 13071 Ciudad Real, SpainHospital General Universitario de Ciudad Real, 13005 Ciudad Real, SpainVISILAB Group (Vision and Artificial Intelligence Group), Universidad de Castilla-La Mancha, ETSII, 13071 Ciudad Real, SpainVISILAB Group (Vision and Artificial Intelligence Group), Universidad de Castilla-La Mancha, ETSII, 13071 Ciudad Real, SpainHER2 overexpression is a prognostic and predictive factor observed in about 15% to 20% of breast cancer cases. The assessment of its expression directly affects the selection of treatment and prognosis. The measurement of HER2 status is performed by an expert pathologist who assigns a score of 0, 1, 2+, or 3+ based on the gene expression. There is a high probability of interobserver variability in this evaluation, especially when it comes to class 2+. This is reasonable as the primary cause of error in multiclass classification problems typically arises in the intermediate classes. This work proposes a novel approach to expand the decision limit and divide it into two additional classes, that is 1.5+ and 2.5+. This subdivision facilitates both feature learning and pathology assessment. The method was evaluated using various neural networks models capable of performing patch-wise grading of HER2 whole slide images (WSI). Then, the outcomes of the 7-class classification were merged back into 5 classes in accordance with the pathologists’ criteria and to compare the results with the initial 5-class model. Optimal outcomes were achieved by employing colour transfer for data augmentation, and the ResNet-101 architecture with 7 classes. A sensitivity of 0.91 was achieved for class 2+ and 0.97 for 3+. Furthermore, this model offers the highest level of confidence, ranging from 92% to 94% for 2+ and 96% to 97% for 3+. In contrast, a dataset containing only 5 classes demonstrates a sensitivity performance that is 5% lower for the same network.https://www.mdpi.com/1999-4893/17/3/97HER2 gradingwhole slide imagedeep learningsubclass levelbreast cancer |
| spellingShingle | Anibal Pedraza Lucia Gonzalez Oscar Deniz Gloria Bueno Deep Neural Networks for HER2 Grading of Whole Slide Images with Subclasses Levels Algorithms HER2 grading whole slide image deep learning subclass level breast cancer |
| title | Deep Neural Networks for HER2 Grading of Whole Slide Images with Subclasses Levels |
| title_full | Deep Neural Networks for HER2 Grading of Whole Slide Images with Subclasses Levels |
| title_fullStr | Deep Neural Networks for HER2 Grading of Whole Slide Images with Subclasses Levels |
| title_full_unstemmed | Deep Neural Networks for HER2 Grading of Whole Slide Images with Subclasses Levels |
| title_short | Deep Neural Networks for HER2 Grading of Whole Slide Images with Subclasses Levels |
| title_sort | deep neural networks for her2 grading of whole slide images with subclasses levels |
| topic | HER2 grading whole slide image deep learning subclass level breast cancer |
| url | https://www.mdpi.com/1999-4893/17/3/97 |
| work_keys_str_mv | AT anibalpedraza deepneuralnetworksforher2gradingofwholeslideimageswithsubclasseslevels AT luciagonzalez deepneuralnetworksforher2gradingofwholeslideimageswithsubclasseslevels AT oscardeniz deepneuralnetworksforher2gradingofwholeslideimageswithsubclasseslevels AT gloriabueno deepneuralnetworksforher2gradingofwholeslideimageswithsubclasseslevels |