A pyramidal deep learning pipeline for kidney whole-slide histology images classification
Abstract Renal cell carcinoma is the most common type of kidney cancer. There are several subtypes of renal cell carcinoma with distinct clinicopathologic features. Among the subtypes, clear cell renal cell carcinoma is the most common and tends to portend poor prognosis. In contrast, clear cell pap...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-99735-6 |
| _version_ | 1818355733004025856 |
|---|---|
| author | Hisham Abdeltawab Fahmi Khalifa Mohammed Mohammed Liang Cheng Dibson Gondim Ayman El-Baz |
| author_facet | Hisham Abdeltawab Fahmi Khalifa Mohammed Mohammed Liang Cheng Dibson Gondim Ayman El-Baz |
| author_sort | Hisham Abdeltawab |
| collection | DOAJ |
| description | Abstract Renal cell carcinoma is the most common type of kidney cancer. There are several subtypes of renal cell carcinoma with distinct clinicopathologic features. Among the subtypes, clear cell renal cell carcinoma is the most common and tends to portend poor prognosis. In contrast, clear cell papillary renal cell carcinoma has an excellent prognosis. These two subtypes are primarily classified based on the histopathologic features. However, a subset of cases can a have a significant degree of histopathologic overlap. In cases with ambiguous histologic features, the correct diagnosis is dependent on the pathologist’s experience and usage of immunohistochemistry. We propose a new method to address this diagnostic task based on a deep learning pipeline for automated classification. The model can detect tumor and non-tumoral portions of kidney and classify the tumor as either clear cell renal cell carcinoma or clear cell papillary renal cell carcinoma. Our framework consists of three convolutional neural networks and the whole slide images of kidney which were divided into patches of three different sizes for input into the networks. Our approach can provide patchwise and pixelwise classification. The kidney histology images consist of 64 whole slide images. Our framework results in an image map that classifies the slide image on the pixel-level. Furthermore, we applied generalized Gauss-Markov random field smoothing to maintain consistency in the map. Our approach classified the four classes accurately and surpassed other state-of-the-art methods, such as ResNet (pixel accuracy: 0.89 Resnet18, 0.92 proposed). We conclude that deep learning has the potential to augment the pathologist’s capabilities by providing automated classification for histopathological images. |
| first_indexed | 2024-12-13T19:46:00Z |
| format | Article |
| id | doaj.art-4955218ae3964c98aacf4f6bf0a13252 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-13T19:46:00Z |
| publishDate | 2021-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-4955218ae3964c98aacf4f6bf0a132522022-12-21T23:33:33ZengNature PortfolioScientific Reports2045-23222021-10-011111910.1038/s41598-021-99735-6A pyramidal deep learning pipeline for kidney whole-slide histology images classificationHisham Abdeltawab0Fahmi Khalifa1Mohammed Mohammed2Liang Cheng3Dibson Gondim4Ayman El-Baz5Bioengineering Department, University of LouisvilleBioengineering Department, University of LouisvilleBioengineering Department, University of LouisvilleDepartment of Pathology, Indiana University School of MedicineDepartment of Pathology and Laboratory Medicine, University of LouisvilleBioengineering Department, University of LouisvilleAbstract Renal cell carcinoma is the most common type of kidney cancer. There are several subtypes of renal cell carcinoma with distinct clinicopathologic features. Among the subtypes, clear cell renal cell carcinoma is the most common and tends to portend poor prognosis. In contrast, clear cell papillary renal cell carcinoma has an excellent prognosis. These two subtypes are primarily classified based on the histopathologic features. However, a subset of cases can a have a significant degree of histopathologic overlap. In cases with ambiguous histologic features, the correct diagnosis is dependent on the pathologist’s experience and usage of immunohistochemistry. We propose a new method to address this diagnostic task based on a deep learning pipeline for automated classification. The model can detect tumor and non-tumoral portions of kidney and classify the tumor as either clear cell renal cell carcinoma or clear cell papillary renal cell carcinoma. Our framework consists of three convolutional neural networks and the whole slide images of kidney which were divided into patches of three different sizes for input into the networks. Our approach can provide patchwise and pixelwise classification. The kidney histology images consist of 64 whole slide images. Our framework results in an image map that classifies the slide image on the pixel-level. Furthermore, we applied generalized Gauss-Markov random field smoothing to maintain consistency in the map. Our approach classified the four classes accurately and surpassed other state-of-the-art methods, such as ResNet (pixel accuracy: 0.89 Resnet18, 0.92 proposed). We conclude that deep learning has the potential to augment the pathologist’s capabilities by providing automated classification for histopathological images.https://doi.org/10.1038/s41598-021-99735-6 |
| spellingShingle | Hisham Abdeltawab Fahmi Khalifa Mohammed Mohammed Liang Cheng Dibson Gondim Ayman El-Baz A pyramidal deep learning pipeline for kidney whole-slide histology images classification Scientific Reports |
| title | A pyramidal deep learning pipeline for kidney whole-slide histology images classification |
| title_full | A pyramidal deep learning pipeline for kidney whole-slide histology images classification |
| title_fullStr | A pyramidal deep learning pipeline for kidney whole-slide histology images classification |
| title_full_unstemmed | A pyramidal deep learning pipeline for kidney whole-slide histology images classification |
| title_short | A pyramidal deep learning pipeline for kidney whole-slide histology images classification |
| title_sort | pyramidal deep learning pipeline for kidney whole slide histology images classification |
| url | https://doi.org/10.1038/s41598-021-99735-6 |
| work_keys_str_mv | AT hishamabdeltawab apyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT fahmikhalifa apyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT mohammedmohammed apyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT liangcheng apyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT dibsongondim apyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT aymanelbaz apyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT hishamabdeltawab pyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT fahmikhalifa pyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT mohammedmohammed pyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT liangcheng pyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT dibsongondim pyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification AT aymanelbaz pyramidaldeeplearningpipelineforkidneywholeslidehistologyimagesclassification |