Squamous Cell Carcinoma of Skin Cancer Margin Classification From Digital Histopathology Images Using Deep Learning
Objectives Now a days, squamous cell carcinoma (SCC) margin assessment is done by examining histopathology images and inspection of whole slide images (WSI) using a conventional microscope. This is time-consuming, tedious, and depends on experts’ experience which may lead to misdiagnosis and mistrea...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SAGE Publishing
2022-10-01
|
Series: | Cancer Control |
Online Access: | https://doi.org/10.1177/10732748221132528 |
_version_ | 1797838515745062912 |
---|---|
author | Beshatu Debela Wako Kokeb Dese Roba Elala Ulfata Tilahun Alemayehu Nigatu Solomon Kebede Turunbedu Timothy Kwa |
author_facet | Beshatu Debela Wako Kokeb Dese Roba Elala Ulfata Tilahun Alemayehu Nigatu Solomon Kebede Turunbedu Timothy Kwa |
author_sort | Beshatu Debela Wako |
collection | DOAJ |
description | Objectives Now a days, squamous cell carcinoma (SCC) margin assessment is done by examining histopathology images and inspection of whole slide images (WSI) using a conventional microscope. This is time-consuming, tedious, and depends on experts’ experience which may lead to misdiagnosis and mistreatment plans. This study aims to develop a system for the automatic diagnosis of skin cancer margin for squamous cell carcinoma from histopathology microscopic images by applying deep learning techniques. Methods The system was trained, validated, and tested using histopathology images of SCC cancer locally acquired from Jimma Medical Center Pathology Department from seven different skin sites using an Olympus digital microscope. All images were preprocessed and trained with transfer learning pre-trained models by fine-tuning the hyper-parameter of the selected models. Results The overall best training accuracy of the models become 95.3%, 97.1%, 89.8%, and 89.9% on EffecientNetB0, MobileNetv2, ResNet50, VGG16 respectively. In addition to this, the best validation accuracy of the models was 94.7%, 91.8%, 87.8%, and 86.7% respectively. The best testing accuracy of the models at the same epoch was 95.2%, 91.5%, 87%, and 85.5% respectively. From these models, EfficientNetB0 showed the best average training and testing accuracy than the other models. Conclusions The system assists the pathologist during the margin assessment of SCC by decreasing the diagnosis time from an average of 25 minutes to less than a minute. |
first_indexed | 2024-04-09T15:42:07Z |
format | Article |
id | doaj.art-80ed4590020a4075b4f91a9cdb38a5e9 |
institution | Directory Open Access Journal |
issn | 1526-2359 |
language | English |
last_indexed | 2024-04-09T15:42:07Z |
publishDate | 2022-10-01 |
publisher | SAGE Publishing |
record_format | Article |
series | Cancer Control |
spelling | doaj.art-80ed4590020a4075b4f91a9cdb38a5e92023-04-27T07:34:34ZengSAGE PublishingCancer Control1526-23592022-10-012910.1177/10732748221132528Squamous Cell Carcinoma of Skin Cancer Margin Classification From Digital Histopathology Images Using Deep LearningBeshatu Debela WakoKokeb DeseRoba Elala UlfataTilahun Alemayehu NigatuSolomon Kebede TurunbeduTimothy KwaObjectives Now a days, squamous cell carcinoma (SCC) margin assessment is done by examining histopathology images and inspection of whole slide images (WSI) using a conventional microscope. This is time-consuming, tedious, and depends on experts’ experience which may lead to misdiagnosis and mistreatment plans. This study aims to develop a system for the automatic diagnosis of skin cancer margin for squamous cell carcinoma from histopathology microscopic images by applying deep learning techniques. Methods The system was trained, validated, and tested using histopathology images of SCC cancer locally acquired from Jimma Medical Center Pathology Department from seven different skin sites using an Olympus digital microscope. All images were preprocessed and trained with transfer learning pre-trained models by fine-tuning the hyper-parameter of the selected models. Results The overall best training accuracy of the models become 95.3%, 97.1%, 89.8%, and 89.9% on EffecientNetB0, MobileNetv2, ResNet50, VGG16 respectively. In addition to this, the best validation accuracy of the models was 94.7%, 91.8%, 87.8%, and 86.7% respectively. The best testing accuracy of the models at the same epoch was 95.2%, 91.5%, 87%, and 85.5% respectively. From these models, EfficientNetB0 showed the best average training and testing accuracy than the other models. Conclusions The system assists the pathologist during the margin assessment of SCC by decreasing the diagnosis time from an average of 25 minutes to less than a minute.https://doi.org/10.1177/10732748221132528 |
spellingShingle | Beshatu Debela Wako Kokeb Dese Roba Elala Ulfata Tilahun Alemayehu Nigatu Solomon Kebede Turunbedu Timothy Kwa Squamous Cell Carcinoma of Skin Cancer Margin Classification From Digital Histopathology Images Using Deep Learning Cancer Control |
title | Squamous Cell Carcinoma of Skin Cancer Margin Classification From Digital Histopathology Images Using Deep Learning |
title_full | Squamous Cell Carcinoma of Skin Cancer Margin Classification From Digital Histopathology Images Using Deep Learning |
title_fullStr | Squamous Cell Carcinoma of Skin Cancer Margin Classification From Digital Histopathology Images Using Deep Learning |
title_full_unstemmed | Squamous Cell Carcinoma of Skin Cancer Margin Classification From Digital Histopathology Images Using Deep Learning |
title_short | Squamous Cell Carcinoma of Skin Cancer Margin Classification From Digital Histopathology Images Using Deep Learning |
title_sort | squamous cell carcinoma of skin cancer margin classification from digital histopathology images using deep learning |
url | https://doi.org/10.1177/10732748221132528 |
work_keys_str_mv | AT beshatudebelawako squamouscellcarcinomaofskincancermarginclassificationfromdigitalhistopathologyimagesusingdeeplearning AT kokebdese squamouscellcarcinomaofskincancermarginclassificationfromdigitalhistopathologyimagesusingdeeplearning AT robaelalaulfata squamouscellcarcinomaofskincancermarginclassificationfromdigitalhistopathologyimagesusingdeeplearning AT tilahunalemayehunigatu squamouscellcarcinomaofskincancermarginclassificationfromdigitalhistopathologyimagesusingdeeplearning AT solomonkebedeturunbedu squamouscellcarcinomaofskincancermarginclassificationfromdigitalhistopathologyimagesusingdeeplearning AT timothykwa squamouscellcarcinomaofskincancermarginclassificationfromdigitalhistopathologyimagesusingdeeplearning |