Endoscopic Image Classification Based on Explainable Deep Learning
Deep learning has achieved remarkably positive results and impacts on medical diagnostics in recent years. Due to its use in several proposals, deep learning has reached sufficient accuracy to implement; however, the algorithms are black boxes that are hard to understand, and model decisions are oft...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/6/3176 |
| _version_ | 1797609096249081856 |
|---|---|
| author | Doniyorjon Mukhtorov Madinakhon Rakhmonova Shakhnoza Muksimova Young-Im Cho |
| author_facet | Doniyorjon Mukhtorov Madinakhon Rakhmonova Shakhnoza Muksimova Young-Im Cho |
| author_sort | Doniyorjon Mukhtorov |
| collection | DOAJ |
| description | Deep learning has achieved remarkably positive results and impacts on medical diagnostics in recent years. Due to its use in several proposals, deep learning has reached sufficient accuracy to implement; however, the algorithms are black boxes that are hard to understand, and model decisions are often made without reason or explanation. To reduce this gap, explainable artificial intelligence (XAI) offers a huge opportunity to receive informed decision support from deep learning models and opens the black box of the method. We conducted an explainable deep learning method based on ResNet152 combined with Grad–CAM for endoscopy image classification. We used an open-source KVASIR dataset that consisted of a total of 8000 wireless capsule images. The heat map of the classification results and an efficient augmentation method achieved a high positive result with 98.28% training and 93.46% validation accuracy in terms of medical image classification. |
| first_indexed | 2024-03-11T05:55:46Z |
| format | Article |
| id | doaj.art-e20618f0f70e4d9bb416a88c7eec056b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:55:46Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e20618f0f70e4d9bb416a88c7eec056b2023-11-17T13:47:02ZengMDPI AGSensors1424-82202023-03-01236317610.3390/s23063176Endoscopic Image Classification Based on Explainable Deep LearningDoniyorjon Mukhtorov0Madinakhon Rakhmonova1Shakhnoza Muksimova2Young-Im Cho3Department of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si 461-701, Republic of KoreaDepartment of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si 461-701, Republic of KoreaDepartment of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si 461-701, Republic of KoreaDepartment of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si 461-701, Republic of KoreaDeep learning has achieved remarkably positive results and impacts on medical diagnostics in recent years. Due to its use in several proposals, deep learning has reached sufficient accuracy to implement; however, the algorithms are black boxes that are hard to understand, and model decisions are often made without reason or explanation. To reduce this gap, explainable artificial intelligence (XAI) offers a huge opportunity to receive informed decision support from deep learning models and opens the black box of the method. We conducted an explainable deep learning method based on ResNet152 combined with Grad–CAM for endoscopy image classification. We used an open-source KVASIR dataset that consisted of a total of 8000 wireless capsule images. The heat map of the classification results and an efficient augmentation method achieved a high positive result with 98.28% training and 93.46% validation accuracy in terms of medical image classification.https://www.mdpi.com/1424-8220/23/6/3176explainable aideep learningclassificationendoscopic image |
| spellingShingle | Doniyorjon Mukhtorov Madinakhon Rakhmonova Shakhnoza Muksimova Young-Im Cho Endoscopic Image Classification Based on Explainable Deep Learning Sensors explainable ai deep learning classification endoscopic image |
| title | Endoscopic Image Classification Based on Explainable Deep Learning |
| title_full | Endoscopic Image Classification Based on Explainable Deep Learning |
| title_fullStr | Endoscopic Image Classification Based on Explainable Deep Learning |
| title_full_unstemmed | Endoscopic Image Classification Based on Explainable Deep Learning |
| title_short | Endoscopic Image Classification Based on Explainable Deep Learning |
| title_sort | endoscopic image classification based on explainable deep learning |
| topic | explainable ai deep learning classification endoscopic image |
| url | https://www.mdpi.com/1424-8220/23/6/3176 |
| work_keys_str_mv | AT doniyorjonmukhtorov endoscopicimageclassificationbasedonexplainabledeeplearning AT madinakhonrakhmonova endoscopicimageclassificationbasedonexplainabledeeplearning AT shakhnozamuksimova endoscopicimageclassificationbasedonexplainabledeeplearning AT youngimcho endoscopicimageclassificationbasedonexplainabledeeplearning |