Image analysis of diabetes pathology: classifying with precision via an upgraded resnet50 framework
Diabetes is a growing global health issue, and effective diagnostic tools are needed to support early detection. This study proposes an enhanced deep learning framework, SE-ResNet50, which integrates a squeeze-and-excitation (SE) block into the conventional ResNet50 architecture to improve the class...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Medicine in Novel Technology and Devices |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590093525000360 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839633601235255296 |
|---|---|
| author | Caisheng Liao Chenhao Pu Tianqi Chen Yuki Todo Kengo Furuichi Tomohisa Yabe DeLai Qiu |
| author_facet | Caisheng Liao Chenhao Pu Tianqi Chen Yuki Todo Kengo Furuichi Tomohisa Yabe DeLai Qiu |
| author_sort | Caisheng Liao |
| collection | DOAJ |
| description | Diabetes is a growing global health issue, and effective diagnostic tools are needed to support early detection. This study proposes an enhanced deep learning framework, SE-ResNet50, which integrates a squeeze-and-excitation (SE) block into the conventional ResNet50 architecture to improve the classification of diabetic kidney pathology from glomerular images. The SE block adaptively recalibrates feature responses, enabling the model to emphasize diagnostically relevant structures better. The proposed framework was trained and validated on a kidney tissue dataset from Kanazawa Medical University, achieving superior performance with an accuracy of 97.02 %, precision of 0.96, and an AUC of 0.9856. SE-ResNet50 exhibited superior robustness and generalizability compared to established CNN architectures such as EfficientNet B0, Inception V3, and ConvNeXt. Further visualization via Grad-CAM revealed that the model effectively localizes critical regions within glomerular images. These results highlight the potential of SE-ResNet50 as a reliable and interpretable tool for advancing diabetes-related CKD diagnosis in clinical settings. |
| format | Article |
| id | doaj-art-fd0ca14ba7cc46e5a8707259a2bc0d12 |
| institution | Matheson Library |
| issn | 2590-0935 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Medicine in Novel Technology and Devices |
| spelling | doaj-art-fd0ca14ba7cc46e5a8707259a2bc0d122025-07-11T04:31:36ZengElsevierMedicine in Novel Technology and Devices2590-09352025-09-0127100385Image analysis of diabetes pathology: classifying with precision via an upgraded resnet50 frameworkCaisheng Liao0Chenhao Pu1Tianqi Chen2Yuki Todo3Kengo Furuichi4Tomohisa Yabe5DeLai Qiu6Division of Electrical, Information and Communication Engineering, Kanazawa University, Kakuma-machi, Kanazawa, 920-1192, JapanDivision of Electrical, Information and Communication Engineering, Kanazawa University, Kakuma-machi, Kanazawa, 920-1192, JapanDivision of Electrical, Information and Communication Engineering, Kanazawa University, Kakuma-machi, Kanazawa, 920-1192, JapanFaculty of Electrical, Information and Communication Engineering, Kanazawa University, Kanazawa, Ishikawa, 920-1192, Japan; Corresponding author.Department of Nephrology, Kanazawa Medical University, 1-1 Daigaku, Uchinada, Kahoku-gun, Ishikawa, 920-0293, Japan; Corresponding author.Department of Nephrology, Kanazawa Medical University, 1-1 Daigaku, Uchinada, Kahoku-gun, Ishikawa, 920-0293, JapanBrain Science Institute, Jilin Medical College, 5 Jilin Street, Jilin, 132013, ChinaDiabetes is a growing global health issue, and effective diagnostic tools are needed to support early detection. This study proposes an enhanced deep learning framework, SE-ResNet50, which integrates a squeeze-and-excitation (SE) block into the conventional ResNet50 architecture to improve the classification of diabetic kidney pathology from glomerular images. The SE block adaptively recalibrates feature responses, enabling the model to emphasize diagnostically relevant structures better. The proposed framework was trained and validated on a kidney tissue dataset from Kanazawa Medical University, achieving superior performance with an accuracy of 97.02 %, precision of 0.96, and an AUC of 0.9856. SE-ResNet50 exhibited superior robustness and generalizability compared to established CNN architectures such as EfficientNet B0, Inception V3, and ConvNeXt. Further visualization via Grad-CAM revealed that the model effectively localizes critical regions within glomerular images. These results highlight the potential of SE-ResNet50 as a reliable and interpretable tool for advancing diabetes-related CKD diagnosis in clinical settings.http://www.sciencedirect.com/science/article/pii/S2590093525000360Diabetes diagnosisResNet50Kidney tissueDeep learningGlomerular images |
| spellingShingle | Caisheng Liao Chenhao Pu Tianqi Chen Yuki Todo Kengo Furuichi Tomohisa Yabe DeLai Qiu Image analysis of diabetes pathology: classifying with precision via an upgraded resnet50 framework Medicine in Novel Technology and Devices Diabetes diagnosis ResNet50 Kidney tissue Deep learning Glomerular images |
| title | Image analysis of diabetes pathology: classifying with precision via an upgraded resnet50 framework |
| title_full | Image analysis of diabetes pathology: classifying with precision via an upgraded resnet50 framework |
| title_fullStr | Image analysis of diabetes pathology: classifying with precision via an upgraded resnet50 framework |
| title_full_unstemmed | Image analysis of diabetes pathology: classifying with precision via an upgraded resnet50 framework |
| title_short | Image analysis of diabetes pathology: classifying with precision via an upgraded resnet50 framework |
| title_sort | image analysis of diabetes pathology classifying with precision via an upgraded resnet50 framework |
| topic | Diabetes diagnosis ResNet50 Kidney tissue Deep learning Glomerular images |
| url | http://www.sciencedirect.com/science/article/pii/S2590093525000360 |
| work_keys_str_mv | AT caishengliao imageanalysisofdiabetespathologyclassifyingwithprecisionviaanupgradedresnet50framework AT chenhaopu imageanalysisofdiabetespathologyclassifyingwithprecisionviaanupgradedresnet50framework AT tianqichen imageanalysisofdiabetespathologyclassifyingwithprecisionviaanupgradedresnet50framework AT yukitodo imageanalysisofdiabetespathologyclassifyingwithprecisionviaanupgradedresnet50framework AT kengofuruichi imageanalysisofdiabetespathologyclassifyingwithprecisionviaanupgradedresnet50framework AT tomohisayabe imageanalysisofdiabetespathologyclassifyingwithprecisionviaanupgradedresnet50framework AT delaiqiu imageanalysisofdiabetespathologyclassifyingwithprecisionviaanupgradedresnet50framework |