Deep learning approach with ConvNeXt-SE-attn model for in vitro oral squamous cell carcinoma and chemotherapy analysis
Oral squamous cell carcinoma (OSCC) continues to present a major worldwide healthcare problem because patients have poor survival outcomes alongside frequent disease returns. Globocan predicts that, OSCC will result in 389,846 new cases and 188,438 deaths globally during 2022 while maintaining an ex...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | MethodsX |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215016125003632 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849254579230736384 |
|---|---|
| author | Abhay Nath Om Roy Priyanka Silveri Sanskruti Patel |
| author_facet | Abhay Nath Om Roy Priyanka Silveri Sanskruti Patel |
| author_sort | Abhay Nath |
| collection | DOAJ |
| description | Oral squamous cell carcinoma (OSCC) continues to present a major worldwide healthcare problem because patients have poor survival outcomes alongside frequent disease returns. Globocan predicts that, OSCC will result in 389,846 new cases and 188,438 deaths globally during 2022 while maintaining an extremely poor 5-year survival rate at about 50%. Our method applies residual connections with Squeeze-and-Excitation blocks along with hybrid attention systems and enhanced activation functions and optimization algorithms to boost gradient movement throughout feature extraction. Compared against established conventional CNN backbones (VGG16, ResNet50, DenseNet121, and more), the proposed ConvNeXt-SE-Attn model outperformed them in all aspects of discrimination and calibration, including precision 97.88% (vs. ≤94.2%), sensitivity 96.82% (vs. ≤92.5%), specificity 95.94% (vs. ≤93.1%), F1 score 97.31% (vs. ≤93.8%), AUC 0.9644 (vs. ≤0.945), and MCC 0.9397 (vs. ≤0.910). The findings are critical to the increased feature-representation power and the robustness of classification of the architecture.The proposed architecture employs ConvNeXt backbone with SE blocks and hybrid attention to extract essential details within class boundaries which standard models usually miss.The activation through Gaussian-based GReLU incorporates Swish activation together with DropPath regularization for producing smooth gradient patterns which lead to generalizable features across imbalanced datasets.Grad-CAM enhances interpretability by showing which image sections lead to predictions in order to enable clinical decisions.The model demonstrates its capability as an effective detection method for minimal variations in oral cells which supports precise non-invasive treatment approaches for OSCC. |
| format | Article |
| id | doaj-art-79a453ddef4745be844fb7ffa97fb236 |
| institution | Kabale University |
| issn | 2215-0161 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | MethodsX |
| spelling | doaj-art-79a453ddef4745be844fb7ffa97fb2362025-08-20T03:56:04ZengElsevierMethodsX2215-01612025-12-011510351910.1016/j.mex.2025.103519Deep learning approach with ConvNeXt-SE-attn model for in vitro oral squamous cell carcinoma and chemotherapy analysisAbhay Nath0Om Roy1Priyanka Silveri2Sanskruti Patel3Department of Information Technology, Devang Patel Institute of Advance Technology and Research, Charotar University of Science and Technology, CHARUSAT Campus, Anand 388421, Gujarat, IndiaDepartment of Information Technology, Smt. Kundanben Dinsha Patel Department of Information Technology, Charotar University of Science and Technology, CHARUSAT Campus, Anand 388421, Gujarat, IndiaDepartment of Electrical and Computer Engineering, College of Engineering Drexel University, Philadelphia, PA, USASmt. Chandaben Mohanbhai Patel Institute of Computer Applications, Charotar University of Science and Technology (CHARUSAT), Changa, 388421, Gujarat, India; Corresponding author.Oral squamous cell carcinoma (OSCC) continues to present a major worldwide healthcare problem because patients have poor survival outcomes alongside frequent disease returns. Globocan predicts that, OSCC will result in 389,846 new cases and 188,438 deaths globally during 2022 while maintaining an extremely poor 5-year survival rate at about 50%. Our method applies residual connections with Squeeze-and-Excitation blocks along with hybrid attention systems and enhanced activation functions and optimization algorithms to boost gradient movement throughout feature extraction. Compared against established conventional CNN backbones (VGG16, ResNet50, DenseNet121, and more), the proposed ConvNeXt-SE-Attn model outperformed them in all aspects of discrimination and calibration, including precision 97.88% (vs. ≤94.2%), sensitivity 96.82% (vs. ≤92.5%), specificity 95.94% (vs. ≤93.1%), F1 score 97.31% (vs. ≤93.8%), AUC 0.9644 (vs. ≤0.945), and MCC 0.9397 (vs. ≤0.910). The findings are critical to the increased feature-representation power and the robustness of classification of the architecture.The proposed architecture employs ConvNeXt backbone with SE blocks and hybrid attention to extract essential details within class boundaries which standard models usually miss.The activation through Gaussian-based GReLU incorporates Swish activation together with DropPath regularization for producing smooth gradient patterns which lead to generalizable features across imbalanced datasets.Grad-CAM enhances interpretability by showing which image sections lead to predictions in order to enable clinical decisions.The model demonstrates its capability as an effective detection method for minimal variations in oral cells which supports precise non-invasive treatment approaches for OSCC.http://www.sciencedirect.com/science/article/pii/S2215016125003632Oral Squamous Cell Carcinoma (OSCC)ConvNeXtGrad-CAMSqueeze-and-Excitation BlocksAttention mechanismsDeep learning |
| spellingShingle | Abhay Nath Om Roy Priyanka Silveri Sanskruti Patel Deep learning approach with ConvNeXt-SE-attn model for in vitro oral squamous cell carcinoma and chemotherapy analysis MethodsX Oral Squamous Cell Carcinoma (OSCC) ConvNeXt Grad-CAM Squeeze-and-Excitation Blocks Attention mechanisms Deep learning |
| title | Deep learning approach with ConvNeXt-SE-attn model for in vitro oral squamous cell carcinoma and chemotherapy analysis |
| title_full | Deep learning approach with ConvNeXt-SE-attn model for in vitro oral squamous cell carcinoma and chemotherapy analysis |
| title_fullStr | Deep learning approach with ConvNeXt-SE-attn model for in vitro oral squamous cell carcinoma and chemotherapy analysis |
| title_full_unstemmed | Deep learning approach with ConvNeXt-SE-attn model for in vitro oral squamous cell carcinoma and chemotherapy analysis |
| title_short | Deep learning approach with ConvNeXt-SE-attn model for in vitro oral squamous cell carcinoma and chemotherapy analysis |
| title_sort | deep learning approach with convnext se attn model for in vitro oral squamous cell carcinoma and chemotherapy analysis |
| topic | Oral Squamous Cell Carcinoma (OSCC) ConvNeXt Grad-CAM Squeeze-and-Excitation Blocks Attention mechanisms Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2215016125003632 |
| work_keys_str_mv | AT abhaynath deeplearningapproachwithconvnextseattnmodelforinvitrooralsquamouscellcarcinomaandchemotherapyanalysis AT omroy deeplearningapproachwithconvnextseattnmodelforinvitrooralsquamouscellcarcinomaandchemotherapyanalysis AT priyankasilveri deeplearningapproachwithconvnextseattnmodelforinvitrooralsquamouscellcarcinomaandchemotherapyanalysis AT sanskrutipatel deeplearningapproachwithconvnextseattnmodelforinvitrooralsquamouscellcarcinomaandchemotherapyanalysis |