Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architecture
Abstract Classifying medical images is essential in computer-aided diagnosis (CAD). Although the recent success of deep learning in the classification tasks has proven advantages over the traditional feature extraction techniques, it remains challenging due to the inter and intra-class similarity ca...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-93718-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850039610007093248 |
|---|---|
| author | Junaid Aftab Muhammad Attique Khan Sobia Arshad Shams ur Rehman Dina Abdulaziz AlHammadi Yunyoung Nam |
| author_facet | Junaid Aftab Muhammad Attique Khan Sobia Arshad Shams ur Rehman Dina Abdulaziz AlHammadi Yunyoung Nam |
| author_sort | Junaid Aftab |
| collection | DOAJ |
| description | Abstract Classifying medical images is essential in computer-aided diagnosis (CAD). Although the recent success of deep learning in the classification tasks has proven advantages over the traditional feature extraction techniques, it remains challenging due to the inter and intra-class similarity caused by the diversity of imaging modalities (i.e., dermoscopy, mammography, wireless capsule endoscopy, and CT). In this work, we proposed a novel deep-learning framework for classifying several medical imaging modalities. In the training phase of the deep learning models, data augmentation is performed at the first stage on all selected datasets. After that, two novel custom deep learning architectures were introduced, called the Inverted Residual Convolutional Neural Network (IRCNN) and Self Attention CNN (SACNN). Both models are trained on the augmented datasets with manual hyperparameter selection. Each dataset’s testing images are used to extract features during the testing stage. The extracted features are fused using a modified serial fusion with a strong correlation approach. An optimization algorithm- slap swarm controlled standard Error mean (SScSEM) has been employed, and the best features that passed to the shallow wide neural network (SWNN) classifier for the final classification have been selected. GradCAM, an explainable artificial intelligence (XAI) approach, analyzes custom models. The proposed architecture was tested on five publically available datasets of different imaging modalities and obtained improved accuracy of 98.6 (INBreast), 95.3 (KVASIR), 94.3 (ISIC2018), 95.0 (Lung Cancer), and 98.8% (Oral Cancer), respectively. A detailed comparison is conducted based on precision and accuracy, showing that the proposed architecture performs better. The implemented models are available on GitHub ( https://github.com/ComputerVisionLabPMU/ScientificImagingPaper.git ). |
| format | Article |
| id | doaj-art-f5b771c7a2db4e70a52f8b295b8ef17a |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-f5b771c7a2db4e70a52f8b295b8ef17a2025-08-20T02:56:16ZengNature PortfolioScientific Reports2045-23222025-03-0115112610.1038/s41598-025-93718-7Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architectureJunaid Aftab0Muhammad Attique Khan1Sobia Arshad2Shams ur Rehman3Dina Abdulaziz AlHammadi4Yunyoung Nam5Department of Computer Engineering, HITEC UniversityDepartment of Artificial Intelligence, College of Computer Engineering and Science, Prince Mohammad bin Fahd UniversityDepartment of Computer Engineering, HITEC UniversityDepartment of Computer Engineering, HITEC UniversityDepartment of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman UniversityDepartment of ICT Convergence, Soonchunhyang UniversityAbstract Classifying medical images is essential in computer-aided diagnosis (CAD). Although the recent success of deep learning in the classification tasks has proven advantages over the traditional feature extraction techniques, it remains challenging due to the inter and intra-class similarity caused by the diversity of imaging modalities (i.e., dermoscopy, mammography, wireless capsule endoscopy, and CT). In this work, we proposed a novel deep-learning framework for classifying several medical imaging modalities. In the training phase of the deep learning models, data augmentation is performed at the first stage on all selected datasets. After that, two novel custom deep learning architectures were introduced, called the Inverted Residual Convolutional Neural Network (IRCNN) and Self Attention CNN (SACNN). Both models are trained on the augmented datasets with manual hyperparameter selection. Each dataset’s testing images are used to extract features during the testing stage. The extracted features are fused using a modified serial fusion with a strong correlation approach. An optimization algorithm- slap swarm controlled standard Error mean (SScSEM) has been employed, and the best features that passed to the shallow wide neural network (SWNN) classifier for the final classification have been selected. GradCAM, an explainable artificial intelligence (XAI) approach, analyzes custom models. The proposed architecture was tested on five publically available datasets of different imaging modalities and obtained improved accuracy of 98.6 (INBreast), 95.3 (KVASIR), 94.3 (ISIC2018), 95.0 (Lung Cancer), and 98.8% (Oral Cancer), respectively. A detailed comparison is conducted based on precision and accuracy, showing that the proposed architecture performs better. The implemented models are available on GitHub ( https://github.com/ComputerVisionLabPMU/ScientificImagingPaper.git ).https://doi.org/10.1038/s41598-025-93718-7HealthcareMedical imagingDeep learningSelf attentionFusionPrediction |
| spellingShingle | Junaid Aftab Muhammad Attique Khan Sobia Arshad Shams ur Rehman Dina Abdulaziz AlHammadi Yunyoung Nam Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architecture Scientific Reports Healthcare Medical imaging Deep learning Self attention Fusion Prediction |
| title | Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architecture |
| title_full | Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architecture |
| title_fullStr | Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architecture |
| title_full_unstemmed | Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architecture |
| title_short | Artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self-attention deep neural network architecture |
| title_sort | artificial intelligence based classification and prediction of medical imaging using a novel framework of inverted and self attention deep neural network architecture |
| topic | Healthcare Medical imaging Deep learning Self attention Fusion Prediction |
| url | https://doi.org/10.1038/s41598-025-93718-7 |
| work_keys_str_mv | AT junaidaftab artificialintelligencebasedclassificationandpredictionofmedicalimagingusinganovelframeworkofinvertedandselfattentiondeepneuralnetworkarchitecture AT muhammadattiquekhan artificialintelligencebasedclassificationandpredictionofmedicalimagingusinganovelframeworkofinvertedandselfattentiondeepneuralnetworkarchitecture AT sobiaarshad artificialintelligencebasedclassificationandpredictionofmedicalimagingusinganovelframeworkofinvertedandselfattentiondeepneuralnetworkarchitecture AT shamsurrehman artificialintelligencebasedclassificationandpredictionofmedicalimagingusinganovelframeworkofinvertedandselfattentiondeepneuralnetworkarchitecture AT dinaabdulazizalhammadi artificialintelligencebasedclassificationandpredictionofmedicalimagingusinganovelframeworkofinvertedandselfattentiondeepneuralnetworkarchitecture AT yunyoungnam artificialintelligencebasedclassificationandpredictionofmedicalimagingusinganovelframeworkofinvertedandselfattentiondeepneuralnetworkarchitecture |