| Autor: |
Aziz MT; Centre for Advanced Machine Learning and Applications (CAMLAs), Bashundhara R/A, Dhaka 1229, Bangladesh., Mahmud SMH; Centre for Advanced Machine Learning and Applications (CAMLAs), Bashundhara R/A, Dhaka 1229, Bangladesh.; Department of Computer Science, American International University-Bangladesh (AIUB), 408/1, Kuratoli, Khilkhet, Dhaka 1229, Bangladesh., Elahe MF; Centre for Advanced Machine Learning and Applications (CAMLAs), Bashundhara R/A, Dhaka 1229, Bangladesh.; Department of Software Engineering, Daffodil International University, Daffodil Smart City (DSC), Savar, Dhaka 1216, Bangladesh., Jahan H; Centre for Advanced Machine Learning and Applications (CAMLAs), Bashundhara R/A, Dhaka 1229, Bangladesh.; Department of Computer Science & Engineering (CSE), Military Institute of Science and Technology (MIST), Mirpur Cantonment, Dhaka 1216, Bangladesh., Rahman MH; Centre for Advanced Machine Learning and Applications (CAMLAs), Bashundhara R/A, Dhaka 1229, Bangladesh.; Department of Computer Science and Engineering, Islamic University, Kushtia 7003, Bangladesh., Nandi D; Department of Computer Science, American International University-Bangladesh (AIUB), 408/1, Kuratoli, Khilkhet, Dhaka 1229, Bangladesh., Smirani LK; The Deanship of Information Technology and E-learning, Umm Al-Qura University, Mecca 24382, Saudi Arabia., Ahmed K; Department of Electrical and Computer Engineering, University of Saskatchewan, 57 Campus Drive, Saskatoon, SK S7N 5A9, Canada.; Group of Biophotomatiχ, Department of Information and Communication Technology (ICT), Mawlana Bhashani Science and Technology University (MBSTU), Tangail 1902, Bangladesh., Bui FM; Department of Electrical and Computer Engineering, University of Saskatchewan, 57 Campus Drive, Saskatoon, SK S7N 5A9, Canada., Moni MA; Artificial Intelligence & Digital Health, School of Health and Rehabilitation Sciences, Faculty of Health and Behavioural Sciences, The University of Queensland, St. Lucia, QLD 4072, Australia. |
| Abstrakt: |
Osteosarcoma is the most common type of bone cancer that tends to occur in teenagers and young adults. Due to crowded context, inter-class similarity, inter-class variation, and noise in H&E-stained (hematoxylin and eosin stain) histology tissue, pathologists frequently face difficulty in osteosarcoma tumor classification. In this paper, we introduced a hybrid framework for improving the efficiency of three types of osteosarcoma tumor (nontumor, necrosis, and viable tumor) classification by merging different types of CNN-based architectures with a multilayer perceptron (MLP) algorithm on the WSI (whole slide images) dataset. We performed various kinds of preprocessing on the WSI images. Then, five pre-trained CNN models were trained with multiple parameter settings to extract insightful features via transfer learning, where convolution combined with pooling was utilized as a feature extractor. For feature selection, a decision tree-based RFE was designed to recursively eliminate less significant features to improve the model generalization performance for accurate prediction. Here, a decision tree was used as an estimator to select the different features. Finally, a modified MLP classifier was employed to classify binary and multiclass types of osteosarcoma under the five-fold CV to assess the robustness of our proposed hybrid model. Moreover, the feature selection criteria were analyzed to select the optimal one based on their execution time and accuracy. The proposed model achieved an accuracy of 95.2% for multiclass classification and 99.4% for binary classification. Experimental findings indicate that our proposed model significantly outperforms existing methods; therefore, this model could be applicable to support doctors in osteosarcoma diagnosis in clinics. In addition, our proposed model is integrated into a web application using the FastAPI web framework to provide a real-time prediction. |
