Intelligent Data Processing and Mining of Histopathological Images using Improved Tunicate Swarm Algorithm with Deep Learning
Rama Asad Nadweh*1, Arwa Hajjari2
1 Online Islamic University, Department Of Science and Information Technology, Doha, Qatar
2 Cairo University, Cairo, Egypt
Emails: ramaanadwehh@gmail.com ; Hajjarint8843@gmail.com
Abstract
Intelligent data processing and mining of histopathological images involve the application of advanced techniques and algorithms to analyze and extract meaningful information from digital pathology images. Osteosarcoma is a general malignant bone cancer generally established in teenagers and children. Manual diagnoses of osteosarcoma is a laborious task and needs skilled professionals. The mortality rate can be minimalized only if it is identified on time. Automatic detection systems and new technologies were utilized to classify and analyze medical images that, minimalize the dependency on specialists and result in fast processing. Recently, a lot of Computer-Aided Diagnosis (CAD) systems were proposed by research workers to diagnose and segment osteosarcoma from medical images. Deep learning (DL) algorithms are employed for the automated recognition and identification of osteosarcoma on histopathological images (HSI). The study proposes an Improved Tunicate Swarm Algorithm with Deep Learning for Osteosarcoma Detection and Classification (ITSA-DLODC) approach on pathological imageries. The proposed ITSA-DLODC method mainly enhances the recognition and classification of osteosarcoma on HSI. To attain this, the presented ITSA-DLODC method performs feature extraction using ShuffleNet convolutional neural network model. Besides, the ITSA-based hyperparameter optimizer is exploited to finetune the hyperparameters of the ShuffleNet model. Moreover, the salp swarm algorithm (SSA) with convolutional autoencoder (CAE) approach was utilized for the recognition and identification of osteosarcoma. A wide range of analyses can be applied to exemplify the higher performance of the ITSA-DLODC methodology. The simulation study demonstrated the development of the ITSA-DLODC methodology over other present models
Keywords: Intelligent data processing; Data mining; Osteosarcoma; Histopathological images; Computer-aided diagnosis; Deep learning; Tunicate swarm algorithm
Intelligent Data Processing and Mining of Histopathological Images using Improved Tunicate Swarm Algorithm with Deep Learning
Rama Asad Nadweh*1, Arwa Hajjari2
1 Online Islamic University, Department Of Science and Information Technology, Doha, Qatar
2 Cairo University, Cairo, Egypt
Emails: ramaanadwehh@gmail.com ; Hajjarint8843@gmail.com
Abstract
Intelligent data processing and mining of histopathological images involve the application of advanced techniques and algorithms to analyze and extract meaningful information from digital pathology images. Osteosarcoma is a general malignant bone cancer generally established in teenagers and children. Manual diagnoses of osteosarcoma is a laborious task and needs skilled professionals. The mortality rate can be minimalized only if it is identified on time. Automatic detection systems and new technologies were utilized to classify and analyze medical images that, minimalize the dependency on specialists and result in fast processing. Recently, a lot of Computer-Aided Diagnosis (CAD) systems were proposed by research workers to diagnose and segment osteosarcoma from medical images. Deep learning (DL) algorithms are employed for the automated recognition and identification of osteosarcoma on histopathological images (HSI). The study proposes an Improved Tunicate Swarm Algorithm with Deep Learning for Osteosarcoma Detection and Classification (ITSA-DLODC) approach on pathological imageries. The proposed ITSA-DLODC method mainly enhances the recognition and classification of osteosarcoma on HSI. To attain this, the presented ITSA-DLODC method performs feature extraction using ShuffleNet convolutional neural network model. Besides, the ITSA-based hyperparameter optimizer is exploited to finetune the hyperparameters of the ShuffleNet model. Moreover, the salp swarm algorithm (SSA) with convolutional autoencoder (CAE) approach was utilized for the recognition and identification of osteosarcoma. A wide range of analyses can be applied to exemplify the higher performance of the ITSA-DLODC methodology. The simulation study demonstrated the development of the ITSA-DLODC methodology over other present models
Keywords: Intelligent data processing; Data mining; Osteosarcoma; Histopathological images; Computer-aided diagnosis; Deep learning; Tunicate swarm algorithm