Abstract
This paper emphasizes on detection and classification of Fluoro-Deoxy-Glucose (FDG) radioactivity uptakes in fused Positron Emission Tomography / Computerized Tomography (PET/CT) images automatically. The deep learning technique using Convolutional Neural Network (CNN) is proposed to reduce the complexity in observation, to solve the problem of low accurateness and the time-consuming process of traditional classification methods. The CNN layers are designed and proposed for the FDG uptakes classification problem in fused PET/CT images. The proposed modified CNN model is trained using different optimizers such as Stochastic Gradient Descent Momentum (SGDM), Adaptive Moment Estimation (ADAM), and Root Mean Square propagation (RMSprop). The deep features extracted from the proposed CNN are classified using different classifiers such as K-Nearest Neighbor (KNN), Decision Trees (DT), Ensemble, Naive Bayes (NB), and multi-class Support Vector Machine (SVM) the results of which are compared. The multi-class SVM classifier trained using SGDM optimizer attains the maximum test accuracy of 98.18% and was found to be superior to pre-trained deep models such as AlexNet, ResNet, and GoogleNet.
ACKNOWLEDGMENTS
The authors sincerely thank Dr. R. Emmanuel, Managing Director and Radiologist of Bharat Scans Private Limited, Chennai, Tamil Nadu, India for providing images and ground truth for the research work.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Notes on contributors
![](/cms/asset/bdcf3f16-c59a-4b1e-9369-3c9bdd887396/tijr_a_2248939_ilg0001.gif)
J. Angelin Jeba
J Angelin Jeba received her BE degree in electronics and communication engineering from Anna University, Chennai in the year 2008. She received her ME degree specialized in applied electronics from Anna University, Chennai in the year 2011. She received her PhD degree in medical image processing from the Faculty of Information and Communication Engineering, College of Engineering, AnnaUniversity, Chennai in the year 2022.Her research interests are image processing, digital signal processing and artificial intelligence. Corresponding author. Email: [email protected]
![](/cms/asset/aa4b42e9-2389-4bdf-a0c7-a2982584ac6e/tijr_a_2248939_ilg0002.gif)
S. Nirmala Devi
S Nirmala Devi received her BE degree in electronics and communication engineering fromMadurai KamarajUniversity in the year 1991. She received her ME degree specialized in medical electronics from Anna University, Chennai in the year 1996. She received her PhD degree in medical image processing from the Faculty of Information and Communication Engineering, College of Engineering, Anna University in the year 2009. Her research interests are medical image processing, advanced neural computing and physiological modeling. Email: [email protected]