Special lssues
Table of Content

Cancer Diagnosis using Deep Learning, Federated Learning, and Features Optimization Techniques

Submission Deadline: 20 October 2022 (closed)

Guest Editors

Dr. Tallha Akram, COMSATS University Islamabad, Pakistan.
Dr. Muhammad Attique Khan, HITEC University Taxila, Pakistan.

Summary

Machine learning based approaches are gaining a lot of attention due to the wide range of application in various fields. The last two decades witnessed the increasing interests in computer-aided medical system for early detection, diagnosis, prognosis, risk assessment and final therapy of diseases. The development of a reliable medical solution is a crucial task, because there is no single standard approach – covering all the subdomains including data processing, regions of interest detection, image segmentation and registration, image fusion and classification with high accuracy. Therefore, computer-aided diagnosis system is still a highly challenging domain which provides enough space for improvement. These days, deep learning-based methods are gaining much attention of researchers in machine learning community due to improved segmentation and classification results. Moreover, deep learning-based methods have also lowered the barriers of data preprocessing and extreme set of users’ dependability. Consequently, the processing burden in medical imaging is now shifted from human-side to computer-side. Thus, allowing more researchers to step into this well-liked and momentous area. This leads to improved performance, both in terms of accuracy and decision time.

This special issue seeks high-quality research articles generally dealing with the methods like semantic segmentation and deep learning in the field of medical image processing. We are only targeting original research articles, proposing novel solutions, covering new theories, and new implementations for medical image analytics.


Keywords

• Deep learning based Segmentation
• Federated Learning
• Semantic segmentation for Medical Infection Diagnosis
• Wireless capsule Endoscopy (WCE)imaging technology using deep learning
• Magnetic resonance imaging (MRI)
• Semantic techniques for MRI images
• FPGA with deep learning for medical imaging
• Mammogram Imaging Modality using deep learning
• Ultrasound Imaging Modality detection using Deep Learning
• X-ray computed tomography (CT)
• Deep learning based CAD systems
• Transfer learning in deep learning for medical imaging
• Cancers classification using deep learning
• Autoencoder based features selection using Deep Learning in Medical
• Fusion of convolutional layers in deep learning for recognition
• Optimal deep learning features selection for recognition
• Fusion of Image Modality using Deep Learning
• Deep Learning based Medical Imaging Retrieval

Published Papers


  • Open Access

    ARTICLE

    3D Kronecker Convolutional Feature Pyramid for Brain Tumor Semantic Segmentation in MR Imaging

    Kainat Nazir, Tahir Mustafa Madni, Uzair Iqbal Janjua, Umer Javed, Muhammad Attique Khan, Usman Tariq, Jae-Hyuk Cha
    CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 2861-2877, 2023, DOI:10.32604/cmc.2023.039181
    (This article belongs to this Special Issue: Cancer Diagnosis using Deep Learning, Federated Learning, and Features Optimization Techniques)
    Abstract Brain tumor significantly impacts the quality of life and changes everything for a patient and their loved ones. Diagnosing a brain tumor usually begins with magnetic resonance imaging (MRI). The manual brain tumor diagnosis from the MRO images always requires an expert radiologist. However, this process is time-consuming and costly. Therefore, a computerized technique is required for brain tumor detection in MRI images. Using the MRI, a novel mechanism of the three-dimensional (3D) Kronecker convolution feature pyramid (KCFP) is used to segment brain tumors, resolving the pixel loss and weak processing of multi-scale lesions. A single dilation rate was replaced… More >

  • Open Access

    ARTICLE

    Deep-Net: Fine-Tuned Deep Neural Network Multi-Features Fusion for Brain Tumor Recognition

    Muhammad Attique Khan, Reham R. Mostafa, Yu-Dong Zhang, Jamel Baili, Majed Alhaisoni, Usman Tariq, Junaid Ali Khan, Ye Jin Kim, Jaehyuk Cha
    CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 3029-3047, 2023, DOI:10.32604/cmc.2023.038838
    (This article belongs to this Special Issue: Cancer Diagnosis using Deep Learning, Federated Learning, and Features Optimization Techniques)
    Abstract Manual diagnosis of brain tumors using magnetic resonance images (MRI) is a hectic process and time-consuming. Also, it always requires an expert person for the diagnosis. Therefore, many computer-controlled methods for diagnosing and classifying brain tumors have been introduced in the literature. This paper proposes a novel multimodal brain tumor classification framework based on two-way deep learning feature extraction and a hybrid feature optimization algorithm. NasNet-Mobile, a pre-trained deep learning model, has been fine-tuned and two-way trained on original and enhanced MRI images. The haze-convolutional neural network (haze-CNN) approach is developed and employed on the original images for contrast enhancement.… More >

  • Open Access

    ARTICLE

    A Hybrid Attention-Based Residual Unet for Semantic Segmentation of Brain Tumor

    Wajiha Rahim Khan, Tahir Mustafa Madni, Uzair Iqbal Janjua, Umer Javed, Muhammad Attique Khan, Majed Alhaisoni, Usman Tariq, Jae-Hyuk Cha
    CMC-Computers, Materials & Continua, Vol.76, No.1, pp. 647-664, 2023, DOI:10.32604/cmc.2023.039188
    (This article belongs to this Special Issue: Cancer Diagnosis using Deep Learning, Federated Learning, and Features Optimization Techniques)
    Abstract Segmenting brain tumors in Magnetic Resonance Imaging (MRI) volumes is challenging due to their diffuse and irregular shapes. Recently, 2D and 3D deep neural networks have become famous for medical image segmentation because of the availability of labelled datasets. However, 3D networks can be computationally expensive and require significant training resources. This research proposes a 3D deep learning model for brain tumor segmentation that uses lightweight feature extraction modules to improve performance without compromising contextual information or accuracy. The proposed model, called Hybrid Attention-Based Residual Unet (HA-RUnet), is based on the Unet architecture and utilizes residual blocks to extract low-… More >

Share Link