scholarly journals Developing intelligent medical image modality classification system using deep transfer learning and LDA

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Mehdi Hassan ◽  
Safdar Ali ◽  
Hani Alquhayz ◽  
Khushbakht Safdar
Keyword(s):  
Transfer Learning ◽  
Classification System ◽  
Medical Image ◽  
Image Modality

Transfer Learning for 3‐Dimensional Medical Image Analysis

2021 ◽  
pp. 151-171
Author(s):  
Sanket Singh ◽  
Sarthak Jain ◽  
Akshit Khanna ◽  
Anupam Kumar ◽  
Ashish Sharma
Keyword(s):  
Image Analysis ◽  
Transfer Learning ◽  
Medical Image ◽  
Medical Image Analysis ◽  
3 Dimensional

scholarly journals Natural Images Allow Universal Adversarial Attacks on Medical Image Classification Using Deep Neural Networks with Transfer Learning

2021 ◽  
Author(s):  
Akinori Minagi ◽  
Hokuto Hirano ◽  
Kazuhiro Takemoto
Keyword(s):  
Neural Networks ◽  
Image Classification ◽  
Transfer Learning ◽  
Medical Image ◽  
Deep Neural Networks ◽  
Disease Diagnosis ◽  
Natural Images ◽  
Fine Tuning ◽  
Security And Privacy ◽  
Medical Image Classification

Abstract Transfer learning from natural images is well used in deep neural networks (DNNs) for medical image classification to achieve computer-aided clinical diagnosis. Although the adversarial vulnerability of DNNs hinders practical applications owing to the high stakes of diagnosis, adversarial attacks are expected to be limited because training data — which are often required for adversarial attacks — are generally unavailable in terms of security and privacy preservation. Nevertheless, we hypothesized that adversarial attacks are also possible using natural images because pre-trained models do not change significantly after fine-tuning. We focused on three representative DNN-based medical image classification tasks (i.e., skin cancer, referable diabetic retinopathy, and pneumonia classifications) and investigated whether medical DNN models with transfer learning are vulnerable to universal adversarial perturbations (UAPs), generated using natural images. UAPs from natural images are useful for both non-targeted and targeted attacks. The performance of UAPs from natural images was significantly higher than that of random controls, although slightly lower than that of UAPs from training images. Vulnerability to UAPs from natural images was observed between different natural image datasets and between different model architectures. The use of transfer learning causes a security hole, which decreases the reliability and safety of computer-based disease diagnosis. Model training from random initialization (without transfer learning) reduced the performance of UAPs from natural images; however, it did not completely avoid vulnerability to UAPs. The vulnerability of UAPs from natural images will become a remarkable security threat.

The Animal Classification: An Evaluation of Different Transfer Learning Pipeline

Mekatronika ◽  
2021 ◽  
Vol 3 (1) ◽  
pp. 27-31
Author(s):  
Ken-ji Ee ◽  
Ahmad Fakhri Bin Ab. Nasir ◽  
Anwar P. P. Abdul Majeed ◽  
Mohd Azraai Mohd Razman ◽  
Nur Hafieza Ismail
Keyword(s):  
Transfer Learning ◽  
Classification System ◽  
Cross Validation ◽  
Support Vector ◽  
Svm Classifier ◽  
Average Classification Accuracy ◽  
Validation Technique ◽  
Search Approach ◽  
Fold Cross Validation

The animal classification system is a technology to classify the animal class (type) automatically and useful in many applications. There are many types of learning models applied to this technology recently. Nonetheless, it is worth noting that the extraction of the features and the classification of the animal features is non-trivial, particularly in the deep learning approach for a successful animal classification system. The use of Transfer Learning (TL) has been demonstrated to be a powerful tool in the extraction of essential features. However, the employment of such a method towards animal classification applications are somewhat limited. The present study aims to determine a suitable TL-conventional classifier pipeline for animal classification. The VGG16 and VGG19 were used in extracting features and then coupled with either k-Nearest Neighbour (k-NN) or Support Vector Machine (SVM) classifier. Prior to that, a total of 4000 images were gathered consisting of a total of five classes which are cows, goats, buffalos, dogs, and cats. The data was split into the ratio of 80:20 for train and test. The classifiers hyper parameters are tuned by the Grids Search approach that utilises the five-fold cross-validation technique. It was demonstrated from the study that the best TL pipeline identified is the VGG16 along with an optimised SVM, as it was able to yield an average classification accuracy of 0.975. The findings of the present investigation could facilitate animal classification application, i.e. for monitoring animals in wildlife.

A COMPARATIVE EVALUATION OF FEATURES FOR MEDICAL IMAGE MODALITY CLASSIFICATION

2016 ◽  
Vol 78 (8-2) ◽  
Author(s):  
Sameer Ahmad Khan ◽  
Suet Peng Yong ◽  
Uzair Iqbal Janjua
Keyword(s):  
Comparative Evaluation ◽  
Medical Image ◽  
Medical Images ◽  
Image Categorization ◽  
Discriminatory Ability ◽  
Automatic Categorization ◽  
Image Characteristic ◽  
The Stability ◽  
Content Information ◽  
Image Modality

Medical images are increasing at an alarming rate. This increasing number of images affects the interpreting capacity of radiologists. In order to reduce the burden of radiologists, automatic categorization of medical images based on modality is the need of the hour. Because image modality is an important and fundamental image characteristic. The important factor in the automatic medical image categorization based on modality are the features used for categorization purpose, because nice treatment on these subtleties can lead to good results. Many descriptors have been proposed in the literature for medical image categorization. It is unclear which descriptor encodes the content information efficiently. The descriptors that are calculated from these medical images should be descriptive, distinctive and robust to various transformations. The stability of these descriptors are evaluated under various transformations and are then analyzed for their discriminatory ability for the task of classification. In this study the criteria of transformations, repeatability, matching and classification accuracy on the basis of precision recall is used to evaluate the performance of these descriptors. The experimental results illustrates that among global descriptors local features patches histogram and among local descriptors SIFT encodes the content information quite efficiently.

Sign in / Sign up

Export Citation Format

Share Document