Transfer Learning With Intelligent Training Data Selection for Prediction of Alzheimer’s Disease

Khan, Naimul; Abraham, Nabila; Hon, Marcia

doi:10.1109/access.2019.2920448

Cited by 137 publications

(71 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, researchers in [55] introduced the Sobolev gradient-based stochastic optimizers used in 3D-CNN to diagnose the AD and obtained the 98.01% accuracy. Another study by Khan et al [40] solved the issue with transfer learning and optimized the VGG architecture for the multi-classification of AD. They introduced the new method for layer-wise tuning, to find out the more informative slices in the data they applied the image entropy.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease

et al. 2020

View full text Add to dashboard Cite

Alzheimer’s disease (AD) may cause damage to the memory cells permanently, which results in the form of dementia. The diagnosis of Alzheimer’s disease at an early stage is a problematic task for researchers. For this, machine learning and deep convolutional neural network (CNN) based approaches are readily available to solve various problems related to brain image data analysis. In clinical research, magnetic resonance imaging (MRI) is used to diagnose AD. For accurate classification of dementia stages, we need highly discriminative features obtained from MRI images. Recently advanced deep CNN-based models successfully proved their accuracy. However, due to a smaller number of image samples available in the datasets, there exist problems of over-fitting hindering the performance of deep learning approaches. In this research, we developed a Siamese convolutional neural network (SCNN) model inspired by VGG-16 (also called Oxford Net) to classify dementia stages. In our approach, we extend the insufficient and imbalanced data by using augmentation approaches. Experiments are performed on a publicly available dataset open access series of imaging studies (OASIS), by using the proposed approach, an excellent test accuracy of 99.05% is achieved for the classification of dementia stages. We compared our model with the state-of-the-art models and discovered that the proposed model outperformed the state-of-the-art models in terms of performance, efficiency, and accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

“…They analyzed the accuracy rate on receiving operating characteristic (ROC) is 95% and sensitivity 100%. One such recent method developed [40] for Alzheimer's diagnosis and multi-classification from MRI images with the help of intelligent data selection. They used the popular CNN architecture VGG on the ADNI database.…”

Section: Deep Learning-based Techniquementioning

confidence: 99%

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Compared with the original MRI image, the image we use is standardized and smoothed, and the skull of the image is removed. Therefore, we sort the slices in descending order of entropy and select the first 32 images for training to provide robustness according to previous research [53].…”

Section: Dain Model Based On 2d Viewmentioning

confidence: 99%

Multi-View Based Multi-Model Learning for MCI Diagnosis

2020

View full text Add to dashboard Cite

Mild cognitive impairment (MCI) is the early stage of Alzheimer’s disease (AD). Automatic diagnosis of MCI by magnetic resonance imaging (MRI) images has been the focus of research in recent years. Furthermore, deep learning models based on 2D view and 3D view have been widely used in the diagnosis of MCI. The deep learning architecture can capture anatomical changes in the brain from MRI scans to extract the underlying features of brain disease. In this paper, we propose a multi-view based multi-model (MVMM) learning framework, which effectively combines the local information of 2D images with the global information of 3D images. First, we select some 2D slices from MRI images and extract the features representing 2D local information. Then, we combine them with the features representing 3D global information learned from 3D images to train the MVMM learning framework. We evaluate our model on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our proposed model can effectively recognize MCI through MRI images (accuracy of 87.50% for MCI/HC and accuracy of 83.18% for MCI/AD).

show abstract

“…This allows general features learned on a large, highly varied dataset such as ImageNet (Deng, Dong et al 2009) which contains 3.2 million images, or Snapshot Serengeti (Swanson, Kosmala et al 2015), which contains 7.3 million images to be transferred to a smaller, similar dataset containing only hundreds to thousands of images. Transfer learning has been shown to improve accuracy and the ability to generalise as well as reducing training time and the quantity of data needed (Khan, Hon et al 2019). Its effectiveness in ecological camera trap applications has been established by (Norouzzadeh, Nguyen et al 2017) and (Willi, Pitman et al 2018).…”

Section: Automatic Species Identification and Localisationmentioning

confidence: 99%

“…As this research involved transfer learning which only requires in the order of hundreds to thousands of images (Khan, Hon et al 2019), we considered the size of the dataset adequate for our purposes. After processing and annotation, our final dataset contained 606 images, including 1061 annotations of the animal family Suidae (pigs).…”

Section: Flickrmentioning

confidence: 99%

Location Invariant Animal Recognition Using Mixed Source Datasets and Deep Learning

Shepley

Falzon²,

Meek³

et al. 2020

Preprint

View full text Add to dashboard Cite

1.A time-consuming challenge faced by camera trap practitioners all over the world is the extraction of meaningful data from images to inform ecological management. The primary methods of image processing used by practitioners includes manual analysis and citizen science. An increasingly popular alternative is automated image classification software. However, most automated solutions are not sufficiently robust to be deployed on a large scale. Key challenges include limited access to images for each species and lack of location invariance when transferring models between sites. This prevents optimal use of ecological data and results in significant expenditure of time and resources to annotate and retrain deep learning models.2. In this study, we aimed to (a) assess the value of publicly available non-iconic FlickR images in the training of deep learning models for camera trap object detection, (b) develop an out-ofthe-box location invariant automated camera trap image processing solution for ecologist using deep transfer learning and (c) explore the use of small subsets of camera trap images in optimisation of a FlickR trained deep learning model for high precision ecological object detection.3. We collected and annotated a dataset of images of "pigs" (Sus scrofa and Phacochoerus africanus) from the consumer image sharing website FlickR. These images were used to achieve transfer learning using a RetinaNet model in the task of object detection. We compared the performance of this model to the performance of models trained on combinations of camera trap images obtained from five different projects, each characterised by 5 different geographical regions. Furthermore, we explored optimisation of the FlickR model via infusion of small subsets of camera trap images to increase robustness in difficult images. 4. In most cases, the mean Average Precision (mAP) of the FlickR trained model when tested on out of sample camera trap sites (67.21-91.92%) was significantly higher than the mAP achieved by models trained on only one geographical location (4.42-90.8%) and rivalled the mAP of models trained on mixed camera trap datasets (68.96-92.75%). The infusion of camera trap images into the FlickR training further improved AP by 5.10-22.32% to 83.60-97.02%. Ecology researchers can use FlickR images in the training of automated deep learningsolutions for camera trap image processing to significantly reduce time and resource expenditure by allowing the development of location invariant, highly robust out-of-the-box solutions. This would allow AI technologies to be deployed on a large scale in ecological applications.

show abstract

Transfer Learning With Intelligent Training Data Selection for Prediction of Alzheimer’s Disease

Cited by 137 publications

References 25 publications

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease

Multi-View Based Multi-Model Learning for MCI Diagnosis

Location Invariant Animal Recognition Using Mixed Source Datasets and Deep Learning

Contact Info

Product

Resources

About