Enhanced Transfer Learning with ImageNet Trained Classification Layer

Shermin, Tasfia; Teng, Shyh Wei; Murshed, Manzur; Lu, Guojun; Sohel, Ferdous; Paul, Manoranjan

doi:10.1007/978-3-030-34879-3_12

Cited by 24 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, we only considered representatives of the base models in this domain as discussed below. Conveniently, these models are all available as part of the Keras API and each support transfer learning [94] in the form of supporting the pre-application to the model of the ImageNet [95] weights.…”

Section: Model Developmentmentioning

confidence: 99%

COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data

et al. 2020

Self Cite

View full text Add to dashboard Cite

Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how transfer learning from deep learning models can be used to perform COVID-19 detection using images from three most commonly used medical imaging modes X-Ray, Ultrasound, and CT scan. The aim is to provide over-stressed medical professionals a second pair of eyes through intelligent deep learning image classification models. We identify a suitable Convolutional Neural Network (CNN) model through initial comparative study of several popular CNN models. We then optimize the selected VGG19 model for the image modalities to show how the models can be used for the highly scarce and challenging COVID-19 datasets. We highlight the challenges (including dataset size and quality) in utilizing current publicly available COVID-19 datasets for developing useful deep learning models and how it adversely impacts the trainability of complex models. We also propose an image pre-processing stage to create a trustworthy image dataset for developing and testing the deep learning models. The new approach is aimed to reduce unwanted noise from the images so that deep learning models can focus on detecting diseases with specific features from them. Our results indicate that Ultrasound images provide superior detection accuracy compared to X-Ray and CT scans. The experimental results highlight that with limited data, most of the deeper networks struggle to train well and provides less consistency over the three imaging modes we are using. The selected VGG19 model, which is then extensively tuned with appropriate parameters, performs in considerable levels of COVID-19 detection against pneumonia or normal for all three lung image modes with the precision of up to 86% for X-Ray, 100% for Ultrasound and 84% for CT scans.

show abstract

Section: Model Developmentmentioning

confidence: 99%

COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…For these reasons we have selected five deep learning models as classifiers for our experiments. Conveniently, these models are all available as part of the Keras API and each support transfer learning [44] in the form of supporting the pre-application to the model of the ImageNet [40] weights.…”

Section: B Model Considerationmentioning

confidence: 99%

X-Ray Image based COVID-19 Detection using Pre-trained Deep Learning Models

Horry¹,

Chakraborty²,

Paul³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how pre-trained deep learning models can be adopted to perform COVID-19 detection using X-Ray images. The aim is to provide over-stressed medical professionals a second pair of eyes through intelligent image classification models. We highlight the challenges (including dataset size and quality) in utilising current publicly available COVID-19 datasets for developing useful deep learning models. We propose a semi-automated image pre-processing model to create a trustworthy image dataset for developing and testing deep learning models. The new approach is aimed to reduce unwanted noise from X-Ray images so that deep learning models can focus on detecting diseases with specific features from them. Next, we devise a deep learning experimental framework, where we utilise the processed dataset to perform comparative testing for several popular and widely available deep learning model families such as VGG, Inception, Xception, and Resnet. The experimental results highlight the suitability of these models for current available dataset and indicates that models with simpler networks such as VGG19 performs relatively better with up to 83% precision. This will provide a solid pathway for researchers and practitioners to develop improved models in the future.

show abstract

“…The network was trained using the weights pre-trained on ImageNet. The frozen block approach was adopted for better results [ 62 ]: each EfficientNetB3 block was trained for three epochs using a learning rate of

for the top layers and

for the rest of the blocks. Training stopped when validation loss no longer yielded an improvement and the model started overfitting.…”

Section: Methodsmentioning

confidence: 99%

Integrating Domain Knowledge into Deep Learning for Skin Lesion Risk Prioritization to Assist Teledermatology Referral

et al. 2021

View full text Add to dashboard Cite

Teledermatology has developed rapidly in recent years and is nowadays an essential tool for early diagnosis. In this work, we aim to improve existing Teledermatology processes for skin lesion diagnosis by developing a deep learning approach for risk prioritization with a dataset of retrospective data from referral requests of the Portuguese National Health System. Given the high complexity of this task, we propose a new prioritization pipeline guided and inspired by domain knowledge. We explored automatic lesion segmentation and tested different learning schemes, namely hierarchical classification and curriculum learning approaches, optionally including additional patient metadata. The final priority level prediction can then be obtained by combining predicted diagnosis and a baseline priority level accounting for explicit expert knowledge. In both the differential diagnosis and prioritization branches, lesion segmentation with 30% tolerance for contextual information was shown to improve classification when compared with a flat baseline model trained on original images; furthermore, the addition of patient information was not beneficial for most experiments. Curriculum learning delivered better results than a flat or hierarchical approach. The combination of diagnosis information and a knowledge map, created in collaboration with dermatologists, together with the priority achieved interesting results (best macro F1 of 43.93% for a validated test set), paving the way for new data-centric and knowledge-driven approaches.

show abstract

Enhanced Transfer Learning with ImageNet Trained Classification Layer

Cited by 24 publications

References 24 publications

COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data

COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data

X-Ray Image based COVID-19 Detection using Pre-trained Deep Learning Models

Integrating Domain Knowledge into Deep Learning for Skin Lesion Risk Prioritization to Assist Teledermatology Referral

Contact Info

Product

Resources

About