An Ensemble-based Approach by Fine-Tuning the Deep Transfer Learning Models to Classify Pneumonia from Chest X-Ray Images

Venu, Sagar Kora

doi:10.5220/0010377403900401

Cited by 10 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach to improve the performance of the transfer learning method is to ensemble the trained models. A weighted average based ensemble technique is implemented among five different transfer learned models to achieve about 0.08 test loss (Kora Venu, 2020). Here, the classification performance for pneumonia identification is also measured using other metrics such as precision, recall, F1 score and the ensemble technique outperforms on classifying pneumonia X‐rays.…”

Section: Literature Surveymentioning

confidence: 99%

Acost‐sensitivedeep learning‐basedmeta‐classifierfor pediatric pneumonia classification using chest X‐rays

2022

View full text Add to dashboard Cite

Literature survey shows that convolutional neural network (CNN)‐based pretrained models have been successfully employed to diagnose and detect childhood pneumonia using chest X‐rays (CXR). However, most of the existing methods are prone to imbalance problems, which become even more significant in medical image classification for example most importantly childhood pneumonia classification using CXR. This is due to the fact that some classes in childhood pneumonia have a very little support in the training dataset. Additionally, though the existing methods have reported better performances for training and testing, in most of the test cases the existing models will not be effective on variants of the childhood pneumonia CXR images or CXR samples from a new pediatric patient. In addition, the models may be effective in detecting latent stage pediatric pneumonia but not show better performances for CXR samples from pediatric patients who are early stage, sick but not pneumonia, sick with other lung diseases, and so on. Generalization is an important term to be considered while designing a pneumonia classifier that can perform well on completely unseen pneumonia CXR datasets. This article presents a cost‐sensitive large‐scale learning with stacked ensemble meta‐classifier and transfer learning‐based deep feature fusion approach for pediatric pneumonia classification using CXR. With the aim to identify the importance among the classes of pneumonia, the larger cost items are introduced based on the class‐imbalance degree during the backpropogation learning methodology in transfer learning models such as Xception, InceptionResNetV2, DenseNet201, and NASNetMobile. Next, the features from the penultimate layer (global average pooling) of Xception, InceptionResNetV2, DenseNet201, and NASNetMobile were extracted and dimensionality of the extracted features were reduced using kernel principal component analysis (KPCA). The reduced features were fused together and passed into a stacked ensemble meta‐classifier for classifying the CXR into either pneumonia or normal. A stacked ensemble meta‐classifier is a two stage approach in which the first stage employs random forest and support vector machine (SVM) for prediction and followed by logistic regression for classification. Experiments of the proposed model were done on publicly available benchmark pediatric pneumonia classification CXR dataset. In addition, the experiments for existing methods as well as various cost‐insensitive models were conducted. In all the experiments, the proposed method has achieved better performances compared to the existing methods as well as various cost‐insensitive models. In particular, the proposed method showed 6% improvement in precision, 10% improvement in recall, 9% improvement in F1 score with less misclassification costs (0.0321) and accuracy (96.8%). Most importantly, the proposed method is insensitive to the imbalance data and more effective to handle variants of the childhood pneumonia CXR images. Thus, the proposed approach can...

show abstract

Section: Literature Surveymentioning

confidence: 99%

Acost‐sensitivedeep learning‐basedmeta‐classifierfor pediatric pneumonia classification using chest X‐rays

2022

View full text Add to dashboard Cite

show abstract

“…In [5], S.K Venu studied the state-of-the-art deep learning models for pneumonia classification. A weighted average ensemble of Inception, ResNet152V2, DenseNet201, MobileNetV2 and Xception was created, and the evaluation results demonstrated a test accuracy of 98.46%, precision of 98.38%, recall of 99.53%, and f1 score of 98.96%.…”

Section: Related Workmentioning

confidence: 99%

Transfer learning for Covid-19 detection in medical images

Azhari¹

2022

Preprint

View full text Add to dashboard Cite

As of late, the Covid infection 2019 (COVID-19) has caused a pandemic sickness in more than 200 nations, therefore impacting billions of people. To control the spread of the coronavirus, it is crucial to detect infected individuals and ensure their complete isolation to prevent further infection. Chest X-rays and CT-scans have been proven to be very promising as signals of the infection can be clearly shown in lung areas. Transfer learning from ImageNet dataset has become the latent trend in medical imaging applications. However, there are major differences between ImageNet and medical imaging datasets. Therefore, the feasibility of transfer learning in medical applications remains questionable. This paper investigates the performance of five fine-tuned pre-trained models for chest x-rays and CT-scans classification in contrast with a deep CNN model built from scratch. DenseNet121, Resnet-50, Inception v2, Resnet101-V2 and VGG16 are selected and initialized with either random or pre-trained weights to classify augmented images into two classes: Covid and non-Covid. The performance evaluation proves the minuscule impact of training transfer learning models for good quality results, as all CNN models contribute almost equally to the classification and achieve considerable results in terms of precision, accuracy, recall and F1 score.

show abstract

Improving the Generalization of Deep Learning Classification Models in Medical Imaging Using Transfer Learning and Generative Adversarial Networks

Venu

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

An Ensemble-based Approach by Fine-Tuning the Deep Transfer Learning Models to Classify Pneumonia from Chest X-Ray Images

Cited by 10 publications

References 32 publications

Acost‐sensitivedeep learning‐basedmeta‐classifierfor pediatric pneumonia classification using chest X‐rays

Acost‐sensitivedeep learning‐basedmeta‐classifierfor pediatric pneumonia classification using chest X‐rays

Transfer learning for Covid-19 detection in medical images

Improving the Generalization of Deep Learning Classification Models in Medical Imaging Using Transfer Learning and Generative Adversarial Networks

Contact Info

Product

Resources

About