Comparing deep learning models for population screening using chest radiography

Sivaramakrishnan, R.; Candemir, Sema; Xue, Zhiyun; Abuya, Joseph; Kohli, Marc D.; Alderson, Philip O.; Thoma, George R.

doi:10.1117/12.2293140

Cited by 32 publications

(29 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The strategy of using the ImagneNet pre-trained network is effective, since lower level natural-image features can be relevant to medical images. This was further verified by Sivaramakrishnan et al [6]. In the current work, we show that although clearly important, this transfer is sub-optimal.…”

Section: Introductionsupporting

confidence: 90%

Deep Feature Learning from a Hospital-Scale Chest X-ray Dataset with Application to TB Detection on a Small-Scale Dataset

Gozes

Greenspan

2019

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

The use of ImageNet pre-trained networks is becoming widespread in the medical imaging community. It enables training on small datasets, commonly available in medical imaging tasks. The recent emergence of a large Chest X-ray dataset opened the possibility for learning features that are specific to the X-ray analysis task. In this work, we demonstrate that the features learned allow for better classification results for the problem of Tuberculosis detection and enable generalization to an unseen dataset.To accomplish the task of feature learning, we train a DenseNet-121 CNN on 112K images from the ChestXray14 dataset which includes labels of 14 common thoracic pathologies. In addition to the pathology labels, we incorporate metadata which is available in the dataset: Patient Positioning, Gender and Patient Age. We term this architecture MetaChexNet. As a by-product of the feature learning, we demonstrate state of the art performance on the task of patient Age & Gender estimation using CNN's. Finally, we show the features learned using ChestXray14 allow for better transfer learning on smallscale datasets for Tuberculosis.

show abstract

Section: Introductionsupporting

confidence: 90%

Deep Feature Learning from a Hospital-Scale Chest X-ray Dataset with Application to TB Detection on a Small-Scale Dataset

Gozes

Greenspan

2019

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

show abstract

“…Variable (x) in Formulas (1) and (2) represents the input values of the activation function. Mish has no upper bound but does have a lower bound; Mish also has smooth and non-monotonic properties that improve the results [34], as shown in Formula (2).…”

Section: Mish Activation Functionmentioning

confidence: 99%

“…lung disease often occurs in developing countries along with human immunodeficiency virus (HIV) and diabetes, which will immediately affect the immunity and infection of lung disease. This disease is a respiratory disease, meaning that it causes lung infections in the thoracic area of patients [1,2]. In early diagnosis by a doctor, chest X-ray (CRX) films are used.…”

Section: Introductionmentioning

confidence: 99%

Analyzing Lung Disease Using Highly Effective Deep Learning Techniques

2020

View full text Add to dashboard Cite

Image processing technologies and computer-aided diagnosis are medical technologies used to support decision-making processes of radiologists and medical professionals who provide treatment for lung disease. These methods involve using chest X-ray images to diagnose and detect lung lesions, but sometimes there are abnormal cases that take some time to occur. This experiment used 5810 images for training and validation with the MobileNet, Densenet-121 and Resnet-50 models, which are popular networks used to classify the accuracy of images, and utilized a rotational technique to adjust the lung disease dataset to support learning with these convolutional neural network models. The results of the convolutional neural network model evaluation showed that Densenet-121, with a state-of-the-art Mish activation function and Nadam-optimized performance. All the rates for accuracy, recall, precision and F1 measures totaled 98.88%. We then used this model to test 10% of the total images from the non-dataset training and validation. The accuracy rate was 98.97% for the result which provided significant components for the development of a computer-aided diagnosis system to yield the best performance for the detection of lung lesions.

show abstract

“…In this study [4] state-of-the-art CADx software makes use of machine learning (ML) techniques that use global and local feature descriptors to extract features from the underlying data. Previously, ML tools have been used to detect abnormal texture in chest radiographs and to exhibit extraction of texture and shape features and classification with a binary classifier in the process of TB screening from CXRs.…”

Section: Literature Review:-mentioning

confidence: 99%