Highlights Radiographic chest images can be used to more accurately detect COVID-19 and assess disease severity. Among different imaging modalities, chest X-ray radiography has advantages of low cost, low radiation dose, wide accessibility and easy-to-operate in general or community hospitals. This study aims to develop and test a new deep learning model of chest X-ray images to detect COVID-19 induced pneumonia. For this purpose, we assembled a relatively large chest X-ray image dataset involving 8,474 cases, which are divided into three groups of COVID-19 infected pneumonia, other community-acquired no-COVID-19 infected pneumonia, and normal (non-pneumonia) cases. After applying a preprocessing algorithm to detect and remove diaphragm regions depicting on images, a histogram equalization algorithm and a bilateral filter are applied to process the original images to generate two sets of filtered images. Then, the original image plus these two filtered images are used as inputs of three channels of the CNN deep learning model, which increase learning information of the model. In order to fully take advantages of the pre-optimized CNN models, this study uses a transfer learning method to build a new model to detect and classify COVID-19 infected pneumonia. A VGG16 based CNN model was originally trained using ImageNet and fine-tuned using chest X-ray images in this study. To reduce the bias in training and testing the CNN model, dataset is randomly divided into 3 subsets namely, training, validation, and testing with respect to the same frequency of cases in each class in all three COVID-19 infected pneumonia, other community-acquired no-COVID-19 infected pneumonia, and normal (non-pneumonia) groups. Testing on a subset of 2544 cases, the CNN model yields 94.5% accuracy in classifying three subsets of cases and 98.1% accuracy in detecting COVID-19 infected pneumonia cases, which are significantly higher than the model directly trained using the original images without applying two image preprocessing steps to remove diaphragm and generate two filtered images.

challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top performing participating solutions. We observe that the top performing approaches utilize a blend of clinical information, data augmentation, and the ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

In order to automatically identify a set of effective mammographic image features and build an optimal breast cancer risk stratification model, this study aims to investigate advantages of applying a machine learning approach embedded with a locally preserving projection (LPP) based feature combination and regeneration algorithm to predict short-term breast cancer risk. A dataset involving negative mammograms acquired from 500 women was assembled. This dataset was divided into two age-matched classes of 250 high risk cases in which cancer was detected in the next subsequent mammography screening and 250 low risk cases, which remained negative. First, a computer-aided image processing scheme was applied to segment fibro-glandular tissue depicted on mammograms and initially compute 44 features related to the bilateral asymmetry of mammographic tissue density distribution between left and right breasts. Next, a multi-feature fusion based machine learning classifier was built to predict the risk of cancer detection in the next mammography screening. A leave-one-case-out (LOCO) cross-validation method was applied to train and test the machine learning classifier embedded with a LLP algorithm, which generated a new operational vector with 4 features using a maximal variance approach in each LOCO process. Results showed a 9.7% increase in risk prediction accuracy when using this LPP-embedded machine learning approach. An increased trend of adjusted odds ratios was also detected in which odds ratios increased from 1.0 to 11.2. This study demonstrated that applying the LPP algorithm effectively reduced feature dimensionality, and yielded higher and potentially more robust performance in predicting short-term breast cancer risk.

Contrast-enhanced digital mammography (CEDM) is a promising imaging modality in breast cancer diagnosis. This study aims to investigate how to optimally develop a computer-aided diagnosis (CAD) scheme of CEDM images to classify breast masses. A CEDM dataset of 111 patients was assembled, which includes 33 benign and 78 malignant cases. Each CEDM includes two types of images namely, low energy (LE) and dual-energy subtracted (DES) images. A CAD scheme was applied to segment mass regions depicting on LE and DES images separately. Optimal segmentation results generated from DES images were also mapped to LE images or vice versa. After computing image features, multilayer perceptron based machine learning classifiers that integrate with a correlation-based feature subset evaluator and leave-one-case-out cross-validation method were built to classify mass regions. When applying CAD to DES and LE images with original segmentation, areas under ROC curves (AUC) were 0.759 ± 0.053 and 0.753 ± 0.047, respectively. After mapping the mass regions optimally segmented on DES images to LE images, AUC significantly increased to 0.848 ± 0.038 (p < 0.01). Study demonstrated that DES images eliminated overlapping effect of dense breast tissue, which helps improve mass segmentation accuracy. The study demonstrated that applying a novel approach to optimally map mass region segmented from DES images to LE images enabled CAD to yield significantly improved performance.

No abstract