Fig 1.
Examples of two X-ray plates that display (a) a healthy lung and (b) a pneumonic lung.
The red arrows in (b) indicate white infiltrates, a distinguishing feature of pneumonia. The images were taken from the Kermany dataset [4].
Fig 2.
Representation of the proposed pneumonia detection framework.
Pre = Precision score, Rec = Recall score, F1 = F1-score, AUC = AUC score, and A(i) = {Prei, Reci, F1i, AUCi}; w(i) is the weight generated for the ith base learner to compute the ensemble, is the probability score for the jth sample by the ith classifier, and ensj is the fused probability score for the jth sample; and the argmax function returns the position having the highest value in a 1D array, i.e., in this case it generates the predicted class of the sample.
Table 1.
Existing methods for pneumonia detection.
Fig 3.
Inception modules in the GoogLeNet architecture.
(a) The naive inception block that is replaced by (b) the dimension reduction inception block in the GoogLeNet architecture to improve computational efficiency.
Fig 4.
Architecture of the GoogLeNet model used in this study.
The inception block is shown in Fig 3(b).
Fig 5.
Architecture of the ResNet-18 model used in this study.
Fig 6.
Basic architecture of the DenseNet convolutional neural network model.
Table 2.
Hyperparameters used for training the convolutional neural network base learners.
Table 3.
Description of images in the training and testing sets in each fold of five-fold cross-validation in the two datasets used in this study.
Fig 7.
Confusion matrices obtained on the Kermany pneumonia chest X-ray dataset by the proposed method by 5-fold cross validation.
a) Fold-1. (b) Fold-2. (c) Fold-3. (d) Fold-4. (e) Fold-5.
Fig 8.
Confusion matrices obtained on the Radiological Society of North America pneumonia challenge chest X-ray dataset by the proposed method by five-fold cross validation.
a) Fold-1. (b) Fold-2. (c) Fold-3. (d) Fold-4. (e) Fold-5.
Fig 9.
Receiver operating characteristic curves obtained by the proposed ensemble method on the two pneumonia chest X-ray datasets used in this research.
Table 4.
Results of five-fold cross-validation of the proposed ensemble method on the pneumonia Kermany dataset [4].
Table 5.
Results of five-fold cross-validation of the proposed ensemble method on the pneumonia Radiological Society of North America challenge dataset.
Fig 10.
Variation of accuracy rates on the Kermany dataset [4]) achieved by the three base learners, GoogLeNet, ResNet-18, and DenseNet-121 and their ensemble, according to the optimizers chosen for fine tuning.
Fig 11.
Variation in performance (accuracy rates) of the ensemble with respect to the number of fixed non-trainable layers in the base learners on the two datasets used in this study.
Table 6.
Results of extensive experiments performed to determine the base learners for forming the ensemble in this study.
Fig 12.
Gradient-weighted class activation map (GradCAM) decision visualization of chest X-ray images when the three chosen base learners were used to form the ensemble.
Different regions of the X-rays are the focus of the different models that capture complementary information. Case-1: (a)–(c) show a pneumonic lung X-ray analyzed using the three base learners; the confidence scores of the three base learners are GoogLeNet: 99.99%, ResNet-18: 75.21%, and DenseNet-121: 98.90% Case-2: (d)–(f) show a healthy lung X-ray analyzed using the three base learners; the confidence scores of the three base learners are GoogLeNet: 99.47%, ResNet-18: 97.61%, and DenseNet-121: 98.93%.
Table 7.
Comparison of the proposed method with other methods in the literature on the Kermany pneumonia dataset [4] and the Radiological Society of North America challenge dataset [33].
Table 8.
Comparison of the proposed ensemble framework with several standard convolution neural network models in the literature on both the Kermany and the Radiological Society of North America challenge datasets.
Table 9.
Performance comparison of the proposed ensemble technique and popular ensemble schemes in the literature for the two datasets used.
The same base learners were used in all the ensembles: GoogLeNet, ResNet-18, and DenseNet-121.
Fig 13.
Examples of samples from the Kermany dataset where two out of three base learners yielded incorrect predictions, but the ensemble yielded the correct prediction.
Both images are of class “Normal”. (a) Case-1: GoogLeNet predicted “Pneumonia” with a confidence score of 53.1%, ResNet-18 predicted “Pneumonia” with a confidence score of 73.8%, and DenseNet-121 predicted “Normal” with a confidence score of 89.4%. The proposed ensemble framework predicted “Normal” (correct classification) with a confidence rate of 68.1 (b) Case-2: GoogLeNet predicted “Normal” with a confidence score of 98.6%, ResNet-18 predicted “Pneumonia” with a confidence score of 58.3%, and DenseNet-121 predicted “Pneumonia” with a confidence score of 69.3%. The proposed ensemble framework predicted “Normal” (correct classification) with a confidence rate of 66.3%.
Fig 14.
Examples of samples from the Kermany dataset [4] that were classified incorrectly by the proposed ensemble framework.
Case-1: (a) shows an image originally belonging to class “Normal” but misclassified as “Pneumonia” by the framework. The GradCAM analysis images are shown in (c), (d), and (e) for GoogLeNet, ResNet-18, and DenseNet-121, respectively. Case-2: (b) shows an image of class “Pneumonia” predicted to belong to the “Normal” class by the framework. The GradCAM analysis images are shown in (f), (g), and (h)for GoogLeNet, ResNet-18, and DenseNet-121, respectively.
Table 10.
Results of McNemar’s statistical test of the ensemble model and the base learners on both datasets.
For all the base learners with which the proposed model is compared, the p−value is less than 0.05, and thus, the null hypothesis is rejected.
Table 11.
Results of analysis of variance (ANOVA) statistical test of the ensemble model and the base learners on both datasets.
For all the base learners with which the proposed model is compared, the p−value is less than 0.05, and thus, the null hypothesis is rejected.