Detection of Pneumonia from Chest X-ray Images Utilizing MobileNet Model

Abstract

Pneumonia has been directly responsible for a huge number of deaths all across the globe. Pneumonia shares visual features with other respiratory diseases, such as tuberculosis, which can make it difficult to distinguish between them. Moreover, there is significant variability in the way chest X-ray images are acquired and processed, which can impact the quality and consistency of the images. This can make it challenging to develop robust algorithms that can accurately identify pneumonia in all types of images. Hence, there is a need to develop robust, data-driven algorithms that are trained on large, high-quality datasets and validated using a range of imaging techniques and expert radiological analysis. In this research, a deep-learning-based model is demonstrated for differentiating between normal and severe cases of pneumonia. This complete proposed system has a total of eight pre-trained models, namely, ResNet50, ResNet152V2, DenseNet121, DenseNet201, Xception, VGG16, EfficientNet, and MobileNet. These eight pre-trained models were simulated on two datasets having 5856 images and 112,120 images of chest X-rays. The best accuracy is obtained on the MobileNet model with values of 94.23% and 93.75% on two different datasets. Key hyperparameters including batch sizes, number of epochs, and different optimizers have all been considered during comparative interpretation of these models to determine the most appropriate model.

Artificial intelligence and feature based transfer learning framework for diagnosis of chest diseases using radiology images

“…The MobileNet model achieved the highest accuracy, scoring 94.23% and 93.75% on two datasets. Key hyperparameters like batch sizes, epochs, and optimizers were considered during the comparison process [17]. To address dataset disparities and guarantee equitable participation, the method makes use of custom splitting.…”

Untitled

“…The study has successfully showcased the potential of the SSD network for automated diagnosis and detection of lung diseases. [13] Single Shot Detection MobileNet model 93.24% Reshan et al [24] MobileNet Model 94.23% Apostolopoulos and Mpesiana [25] MobileNetV2 96.78% Karaci et al [26] VGGCOV19-NET: YOLOv3 97.16% Kaya et al [27] MobileNetV2+Exponential fine-tuning 97.61% Kedia et al [28] CoVNet…”

Detection of Pneumonia Using A Hybrid Approach Consisting of MobileNetV2 and Squeeze-and-Excitation Network

“…Regrettably, pneumonia constitutes merely one among numerous pulmonary ailments, and as a result, radiographic findings don't consistently verify a pneumonia diagnosis. Consequently, given the present technology available, it remains unfeasible to definitively differentiate pneumonia from alternative lung disorders based on radiological criteria [1,2].…”

“…Reshan et al [2] introduced an advanced DL model for distinguishing between severe and normal cases of pneumonia. They harnessed eight pretrained models: ResNet50, ResNet152V2, DenseNet121, DenseNet201, Xception, VGG16, EfficientNet.…”

“…The proposed MSENet model achieved 98.81% classification accuracy. The MobileNet model developed by Reshan et al[2] achieved an accuracy of 94.23%, while the Quaternion CNN model developed by Singh et al[4] reached 93.75%. Szepesi et al[10] achieved a 97.2% accuracy using CNN with modified dropout.…”