Table 1.
Dataset for model development and evaluation.
Fig 1.
Flow diagram of the pre-processing module process.
Fig 2.
Architecture of DenseNet.
Table 2.
Summary of AI models for the diagnosis of pneumonia.
Table 3.
Performance of AI models for pneumonia.
Table 4.
Performance of the ensemble models.
Fig 3.
ROC curves of AI models for pneumonia.
Fig 4.
AI probability score changes and heatmap in improved patient.
(a) In a 42-year-old female patient, initial chest X-ray shows bilateral patchy increased opacity, compatible with pneumonia. AI pneumonia model (A-2) shows the probability score of 0.787 and color map for pneumonia. (b) After 7 days of treatment, the chest X-ray shows marked improvement. AI pneumonia model (B-2) shows the decrease of probability score (0.318) for pneumonia.
Fig 5.
AI probability score changes and heatmap in aggravated patient.
(a) In an 81-year-old male patient, initial chest X-ray shows bilateral patchy increased opacity, compatible with pneumonia. AI pneumonia model (A-2) shows the probability score of 0.833 and color map for pneumonia. (b) After 7 days of treatment, the chest X-ray shows slight aggravation. AI pneumonia model (B-2) shows slight increase of probability score (0.876) and increased extent of color map for pneumonia.
Fig 6.
Box plot of probability score changes on follow-up images on pneumonia test dataset (n = 100).