Fig 1.
Examples of chest X-ray images and radiology reports.
Table 1.
Summarized specification of publically available chest X-ray datasets.
Fig 2.
VGG-16 neural network architecture with highlighted sizes and each layer units.
Fig 3.
VGG-16 architecture and associated parameters.
Fig 4.
Complete and combined model of CNN image embedder and LSTM with the word embedding.
The LSTM is shown in the unrolled version. All LSTMs are using the same parameters.
Fig 5.
Long Short-Term Memory (LSTM) network architecture: In the above diagram the memory block comprises a cell c which is essentially controlled by three gates.
These gates are the input, the forget and the output gates.
Table 2.
Proposed technique hyper parameters and related configuration.
Table 3.
Comparison of proposed technique with different combination of available options in terms of BLEU score up to n gram for the medical report generated on the IU CXR dataset.
Table 4.
Comparison of proposed technique with existing state of the art in terms of BLEU score up to n gram for the medical report generated on the IU CXR dataset.
Table 5.
Comparison of proposed technique with current state of the art techniques in terms of BLEU-4 for the medical report generated on the MIMIC-CXR dataset.
Fig 6.
Graph between accuracy and epochs using proposed model.
Fig 7.
Graph between loss and epochs using proposed model.
Fig 8.
Different examples of generated results.
Column 1 contains the original image, column 2 contain the attention maps and column 3 contain the actual and predicted captions.
Fig 9.
Randomly selected CXR from datasets used along with original and predicted reports.