Deep Learning Use Case
Improving medical prediction of pneumonia cases using Deep Learning
![Deep Learning Use Case 1 Captura de pantalla 2021 09 15 a las 17.13.05](https://apiumhub.com/wp-content/uploads/2021/09/Captura-de-pantalla-2021-09-15-a-las-17.13.05.png)
![Deep Learning Use Case 2 Captura de pantalla 2021 09 15 a las 17.13.19](https://apiumhub.com/wp-content/uploads/2021/09/Captura-de-pantalla-2021-09-15-a-las-17.13.19.png)
Fig1. Example of dataset image with pneumonia AND example of normal dataset. Lung X-ray with pneumonia shows opaque spots on the image.
The dataset released in 2018 by Kermany et al. has a sample of 5840 images belonging to lung radiographs labelled as pneumonia diagnosis and non-pneumonia X-ray radiographs. These images have been selected under human quality control and labelled according to an expert’s diagnosis before being validated for training in the system.
1- Dataset Preparation
![Deep Learning Use Case 3 Captura de pantalla 2021 09 15 a las 17.15.48](https://apiumhub.com/wp-content/uploads/2021/09/Captura-de-pantalla-2021-09-15-a-las-17.15.48.png)
Fig 2. The dataset is subdivided into Train, Test and Validation sets.
![Deep Learning Use Case 4 Captura de pantalla 2021 09 15 a las 17.16.47](https://apiumhub.com/wp-content/uploads/2021/09/Captura-de-pantalla-2021-09-15-a-las-17.16.47.png)
Fig 3. Division of the dataset into training, test and validation sets with the processes used for each dataset.
2- Model Architecture
![Deep Learning Use Case 5 Captura de pantalla 2021 09 15 a las 17.19.13](https://apiumhub.com/wp-content/uploads/2021/09/Captura-de-pantalla-2021-09-15-a-las-17.19.13.png)
Fig 4. Schematic of convolutional neural network architecture. The convolutional layers help with feature learning, the final perceptron layers classify images with Pneumonia.
3- Evaluating the performance of the model
![Deep Learning Use Case 6 Captura de pantalla 2021 09 15 a las 17.21.40](https://apiumhub.com/wp-content/uploads/2021/09/Captura-de-pantalla-2021-09-15-a-las-17.21.40.png)
Fig 5. Loss and accuracy functions evaluating training and validation datasets.
Conclusion
![Deep Learning Use Case 7 Captura de pantalla 2021 09 15 a las 17.23.53](https://apiumhub.com/wp-content/uploads/2021/09/Captura-de-pantalla-2021-09-15-a-las-17.23.53.png)
Do you want a data-driven solution?
![Deep Learning Use Case 8 apiumhub software development projects barcelona](https://apiumhub.com/wp-content/uploads/2021/02/projects-scaled.jpg)