In our final project at T5 bootcamp we will build models that can detect the presence of pneumonia with chest X-rays using Deep Convololutional Neural Network. Chest X-rays are currently the best available method for diagnosing pneumonia, playing a crucial role in clinical care. Over 150 million people get infected with pneumonia on an annual basis especially children under 5 years old.
Providing a clinical aid for higher accuracy image reads of diseases that are hard to diagnose. Clinical diagnoses from chest X-rays can be challenging, however, even by skilled radiologists. The diagnosis of pneumonia from chest X-rays is difficult for several reasons:
- The appearance of pneumonia in a chest X-ray can be very vague depending on the stage of the infection
- Pneumonia often overlaps with other diagnoses
The dataset is organized into 3 folders (train, test, validation). There are 5,863 X-Ray images (JPEG) and 2 categories (Pneumonia/Normal). Chest X-ray images (anterior-posterior) were selected of pediatric patients of one to five years old.
- High accuracy
- Less medical test
- Low cost
- Reduce time
- Reduce death rate
- Getting knowledge about machine learning techniques
- Determining binary classification of lung diseases
- Sequential
- Vgg16
- Vgg19
- MobileNetV2
- InceptionV3
Languages : Python Tools/IDE : Google colab Libraries : numpy, pandas, matplotlib, Keras, TensorFlow