Problem Statement:

Malaria is a threatening disease caused by parasites transmitted to people through the bites of infected female Anopheles mosquitoes. It is preventable and curable. Plasmodium parasites cause malaria. The parasites are spread to people through the bites of infected female Anopheles mosquitoes, called "malaria vectors." Five parasite species cause malaria in humans, and 2 of these species – P. falciparum and P. vivax – pose the greatest threat.

Diagnosis of malaria can be difficult:

• Where malaria is not endemic anymore (in the United States), healthcare providers may not be familiar with the disease. Clinicians seeing a malaria patient may forget to consider malaria among the potential diagnoses and not order the needed diagnostic tests. Laboratorians may lack experience with malaria and fail to detect parasites when examining blood smears under the microscope.


• Malaria is an acute febrile illness. In a non-immune individual, symptoms usually appear 10–15 days after the infective mosquito bite. The first symptoms – fever, headache, and chills – may be mild and difficult to recognize as malaria. However, if not treated within 24 hours, P. falciparum malaria can develop severe illnesses, often death.

Usage:

This dataset contains segmented cells from the thin blood smear slide images from the Malaria Screener research activity. To reduce the burden for microscopists in resource-constrained regions and improve diagnostic accuracy, therefore, proposes automated detection of malaria using a deep learning framework. 

Dataset:

Dataset link: https://www.kaggle.com/iarunava/cell-images-for-detecting-malaria

This dataset contains 2 folders

• Infected


• Uninfected
  And a total of 27,558 images.

Model Used:

CNN (Convolutional Neural Network) network is built for the training. This network architecture is as follows:

• It Uses 3×3 CONV filters.


• Mound these filters on top of each other.


• Performed max-pooling.


• Use depthwise separable convolution (more efficient, takes up less memory)


• Taking optimizer as adam and loss function as categorical_crossentropy.

SeparableConv2D - The SeparableConv2D is a variation of the traditional convolution that was proposed to compute it faster. It performs a depthwise spatial convolution followed by a pointwise convolution which mixes the resulting output channels.

BatchNormalization - Increases the speed for loss to converge by normalizing the hidden units to zero mean and unit variance.

MaxPooling2D - Downsamples the input along its spatial dimensions (height and width) by taking the maximum value over an input window (of size defined by pool_size) for each channel of the input. Strides shift the window along each dimension.

Dropout - To prevent the nodes from depending on each other. In addition, it reduces overfitting by dropping nodes in each layer with some probability.

Dense - used in the output layer, with 2 units, and activation function as softmax.

Categorical Crossentropy: Categorical cross-entropy is a loss function that is used in multi-class classification use cases. These are use cases where an example can only belong to one out of many possible categories, and the model must decide which one

Adam Optimizer: Adam(Adaptive Moment Estimation) is an optimization algorithm that can be used instead of the classical stochastic gradient descent procedure to update network weights iterative based on training data. Adam works with momentums of first and second order. The intuition behind the Adam is that we don’t want to roll so fast just because we can jump over the minimum, we want to decrease the velocity a little bit for a careful search.

Results:

The results are displayed as-