Malaria Parasite Detection

AI COMMONS HEALTH & WELLBEING HACKATHON SOLUTIONS

OVERVIEW

The AI Commons Project is a proof of concept of a new methodology of developing Artificial Intelligence solutions that allows anyone, anywhere to benefit from the possibilities that AI can provide. The project aims to increase/improve the accessibility, reproducibility, contextualization and enhancement of Artificial Intelligence solutions globally and especially in emerging markets.

The project aims to demonstrate how a global community of AI experts can learn and co-create mutually beneficial solutions with the opportunity for cross-county incremental enhancement.

STATEMENT OF PURPOSE

INTRODUCTION

Introduce yourself (Documentation team)
Name(s) and institution/organization affiliated with

Data Science Nigeria

Introduce yourself (Solution owners)
Name(s) and institution/organization affiliated with

Gbemileke Onilude, Data Science Nigeria and Wuraola Oyewusi, Data Science Nigeria

PROBLEM DEFINITION

Define the problem
What problem does the solution seek to solve? For how long has the problem existed? How prevalent is problem? Provide any background information relevant to the problem.

Plasmodium falciparum malaria is one of the greatest world health burdens with over 200 million cases globally and almost half a million deaths yearly, most of them in Sub-Saharan Africa. Thick Film Microscopy (TFM) remains the gold standard for diagnosing malaria in sub-Saharan regions. TFM relies on the availability of a trained human microscopist to visually inspect Giemsa stained blood smears under a light microscope to identify and count the P. falciparum parasites. This is time-consuming and subject to human error. Without the presence of a trained human microscopist diagnosing is almost impossible.

Who are those affected by the problem (Problem owners)
Class of people. Country/region where they live. Impact of problem on their lifestyle

People from Sub-Saharan Africa are mostly affected. Pregnant women and children face higher fatality from the parasite.

How is the problem currently solved?
Describe the current/existing workaround for the problem

A blood sample is taken from the paitent and a trained microscopist examines it with the help of a microscope to detect malaria parasite

Yes, Malaria parasite detection using machine learning and cancer detection using machine learning have been developed

SOLUTION

What is this solution about?
Describe the solution. Describe the solution space and opportunity. When was the solution first released? When was the last release? Link to the solution Deck/publications

The solution developed is a computer vision technique able to accurately detect Malaria Parasites (MP) and White Blood Cell nuclei (WBC) in color brightfield digitized images of Giemsa-stained thick blood films captured with a 100x/1.4 oil-immersion objective lens.
Presentation deck: Here

Describe the outputs of the solution
Please ensure that your solution output sufficiently address the problem defined in the section above

The output of the solution is an image with bounding boxes drawn within it for detecting both malaria parasite and white blood cell within an image.

Who are the key stakeholders?

Health practitioners
Patients

What is the expertise types required to develop this solution?
Please provide all technical expertise required to build solution and their roles in the solution development

A trained microscopist to create the training dataset and a machine learning engineer to build the model.

What are the challenges faced while developing the solution
Decribe the challenges/obstacles faced

Small amount of training data and low computational resources

What are your recommendations to improve the solution?
Provide a list of recommendations, if any, to improve the solution

Get more training data.

Have you updated this solution documentation before?
When and how often? What sections have changed? Is the documentation updated every time the solution is retrained or updated?

No.

USAGE

What is the intended use of the solution output?
Briefly describe a simple use-case

For use in hospitals and labs to aid in the fast detection of malaria parasites.

Who are the target users?

Laboratory technicians.

DOMAIN AND APPLICATIONS

What are the domains and applications the solution was tested on or used for?
Were domain experts involved in the development, testing, and deployment? Please elaborate

Yes. Expert microscopist was used to label the train dataset.

List applications that the solution has been used for in the past
Please provide information about these applications or relevant pointers. Please provide key performance results for those applications.

None.

DATASET

Describe the dataset
Please provide a brief description of the dataset

The dataset consists of images captured using an upright brightfield microscope, a total number of 239 images which were already annotated by expert microscopists. The annotation consisting of 2986 Malaria Parasites and 1272 White Blood Cell nuclei from 13 unique blood smears

For what purpose was the dataset created?
Was there a specific task in mind? Was there a specific gap that needed to be filled? Please provide a description

Creation of malaria parasites detection model

Who created this dataset (e.g., which team, research group) and on behalf of which entity (e.g., company, institution, organization)?

The dataset was created by researchers from University College London and University College Hospital, Ibadan.

COMPOSITION

What do the instances that comprise the dataset represent (e.g., documents, photos, people, countries)?
Are there multiple types of instances (e.g., movies, users, and ratings; people and interactions between them; nodes and edges)? Please provide a description.

Images and Json file.

How many instances are there in total (of each type, if appropriate)?

Images = 239, Json files = 13

Does the dataset contain all possible instances or is it a sample (not necessarily random) of instances from a larger set?
If the dataset is a sample, then what is the larger set? Is the sample representative of the larger set (e.g., geographic coverage)? If so, please describe how this representativeness was validated/verified. If it is not representative of the larger set, please describe why not (e.g., to cover a more diverse range of instances, because instances were withheld or unavailable).

No, it does not contain all possible instances available. All available set would be all individual blood smear diagnosis of malaria

What data does each instance consist of? “Raw” data (e.g., unprocessed text or images)or features?
In either case, please provide a description

Each instance consist of an Image of Giemsa-stained thick blood films captured with a 100x/1.4 oil-immersion objective lens and an associated Json file that describes the image.
A sample image in the dataset is shown here.

Is there a label or target associated with each instance?
If so, please provide a description.

JSON file: An annotation file consisting of the location of malaria parasites and white blood cell nuclei

Is any information missing from individual instances?
If so, please provide a description, explaining why this information is missing (e.g., because it was unavailable). This does not include intentionally removed information, but might include, e.g., redacted text.

No.

Are relationships between individual instances made explicit (e.g., users’ movie ratings, social network links)?
If so, please describe how these relationships are made explicit.

No.

Are there recommended data splits (e.g., training, development/validation, testing)?
If so, please provide a description of these splits, explaining the rationale behind them

No.

Are there any errors, sources of noise, or redundancies in the dataset?
If so, please provide a description.

No.

Is the dataset self-contained, or does it link to or otherwise rely on external resources (e.g., websites, tweets, other datasets)?
If it links to or relies on external resources, a) are there guarantees that they will exist, and remain constant, over time; b) are there official archival versions of the complete dataset (i.e., including the external resources as they existed at the time the dataset was created); c) are there any restrictions (e.g., licenses, fees) associated with any of the external resources that might apply to a future user? Please provide descriptions of all external resources and any restrictions associated with them, as well as links or other access points, as appropriate

The dataset is self – contained.

Does the dataset contain data that might be considered confidential (e.g., data that is protected by legal privilege or by doctorpatient confidentiality, data that includes the content of individuals non-public communications)? If so, please provide a description

No.

Does the dataset contain data that, if viewed directly, might be offensive, insulting, threatening, or might otherwise cause anxiety?
If so, please describe why.

No.

Does the dataset relate to people?
If not, you may skip the remaining questions in this section.

Yes.

Does the dataset identify any subpopulations (e.g., by age, gender)?
If so, please describe how these subpopulations are identified and provide a description of their respective distributions within the dataset

No.

Is it possible to identify individuals (i.e., one or more natural persons), either directly or indirectly (i.e., in combination with other data) from the dataset?
If so, please describe how.

No.

Does the dataset contain data that might be considered sensitive in any way (e.g., data that reveals racial or ethnic origins, sexual orientations, religious beliefs, political opinions or union memberships, or locations; financial or health data; biometric or genetic data; forms of government identification, such as social security numbers; criminal history)?
If so, please provide a description

No.

COLLECTION PROCESS

Does the dataset relate to people?
If not, you may skip the remainder of the questions in this section.

Yes

PREPROCESSING/CLEANING/
LABELLING

Was any preprocessing/cleaning/labeling of the data done (e.g., discretization or bucketing, tokenization, part-of-speech tagging, SIFT feature extraction, removal of instances, processing of missing values)?
If so, please provide a description. If not, you may skip the remainder of the questions in this section.

Labeling was done by expert microscopist.

Was the “raw” data saved in addition to the preprocessed/cleaned/labeled data (e.g., to support unanticipated future uses)?
If so, please provide a link or other access point to the “raw” data.

No.

Is the software used to preprocess/clean/label the instances available?
If so, please provide a link or other access point.

No.

USES

Is there a repository that links to any or all papers or systems that use the dataset?
If so, please provide a link or other access point

No.

What (other) tasks could the dataset be used for?

Tasks related to the solution.

Is there anything about the composition of the dataset or the way it was collected and preprocessed/cleaned/labeled that might impact future uses?
For example, is there anything that a future user might need to know to avoid uses that could result in unfair treatment of individuals or groups (e.g., stereotyping, quality of service issues) or other undesirable harms (e.g., financial harms, legal risks) If so, please provide a description. Is there anything a future user could do to mitigate these undesirable harms?

Are there tasks for which the dataset should not be used?
If so, please provide a description.

Cancer prediction, blood type prediction, e.t.c.

MAINTENANCE

Who is supporting/hosting/maintaining the dataset?

University College London and University College Hospital, Ibadan

DATASET PUBLICLY AVAILABLE

Did the solution require any transformation of the data in addition to those provided in the datasheet? If yes, specify which dataset(s) the transformation was done on and describe the transformation

No.

Did you use synthetic data? If yes, how was it created? Brieﬂy describe its properties and the creation procedure.

No.

MODEL

MODEL DETAILS

A clear description of the model.
Please provide the model date, model version, model type and Information about training algorithms, parameters, fairness constraints or other applied approaches, and features

Model date: 2019. The model built is an object detection model, The model was built using Mask-RNN which uses ResNet50 for Feature Extraction

A clear description of the data preparation for the model.
Please provide details of preprocessing, feature engineering and feature selection.

The dataset was loaded into the workspace from a file directory, each image was matched with is annotation file and feed into the model as an input. the image input shape was 2560 by 2160 by 3

Is a pre-trained model used?
If yes, please give a brief description of the pre-trained model(s)

The Model training started with a weights file that’s been trained on the COCO dataset. Coco dataset has about 120000 images and does not contain micrographs or biomedical images but the data is large enough to have learned features from objects of similar shape with regions of interest.

A clear explanation of any assumptions.

None.

When were the models last updated?
How much did the performance change with each update? How often are the models retrained or updated?

None.

EVALUATION

TESTING THE SOLUTION

Describe the testing methodology
Please provide details on train, test and holdout data. What performance metrics were used? (e.g. accuracy, error rates, AUC, precision/recall). Please briefly justify the choice of metrics.

The dataset was split in the ratio 80:10:10 (train, validation, and test dataset). The performance metric used is mean average precision (mAP), it is a very important metric to use when building an object detection model.

Describe the test results
Were latency, throughput, and availability measured? If yes, briefly include those metrics as well.

The model achieved a mean average precision of 0.6 with a training time of more than 2 hours.

TESTING BY THIRD PARTIES

Is there a way to verify the performance metrics (e.g., via a service API )?
Briefly describe how a third party could independently verify the performance of the service. Are there benchmarks publicly available and adequate for testing the service

None.

In addition to the solution provider, was this service tested by any third party?
Please list all third parties that performed the testing. Also, please include information about the tests and test results.

None.

RESULT

RESULT DETAILS

A clear description of the model result.
Please include the range of hyper-parameters considered, method to select the best hyper-parameter configuration, and specification of all hyper-parameters used to generate results.

The model was trained with an epoch of 30, steps per epoch of 100. The other hyper-parameters were held constant as inherent from the pre-train model. Try and error was used to determine the best epoch to use

The exact number of training and evaluation runs

30.

A clear definition of the specific measure or statistics used to report results.

Mean average precision for a set of queries is the mean of the average precision scores for each query.