Open Science for Improve diagnostics of Breast Cancer through Artificial Intelligence and Digital Pathology.
Preject's repository for the OLS5 Hope cohort 2022 project: Open Science for Improve diagnostics of Cancer through Artificial Intelligence and Digital Pathology
Content:
Cancer is becoming increasingly prevalent among the group of treatable diseases in African countries. In sub-Saharan Africa, only 10% of histopathology needs are met and this is a major barrier to comprehensive management of cancers (1). There is a shortage of clinicians and pathologists available for cancer diagnosis and treatment. One of the critical factors in treatment efficiency is the correct and timely diagnosis of specimens by pathologists. However, there is currently a significant shortage of cancer care clinicians in Africa and an even more considerable shortage of pathologists. In Cameroon, there are 19 pathologists currently in practice for 22,179,707 inhabitants (2). The absolute number of patients with cancer in Cameroon was estimated to be 25,000 cases a year.
Diagnosis of cancer relies on histology in nearly 80% of cases, cytology in 10%, and clinical diagnosis in 10%. There is, therefore, an urgent need to develop a rapid, highly sensitive and diagnostic tool for the diagnosis of cancers, to increase cancer treatment efficacy and reduce overtreatment of tumors clinically suspicious for malignancy.
We propose a hybrid diagnosis method with a deep Learning algorithm applied on hematoxylin and eosin histology slides. Digital microscopy and telepathology were already successfully used to mitigate the lack of pathologists in Cameroon, thus confirming the availability of a robust dataset for our project (1). Following splitting into training, validation and test sets, we will use CNNs as algorithms on the collected images to train the algorithm before deployment and tests. In addition to automated diagnostic, the developed program will have specific features such as sample information storage and tracking software as well as image optimization and analysis tools.
The aim of this project is to develop a hybrid diagnosis method combining deep Learning algorithms and Digital microscopy of stained specimens for diagnosis of cancers, breast cancer in particular.
Open and multy faceted contribution to this project are highly encouraged! Contributrions of any form following personnal interest, availability, or skill can be made through this project repository on GitHub. All participants are expected to follow our project's code of conduct and check the Contributions Guidelines.
If you want to report a problem or suggest an improvement, feel free to send a pulled request to this Github repository or contact a project's team members following details below.
- Jafsia elisee Personal info: JAFSIA Elisee is the head of the Electromechanical and Artificial Intelligence department at MboaLab in Cameroon. JAFSIA is holder of a MSc in Material sciences from the University of Yaounde I as well as a MEd in Physics from the Higher teacher’s training college of Yaounde. He is currently member of the DIDA (Digital diagnostics for better healthcare in Africa) network and the technical lead for the OpenFlexure Microscope project in the MbaoLab.
Timezone: Africa/Douala Location: Cameroun Contact info: Personal email: "jafsia elisee" [email protected] Username on community forums or chat: Elja GitHub profile: https://www.github.com/jafsia GitLab profile: https://gitlab.com/jafsia Blog: https://www.linkedin.com/jafsiaelisee Twitter profile: https://twitter.com/euclude
- Stephane Fadanka Personal info: Stephane Fadanka is a Molecular Biology researcher and a fervent advocate of Open Science in Africa with a particular interest in plant and synthetic biotechnology. Carrying a long-standing passion for agriculture and plant biotechnology, he conducted a study on microbial host interaction for integrated pest management to Masters level. His current research interests include (1) developing and adapting modern Biotechnology tools and methods to be used in low resource settings and (2) screening of novel, cheap and environmentally friendly biologically active compounds from microorganisms and (3) the development of cost-effective and widely accessible plant propagation methods. Stephane is currently the Executive Director of MboaLab and has close to two years of professional experience as a researcher then research manager for the UK-based social enterprise Beneficial Bio Ltd.
Timezone: Africa/Douala Location: Yaoundé, Cameroon Contact info: Personal email: "Stephane Fadanka" [email protected] Username on community forums or chat: Stephane Fadanka GitHub profile: https://github.com/Fadanka GitLab profile: https://gitlab.com/stephanefadanka Twitter profile: https://twitter.com/StephaneFadanka
- Nodira Ibrogimova Personal info: Nodira Ibrogimova is a Machine Learning enthusiast with 3+ years of experience in Web Development and Machine Learning.
Her passion in Computer Science and Artificial Intelligence has ultimetely lead to hold a Bachelor's Degree from South Korean university - Inha University.
Currently researching and working on early diagnosis tools.
Timezone: (GMT+5) Location: Uzbekistan Contact info: Personal email: "Nodira Ibrogimova" [email protected] Username on community forums or chat: Nodira Ibrogimova GitHub profile: https://github.com/NodiraIbrogimova