|Published||January 28, 2023|
Since 2002, Median Technologies has been expanding the boundaries of the identification, interpretation, analysis and reporting of imaging data in the medical world. Our core activity is to develop advanced imaging software solutions and platforms for clinical drug development in oncology, diagnostic support, and cancer patient care. Our software solutions improve the management of cancer patients by helping to better identify pathologies, develop and select patient-specific therapies (precision medicine).
The company employs a highly-qualified team and leverages its scientific, technical, medical, and regulatory expertise to develop innovative medical imaging analysis software based on Artificial Intelligence, cloud computing and big data. We are driven by our core values that are essential to us. These values define who we are, what we do, the way we do it, and what we, as Median, aspire to:
• Leading innovation with purpose
• Committing to quality in all we do
• Supporting our customers in achieving their goals
• Always remembering to put the patient first
Today, we are a team of more than 220 people spread worldwide in the US, Europe and China. Our company is growing in a fulfilling international and multicultural environment.
Lung cancer has the most impact in cancer related death. Medical imaging such as CT scan has an important role to detect such disease. Generally, radiologist read those images to make diagnosis and decide the treatment for patients. Reading a CT scan is very time consuming and error prone, which could lead to both false positive and false negative in the decision. Therefore, many efforts have been assigned to create computer assist device (CAD) to read and analyze CT scan automatically and increase radiologist performance.
There are two stages to process a lung CT scan in CAD system. The first stage read the whole scan and identify all suspected lesions inside lung (CADe), and the second stage characterize each lesion and diagnose their malignancy (CADx). In the screening program that has been applied in some countries, especially America, low dosed CT scan is used. This type of CT scan does not well reflect all the lesions in the image and therefore lots of false positives are generated in the CADe which is called nodule detection. The model can detect vessels or bronchus instead of nodules, which could potentially cause issue in later stages of the pipeline, and make the results become difficult to present to radiologists. Some research has been done to reduce false positives of nodule detection in lung CT scan, however the issue is still not properly solved.
Objective of this internship is to research and implement an effective solution to classify false positive from a list of bounding boxes detected from the nodule detection model, without filtering the true lesion.
A good result can lead to a publication, and the algorithm will be deployed in our iBiopsy product of Lung Cancer Screening.
In this internship, we are looking for someone who has experience in programming notably python. The candidate should also have some experiences in research and computer vision domain.
He/she should ideally have experience in deep learning, especially on classification problems using pytorch framework.
Skills and Knowledge
• Computer Vision
• Deep learning, pytorch
Education: in the process of obtaining a Master’s Degree or an Engineer Degree in any field related
to Deep Learning.
- Good communication in English, spoken and written. French would be a plus.
- Curiosity, open-mindedness, determination and persistence, patience