Applying Deep Learning technology to bring Healthcare to the
"Forgotten Billion"
Mine and cultivate existing medical archives using computational techniques seeking patterns that can help doctors with disease diagnosis, prognosis, and treatment.
Team with technology firms Health care organizations to access medical data in order to provide timely, doctor assisted solutions utilizing technologies such as portable devices, cloud computing, and deep learning
To create and predict Early Warning Systems for preventing fatal diseases and ailments
We are working in the Deep Learning space to solve healthcare problems. We seek to make products, which would complement the knowledge and assist the clinician in making faster and accurate diagnosis.
We are leveraging the cutting edge technologies like Deep Learning and artificial intelligence to increase the capacity of healthcare providers enabling them to offer higher quality care without over burdening the system.
Solutions using Deep Learning Algorithms have a higher rate of accuracy and early detection can save lives.
Artelus R&D team constantly strives to innovate new ways of developing accurate primary screening solution. Our team is working on developing primary screening tools to detect TB, Breast cancer and Lung cancer. We are also working in diagnostic solutions that would assist the doctors in accurate diagnosis for faster treatment by providing a comprehensive reporting of anomalies detected during primary screening process.
Our products offer primary screening solutions for problems that are inevitably going to strike, and preempt them from getting worse. Identifying people with diseases at early stage can help them avoid disease complications and expensive treatments. In many cases, screening can help people avoid onset of disease altogether. We are taking health care experience beyond the boundaries of hospitals and specialized clinics.
This will have the natural outcome of reducing cost, improving health and making the world a happy and healthy place to live in.
Great products are made by great teams and great teams are made of great individuals. We prefer to associate ourselves with people who are passionate about what they do, since that is how we are. We work to make a difference in the world with our work. Are you such a person too? Here are the openings we have currently- if you think you fit the bill, go ahead and apply! You can either send your resumes to contact@artelus.com or use the Apply button below.
| Open Positions | Job Description | Apply |
| Python Developer | View JD | Apply |
| Angular Developer | View JD | Apply |
| UI / UX Developer | View JD | Apply |
| Android Developer | View JD | Apply |
| Python Tech Lead | View JD | Apply |
| Data Scientist | View JD | Apply |
| DevOps Engineer | View JD | Apply |
| Software Test Engineer | View JD | Apply |
| Technical Architect | View JD | Apply |
| Quality Assurance Manager | View JD | Apply |
Towards Ophthalmologist Level Accurate Deep Learning System for OCT Screening and Diagnosis
Abstract: In this work, we propose an advanced AI based grading system for OCT images. The proposed system is a very deep fully convolutional attentive classification network trained with end to end advanced transfer learning with online random augmentation. It uses quasi random augmentation that outputs confidence values for diseases prevalence during inference. Its a fully automated retinal OCT analysis A… ▽ More
Towards Radiologist-Level Accurate Deep Learning System for Pulmonary Screening
Abstract: In this work, we propose advanced pneumonia and Tuberculosis grading system for X-ray images. The proposed system is a very deep fully convolutional classification network with online augmentation that outputs confidence values for diseases prevalence. Its a fully automated system capable of disease feature understanding without any offline preprocessing step or manual feature extraction. We have… ▽ More
Rethinking Convolutional Semantic Segmentation Learning
Abstract: Deep convolutional semantic segmentation (DCSS) learning doesn't converge to an optimal local minimum with random parameters initializations; a pre-trained model on the same domain becomes necessary to achieve convergence.In this work, we propose a joint cooperative end-to-end learning method for DCSS. It addresses many drawbacks with existing deep semantic segmentation learning; the proposed appr… ▽ More
Deep Learning: Generalization Requires Deep Compositional Feature Space Design
Abstract: Generalization error defines the discriminability and the representation power of a deep model. In this work, we claim that feature space design using deep compositional function plays a significant role in generalization along with explicit and implicit regularizations. Our claims are being established with several image classification experiments. We show that the information loss due to convolu… ▽ More
Diabetic Retinopathy Screening using Deep Learning Technology
The Deep Learning Computer model in reading Diabetic Retinopathy & Normal Images
Towards Human Level Accurate Deep Learning System for Diabetic Reinopathy Screening
1665/A, 14th Main Rd, Sector 7, HSR Layout, Bengaluru, Karnataka 560102
246 E Janata Boulevard, Suite 224, Lombard, Illinois, 60148, United States of America
The Binary by Omniyat Building,Floor P4, Office No: P409,Business Bay, Dubai, UAE
100%
image1.jpg - predection complete.
Result: Doctor review recommended(1).
Diabetic retinopathy affects over one third of all people with diabetes and is the leading cause of vision loss. Globally the prevalence of diabetes is increasing rapidly. Since DR is a progressive disease, early stage detection and treatment can save the patient from losing sight. Due to the alarming increase of Diabetic retinopathy the screening for DR every 6 months becomes important to check progression of DR.
Our AI Product Diabetic Retinopathy Screening System is a novel and cost effective screening tool for identifying presence of Diabetic Retinopathy with a Sensitivity and Specificity above 90.
100%
image1.jpg - predection complete.
Result: Bad Image(0).
The prevalence of Diabetic Retinopathy is increasing worldwide,due to these increasing numbers screening for early detection of DR and have regularly screening for every 6 months to check the progression of DR becomes important.
Our AI product Hansanet is used to grade the quality of retina image captured by Fundus camera during the DR screening, which the Doctors view for further diagnosis.
It is important for doctors to view gradable fundus images to accurately diagnose the presence or absence of DR versus viewing non gradable fundus images which might increase the chances of misdiagnosis due to poor quality image.
100%
1image.jpg - segmentation complete.
Result: Doctor review recommended(1).
Our AI product Nimi not only identifies the presence of DR during screening, it also segments the region for lesions or abnormalities present in fundus images, which helps the doctors to accurately diagnose the presence or absence of DR.
Social