THE INDIAN Institute of Technology, Kharagpur has come up with a smartphone app, which would act as an “assistive pathological tool” to help automatic detection of malaria.
As of now, the definitive diagnosis of malaria infection can be done only by a pathologist, where he manually examines the presence of the parasite in stained blood smear slides under a light microscope. “The major drawback of such manual examination is subjectivity, which varies from pathologist to pathologist in terms of their experience and knowledge. Additionally, it is of course a time consuming evaluation,” said Professor Chandan Chakraborty of BioMedical Imaging Informatics (BMI) laboratory at IIT’s School of Medical Science and Technology.
WHAT ELSE IS MAKING NEWS
To provide a reliable and rapid detection of malaria, researchers, led by Chakraborty, have developed a smartphone-based android app for automatic recognition of parasite-infected red blood cells (RBCs) and its count. For this, Chakraborty’s team has worked in tandem with Midnapore Medical College Hospital pathologist Dr Ashok Kumar Maity. Their research, on ‘Medical Imaging Informatics For Malaria Detection’, was funded by a CSR grant from Microsoft Corporation through their partner CAF India.
According to the researchers, the smartphone would be attached to an adapter with the eye-piece of conventional light microscopes that are available in any pathology lab. The stained blood smear slide is then kept under the microscope and the smartphone camera grabs microscopic images from the slide. These images can be saved digitally and then the app could be used to detect infected RBCs present in the image.
The technology is expected to be particularly useful for labs where no expert pathologist is available. Para-medical or trained personnel will also be able to use the app. “The app uses microscopic image analytics and machine learning techniques for automatically detecting only malaria parasite-infected RBCs among others from microscopic image frames. It can be very useful for rapid malaria screening under tele-pathology framework,” Chakraborty said.
Till now, the app has been tested on more than 200 microscopic images of 80 patients as a pilot study with more than 90 per cent accuracy, he added. “As the malaria diagnostic app is developed in an open source platform, it may cost very less or nothing at all,” he said.