We’re building an artificial intelligence (AI) platform called Manthana (मंथन) which helps us analyse visual medical data efficiently. Manthana has enabled us to work on five major high-volume, screening processes of the healthcare industry – analysis of peripheral blood smears, urine microscopy, semen, fundus & OCT scans and chest x-rays.

Shonit™ : is a complete peripheral blood smear analyser solution which automates the routine tasks like differential counts. Additionally, it provides a screening solution for various parasitic infections like malaria and disorders like anaemia. It starts by capturing images of blood smear slides with a phone fitted on a microscope. The images are analysed on cloud using state of the art image processing and deep learning techniques. Finally it generates reports containing differential blood counts, visualisations on various blood metrics and suggestions about any abnormalities. The report can then be reviewed by pathologists on any net connected device, from anywhere in the world, making this product useful for areas having a dearth of specialists.

Status : Shonit has undergone 3 clinical validations and is being used in a closed beta by our partners.

Shrava: After serum chemistry and blood, urine analysis is the most common pathology test. Our urinalysis solution detects substances like crystals and casts, cellular material like epithelial cells, RBCs and WBCs, and also calculates related volumetric parameters. The presence of these bodies in urine are indicative of a host of metabolic and kidney disorders. In urine microscopy the sample is liquid and multilayered unlike blood. This poses a greater challenge in the image capturing process.

Status: Shrava is nearing clinical validation stage

Aadi – Semen analysis is one of the core aspects in infertility investigations for measurement of male fecundity in clinical andrology. Our capability, Aadi, uses state-of-the-art artificial intelligence techniques to estimate pivotal parameters of ejaculated human spermatozoa like progressive motility, concentration and morphological characteristics. These parameters aid andrologists to correlate with clinical findings and help them to predict the ability of the spermatozoa to fertilise the oocyte.

Status: Aadi is nearing clinical validation stage

Dhrishti (Retinal Scans Analysis) – The scope of the Retinal Scan Analysis solution covers two major imaging modalities used by ophthalmologists to examine the inner eye (retina).

  1. Fundus Photography: This captures images of the fundus (back wall) of the eye – covering the retina, the optical disk and the macula. This is the more popular screening procedure of the two.
  2. Optical Coherence Tomography (OCT) Images: This provides high resolution cross sectional views of the internal retinal tissue of the eye. This is a more recent development and hasn’t caught on as much as fundus photography, specially in developing countries like India.

This solution aims to use computer vision and artificial intelligence techniques to identify and localise base pathologies and abnormal structures in both fundus and OCT scans. These findings can be used to provide various diagnostic indications to the ophthalmologist about the patient.

Status: Retinal Scan analysis is in product development. The research phase is complete.

Chest X-Ray Analysis – The chest x-ray is the most common diagnostic scan performed in radiology. It reveals images of the heart, lungs, blood vessels, ribs, etc. We are building a screening solution for chest x-rays, which separates the normal cases from those having abnormalities. It points out the abnormalities (fractured ribs, lung infections, etc.) when present. The solution works on digital x-ray images from any standard x-ray machine.

Status: Chest x-ray analysis is in research.