Problem Statement
Patients’ waiting time at the hospital/doctor’s clinic is high. In addition to that sometimes patient cannot go to the hospital or the doctor’s clinic because of vast geographical distance. Hospital crowding because of non-emergency or non-fatal injury like redressing of injury has become a common place occurrence.
Solution
DTC built a Deep Learning (DL) based model trained on thousands of images. This trained model accepts images and identifies the wound region, and consequently finds the area of the wound, which is measured in square centimeters.
-
Tech stack
- Deep Learning algorithms
- Python, Pytorch, and TensorFlow
- Flask, Postman
Solution Benefits
DTC’s DL based solution is able to
accurately identify the wound
region and accurately measure the
wound area in sq cm. The
difference in measurement by the
DL model to the ground truth is in
the order of 10e-1 sq cm. This
method allows doctor to
accurately understand the
patients’ wound healing progress
and prescribe necessary redressing
or medicine
