Medical Diagnostics Image Recognition

Detection of Brachial Plexus on Ultrasound Image


A medical surgery center with multiple locations in the USA.
This project is in the field of medical surgery, specifically shoulder surgery. Surgery is a medical specialty that uses operative manual and instrumental techniques on a person to investigate or treat a pathological condition such as a disease or injury, to help improve bodily function or appearance or to repair unwanted ruptured areas. Post-surgery effects are associated with discomfort and complications, like pain and soreness.

Currently, the patient’s pain is frequently managed by means of drugs, which causes plenty of undesirable side effects. One of the methods to reduce the patient’s pain instead of using drugs is implanting catheters that block or mitigate the pain at the source. Pain management catheters reduce drug addiction and speed up the patient’s recovery. So the catheter should be implanted into the correct area of the body and affect the nerves directly.

Project Objectives

Detection of Brachial Plexus and Location
To allow users to detect the nerve structure called the brachial plexus on the ultrasound picture and the exact area in the patient’s body to implant the catheter.

The Challenge

The main challenge of the project was to train and set up the neural network to provide users with a high segmentation accuracy. This task involved a lot of time to spend on setting the neural network learning rate, its size and defining the optimal learning deviation (optimal loss function).


To solve this problem, we chose UNet architecture. It is a special neural network architecture developed for biomedical images segmentation. The hyper-parameters tuning has shown that the maximum accuracy in recognition is achieved through the combination of Dice + Binary Cross-entropy as a loss function.

Shows the highlighted brachial plexus and its location

medical diagnostics image recognition
medical diagnostics image recognition


The script was developed using image processing, mapping and computer vision.

To start the microscope takes 10 pictures as an input. The images seen on the slide are sent electronically to a computer, or laptop. Next the algorithm recognizes the living and dead cells and marks them on the image. Next the script returns the images with the marked cells and several text reports containing detailed information about the cells. The script is currently being used by our client and is already helping them in their research.

*All case studies are for illustration purposes only. Due to NDA agreements between the client and the development team, project details cannot be disclosed.


Machine Learning Algorithm


Medical Research


NumPy, Pandas, Python, TensorFlow, Skimage

Areas of Expertise

Computer Vision, Machine Learning, Deep Learning, Mapping, Image Processing, Neural Networks


2 months


1 developer, 1 QA specialist