Computer Vision for Healthcare

Computer vision is a technology based on image processing and synthesis. It usually involves machine learning and allows AI to simulate human vision. This technology aims to save time by automating manual image analysis and achieving a higher level of accuracy. For this purpose, an algorithm is fed with a vast amount of representative pictures and trained to detect particular parts of them. Developers currently use computer vision in a wide range of spheres: from Snapchat and Instagram masks to scientific research and medical objectives. 

Main Reasons to Use Computer Vision in the Medical Field

Even though the state of the art computer vision does not enable technology to replace medical professionals, it does simplify their work. Here are some significant causes to start using computer vision in health care.

  • Speed

If there is one main reason to use computers instead of people in specific processes, it is their ability to conduct calculations and analytical work faster. Paradoxical as it may seem, speed applies to medicare as well, along with other fields. People can process only a limited amount of information at a time. This is where AI takes over the monotonous and routine part of work.

With all the hardware, fast internet, and cloud we have nowadays, computers can process images in microseconds. This allows doctors to have AI analyze, let’s say, all the X-ray images while they can focus more on patients. Thus, doctors have a chance to find out more specific details through their soft skills and provide care to more of those who need it.

  • Accuracy

Some diseases, like cancer, require early-stage diagnostics for doctors to save a human life. False-negative and false-positive results can both be rather destructive. In such cases, a patient either does not start treatment on time or make crucial decisions based on their knowledge about a presumed non-existent disease. Computer vision excludes the possibility of human error to some degree and serves as an assistant for radiologists. AI can help doctors detect such conditions as cancer, pneumonia, osteoporosis, and many others.

  • Urgency

Healthcare presupposes many urgent situations that need an immediate reaction. Medical specialists are taught to estimate the situation visually very quickly in such cases. But what happens if they are not accurate enough? This is why a combination of speed and accuracy provided by computer vision might be crucial for urgent situations.

Automatic postpartum hemorrhage estimation is an example of the application of computer vision in the medical field. It allows surgeons to understand how much blood a patient has lost. The Triton system measures amounts of blood on used sponges and in canisters. The system helps doctors to decrease the number of maternal deaths and the duration of hospital stay.

  • Pattern Recognition

Radiologists may also receive help from computers. You only need to compose a dataset of images with particularly associated diagnoses and train a deep learning model based on that dataset. Then, the AI will start detecting patterns in the images. For example, it can find tumors, pneumonia, or potentially dangerous moles.

Examples of Computer Vision Applications in Healthcare

Let’s have a closer look at the applications of computer vision in healthcare.

Skin Cancer Detection

“1 in 5 people get skin cancer”, according to the website of SkinVision — an app that helps the user detect skin cancer. You need to download, install the app, and take a photo of a mole or spot that concerns you. Then, the app will tell you whether you need to see a dermatologist or not. The software sensitivity is 95% due to the Machine Learning algorithm.

deep learning in healthcare

Surgery Simulations

Computer vision for medical imaging is also used for training. CV-empowered training especially applies to surgeons: nowadays, they can master their skills with digital models. The Touch Surgery software allows doctors to go through simulations of different surgeries. Artificial Intelligence creates interactive 3D models of human bodies, allowing surgeons to operate them almost the same as in real life.

image recognition in healthcare

Pneumonia Detection

A pneumonia detection web app is based on a neural network that was trained on 500 chest X-ray images. The deep learning model achieved 86%+ accuracy. Yet, it is an open-source project which can only be used for research purposes, not clinical ones.

Developers of another pneumonia detection instrument complain that finding labeled data is difficult because only certified doctors can give a diagnosis. They are also unsure that the result will be relevant for other conditions since their database was limited to 1–5-year-old patients from a single hospital.

image recognition for pneumonia detection

[Pneumonia detection from chest radiograph using deep learning]

Considering Developing a Healthcare Mobile App?

Download Free Ebook

Our Expertise

The APP Solutions team built a skin cancer classification neural network. One of the project’s main challenges was time-sensitivity. While the system needs time to process data, the result should be visible as soon as possible. Another difficulty lies within the computational resources the product requires. Building the entire system on the cloud was a single solution. Additionally, it cut the cost of the project by half.

image recognition in health care segment


Eventually, the product flow worked like this:

  1. Input image uploaded to the Cloud Storage and sent to Convolutional Neural Network;
  2. CNN processes input images;
  3. Anomaly detection algorithm finds suspicious elements;
  4. The classification algorithm determines the anomaly type;
  5. Processing results saved to the database; 
  6. The results summarized and visualized. 

The classifier takes into account the anatomic location of the lesion, patient profile data, lesion size, scale, and other characteristics.

As a result, we created a system with an average accuracy of 90% on testing data and a result delivery duration of one hour. The longer the system works, the more efficient it becomes.

Want to Learn More About The APP Solutions Approaches In Project Development?

Download Free Ebook

Future of Computer Vision in Healthcare

Currently, there exists one big problem in healthcare computer vision. Deep learning models tend to not work well on new data (different from those they were trained on). So, there is still a whole lot to be done in the field.

Market predictions are showing the same: the peak of computer vision in healthcare is not here yet. CV in the healthcare market is predicted to grow at 47.2% and reach USD 1,457 million by 2023 compared to USD 210.5 million in 2018. 


Computer vision in healthcare has a lot to offer: it is already helping radiologists, surgeons, and other doctors. This technology can also partially substitute professional training for doctors and primary skin cancer screening. Tendencies and challenges show: a computer vision breakthrough in the medical field is yet to come. If you are interested in becoming a part of it, do not hesitate to contact us.

What our clients say

Read also: 

Benefits of Cloud Computing in the Healthcare Industry

Calmerry Telemedicine Platform Case Study 

What solutions can we offer?

Find Out More


PassportScan Case Study

How it started

When we travel on vacation, the last thing we want is to spend extra time at the hotel reception desk during the check-in procedure. Now, we have PassportScan, an app that allows travelers to register at hotels seamlessly via mobile devices and tablets. 

The story began when David Palo, CEO of PassportScan, was looking for an answer to a fundamental yet straightforward question “whether to develop an iOS or Android app for an existing software?”. 

To find the answer, he searched the web and came across our blog post on the subject. After reading our article, David still had specific issues that remained unresolved, so he decided to contact us and find out more about the mobile app development process.

Once we got in touch with David, he told us more about his challenges. David already had the existing hotel front desk software for document scanning and classification, but he needed an app for tablets and mobile devices that would automate the rest of the check-in procedures done manually by hotel personnel.

As a result, we started a long-term co-operation and developed a PassportScan app for iPads and Android devices, a web service for hotel employees, and a subscription web portal. 

What is the PassportScan app?

Passportscan app development

PassportScan is a SaaS for hotels, currently used by Mariott, Four Seasons, Hyatt Regency, and Hilton. The app turns the check-in process into a 30-second operation and streamlines data gathering using image scanning tools. 

By using PassportScan, hotel employees can scan a guest’s documents, let guests sign registration cards digitally, manage the information via the app, and send data to the hotel’s property management system or customer relationship management system. 

PassportScan app

PassportScan helps to get rid of paper documentation and reduces the number of human errors in the client’s profile by leveraging optical character recognition (OCR) features and the integrated Address Validation Engine. 

passportscan app

Our goals 

  • Develop an app for iOS and Android. We needed to develop an app for tablets and iPads that would allow managers from different hotels to log-in to the PassportScan system via personal accounts, scan guest documents, and send the data to the hotel’s database. 
  • Integrate the app into the client’s eco-system. Each hotel has its own in-house system to track check-ins and information about guests. Thus, the app should send scanned data and other guest info to the hotel’s database seamlessly and error-free. 
  • Build a data management system. Apart from scanning passports, users need a platform to manage data, set up owner and branch settings, payment information, and user access.
  • Enable user payment. Since PassportScan applies a subscription payment model, we needed to create an e-commerce module for online payments via credit card. 
  • Protect personal data. Since the app deals with sensitive data (customer data, document images, and biometric signature), we needed to apply advanced security measures and make the app compatible with new European regulations regarding personal data privacy, such as GDPR.  

Our solution – PassportScan app 

PassportScan consists of three main parts.

PassportScan Workspace 

Workspace is a web portal designed to manage apartment bookings in hostels and hotels. Workspace stores guest profiles, booking details, ID information, and signed documents. 

PassportScan Workspace keeps data received from

  • A mobile PassportScan app
  • A PassportScan desktop software
  • Hotels PMS (Property Management System)

PassportScan Workspace supports integration with Oracle products, such as Suite 8 and Opera, to import and export data. The web portal also includes the support ticketing system so that hotel employees can get in touch with developers in case of bugs or system failures. 

PassportScan Billing System 

This is a web-based app for PassportScan users to pay their subscriptions via the Stripe payment gateway. Initially, users have a one month trial period. At the end of each month, users receive auto-generated invoices based on the number of scans and signs added to the system, and the number of gigabytes used. 

PassportScan’s billing system includes the following features:

  • Billing details validation
  • Credit card validity checking
  • Online payments via Stripe payment gateway 
  • Editing payment methods
  • “Payment history” with digital invoices 

PassportScan Native Apps for iPads and Android tablets 

Native applications allow hotel employees to scan a guest’s documents with iPads and Android tablets, then send data to the Workspace.

Apps for both platforms include the same feature set:

  • Search for available bookings in the PassportScan system
  • Scan front and back sides of documents 
  • Edit the guest’s details
  • Digital Signature 
  • PassportScan privacy policy 
  • GDPR compliant Data Use Agreement 
  • List with additional hotel services 

PassportScan’s check-in takes six steps:

Step 1. Hotel employee starts the registration/check-in process and finds the guest’s booking 

Step 2. Hotel employee updates guest info by scanning documents using the PassportScan app

Step 3. The app recognizes the image from the guest’s passport, captures the data, then classifies and verifies it

Step 4. Hotel employee edits the identified elements if needed

Step 5. The guest agrees with the privacy policy with the GDPR compliant Data Use Agreement 

Step 6. The guest puts a digital signature and may ask for additional hotel services

Our challenges and solutions


Due to the system’s complexity, we developed the project’s back-end system with a potential high load in mind by applying a microservice architecture approach that enabled the system with both vertical and horizontal scaling. 

In this way, the application is divided by functionality (vertical scaling), and each microservice can run as multiple instances behind a load balancer (horizontal scaling). Also, we achieved a more effective consumption of computational resources, since, under high load,  the architecture scales horizontally. 

Passport scan case study

The project’s core consists of 8 back-end services for reading, scanning, and saving documents, digital signatures, etc., and three public components:

  • The Public API provides an interface to the back-end for a native application, as well as integration capabilities for 3rd party external systems
  • The Admin panel with a dashboard for configuration management
  • The Workspace, a web interface to manage the system for hotel staff
Passport scan public api


For every type of app user, the system provides an authentication procedure with personalized credentials and password security provided by Admin. The system interacts with the outer world via SSL with 128-bit keys. Services without external connections, placed on the private cloud, are entirely isolated from external access. The system protects sensitive customer data by encrypting with AES 256 algorithm.

Tight deadlines 

The biggest challenge we faced was keeping tight deadlines during the development stage. The main reason for such a rush was that David and the PassportScan team had already scheduled presentations of the app’s MVP at several RoadShows and Hospitality conferences. Thus, there was no room for error.

We nailed the project’s release within the deadlines, thanks to defined Milestones, a carefully prepared back-end, and microservices project architecture. Thanks to microservices technology, we managed to develop several modules simultaneously, and the further module orchestration helped us to avoid any kind of server shut down. Thus, if any of the modules fail, other modules quickly help (less than 5 sec) to retrieve all the data.

Project tech stack 

  • Symfony 4.3 for web-based WorkSpace and Billing systems
  • Document reader SDK for identifying letters and numbers in passports 
  • Signature module SDK for capturing digital signatures 
  • Scan module SDK for scanning passports 
  • Storage Module SDK for sending data to the cloud storage
  • License and modules management SDK for managing the owners, hotel data, and native clients device identity
  • User management API for setting different levels of user access
  • Stripe SDK as online payment gateway
  • JSON (JavaScript Object Notation) for generating custom invoices
  • Google Maps API for address validation
  • Google Cloud Platform Storage for secured data storage
  • Amazon Web Services Mailer for ticketing system and streamlined technical support 
  • Google Cloud Platform Pub/Sub messaging for connecting microservices architecture components 
  • Swift SDK for iPad app version 
  • Android SDK and Android Studio for Android-powered devices

Team composition

  • 4 Back-end developers
  • 1 DevOps
  • 2 Project managers
  • 2 iOS developer
  • Android developer
  • 2 QA engineer
  • 2 Business Analysts


PassportScan is shaping the hospitality industry by showing how technology can eliminate routine tasks and paperwork for hotel employees. 

Thanks to clear project goals and timely communication with David and the PassportScan team, we managed to build the first app version in just one month from the project launch. We are proud to be a part of such products as PassportScan because they improve the world we live in today. Watch the video where we share our thoughts on the PassportScan project. 

Recently, we launched the discovery phase of the Self-check-in app for PassportScan to enable guests to make check-ins via the app with their own mobile devices. This is very important right now with the situation of the Pandemic of COVID-19, allowing the possibility of non-contact services in the Hospitality industry. 

Client’s testimonial 

Want to develop an application for your business?