get in touch

Enhancing Healthcare with 3D Medical Imaging Integration

3D MEDICAL IMAGING SOFTWARE

3D Medical Imaging Software Development

Our team built a 3D medical imaging software for reconstruction of bones, skin, and various organs from X-rays and CT scans implementing machine learning.

#Healthcare

#IoT

#ComputerVision

Client*

A healthcare technology firm producing advanced devices and software that support healthcare professionals in their everyday tasks.

*We cannot provide any information about the client or specifics of the case study due to non-disclosure agreement (NDA) restrictions.

Project in numbers

duration

Ongoing project

team

12 specialists

Team involved in the project

industry

Healthcare

solution

Web

technologies

Python, FastAPI, PyQt, JavaScript, React, MS SQL Server, Weights and Biases, MLFlow, PyTorch, OpenCV, TensorFlow, Keras, ONNXRuntime, PyDICOM, Albumentations, AWS (S3, EC2, Lambda), AWS SageMaker (Studio, Model Monitoring, Inference endpoint), Qase, Postman, Swagger, TestFlight, Arduino, Thonny

Services

Custom Software Development / Backend Development Services

2 x Front-end developers

2 x Back-end developers

1 x Project manager

4 x ML engineers

2 x QA specialists

1 x UX/UI Designer

hire the team

Challenge

Develop an ML-based tool that could do 3D medical imaging of bones, skin, and other body parts by converting flat scans into three-dimensional volumetric models from X-rays and CT scans.

Solution & functionality

We integrated medical imaging analysis into the customer’s system, ensuring compatibility with X-rays and CT scans from radiology, cardiology, and other labs. As a result, all the 3D medical images can be accessed across hospital workstations and personal laptops.

3D rendering for X-rays and CT scans

Conversion of black-and-white images into 3D medical models takes just a few clicks. Once the X-ray or CT scan is uploaded, clinicians can set threshold attenuation values to define 3D detail, and let the platform scan each piece and create voxels reconstructing denser body fragments. This results in volumetric 3D medical images.

After rendering, clinicians can use a toolbar to manage objects: zoom in/out, add/remove skin, tissue, muscles, bones, and cut away excess parts. The primary tool, a cube, allows the image rotation for a more accurate view of the pathology.

Compatibility and security for DICOM files

Initially, we made sure that the web platform effortlessly works with DICOM files, the standard format for medical imaging management. Next, we enhanced security to safeguard the confidential health information they carry.

Our developers built a secure space to store imported DICOM files, encompassing patient details, diagnoses, treatments, dates, and test results.

ROI manager for highlighting pathologies

Our team developed an advanced ROI manager for highlighting pathology. Doctors can easily identify and outline tumors in 3D reconstructions, and measure lesion sizes for informed surgical decisions.

For precise segmentation, our developers set thresholds, pixel values, and previews. This allows for detailed 3D customization in form of reports with anatomical annotations and organ distance measurements helping more accurate surgical planning. In addition, practitioners can export and share 3D images based on the user access.

Results and business value

The 3D rendering platform allows professionals to monitor organs, evaluate tissue composition, assess fractures and thus diagnose diseases accurately. The platform generates detailed 3D medical imaging models and reports with anatomical annotations, as well as measures tumors, pathologies, and distances between organs for precise and effective surgical planning.

3X

faster pre-operational preparation

30%

more accurate diagnoses

Related cases

see all case studies

We appreciate your interest in Timspark

    How Computer Vision in Agriculture Helps Track Bee Population and Health

    Computer Vision in Agriculture

    How Computer Vision in Agriculture Helps Track Bee Population and Health

    Timspark used AI to make mobile computer vision software to track the beehive life. We also predict how the bee population will grow and how healthy it is overall.

    #AI

    #MobileDevelopment

    #ComputerVision

    Client*

    It was Timspark’s internal project. We were eager to independently grow expertise in Machine Learning and built an ML-powered app with prediction functionality for agriculture.

    Project in numbers

    duration

    6 months

    team

    4 specialists

    Team involved in the project

    industry

    Agriculture

    solution

    Mobile computer vision software for beehive tracking

    technologies

    Python, PyTorch, YOLOv3, Google Cloud Platform, DigitalOcean, Swift 5

    1 x Lead Data Scientist

    1 x iOS Developer

    1 x Data Engineer

    1 x Project Manager

    1 x QA

    HIRE THE TEAM

    Challenge

    Our team did it all for this project – from planning the product’s architecture to labeling the data and training the neural network. This hands-on approach to computer vision services helped us become experts in the field and led to a fully working product as the outcome. We tackled a set of machine learning challenges and industry-related standards of using computer vision in agriculture, too.

    Solution & functionality

    Our ready-made solution is a mobile app that uses computer vision in agriculture to count bees in the hive accurately. It also creates user-friendly charts and graphs, making it easy to monitor the hive’s growth and health.

    Object detection for beehive population count and health tracking

    We have harnessed object recognition technology, so now it is possible to scan and instantly figure out how many bees are in the hive. Also, the solution helps distinguish the regular bees from the queen bees.

    A modern user-friendly mobile app

    Our team built mobile computer vision software from the ground up with an easy-to-use interface. We also added a feature where a client can get automatic reports about the hive’s status using the information uploaded.

    Results and business value

    We’ve successfully crafted computer vision solutions for iOS, designed to assist beekeepers in caring for their beehives more effectively.

    Benefits 

    Our app offers a major time-saving advantage. With traditional manual inspections taking up to an hour per beehive, our computer vision services help beekeepers inspect a hive in just 10 minutes or even less.

    Related cases

    see all case studies

    We appreciate your interest in Timspark

      How to Use Computer Vision in Agriculture for Detecting Diseased Banana Leaves

      Computer Vision in Agriculture

      How to Use Computer Vision in Agriculture for Detecting Diseased Banana Leaves

      Our team developed a computer vision software that checks banana seedling leaves for damage all on its own. We also use advanced analytics to help our client reduce crop loss probability.

      #AI

      #WebDevelopment

      #ComputerVision

      Client*

      Top banana seeding supplier in the world

      *We cannot provide any information about the client or specifics of the case study due to non-disclosure agreement (NDA) restrictions.

      Project in numbers

      duration

      4 months

      team

      5 specialists

      The team involved in the project

      industry

      Agriculture

      solution

      Computer vision software for plant disease detection

      technologies

      Python, Pandas, Numpy, Pytorch, Streamlit, Opencv

      1 x Lead Data Scientist

      1 x Data Scientist

      1 x Data Engineer

      1 x Project Manager

      1 x QA

      HIRE THE TEAM

      Challenge

      The client was concerned about the possibility of using computer vision in agriculture to detect plant disease and prevent crop loss automatically. On the tech side of things, our team faced a scarcity of data available to train AI-based computer vision solutions.

      Solution & functionality

      We came up with a solution to place cameras in the greenhouse, putting them up high and to the side. These cameras take periodic snapshots of banana seedlings. The client can adjust the frequency of these snapshots.

      Deep learning for object detection and classification

      Timspark made a computer vision software module that grabs pictures of the leaves spotted by the camera. These pictures later get sent to the deep learning classifier model, which has a closer look at images and tells if a banana leaf is healthy or damaged. It can even figure out what kind of damage it is.

      Plant condition reports and analytics

      Our computer vision software checks out the uploaded pictures and generates a PDF report with the results. It further gives recommendations on what to do next based on the analyzed data.

      Results and business value

      Timspark didn’t just create and tweak the classifier model; we did it thoroughly, making sure it fits the project’s special needs and industry standards. The client is satisfied with the outcome and still partners with us on more projects to facilitate computer vision in agriculture.

      Benefits for client

      Thanks to computer vision services, the customer has successfully put this technology to work and significantly cut down on banana seedling losses.

      Related cases

      see all case studies

      We appreciate your interest in Timspark

        AI-based Web Solution: X2 Sales Rise for Custom Sports Clubs

        AI-based Web Solution for Maximizing Sales

        AI-based Web Solution: X2 Sales Rise for Custom Sports Clubs

        The team developed an AI-based solution to automate the analysis of golf players’ positions and strokes, to boost sales for custom golf clubs manufacturing business.

        #AI

        #WebDevelopment

        #ComputerVision

        Client*

        The client is a major manufacturer of custom golf clubs.

        *We cannot provide any information about the client or specifics of the case study due to non-disclosure agreement (NDA) restrictions.

        Project in numbers

        duration

        3 months

        team

        6 specialists

        Team involved in the project

        industry

        Sport and Entertainment

        solution

        AI-powered analyzer for golf players

        technologies

        TensorFlow, Keras, Python, OpenCV, Mediapipe, LabelMe, MLFlow, NumPy, Colab, Matplotlib

        1 x Lead Data Scientist

        2 x Data Scientists

        1 x Data Engineer

        1 x Project Manager

        1 x QA

        HIRE THE TEAM

        Challenge

        Develop an AI-based product for analyzing golf players’ positions and strokes in order to design individually fitting golf clubs. The client was already using computer analysis software for analyzing the players’ movements and consistency of strokes and wanted to fully automate the process.

        Solution & functionality

        The team created an AI-powered solution capable of recognizing the golf club in a player’s hand and correctly estimating the angles of his joints (the posture).

        Detection of player’s positions and golf club

        Our team developed a model that successfully identifies the position of a person’s body, including their arms and legs, as well as the position of the golf club, using computer vision technology.

        Robust pose estimation

        Our developers enhanced the model to gather additional information by measuring the angles of specified body joints through computer vision technology. Data is captured either via a mobile device camera or via a pre-installed kiosk with a camera.

        Collection, analysis and processing of advanced metrics

        Timspark’s specialists developed and fine-tuned the classifier model to meet the project’s unique requirements. The model analyzes received images, determines the average class among all attributes of captured objects, and subsequently identifies the target audience for the advertisement.

        Results and business value

        The product was developed as an MVP. All the intended functionality operates with the help of computer vision and artificial intelligence technologies.

        Benefits for client

        The client remained highly content with the quality and speed of the team’s work. By successfully implementing the technology into their sales process, the client doubled their sales.

        Related cases

        see all case studies

        We appreciate your interest in Timspark

          Computer Vision Solution for Effective Advertising Placement

          computer vision device

          Computer Vision Solution for Effective Advertising Placement

          Our team developed an on-premises device based on AI technologies for detecting individuals and showcasing advertisements on DOOH displays in transportation or outdoor locations.

          #AI

          #WebDevelopment

          #Ecommerce

          Client*

          The client is a world-leading provider of comprehensive visual technology solutions.

          *We cannot provide any information about the client or specifics of the case study due to non-disclosure agreement (NDA) restrictions.

          Project in numbers

          duration

          11 months

          team

          5 specialists

          Team involved in the project

          industry

          E-commerce

          solution

          Computer vision and artificial intelligence device for target audience analysis

          technologies

          Python, Pytorch, Cnvrg.io, AWS SageMaker, GCP Vertex AI, Fastdup, Pandas, Numpy, Scipy.

          1 x Lead Data Scientist

          2 x Data Scientists

          2 x Data Engineers

          HIRE THE TEAM

          Challenge

          The fundamental idea was to create a device harnessing AI technologies for analyzing captured images, discerning the audience’s average attributes, and enabling the presentation of targeted advertising.

          Related objectives

          Deploy the computer vision model on edge devices with limited GPU and RAM

          Train the AI computer vision model with labeled data

          Solution & functionality

          In collaboration with the client’s team, Timspark created a compact on-premises computer vision device that can capture and analyze visual data.

          Machine learning model training for successful object recognition

          The team developed and fine-tuned the classifier model to meet the project’s unique requirements. The model analyzes received images, determines the average class among all attributes of captured objects, and subsequently identifies the target audience for the advertisement.

          Deployment on Jetson Nano and Jetson Xavier

          To address challenges linked to the limited memory and slow data processing, the model was transformed into ONNX and TensorRT formats, ensuring its seamless deployment on edge devices such as Jetson Nano and Jetson Xavier.

          Results and business value

          Our specialists successfully developed a classifying model that detects and tracks individuals within the camera’s field of view. The model analyzes the captured visual data, accurately identifying selected class among all attributes, and displays targeted advertisements on nearby screens in accordance with the specified class request.

          Benefits for client

          The client successfully applies the computer vision software to show the advertisement effectively to the relevant audience.

          Based on the successful results, we are going to improve the model further in our ongoing collaboration.

          Related cases

          see all case studies

          We appreciate your interest in Timspark

            Let’s build something great together

              Let’s build something great together

                Let’s build something great together

                  Let’s build something great together

                    Let’s build something great together

                      Let’s build something great together