At a glance

At Graylight Imaging, we empower our clients to bring their innovative medical devices and products to life with our expertise in ISO 13485 compliant software development and AI.

Our team of certified specialists in coding and software engineering, ML engineering, cloud solutions, Quality Assurance, IT security, and medical imaging provides a holistic approach to medical device development, ensures that your products meet the highest standards of quality, safety, and regulatory requirements.

The history of our company

Future Processing SA established – initial R&D included image analysis (astronomical)
Enter the software outsourcing market
Machine vision product developed (image analysis of industrial processes)
First medical imaging customer engagement (and still working with them)
Acquired first medical certification ISO 13485
Achieve medical certification for brain lesion evaluation software
Medical imaging subsidiary Future Processing Healthcare Sp. z o.o. established
Launch of Graylight Imaging

Clients and partners

National Research Institute of Oncology logo
AI w Zdrowiu logo


Collaborating with Graylight Imaging was seamless despite the tight project timeline. All stages were efficiently executed according to the plan. GLI fully comprehended the project’s objective and provided valuable support with their technical and medical expertise. Their specialists successfully carried out several key tasks, including developing a predictive model for medical data analysis, conducting UX analysis, creating the application’s GUI, and preparing certification documentation. A truly remarkable partnership.

Benjamin Dodsworth, Co-founder & CSO/CTO at PIPRA AG

Working with Graylight has been a game-changer in our software projects. Their real expertise in software development, combined with robust computer science skills, allowed them to unravel complex problems effortlessly. What stands out is their proactive approach – always suggesting improvements and pushing beyond initial requirements. Their unique blend of quality and regulatory expertise adds immense value, delivering not just code but also quality documents that are a must for medical software.
Communication is a breeze, always friendly and dependable making them the rare subcontractor you want to work with.

Frédéric CHAMP, Director – Technology Development at Biomodex

As a long-time collaborator of both Future-Processing and Graylight-imaging, I can recommend Graylight-imaging as a software company of excellence.

They have demonstrated their proficiency in various cutting-edge technologies and their ability to apply them to diverse projects. Graylight-imaging team is professional and friendly and are easy to work with.

George Jachode, President, Imaging Engineering, LLC

Our last publications 
Deep learning automates bidimensional and volumetric tumor burden measurement from MRI in pre- and post-operative glioblastoma patients


Jakub Nalepa, Krzysztof Kotowski, Bartosz Machura, Szymon Adamski, Oskar Bozek, Bartosz Eksner, Bartosz Kokoszka, Tomasz Pekala, Mateusz Radom, Marek Strzelczak, Lukasz Zarudzki, Agata Krason, Filippo Arcadu, Jean Tessier


Computers in Biology and Medicine, March 2023


Tumor burden assessment by magnetic resonance imaging (MRI) is central to the evaluation of treatment response for glioblastoma. This assessment is, however, complex to perform and associated with high variability due to the high heterogeneity and complexity of the disease. In this work, we tackle this issue and propose a deep learning pipeline for the fully automated end-to-end analysis of glioblastoma patients. Our approach simultaneously identifies tumor sub-regions, including the enhancing tumor, peritumoral edema and surgical cavity in the first step, and then calculates the volumetric and bidimensional measurements that follow the current Response Assessment in Neuro-Oncology (RANO) criteria. Also, we introduce a rigorous manual annotation process which was followed to delineate the tumor sub-regions by the human experts, and to capture their segmentation confidences that are later used while training deep learning models. The results of our extensive experimental study performed over 760 pre-operative and 504 post-operative adult patients with glioma obtained from the public database (acquired at 19 sites in years 2021–2020) and from a clinical treatment trial (47 and 69 sites for pre-/post-operative patients, 2009–2011) and backed up with thorough quantitative, qualitative and statistical analysis revealed that our pipeline performs accurate segmentation of pre- and post-operative MRIs in a fraction of the manual delineation time (up to 20 times faster than humans). Volumetric measurements were in strong agreement with experts with the Intraclass Correlation Coefficient (ICC): 0.959, 0.703, 0.960 for ET, ED, and cavity. Similarly, automated RANO compared favorably with experienced readers (ICC: 0.681 and 0.866) producing consistent and accurate results. Additionally, we showed that RANO measurements are not always sufficient to quantify tumor burden. The high performance of the automated tumor burden measurement highlights the potential of the tool for considerably improving and simplifying radiological evaluation of glioblastoma in clinical trials and clinical practice.

Deep Learning Meets Particle Swarm Optimization For Aortic Valve Calcium Scoring From Cardiac Computed Tomography


Jaroslaw Goslinski; Filip Malawski; Mariusz Bujny; Marcin Kostur; Karol Miszalski-Jamka, Jakub Nalepa

Conference paper

2023 IEEE International Conference on Image Processing (ICIP), October 2023


Aortic stenosis is the most common primary valvular pathology requiring surgical or transcatheter intervention in developed countries. Quantification of aortic valve calcification with cardiac computed tomography (CCT) is used for assessment of aortic stenosis severity, disease progression and prediction of major cardiovascular events. The calcium deposits, however, commonly appear in different regions of the aorta and heart, leading to false-positive regions, and to an incorrectly calculated aortic valve calcium score. We tackle the issue of pruning such false-positive regions from CCT scans, and introduce a particle swarm optimization (PSO) algorithm for this task. In our approach, PSO optimizes the radius while benefiting from the evolved position of a sphere which would embrace those calcifications that are positioned near the aortic valve. Our experimental study, performed over 30 non-contrast CCT scans, showed that our results are in strong agreement with the experienced human reader, and indicate the potential of PSO in data-driven pruning of false-positive calcifications which are positioned in other parts of the aorta and heart. Additionally, PSO outperformed a geometrical-based approach for this task.

Deep Learning Meets Computational Fluid Dynamics to Assess CAD in CCTA


Filip Malawski, Jarosław Gośliński, Mikołaj Stryja, Katarzyna Jesionek, Marcin Kostur, Karol Miszalski-Jamka, Jakub Nalepa


Applications of Medical Artificial Intelligence, September 2022


Early diagnosis and effective monitoring of the coronary artery disease are critical in ensuring its effective treatment. Although there are established invasive examinations to assess this condition, the current research focus is put on non-invasive procedures. Here, the coronary computed tomography angiography is the first-choice modality, but its manual analysis is cost-inefficient, lacks reproducibility, and suffers from significant inter- and intra-rater disagreement. We tackle those issues and introduce an end-to-end deep learning-powered pipeline for automated analysis of such imagery which additionally exploits computational fluid dynamics to capture the functional vessel characteristics. Our experiments, performed over clinically acquired scans, revealed that the suggested segmentation approaches not only outperform state-of-the-art nnU-Nets, but also lead to the blood-flow parameters which are in strong agreement with those elaborated for the ground-truth delineations.


Segmenting pediatric optic pathway gliomas from MRI using deep learning


Jakub Nalepa, Szymon Adamski, Krzysztof Kotowski, Sylwia Chelstowska, Magdalena Machnikowska-Sokolowska, Oskar Bozek, Agata Wisz, Elzbieta Jurkiewicz


Computers in Biology and Medicine, March 2022


Optic pathway gliomas are low-grade neoplastic lesions that account for approximately 3–5% of brain tumors in children. Assessing tumor burden from magnetic resonance imaging (MRI) plays a central role in its efficient management, yet it is a challenging and human-dependent task due to the difficult and error-prone process of manual segmentation of such lesions, as they can easily manifest different location and appearance characteristics. In this paper, we tackle this issue and propose a fully-automatic and reproducible deep learning algorithm built upon the recent advances in the field which is capable of detecting and segmenting optical pathway gliomas from MRI. The proposed training strategies help us elaborate well-generalizing deep models even in the case of limited ground-truth MRIs presenting example optic pathway gliomas. The rigorous experimental study, performed over two clinical datasets of 22 and 51 multi-modal MRIs acquired for 22 and 51 patients with optical pathway gliomas, and a public dataset of 494 pre-surgery low-/high-grade glioma patients (corresponding to 494 multi-modal MRIs), and involving quantitative, qualitative and statistical analysis revealed that the suggested technique can not only effectively delineate optic pathway gliomas, but can also be applied for detecting other brain tumors. The experiments indicate high agreement between automatically calculated and ground-truth volumetric measurements of the tumors and very fast operation of the proposed approach, both of which can increase the clinical utility of the suggested software tool. Finally, our deep architectures have been made open-sourced to ensure full reproducibility of the method over other MRI data.

Detecting liver cirrhosis in computed tomography scans using clinically-inspired and radiomic features


Krzysztof Kotowski, Damian Kucharski, Bartosz Machura, Szymon Adamski, Benjamín Gutierrez Becker, Agata Krason, Lukasz Zarudzki, Jean Tessier, Jakub Nalepa


Computers in Biology and Medicine, November 2022


Hepatic cirrhosis is an increasing cause of mortality in developed countries-it is the pathological sequela of chronic liver diseases, and the final liver fibrosis stage. Since cirrhosis evolves from the asymptomatic phase, it is of paramount importance to detect it as quickly as possible, because entering the symptomatic phase commonly leads to hospitalization and can be fatal. Understanding the state of the liver based on the abdominal computed tomography (CT) scans is tedious, user-dependent and lacks reproducibility. We tackle these issues and propose an end-to-end and reproducible approach for detecting cirrhosis from CT. It benefits from the introduced clinically-inspired features that reflect the patient’s characteristics which are often investigated by experienced radiologists during the screening process. Such features are coupled with the radiomic ones extracted from the liver, and from the suggested region of interest which captures the liver’s boundary. The rigorous experiments, performed over two heterogeneous clinical datasets (two cohorts of 241 and 32 patients) revealed that extracting radiomic features from the liver’s rectified contour is pivotal to enhance the classification abilities of the supervised learners. Also, capturing clinically-inspired image features significantly improved the performance of such models, and the proposed features were consistently selected as the important ones. Finally, we showed that selecting the most discriminative features leads to the Pareto-optimal models with enhanced feature-level interpretability, as the number of features was dramatically reduced (280×) from thousands to tens.

Segmenting Brain Tumors from MRI Using Cascaded 3D U-Nets


Krzysztof Kotowski, Szymon Adamski, Wojciech Malara, Bartosz Machura, Lukasz Zarudzki, Jakub Nalepa

Conference paper 

International MICCAI Brainlesion Workshop, March 2021


In this paper, we exploit a cascaded 3D U-Net architecture to perform detection and segmentation of brain tumors (low- and high-grade gliomas) from multi-modal magnetic resonance scans. First, we detect tumors in a binary-classification setting, and they later undergo multi-class segmentation. To provide high-quality generalization, we investigate several regularization techniques that help improve the segmentation performance obtained for the unseen scans, and benefit from the expert knowledge of a senior radiologist captured in a form of several post-processing routines. Our preliminary experiments elaborated over the BraTS’20 validation set revealed that our approach delivers high-quality tumor delineation.

Let’s talk

Ready to take your medical software to the next level?

Contact Przemek now to discuss how we can support you in reaching your business objectives.