AI-Powered Single-Cell Analysis for Oncology and Diagnostics

Aegis Digital Technologies is developing Micro-SDP, a mathematically rigorous, deterministic AI platform for automated detection and classification of single blood cells in microscopic images, targeting cancer monitoring and clinical diagnostics.

Micro-SDP

Smart Detection & Prediction of Single Cells in Microscopic Images

What is Micro-SDP?

Micro-SDP, which is a Software as a Medical Device (SaMD), is a custom developed detereministic ML system for automated detection and classification of single blood cells in heterogeneous microscopic images, built on a hybrid architecture: learning algorithms and model updates are computed server-side on Aegis infrastructure, while all patient image analysis is performed locally on the clinical device. Its core mission is to enable continuous, data-driven monitoring of cancer-relevant cell populations, with the goal of giving clinicians a faster, reproducible, and auditable tool for oncology diagnostics.

Unlike probabilistic deep learning approaches, Micro-SDP is built on a deterministic variational mathematical framework, specifically, a Primal-Dual Hybrid Gradient (PDHG) optimisation algorithm applied to dictionary learning. This yields mathematically proven existence, uniqueness, and stability guarantees that are essential for clinical-grade reproducibility and regulatory traceability.

Product Overview

Key Properties

• Deterministic and interpretable: Every classification decision is traceable to input features, no black-box inference.
• Privacy-by-architecture: All patient image analysis runs locally on the clinical device — no blood cell images or patient-identifiable data are ever transmitted to a cloud server. Model training and updates are performed server-side on Aegis infrastructure using anonymised data only. GDPR and HIPAA compliant by design.
• Longitudinal monitoring (roadmap): Beyond detection and classification, Micro-SDP is designed to model the expected count of target cell populations over time, enabling data-driven longitudinal oncology monitoring from microscopic image sequences.

Scientific Development; Dataset & Source Code

Micro-SDP's learning algorithm is based on dictionary learning, developed and validated on the Berkeley Single Cell Computational Microscopy (BSCCM) dataset [Pinkard et al., 2024], openly provided by the computational imaging laboratory of UC Berkeley. More about the mathematical development behind the algorithms can be learnt in the following links.

Regulatory & IP Strategy

Micro-SDP is being developed in alignment with EU IVDR 2017/746 (In Vitro Diagnostic Regulation) and FDA Software as a Medical Device (SaMD) guidelines, targeting Class C IVD classification under the IVDR framework.

About Aegis Digital Technologies

Aegis Digital Technologies is a deep-tech startup founded in Dresden, Germany, in September 2024. The company's sole focus is currently the development of Micro-SDP, an SaMD (Software as a Medical Device) for automated single-cell detection and classification in prephera blood smear images, targeting oncology and diagnostics.

The Founders

Erdem Altuntaç, PhD

Co-Founder & CEO

Dr. Erdem Altuntaç holds a PhD in Applied Mathematics from the University of Göttingen (2016), where his research focused on iterative variational regularisation and optimisation algorithms for inverse ill-posed problems. His postdoctoral work at the Université Libre de Bruxelles (2017-2019) introduced him to primal-dual splitting methods, the mathematical foundation that directly underpins Micro-SDP's core algorithm. At Fraunhofer FHR (2019-2021), he applied these methods to radar signal processing and LiDAR-based depth completion in automotive perception systems. His subsequent postdoctoral position at DZNE Dresden (2021-2024) brought him into biomedical signal processing, where he developed predictive models for physiological time-series data using deep learning. This trajectory, from inverse problems and variational mathematics, through industrial signal processing, to biomedical AI, converges directly in Micro-SDP. The human motivation behind the project is deeply personal: family experiences with misdiagnosis and its consequences drives the commitment to building diagnostic tools that are rigorous, reproducible, and trustworthy.

Preethi Ganesh, MSc

Co-Founder & CPCO

Preethi Ganesh is Co-Founder and Chief Product & Commercial Officer at Aegis Digital Technologies, bringing over six years of experience at the intersection of MedTech, life sciences, and commercial development across India and the DACH region. She holds an MSc in Smart Systems, specialising in Medical and Mechanical Engineering, and a BE in Biomedical Engineering, giving her a strong foundation across both the clinical and engineering worlds of healthcare. Her career has taken her through some of the most complex and regulated areas of the medical device industry, invasive and non-invasive ventilators, clinical laboratory quality management, drug discovery through human pluripotent stem cells, liquid biopsy reference materials, and endocrine disrupting chemicals research. In every role, her focus has been the same: bridging the gap between deep science and the market. With additional expertise in AI product management, Preethi joined Aegis Digital Technologies to bring the commercial and product leadership needed to take a mathematically rigorous technology into the hands of the clinicians and laboratories that need it most. Having lived in Germany for over ten years as an international herself, she understands first-hand what it means to navigate complex systems, and why building tools that are transparent, trustworthy, and explainable is not just a technical goal, but a human one.

Name & Values

The name Aegis, the shield of protection in Greek mythology, reflects the founding principle of Aegis Digital Technologies: to build technology that protects. Whether in medical diagnostics, clinical decision support, or any future domain where software touches human outcomes, our commitment remains the same. Determinism, transparency, and reproducibility are not design preferences, they are non-negotiable requirements for systems where the cost of failure is measured in human lives.