Translational Surgical Oncology

Robotics Institute Germany (RIG)

Duration: 01.07.2024 - 30.06.2028

A strong robotics industry is crucial for future social and economic growth. The Robotics Institute Germany (RIG) is committed to overcoming challenges such as the shortage of skilled workers, demographic change and climate change.

TU Dresden plays a central role in the RIG through the development of educational modules, student research projects and incubator programs. In addition, the establishment of a medical robotics cluster and participation in AI-driven robotics initiatives are planned.

Core measures include robotics kits, interactive learning modules and teacher training to strengthen education. TU Dresden also promotes student research projects in cooperation with industry and supports start-ups through an incubator program.

In addition, the testbed for medical robotics is being further expanded as a test platform within the RIG. Outreach activities integrate initiatives such as CeTI and 6G-life, contribute to the visual identity of the RIG and provide best practice examples for communication and branding.

Objective Measurement of Surgical Quality through the Development of a Data-Drive Value Creation Network (Surgical AI Hub Germany)

Duration: 01.01.2024 - 31.12.2026

The Surgical AI Hub Germany project aims to measure and improve surgical quality through the use of artificial intelligence (AI). A data-based technology platform will significantly accelerate the development of AI methods in surgery while overcoming legal, organizational and technological hurdles.

The project will create a demonstration platform for handling surgical data that will enable surgeons worldwide to analyze and optimize the quality of their procedures. Surgical videos will be systematically collected for AI training, while a European network of surgeons will advance research into AI-supported surgical methods. At the same time, business models for small and medium-sized companies are being developed and best practices for secure and efficient data exchange are being established.

Adaptive Virtualization for AI-enabled Cloud-edge Continuum (CloudSkin)

Duration: 01.01.2023 - 31.12.2025

To realize the European vision of a seamless cloud continuum in the coming years, CloudSkin is developing a cognitive cloud continuum platform with three key innovations. First, the platform uses artificial intelligence (AI) and machine learning (ML) to optimize workloads, resources, energy consumption and network traffic between cloud and edge in real time and adapt to dynamic conditions. Second, CloudSkin enables "stack identity" across the entire cloud edge continuum, providing users with a unified system environment. Third, CloudSkin prepares the necessary infrastructure to integrate new virtualized execution abstractions into the virtual resource continuum, supported by an AI/ML-based orchestration layer within the platform.

Extreme Near-Data Processing Platform (NEARDATA)

Duration: 01.01.2023 - 31.12.2025

The main goal is to develop an extreme near-data platform that enables access, analysis and processing of distributed and federated data without requiring users to master the complex logistics of accessing data across heterogeneous storage locations and data pools. We are moving beyond traditional passive or bulk-loaded data from storage systems to develop a next generation of near-data processing platforms both in the cloud and at the edge. Our platform includes Extreme Data, which contains both metadata and trusted data connectors. These enable advanced data management operations such as data discovery, mining and filtering from heterogeneous data sources.

School of Embedded Composite AI Dresden/Leipzig (SECAI)

Duration: 01.07.2022 - 31.12.2027

The School of Embedded Composite Artificial Intelligence (SECAI) is a project of TU Dresden and Leipzig University to promote artificial intelligence (AI) in research and education. SECAI awards scholarships, strengthens teaching, finances researchers and promotes international exchange.

DFG Cluster of Excellence: Center for Tactile Internet with Human-in-the-loop (CeTI)

Duration: 01.01.2019 - 31.12.2025

The central vision of CeTI is to enable people to interact with cyber-physical systems (CPS) in near real-time - both in the real and virtual world, via intelligent wide-area communication networks. These advances go far beyond the current state of the art in computer science and engineering: intelligent communication networks and adaptive CPS require online-based mutual learning mechanisms, which are a key challenge.

To address these challenges, CeTI conducts cutting-edge interdisciplinary research and addresses central open research questions in key areas. These include the complexity of human control in the human-machine loop, innovative sensor and actuator technologies, software and hardware developments and communication networks as the basis for a variety of new applications. These are used in particular in the fields of medicine, industry and the "Internet of Skills".

Digital Transformation and Sovereignty of Future Communication Networks (6G-life)

Duration: 15.08.2021 - 14.08.2025

6G-life will significantly stimulate industry and the start-up landscape in Germany through pioneering application projects and thus sustainably strengthen Germany's digital sovereignty. Research and test fields for two central use cases will provide both scientific and economic impetus. The aim is to establish at least 10 new start-ups within the first four years andactively involve at least 30 start-ups.

In addition, 6G-life will make a significant contribution to the training of highly qualified specialists.Another key objective isto support society in the digital transformation in order to actively shape the digital transformation and create sustainable added value for society.

The International Research Training Group (TransCampus IRTG) 2251 "Immunological and Cellular Strategies in Metabolic Disease" (ICSMD)

Duration: 01.01.2024 - 31.12.2025

The transCampus is a unique partnership between King's College London and the Technische Universität Dresden, based on genuine cooperation and close interdisciplinary collaboration in all areas.

As part of IRTG 2251: ICSMD, transCampus offers outstanding doctoral students a specialized, interdisciplinary program with tandem supervision by two Principal Investigators and the opportunity to earn degrees from both institutions.

One focus is on negative latency for shared autonomy in remote surgery for metabolic diseases. Predicting tasks and events in surgery is critical for remote surgery, which requires high data rates and low latency. Robot-assisted devices and sensors in the operating room enable the creation of a compact, data-driven digital twin of the surgical environment, reducing data transmission. This digital twin also forms the basis for predicting events and workflows using machine learning. This enables shared autonomy by compensating for transmission latencies and ensuring synchronization with the real operating room.

Software Campus (Micro project: NeuralNodes): Neural adaptive meshing for topology changes in dynamic 3D volumes

Duration: 01.04.2024 - 31.03.2026

If the proof of concept is positive, the method should be validated with data that is as close to reality as possible. The code and the API should reach the maturity level of a prototype to enable further development of the method as a component for future products or for integration into existing software. In this context, "code" refers to the code of the neural network.

In addition, a visualization of the remeshing process by the network is planned for demonstration purposes. The integration code for the simulation software used, the training data and the evaluation data are considered valuable interim results.

Machine learning-based surgical guidance system for robot-assisted rectal surgery - a first-in-human interventional study (CoBot 2.0)

Duration: 01.10.2022 - 31.03.2026

CoBot 2.0, the follow-up project to CoBot, is a pioneering NCT proof-of-concept study and the first-in-human interventional study to evaluate the efficacy of a machine learning-based CoBot assistance system in robot-assisted rectal surgery. The aim of the study is to improve surgical outcomes through the use of advanced AI technologies and to increase precision in oncologic rectal resections. These procedures often carry the risk of complications such as sexual dysfunction and incontinence caused by nerve damage.

The CoBot system is designed to help identify and protect critical anatomical structures to minimize these risks. The main objectives of the project include the reduction of postoperative complications through improved anatomical recognition, the evaluation and optimization of the user-friendliness of AI-supported assistance systems in robot-assisted rectal surgery, and the creation of a paradigm for the integration of AI in complex surgical procedures from preclinical research to clinical application.

This study could fundamentally change surgical practice, lead to better treatment outcomes and set new standards for the use of AI in surgery.

3D Navigation for Intraoperative Visualization of Tumor (NAIV)

Duration: 01.07.2022 - 30.06.2026

Radical prostatectomy carries several risks, including incontinence, impotence and other surgical complications. Nerve-sparing techniques can reduce some of these risks, but are associated with a higher likelihood of positive resection margins, which may worsen the oncologic prognosis. Improved intraoperative visualization of critical structures could optimize both functional and oncological outcomes. In addition, the visualization of tumor foci - which are often invisible to surgeons but visible on preoperative MRI - could further reduce the rate of positive resection margins.

The NCT Proof-of-Concept project NAIV aims to implement a 3D computer-assisted intraoperative navigation system and adapt it for use in robot-assisted radical prostatectomy (RRP). This system, developed by the Division of Translational Surgical Oncology (TCO), NCT Dresden (PI: Speidel), investigates and integrates interactive features such as surgically guided online adjustment of segmentation networks to improve intraoperative navigation.

In the test phase, the AI-supported system will be applied to surgical data of suitable patients with intermediate and high risk prostate cancer undergoing RRP at the UKD, Division of Urology (PI: Borkowetz) . Preoperatively, a bpMRI of the neurovascular bundle is performed, on the basis of which the Division of Radiology, UKD (PI: Platzek) creates MRI-based 3D prostate models highlighting critical anatomical structures.