On May 16th 2025 at 16:00, Pooria Iranian will defend their PhD entitled “FLUORESCENCE-LIFETIME ENDOSCOPY WITH A TIME-GATED CAMERA”.

Everybody is invited to attend the presentation in room I.0.01 or online via this link.

The diagnosis and treatment of cancer remain complex and challenging, particularly during surgical procedures where accurately distinguishing between malignant and healthy tissue is critical. Conventional imaging modalities such as MRI and CT often fail to provide the real-time, high-contrast visualization necessary for precise tumour removal.

Fluorescence imaging has emerged as a valuable technique, offering real-time, high-sensitivity visualization of tissues. However, traditional fluorescence-intensity imaging is limited by the fluorophore’s intensity and differentiating between fluorophores with overlapping emission spectra. In contrast, Fluorescence Lifetime Imaging (FLT) provides a more reliable alternative. FLT is less susceptible to variations in fluorophore concentration and offers a more accurate representation of the tissue environment.

To enhance the accuracy of tumour resection during image-guided surgeries, our research team is developing an innovative imaging system based on the Current-Assisted Photonic Sampler (CAPS). This advanced camera enables real-time FLT imaging in the near-infrared (NIR) spectrum, specifically between 700–900 nm, which is particularly effective for deep tissue imaging.

By integrating this FLT technology into an endoscopic system incorporating standard white light imaging, we aim to provide surgeons with enhanced visual information. This dual-imaging capability enables better differentiation between malignant and benign tissues, which traditional white light endoscopy imaging systems cannot adequately achieve. Current systems often require separate RGB and FLT imaging cameras, leading to alignment issues and bulky configurations.

To address these limitations, we have developed a comprehensive endoscopy system that combines a rigid Hopkins endoscope with a state-of-the-art time-gated camera utilizing the CAPS sensor (tauCAM). This system capitalizes on the strengths of FLT to improve intraoperative imaging.

Additionally, we have introduced a novel deep learning-based algorithm, FLTCNN, which accurately estimates fluorescence lifetimes without requiring the system’s intrinsic parameters. The algorithm significantly reduces computational demands using a few data points, making real-time FLT imaging feasible.

Moreover, we have introduced a technique known as time-sequential RGB imaging. In this method, the surgical scene is sequentially illuminated with red, green, blue, and NIR light pulses, enabling the simultaneous acquisition of both RGB and FLT images. These images can be overlaid to give surgeons comprehensive real-time visual feedback.

Our research addresses the critical need for efficient recording of IRFs and dramatically reduces the time points required for lifetime estimation. By combining time-sequential RGB imaging with FLT in a single-camera system, we overcome challenges related to image alignment and equipment bulkiness. This development promises an advancement in surgical imaging technology, offering improved precision and better outcomes for cancer patients.

ETRO’s Senior Business Development Manager Bugra Ersu was invited by Istanbul Project Management Institute to give a webinar on problems encountered in technology transfer projects.
A very productive event was held with the participation of more than 100 project professionals from different sectors.

https://www.linkedin.com/feed/update/urn:li:activity:6760177146632691712/

On November 7th 2024 at 16:00, Boris Joukovsky will defend their PhD entitled “ SIGNAL PROCESSING MEETS DEEP LEARNING: INTERPRETABLE AND EXPLAINABLE NEURAL NETWORKS FOR VIDEO ANALYSIS, SEQUENCE MODELING AND COMPRESSION”.

Everybody is invited to attend the presentation in room I.0.01 or online via this link.

There is growing use of deep learning for solving signal processing tasks, and deep neural networks (DNNs) often outperform traditional methods little domain knowledge needed. However, DNNs behave as black boxes, making it difficult to understand their decisions. The empirical approaches to design DNNs often lack theoretical guarantees and create high computational requirements, which poses risks for applications requiring trustworthy artificial intelligence (AI). This thesis addresses these issues, focusing on video processing and sequential problems across three domains: (1) efficient, model-based DNN designs, (2) generalization analysis and information-theory-driven learning, and (3) post-hoc explainability.

The first contributions consist of new deep learning models for successive frame reconstruction, foreground-background separation, and moving object detection in video. These models are based on the deep unfolding method, a hybrid approach that combines deep learning with optimization techniques, leveraging low-complexity prior knowledge of the data. The resulting networks require fewer parameters than standard DNNs. They outperform DNNs of comparable size, large semantic-based convolutional networks, as well the underlying non-learned optimization methods.

The second area focuses on the theoretical generalization of deep unfolding models. The generalization error of reweighted-RNN (the model that performs video reconstruction) is characterized using Rademacher complexity analysis. This is a first-of-its-kind result that bridges machine learning theory with deep unfolding RNNs.

Another contribution in this area aims to learn optimally compressed, quality-scalable representations of distributed signals: a scheme traditionally known as Wyner-Ziv coding (WZC). The proposed method shows that deep models can retrieve layered binning solutions akin to optimal WZC, which is promising to learn constructive coding schemes for distributed applications.

The third area introduces InteractionLIME, an algorithm to explain how deep models learn multi-view or multi-modal representations. It is the first model-agnostic explanation method design to identify the important feature pairs across inputs that affect the prediction. Experimental results demonstrate its effectiveness on contrastive vision and language models.

In conclusion, this thesis addresses important challenges in making deep learning models more interpretable, efficient, and theoretically grounded, particularly for video processing and sequential data, thereby contributing to the development of more trustworthy AI systems.

The Charcot Fund Jury met on December 9, 2022.

The project “Disentangling cognitive functioning and visual scanning deficits in cognitive test scores” (Prom: Prof J. Van Schependom), has been selected by the Jury for the Charcot Fund 2023.

The Charcot Fund Ceremony will take place on 31 January 2023 at the University Foundation.  

https://www.fondation-charcot.org/en/charcot-research-fund

On September 21 2021 at 15.00 Placide Shabisha will defend his PhD entitled “EFFICIENT SECURITY SCHEMES FOR THE INTERNET OF THINGS AND DATA STORAGE ON THE CLOUD”.

Everybody is invited to attend the online presentation via  this teams link.

The Internet of Things (IoT) and its applications have literally invaded our environment, home, cities, cars, etc. and there could be more than 40 billion IoT devices generating around 80 zettabytes of data in 2025. Most of the generated IoT data are stored on the cloud from where they can be downloaded by users.
End-to-end security in this process is of ultimate importance in order to obtain trust of the users. The process consists of two main phases, data transmission from the IoT devices to a cloud service provider, and data transmission from the cloud service provider to a legitimate receiver. The cloud service provider is in our set-up considered as a so-called honest but curious entity, who executes the required steps but is interested in retrieving the data for own purposes. Security includes besides confidentiality of the data between sender and legitimate receiver, also integrity of the data and authentication of the entities participating in the process. In addition, anonymity and non-traceability of the sender are also often included as important requirements in order to increase the privacy. In this thesis, we have studied dedicated security mechanisms for both phases with a focus on efficiency since the IoT devices are assumed to be constrained devices and require a highly scalable approach due to their large amount.
In the first part of the thesis, we focused on security primitives enabling the secure data transmission from cloud service provider to receiver. On the one hand we proposed public key-based mechanisms to enable proxy re-signcryption, on the other hand symmetric key based mechanisms were proposed to enable proxy re-encryption. Public key-based schemes offer data integrity using signatures and are interesting for powerful devices. The symmetric key based approach is more efficient in terms of communication and computation cost. However, it requires the presence of a completely trusted third party, which is in possession of all keys and thus is vulnerable for key escrow.
In the second part of the thesis, we elaborate on the proposed mechanisms for secure data transmission between IoT devices and cloud service provider in which we consider a fog-based architecture. This fog type of architecture is nowadays very popular as they are efficient in terms of location awareness, hardware size, easy deployment, decentralized and simplified operations, time criticalness, internet connectivity and bandwidth usage, etc. We proposed two fog-based solutions. In the first scheme, a
new key agreement is designed for an architecture model with one device, a fog and a server. In the second solution, the proposed key agreement protocol is suitable for a group of devices, a fog and a server.
To conclude, this thesis contributes to the development and analysis of highly efficient security primitives required for an end-to-end security solution between IoT devices and different legitimate receivers.

The Brubotics Rehabilitation Research Center (BRRC) is the new lab of the BruBotics Rehabilitation Research group of the Vrije Universiteit Brussel. This lab is a state-of-the-art, interdisciplinary innovation hub that offers human movement analysis and technology-supported rehabilitation research. The BRRC is the result of a longstanding collaboration with different partners of the Brubotics group and is located centrally between the university hospital UZ Brussel and the VUB Health Campus.

ETRO is one of the partners of Brubotics and Prof. Bart Jansen is member of the steering group od the Brubotics Rehabilitation Research Center.

The official opening was organized on September 14 and was covered in de tijd and Bruzz.