Master thesis: HPC/AI for breast cancer detection

Ms. Tamara Pavlovic defended her MSc thesis on the use of HPC/AI for creating prediction models for breast cancer detection on 23.10.2024. With the support from NCC Montenegro, Ms Pavlovic did her research in the context of the HPC4S3ME project and the focus was on AI and computer vision applications in medicine. From the motivational point of view, we congratulate Tamara for finalizing and defending her thesis during the Breast Cancer Awareness Month (‘Pink October’) as people around the world adopt the pink colour and display a pink ribbon to raise awareness about breast health.

ABSTRACT – Artificial Intelligence (AI) is revolutionizing numerous sectors, including medicine, by offering innovative methods for diagnosing, treating, and researching diseases. This master’s thesis focuses on the application of AI in the diagnosis of breast cancer, using computer vision algorithms to analyze mammographic images. Through a combination of convolutional neural networks (CNNs) and deep learning, models have been developed that identify malignant changes, potentially contributing to earlier and more precise disease detection. The thesis examines in detail how AI can improve the efficiency of screening processes, reduce the time required for diagnosis, and enable a more personalized approach to treatment. In addition to technological progress, ethical issues such as patient safety and the transparency of AI systems are also considered. The results of this study confirm that the application of AI in breast cancer diagnostics can significantly enhance medical procedures. The models tested, ResNet152 and DenseNet121, demonstrated quite good performance in classifying breast cancer. Their AUC scores, which exceed the threshold of 0.9, indicate their potential for use in clinical practice. These findings not only contribute to the improvement of diagnostic processes but also open up opportunities for further research and development of AI technologies in medicine.

This research was done in th context of HPC4S3ME and with the support from EUROCC NCC Montenegro
Ms Pavlovic finalized her thesis during the Breast Cancer Awareness Month (‘Pink October’)

The AI Conference on Building a National AI Strategy

The AI Conference, organized by the World Bank on September 24-25, 2024, in Budva, Montenegro, brought together global AI experts, policymakers, and stakeholders from both the public sector and academia to explore the integration of AI into national strategies/policies, government operations, and public services. Representatives from NCC Montenegro actively participated in the two-day workshops, engaging in discussions on AI opportunities, challenges, and practical use cases for public administration. They emphasize the importance of digital upskilling and AI expertise, the need for data repositories and open data policies, and the establishment of advanced computing infrastructure. NCC also elaborated on its activities and efforts in the development of a HPC/AI ecosystem in Montenegro.

Mr. Marash Dukaj, Minister of Public Administration, delivered a welcoming speech recognizing the necessity of AI and its potential to enhance public administration, economic development, and societal progress. He highlighted AI’s ability to enrich citizens’ lives through personalized services, enhanced resource management, business process optimization, and new innovation opportunities. The Ministry of Public Administration, in partnership with the World Bank through the BEST project, is set to develop a strategic roadmap for AI adoption in Montenegro.

Dr. Keegan McBride, lecturer in AI, Government, and Policy at the Oxford Internet Institute, outlined essential AI concepts for public sector implementation. Barbara Ubaldi, Head of the Digital Government and Data Unit at OECD, shared valuable insights from AI strategies in OECD countries, highlighting various public sector AI applications, and lessons learned. AI expert, Varun Hemachandran presented practical examples of AI in government contexts, while Divya Siddarth, Executive Director of the Collective Intelligence Project, stressed the critical role of stakeholder engagement in AI development.

Participants engaged in working groups and brainstorming sessions focused on envisioning a national AI strategy, creating building blocks for AI governance, and addressing potential challenges in administrative services, tax policies, and digital health. The conference provided a dynamic platform for discussing strategic, transparent, and responsible approaches to AI integration in the public sector, fostering valuable knowledge, insights and networking opportunities to advance Montenegro’s AI agenda.

AI and Data-intensive Applications EuroHPC JU Access call 2024

The call is designed to serve industry organisations, small to medium enterprises (SMEs), startups, as well as public sector entities, requiring access to supercomputing resources to perform artificial intelligence and data-intensive activities.

Start date: time-to-resources-access of one (1) month after the date of cut-off.

Duration: The allocations are granted for one (1) year.

Next cut-off dates: 11 Oct 2024, 22 Nov 2024.

For more information, feel free to visit our website eurohpc-ju.europa.eu or drop an email to access@eurohpc-ju.europa.eu

Lecture on AI and Collective Intelligence

On Friday, September 27, UDG welcomed Divya Siddarth, one of the 100 most influential young people in the field of artificial intelligence, as chosen by TIME magazine! Divya is a researcher at Microsoft Research, in the Political Economy and Social Technologies (PEST) department, and co-founder of the Collective Intelligence Project. Her work focuses on using technology to create fairer societies, with a particular emphasis on decentralized technologies, artificial intelligence and digital democracy. She was recently recognized as one of the key minds shaping the future of artificial intelligence in the service of the common good! The audience included students, researchers and industry representatives.

Ms Divya Siddarth is one of the 100 most influential young people in the field of artificial intelligence
It was a pleasure to be a part of this discussion. There was over 200 people in the audience
Ms Siddarth is a researcher at Microsoft Research and co-founder of the Collective Intelligence Project

Revolutionising Agriculture with HPC and AI: Real-World Applications

At the Revolutionising Agriculture with HPC and AI: Real-World Applications conference, the project, AIMHiGH, was presented, with DigitalSmart as the coordinator. The project, implemented as part of the HPC Fortissimo initiative and funded through the Horizon 2020 FF4EuroHPC program, was titled AI/ML Enabled by HPC for Edge Camera Devices for the Next Generation Hen Farms. Stevan Cakic presented experience with the AIMHiGH project that introduced cutting-edge HPC and AI/ML technologies that significantly impacted the poultry farming sector. One of the key achievements of the project was enabling real-time monitoring and data-driven insights. Farmers gained access to continuous, real-time surveillance of their poultry through edge cameras equipped with AI models. These models could analyze live footage to identify early signs of illness, stress, or abnormal behavior, allowing immediate intervention. This innovation improved animal welfare, minimized losses, and enhanced overall productivity on the farms.

In addition, the project provided an advanced solution for disease detection and prevention. The AI models developed during the project were capable of detecting subtle signs of illness long before they became visible to the human eye. This early detection allowed for more effective prevention and control, reducing the spread of diseases and ultimately leading to lower usage of antibiotics, which had a positive impact on both costs and animal health. Moreover, the project’s technological solutions helped optimize resource usage, particularly in terms of feed and water management. With real-time behavioral and health data from the birds, farmers could adjust feeding schedules and amounts according to actual needs, reducing waste and cutting down on unnecessary resource consumption. This not only reduced environmental impact but also contributed to more efficient and sustainable production practices.

Presenting HPC and deep learning appraoch

The project’s approach to automating monitoring and decision-making processes also had a transformative effect on production efficiency. By reducing the need for manual supervision, the system allowed farm workers to focus on more critical tasks, leading to higher production outputs while maintaining lower operational costs. A further advantage was the scalability and flexibility of the technology. The use of edge devices allowed these AI models to be easily deployed in various farm setups without requiring expensive infrastructure. This made the technology accessible to both large-scale operations and smaller farms, ensuring that the benefits of AI and HPC could reach a broader segment of the poultry farming industry. Throughout the project, collaboration with key partners played a crucial role. DunavNET contributed its expertise in AI, machine learning, IoT, and software development, while The University of Donja Gorica brought significant HPC expertise through NCC Montenegro and the FoodHub Centre of Excellence. Montenegrin companies Meso-promet Franca and Radinović Company participated actively in the evaluation and piloting phases of the project, ensuring the practical relevance and success of the solutions developed. Overall, the AIMHiGH project was fully aligned with the priorities of Montenegro’s S3 Smart Specialisation Strategy, making significant contributions to technological innovation in the poultry sector, while strengthening the local economy and supporting more sustainable farming practices.

Discussing experiment results and prospects for future work

HPC in Europe Podcast

Welcome to “Supercomputing in Europe” podcast from the EuroCC and Centre of Excellence network where we will talk about all things supercomputers.

Listen to stories by guests from all around Europe who talk about their work and give us interesting insights on the role of supercomputers in multiple fields such as life science, machine learning, engineering, data science, quantum computing, and more.

In the first episode, listen to EuroHPC Joint Undertaking (EuroHPC JU) executive director Anders Dam Jensen discuss with communication specialist Apostolos Vasileiadis (ENCCS, RISE Research Institutes of Sweden) about EuroHPC JU and the state of supercomputing in Europe and its future.

In the second episode listen to Marta García-Gasulla and Filippo Mantovani from Barcelona Supercomputing Center discuss with Sally Kiebdaj (Center of Excellence in Exascale CFD, HLRS – High-Performance Computing Center Stuttgart) about the European Processor Initiative and CEEC CoE.

Spotify: https://lnkd.in/dSHmk2Kx
Apple podcasts: https://lnkd.in/dyuBMFyM

NCC Montenegro hosts Supercomputing Workshops for new UDG students

As a part of the orientation week for new students, the EuroCC National Competence Centre Montenegro has organized a Supercomputing Workshop aimed at introducing incoming university students to the exciting world of high-performance computing (HPC).

The workshop featured interactive sessions where students could get insights into cutting-edge technologies used in supercomputing, such as parallel processing, intelligent algorithms, and data analytics. Experts from the NCC guided the participants through the technical fundamentals of HPC systems, demonstrated real-world applications related to Big Data processing and advanced AI modelling, but also provided examples of academic study cases and industry use cases, including Montenegro’s success stories.

The aim of the workshop was also to provide brief overview on HPC/AI related academic programs, training portfolio and NCC activities, to show how students can leverage supercomputing resources for academic projects and scientific research, or even for startup ideas and potential industry collaboration.

By exposing new students to the potential of supercomputing early in their academic journey, the NCC aims to support students’ development in high-demand, tech-driven carriers, and to foster community of innovative thinkers prepared to tackle complex and critical challenges of the modern world.