Project acronym 2LIVEr
Project IL-2 gene therapy for chronic hepatitis B virus infection
Researcher (PI) Matteo IANNACONE
Host Institution (HI) OSPEDALE SAN RAFFAELE SRL
Country Italy
Call Details Proof of Concept (PoC), ERC-2020-PoC
Summary Hepatitis B virus (HBV) infections remain a major public health issue worldwide. Over 350 -400 million people are chronically infected by HBV, and about 1 million people die each year from the complications of this infection (cirrhosis and hepatocellular carcinoma) with a consequent hefty economic impact on national health systems. This led the World Health Organization to recognise HBV infection as a key priority and adopt the global health sector strategy to eliminate viral hepatitis, with a target of reducing new infections by 90% and mortality by 65% by 2030.
The risk of developing a chronic infection in healthy adults is due to a weaker, dysfunctional and narrowly focused CD8+ T cell response. Since the mechanisms underlying HBV persistence are not fully elucidated, current treatments (antiviral drugs and Interferon) aim to reduce the development of liver disease, while a definitive treatment for curing this infection is not yet available on the market.
Within the ERC Consolidator Grant 725038 “FATE”, we recently characterized the mechanisms behind the ineffective CD8+ T cell response towards HBV, demonstrating the potential efficacy of interleukin-2 (IL-2) – a cytokine – to reactivate it, thus achieving antiviral activity. This discovery, jointly with our proprietary third-generation, self-inactivating lentiviral vectors (LVs) that allow selective hepatocellular expression of IL-2, pave the way to single-dose gene therapy-based approach, a potential functional cure against chronic hepatitis B.
2LIVEr project intends to optimize and further validate our novel therapeutic approach from both a technical and commercial standpoint, moving from TRL3 to TRL4, thus fastening the roadmap towards the market.
Summary
Hepatitis B virus (HBV) infections remain a major public health issue worldwide. Over 350 -400 million people are chronically infected by HBV, and about 1 million people die each year from the complications of this infection (cirrhosis and hepatocellular carcinoma) with a consequent hefty economic impact on national health systems. This led the World Health Organization to recognise HBV infection as a key priority and adopt the global health sector strategy to eliminate viral hepatitis, with a target of reducing new infections by 90% and mortality by 65% by 2030.
The risk of developing a chronic infection in healthy adults is due to a weaker, dysfunctional and narrowly focused CD8+ T cell response. Since the mechanisms underlying HBV persistence are not fully elucidated, current treatments (antiviral drugs and Interferon) aim to reduce the development of liver disease, while a definitive treatment for curing this infection is not yet available on the market.
Within the ERC Consolidator Grant 725038 “FATE”, we recently characterized the mechanisms behind the ineffective CD8+ T cell response towards HBV, demonstrating the potential efficacy of interleukin-2 (IL-2) – a cytokine – to reactivate it, thus achieving antiviral activity. This discovery, jointly with our proprietary third-generation, self-inactivating lentiviral vectors (LVs) that allow selective hepatocellular expression of IL-2, pave the way to single-dose gene therapy-based approach, a potential functional cure against chronic hepatitis B.
2LIVEr project intends to optimize and further validate our novel therapeutic approach from both a technical and commercial standpoint, moving from TRL3 to TRL4, thus fastening the roadmap towards the market.
Max ERC Funding
150 000 €
Duration
Start date: 2020-07-01, End date: 2021-12-31
Project acronym AAV-FACTORY
Project Synthetic Viral Nanosystem for Highly Efficient AAV Manufacturing for Gene Therapy
Researcher (PI) Imre Berger
Host Institution (HI) UNIVERSITY OF BRISTOL
Country United Kingdom
Call Details Proof of Concept (PoC), ERC-2020-PoC
Summary Gene therapy is one of the most innovative and fastest growing fields in the pharmaceutical industry. The first approved gene therapy utilized a recombinant AAV vector (rAAV), and dozens of additional rAAVs for gene therapy are presently in clinical trials. rAAV gene therapy drugs have been priced in the region of € 500’000 and above, which is partially a result of them being manufactured by highly complex processes combining multiple components, requiring 5-7 separate GMP production runs. We intend to introduce the first scalable, single-virus rAAV production platform to resolve this bottleneck. The resulting significant reduction of manufacturing complexity will both lower the price of future rAAV gene therapies, and also deliver additional, currently unaddressed or unaffordable rAAV treatments for genetic diseases into the clinic by providing scientists operating at the laboratory R&D stage with more user friendly and productive tools. The proposed project also develops for PoC purposes an rAAV gene therapy candidate to treat the devastating childhood congenital disease known as steroid resistant nephrotic syndrome SRNS.
Summary
Gene therapy is one of the most innovative and fastest growing fields in the pharmaceutical industry. The first approved gene therapy utilized a recombinant AAV vector (rAAV), and dozens of additional rAAVs for gene therapy are presently in clinical trials. rAAV gene therapy drugs have been priced in the region of € 500’000 and above, which is partially a result of them being manufactured by highly complex processes combining multiple components, requiring 5-7 separate GMP production runs. We intend to introduce the first scalable, single-virus rAAV production platform to resolve this bottleneck. The resulting significant reduction of manufacturing complexity will both lower the price of future rAAV gene therapies, and also deliver additional, currently unaddressed or unaffordable rAAV treatments for genetic diseases into the clinic by providing scientists operating at the laboratory R&D stage with more user friendly and productive tools. The proposed project also develops for PoC purposes an rAAV gene therapy candidate to treat the devastating childhood congenital disease known as steroid resistant nephrotic syndrome SRNS.
Max ERC Funding
150 000 €
Duration
Start date: 2021-02-01, End date: 2022-07-31
Project acronym AdOptEx
Project Translation of adaptive optical microscopy expertise to the commercial domain
Host Institution (HI) THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORD
Country United Kingdom
Call Details Proof of Concept (PoC), ERC-2020-PoC
Summary Adaptive optics (AO) is an important technology for high-resolution microscopy that overcomes imaging problems when focusing inside biological specimens. Through the ERC Advanced Grant AdOMiS we have developed and experimentally validated new, broadly applicable AO tools that make integration of this technology more practical for a range of different microscopy techniques. We have also accumulated significant know-how about effective implementation of this technology. The challenge now is to translate these laboratory-based methods and know-how outside the academic research environment. This project will facilitate access to the products of our research to potential research and commercial adopters so that they can successfully deploy our AO methods in their systems.
Summary
Adaptive optics (AO) is an important technology for high-resolution microscopy that overcomes imaging problems when focusing inside biological specimens. Through the ERC Advanced Grant AdOMiS we have developed and experimentally validated new, broadly applicable AO tools that make integration of this technology more practical for a range of different microscopy techniques. We have also accumulated significant know-how about effective implementation of this technology. The challenge now is to translate these laboratory-based methods and know-how outside the academic research environment. This project will facilitate access to the products of our research to potential research and commercial adopters so that they can successfully deploy our AO methods in their systems.
Max ERC Funding
150 000 €
Duration
Start date: 2021-03-01, End date: 2022-08-31
Project acronym AI4Dignity
Project Collaborative AI Counters Hate
Researcher (PI) Sahana Udupa
Host Institution (HI) LUDWIG-MAXIMILIANS-UNIVERSITAET MUENCHEN
Country Germany
Call Details Proof of Concept (PoC), ERC-2020-PoC
Summary Online hate speech and disinformation have emerged as a major problem for democratic societies worldwide. Governments, companies and civil society groups have responded to this phenomenon by increasingly turning to Artificial Intelligence (AI) as a tool that can detect, decelerate and remove online extreme speech. However, such efforts confront many challenges. One of the key challenges is the quality, scope, and inclusivity of training data sets. The second challenge is the lack of procedural guidelines and frameworks that can bring cultural contextualization to these systems. Lack of cultural contextualization has resulted in false positives, over-application and systemic bias. The ongoing ERC project has identified the need for a global comparative framework in AI-assisted solutions in order to address cultural variation, since there is no catch-all algorithm that can work for different contexts. Following this, the proposed project will address major challenges facing AI assisted extreme speech moderation by developing an innovative solution of collaborative bottom-up coding. The model, “AI4Dignity”, moves beyond keyword-based detection systems by pioneering a community-based classification approach. It identifies fact-checkers as critical human interlocutors who can bring cultural contextualization to AI-assisted speech moderation in a meaningful and feasible manner. AI4Dignity will be a significant step towards setting procedural benchmarks to operationalize “the human in the loop” principle and bring inclusive training datasets for AI systems tackling urgent issues of digital hate and disinformation.
Summary
Online hate speech and disinformation have emerged as a major problem for democratic societies worldwide. Governments, companies and civil society groups have responded to this phenomenon by increasingly turning to Artificial Intelligence (AI) as a tool that can detect, decelerate and remove online extreme speech. However, such efforts confront many challenges. One of the key challenges is the quality, scope, and inclusivity of training data sets. The second challenge is the lack of procedural guidelines and frameworks that can bring cultural contextualization to these systems. Lack of cultural contextualization has resulted in false positives, over-application and systemic bias. The ongoing ERC project has identified the need for a global comparative framework in AI-assisted solutions in order to address cultural variation, since there is no catch-all algorithm that can work for different contexts. Following this, the proposed project will address major challenges facing AI assisted extreme speech moderation by developing an innovative solution of collaborative bottom-up coding. The model, “AI4Dignity”, moves beyond keyword-based detection systems by pioneering a community-based classification approach. It identifies fact-checkers as critical human interlocutors who can bring cultural contextualization to AI-assisted speech moderation in a meaningful and feasible manner. AI4Dignity will be a significant step towards setting procedural benchmarks to operationalize “the human in the loop” principle and bring inclusive training datasets for AI systems tackling urgent issues of digital hate and disinformation.
Max ERC Funding
150 000 €
Duration
Start date: 2021-01-01, End date: 2022-06-30
Project acronym AI4SmartCities
Project Artificial Intelligence for Smart Cities
Researcher (PI) Xiaoxiang Zhu
Host Institution (HI) TECHNISCHE UNIVERSITAET MUENCHEN
Country Germany
Call Details Proof of Concept (PoC), ERC-2020-PoC
Summary It is estimated that by 2050, 68% of the world population will live in urban areas, according to the United Nations. With the accelerated rhythm of population growth, the expected number of urban citizens in 2050 is close to 6.5 billion (compared to 4.2 billion nowadays). Uncontrolled urbanization raises a significant problem, the topic of the United Nations Development Programme Goal 11: ensuring sustainable and safe growth of urban areas. This project therefore addresses a global problem. To enable smart urban planning and scalable methods for example to predict the risk of structural degradation or damage to city buildings, it is essential to create efficient tools that can analyse large amounts of data, over time (4D), to create comprehensive global urban maps. The continuous expansion of data sets poses a significant problem for data analytics for global smart urban planning: we currently lack solutions that can generate useful insights from the data.
In this PoC project, I aim to extend the AI algorithms and the big Earth observation data management features developed in the ERC Starting grant to very high resolution data for Smart City applications and offer our software as a commercial, integrated service. Within the PoC, a comprehensive business case that will assist us in designing an exploitation strategy will be developed. Achieving these objectives will advance our AI solution for Smart City from a technology readiness level (TRL) of 4 to 6.
Our value proposition in AI4SmartCities is a set of professional solutions for very high resolution geo-spatial and social-economic indicators for Smart City planning and management by retrieving them from big EO data using AI. For example, high resolution building footprint map, urban building change map, and traffic flow map. Supporting the abovementioned solutions is an easy-to-use, interactive big EO data analysis platform.
Summary
It is estimated that by 2050, 68% of the world population will live in urban areas, according to the United Nations. With the accelerated rhythm of population growth, the expected number of urban citizens in 2050 is close to 6.5 billion (compared to 4.2 billion nowadays). Uncontrolled urbanization raises a significant problem, the topic of the United Nations Development Programme Goal 11: ensuring sustainable and safe growth of urban areas. This project therefore addresses a global problem. To enable smart urban planning and scalable methods for example to predict the risk of structural degradation or damage to city buildings, it is essential to create efficient tools that can analyse large amounts of data, over time (4D), to create comprehensive global urban maps. The continuous expansion of data sets poses a significant problem for data analytics for global smart urban planning: we currently lack solutions that can generate useful insights from the data.
In this PoC project, I aim to extend the AI algorithms and the big Earth observation data management features developed in the ERC Starting grant to very high resolution data for Smart City applications and offer our software as a commercial, integrated service. Within the PoC, a comprehensive business case that will assist us in designing an exploitation strategy will be developed. Achieving these objectives will advance our AI solution for Smart City from a technology readiness level (TRL) of 4 to 6.
Our value proposition in AI4SmartCities is a set of professional solutions for very high resolution geo-spatial and social-economic indicators for Smart City planning and management by retrieving them from big EO data using AI. For example, high resolution building footprint map, urban building change map, and traffic flow map. Supporting the abovementioned solutions is an easy-to-use, interactive big EO data analysis platform.
Max ERC Funding
150 000 €
Duration
Start date: 2021-01-01, End date: 2022-06-30
Project acronym ALPI
Project ALl optical signal recovery by Photonic neural network Integrated in a transceiver module
Researcher (PI) Lorenzo PAVESI
Host Institution (HI) UNIVERSITA DEGLI STUDI DI TRENTO
Country Italy
Call Details Proof of Concept (PoC), ERC-2020-PoC
Summary ALPI aims at the integration of a photonic neural network within an optical transceiver to increase the transmission capacity
of the optical link. Based on a deep learning approach, the new compact device provides real time compensation of fiber
nonlinearities which degrade optical signals. In fact, the tremendous growth of transmission bandwidth both in optical
networks as well as in data centers is baffled by the optical fiber nonlinear Shannon capacity limit. Nowadays, computational
intensive approaches based on power hungry software are commonly used to mitigate fiber nonlinearities. Here, we propose
to integrate in the optical link the neuromorphic photonic circuits which we are currently developing in the ERC-AdG
BACKUP project. Specifically, the proposed error-correction circuit implements a small all-optical complex-valued neural
network which is able to recover distortion on the optical transmitted data caused by the Kerr nonlinearities in multiwavelength
optical fibers. Network training is realized by means of efficient gradient-free methods using a properly designed
data-preamble.
A new neuromorphic transceiver demonstrator realized in active hybrid Si/InP technology will be designed, developed and
tested on a 100 Gbps 80 km long optical link with multiple-levels symbols. The integrated neural network will mitigate the
nonlinearities either by precompensation/autoencoding at the transmitter TX side or by data correction at the receiver RX
side or by concurrently acting on both the TX and RX sides. This achievement will bear to the second ALPI’s goal: moving
from the demonstrator to the industrialization of the improved transceiver. For this purposes, patents will be filed and a business plan will be developed in partnership with semiconductor, telecom and IT companies where a path to the commercialization will be
individuated. The foreseen market is the big volume market of optical interconnection in large data centers or metro
networks.
Summary
ALPI aims at the integration of a photonic neural network within an optical transceiver to increase the transmission capacity
of the optical link. Based on a deep learning approach, the new compact device provides real time compensation of fiber
nonlinearities which degrade optical signals. In fact, the tremendous growth of transmission bandwidth both in optical
networks as well as in data centers is baffled by the optical fiber nonlinear Shannon capacity limit. Nowadays, computational
intensive approaches based on power hungry software are commonly used to mitigate fiber nonlinearities. Here, we propose
to integrate in the optical link the neuromorphic photonic circuits which we are currently developing in the ERC-AdG
BACKUP project. Specifically, the proposed error-correction circuit implements a small all-optical complex-valued neural
network which is able to recover distortion on the optical transmitted data caused by the Kerr nonlinearities in multiwavelength
optical fibers. Network training is realized by means of efficient gradient-free methods using a properly designed
data-preamble.
A new neuromorphic transceiver demonstrator realized in active hybrid Si/InP technology will be designed, developed and
tested on a 100 Gbps 80 km long optical link with multiple-levels symbols. The integrated neural network will mitigate the
nonlinearities either by precompensation/autoencoding at the transmitter TX side or by data correction at the receiver RX
side or by concurrently acting on both the TX and RX sides. This achievement will bear to the second ALPI’s goal: moving
from the demonstrator to the industrialization of the improved transceiver. For this purposes, patents will be filed and a business plan will be developed in partnership with semiconductor, telecom and IT companies where a path to the commercialization will be
individuated. The foreseen market is the big volume market of optical interconnection in large data centers or metro
networks.
Max ERC Funding
150 000 €
Duration
Start date: 2020-11-01, End date: 2022-04-30
Project acronym AMNIOGEL
Project Extracellular matrix derived products from human placenta to engineer bone microtissues for in vitro disease models.
Researcher (PI) Joao Filipe Colardelle Da Luz Mano
Host Institution (HI) UNIVERSIDADE DE AVEIRO
Country Portugal
Call Details Proof of Concept (PoC), ERC-2020-PoC
Summary The aim of ‘AMNIOGEL’ is the development of human extracellular matrix (ECM) based materials, as radically innovative,
highly versatile human-derived platforms for 3D cell culture, microtissue development and disease models establishment. In
particular, we will develop 3D disease models that could be used as an enabling tool for personalized drug discovery,
increasing our understanding of the mechanisms behind bone cancer.
The proposed cutting-edge technology enables the culture of human cells in a physiologically relevant microenvironment for
applications in cell culture research, drug screening and development, cancer research, tissue engineering, replacement of
animal testing and therapeutic applications. The potential of this technology to reduce or completely replace use of animals
for biological screenings is expected to have a significant impact in the 3D cell culture market and pharmaceutical industry
by accelerating drug screening and development reducing associated costs. The innovation potential of our products is
based on the fact that contain human biochemical cues (vital for cell function), is a complete xeno-free solution (avoids
contamination) for human cell culture and easy to manipulate. It is worth mentioning that offers the possibility to be
personalised (using the patient’s own ECM) according to the customer needs. Moreover, our culture substrates are easily
processed in multiple geometries and in microarrays amenable to ‘organ-on- a-chip’ systems designed for high-throughput
screening (HTS) applications.
Summary
The aim of ‘AMNIOGEL’ is the development of human extracellular matrix (ECM) based materials, as radically innovative,
highly versatile human-derived platforms for 3D cell culture, microtissue development and disease models establishment. In
particular, we will develop 3D disease models that could be used as an enabling tool for personalized drug discovery,
increasing our understanding of the mechanisms behind bone cancer.
The proposed cutting-edge technology enables the culture of human cells in a physiologically relevant microenvironment for
applications in cell culture research, drug screening and development, cancer research, tissue engineering, replacement of
animal testing and therapeutic applications. The potential of this technology to reduce or completely replace use of animals
for biological screenings is expected to have a significant impact in the 3D cell culture market and pharmaceutical industry
by accelerating drug screening and development reducing associated costs. The innovation potential of our products is
based on the fact that contain human biochemical cues (vital for cell function), is a complete xeno-free solution (avoids
contamination) for human cell culture and easy to manipulate. It is worth mentioning that offers the possibility to be
personalised (using the patient’s own ECM) according to the customer needs. Moreover, our culture substrates are easily
processed in multiple geometries and in microarrays amenable to ‘organ-on- a-chip’ systems designed for high-throughput
screening (HTS) applications.
Max ERC Funding
150 000 €
Duration
Start date: 2020-09-01, End date: 2022-02-28
Project acronym aSINdo
Project Active dielectric-on-Si3N4 double layer platform
Researcher (PI) Sonia Maria GARCIA BLANCO
Host Institution (HI) UNIVERSITEIT TWENTE
Country Netherlands
Call Details Proof of Concept (PoC), ERC-2020-PoC
Summary aSINdo will study the technical feasibility and commercialization strategy of on-chip optical gain building blocks based on rare-earth ion doped Al2O3 that can be integrated onto passive integrated photonic material platforms, in particular Si3N4, to realize on-chip amplifiers and lasers.
The value proposition of this technology is to enable photonic integrated circuits to achieve sufficient output power to empower multiple emerging applications. Important advantages with respect to existing solutions are the manufacturability, cost reduction, power efficiency and building block approach, which will ease the adoption of this technology by design houses and system integrators.
In aSINdo we will increase the readiness level of the technology, we will define an IPR strategy and we will give the first
steps towards its commercialization by means of a market study and business plan. Dissemination activities will ensure
knowledge transfer to relevant parties, which may play a crucial role in defining the commercialization strategy.
Summary
aSINdo will study the technical feasibility and commercialization strategy of on-chip optical gain building blocks based on rare-earth ion doped Al2O3 that can be integrated onto passive integrated photonic material platforms, in particular Si3N4, to realize on-chip amplifiers and lasers.
The value proposition of this technology is to enable photonic integrated circuits to achieve sufficient output power to empower multiple emerging applications. Important advantages with respect to existing solutions are the manufacturability, cost reduction, power efficiency and building block approach, which will ease the adoption of this technology by design houses and system integrators.
In aSINdo we will increase the readiness level of the technology, we will define an IPR strategy and we will give the first
steps towards its commercialization by means of a market study and business plan. Dissemination activities will ensure
knowledge transfer to relevant parties, which may play a crucial role in defining the commercialization strategy.
Max ERC Funding
150 000 €
Duration
Start date: 2020-12-01, End date: 2022-05-31
Project acronym AssemblySkills
Project Acquiring assembly skills by robot learning
Researcher (PI) Jan Peters
Host Institution (HI) TECHNISCHE UNIVERSITAT DARMSTADT
Country Germany
Call Details Proof of Concept (PoC), ERC-2020-PoC
Summary Present-day industrial robots are made for the purpose of repeating several tasks thousands of times. What the
manufacturing industry needs instead is a robot that can do thousands of tasks, a few times. Programming a robot to solve
just one complex motor task has remained a challenging, costly and time-consuming task. In fact, it has become the key
bottleneck in industrial robotics. Empowering robots with the ability to autonomously learn such tasks is a promising
approach, and, in theory, machine learning has promised fully adaptive control algorithms which learn both by observation
and trial-and-error. However, to date, learning techniques have yet to fulfil this promise, as only few methods manage to
scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of collaborative robots.
The goal of the AssemblySkills ERC PoC is to validate an autonomous skill learning system that enables industrial robots to
acquire and improve a rich set of motor skills. Using structured, modular control architectures is a promising concept to scale
robot learning to more complex real-world tasks. In such a modular control architecture, elemental building blocks – called
movement primitives, need to be adapted, sequenced or co-activated simultaneously. Within the ERC PoC AssemblySkills,
our goal is to group these modules into an industry-scale complete software package that can enable industrial robots to
learn new skills (particularly in assembly tasks). The value proposition of our ERC PoC is a cost-effective, novel machine
learning system that can unlock the potential of manufacturing robots by enabling them to learn to select, adapt and
sequence parametrized building blocks such as movement primitives. Our approach is unique in the sense that it can
acquire more than just a single desired trajectory as done in competing approaches, capable of save policy adaptation,
requires only little data and can explain the solution to the robot operator.
Summary
Present-day industrial robots are made for the purpose of repeating several tasks thousands of times. What the
manufacturing industry needs instead is a robot that can do thousands of tasks, a few times. Programming a robot to solve
just one complex motor task has remained a challenging, costly and time-consuming task. In fact, it has become the key
bottleneck in industrial robotics. Empowering robots with the ability to autonomously learn such tasks is a promising
approach, and, in theory, machine learning has promised fully adaptive control algorithms which learn both by observation
and trial-and-error. However, to date, learning techniques have yet to fulfil this promise, as only few methods manage to
scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of collaborative robots.
The goal of the AssemblySkills ERC PoC is to validate an autonomous skill learning system that enables industrial robots to
acquire and improve a rich set of motor skills. Using structured, modular control architectures is a promising concept to scale
robot learning to more complex real-world tasks. In such a modular control architecture, elemental building blocks – called
movement primitives, need to be adapted, sequenced or co-activated simultaneously. Within the ERC PoC AssemblySkills,
our goal is to group these modules into an industry-scale complete software package that can enable industrial robots to
learn new skills (particularly in assembly tasks). The value proposition of our ERC PoC is a cost-effective, novel machine
learning system that can unlock the potential of manufacturing robots by enabling them to learn to select, adapt and
sequence parametrized building blocks such as movement primitives. Our approach is unique in the sense that it can
acquire more than just a single desired trajectory as done in competing approaches, capable of save policy adaptation,
requires only little data and can explain the solution to the robot operator.
Max ERC Funding
150 000 €
Duration
Start date: 2021-01-01, End date: 2022-06-30
Project acronym AUTO.DISTINCT
Project A fully automated deep learning-based software for fast, robust and accurate detection and segmentation of tumours and metastasis
Researcher (PI) Philippe LAMBIN
Host Institution (HI) UNIVERSITEIT MAASTRICHT
Country Netherlands
Call Details Proof of Concept (PoC), ERC-2020-PoC
Summary The inaccuracy and inconsistency of state-of-the-art tumour volume detection and segmentation has an adverse influence on patient outcomes. Accurately determining the exact location and volume of tumours is a prerequisite for the detection, segmentation, characterisation and therapy response monitoring for any type of cancer. Today, tumour segmentation is performed manually or semi-automatically in a laborious and time-consuming process that exhibits low accuracy and inconsistency. This compromises quality of care by limiting the certainty of lesion detection on medical images, hindering the effectivity of radiotherapy and restricting the accuracy of treatment response monitoring.
In this ERC PoC project, we introduce fully automated software for fast, accurate, observer independent and reproducible detection and volumetric segmentation of (lung) tumours and metastases on CT images. Through a unique three-step approach, our software demonstrates superior speed, accuracy and robustness of tumour segmentation over both the state-of-the-art as well as published competing solutions for automated tumour segmentation. Hence, our software has the potential to drastically reduce the adverse impact that inaccurate tumour detection and segmentation currently has on (lung) cancer patient outcomes by: improving the detection of lesions on CT images, increasing the accuracy of radiotherapy treatment to reduce the occurrence of geometric misses, and advance the evaluation of tumour response to treatments through volumetric treatment monitoring.
In AUTO.DISTINCT, we will provide technical and commercial proof-of-concept for our novel software. We will solve the remaining technical challenges and develop a user-friendly prototype that can be validated with end users. Moreover, we will develop a business strategy that incorporates all technical, commercial, IPR and regulatory aspects of our invention to ensure successful commercialisation.
Summary
The inaccuracy and inconsistency of state-of-the-art tumour volume detection and segmentation has an adverse influence on patient outcomes. Accurately determining the exact location and volume of tumours is a prerequisite for the detection, segmentation, characterisation and therapy response monitoring for any type of cancer. Today, tumour segmentation is performed manually or semi-automatically in a laborious and time-consuming process that exhibits low accuracy and inconsistency. This compromises quality of care by limiting the certainty of lesion detection on medical images, hindering the effectivity of radiotherapy and restricting the accuracy of treatment response monitoring.
In this ERC PoC project, we introduce fully automated software for fast, accurate, observer independent and reproducible detection and volumetric segmentation of (lung) tumours and metastases on CT images. Through a unique three-step approach, our software demonstrates superior speed, accuracy and robustness of tumour segmentation over both the state-of-the-art as well as published competing solutions for automated tumour segmentation. Hence, our software has the potential to drastically reduce the adverse impact that inaccurate tumour detection and segmentation currently has on (lung) cancer patient outcomes by: improving the detection of lesions on CT images, increasing the accuracy of radiotherapy treatment to reduce the occurrence of geometric misses, and advance the evaluation of tumour response to treatments through volumetric treatment monitoring.
In AUTO.DISTINCT, we will provide technical and commercial proof-of-concept for our novel software. We will solve the remaining technical challenges and develop a user-friendly prototype that can be validated with end users. Moreover, we will develop a business strategy that incorporates all technical, commercial, IPR and regulatory aspects of our invention to ensure successful commercialisation.
Max ERC Funding
150 000 €
Duration
Start date: 2020-10-01, End date: 2022-03-31
