Periodic Reporting for period 3 - iToBoS (Intelligent Total Body Scanner for Early Detection of Melanoma)
Période du rapport: 2024-04-01 au 2025-03-31
Melanoma is a highly aggressive form of skin cancer that causes a disproportionate number of skin cancer-related deaths, yet is treatable if detected early. However, rising incidence rates and limitations of current screening methods, particularly for high-risk individuals, have made early diagnosis a public health challenge.
The iToBoS project addressed this issue by developing a novel AI-driven diagnostic platform that combines a non-contact total body imaging system with an AI Cognitive Assistant capable of generating personalised melanoma risk assessments. The platform integrates clinical, genomic, and imaging data, offering a holistic and accurate view of patient risk.
A key innovation of iToBoS is its focus on explainability, enabling clinicians to understand and trust AI-generated decisions, overcoming a major limitation of traditional black-box AI systems. The platform includes an interactive, clinician-friendly interface, co-designed with dermatologists to support real-world usability.
Technologically, iToBoS introduced custom-designed liquid lenses and automated image stacking, enabling high-quality, non-contact dermoscopy comparable to conventional methods. These innovations led to three patents covering key optical and image acquisition components.
Overall, iToBoS has delivered a validated, fully integrated system that enhances diagnostic precision, reduces screening time, and supports personalised melanoma prevention. The project marks a significant step forward in dermatological diagnostics and contributes to broader efforts to improve cancer care and reduce healthcare burdens across Europe.
The iToBoS project addressed this issue by developing a novel AI-driven diagnostic platform that combines a non-contact total body imaging system with an AI Cognitive Assistant capable of generating personalised melanoma risk assessments. The platform integrates clinical, genomic, and imaging data, offering a holistic and accurate view of patient risk.
A key innovation of iToBoS is its focus on explainability, enabling clinicians to understand and trust AI-generated decisions, overcoming a major limitation of traditional black-box AI systems. The platform includes an interactive, clinician-friendly interface, co-designed with dermatologists to support real-world usability.
Technologically, iToBoS introduced custom-designed liquid lenses and automated image stacking, enabling high-quality, non-contact dermoscopy comparable to conventional methods. These innovations led to three patents covering key optical and image acquisition components.
Overall, iToBoS has delivered a validated, fully integrated system that enhances diagnostic precision, reduces screening time, and supports personalised melanoma prevention. The project marks a significant step forward in dermatological diagnostics and contributes to broader efforts to improve cancer care and reduce healthcare burdens across Europe.
Throughout the project, substantial work was carried out across hardware development, data acquisition, algorithm design, and system integration to realise the technical and clinical objectives of iToBoS.
Early efforts were directed towards the development of the high-resolution imaging module (HRIM), a critical component of the total body scanner. This included the design and validation of a custom liquid lens system, integrated with automated image stacking algorithms to enable non-contact dermoscopic imaging. The HRIM was successfully incorporated into a robotic scanning platform that enables whole-body imaging with precise lesion targeting. The full scanner system was completed, tested, and used in clinical trials.
In parallel, the project established a clinical data acquisition study, enrolling 496 patients and collecting a rich dataset comprising whole-body images, dermoscopic image stacks, clinical variables, and polygenic risk information. Image resolution ranged from 60–80 microns per pixel, allowing detailed visual analysis of pigmented skin lesions. A multi-layer annotation pipeline was implemented, combining algorithmic pre-annotations with expert dermatological validation.
Building on this dataset, a range of AI modules were developed to support skin lesion detection, classification, change tracking and risk estimation. These models were trained and validated using multimodal inputs, including image tiles, 3D surface reconstructions, and structured patient data. The resulting outputs were consolidated into a Cognitive Assistant, capable of producing risk scores at both lesion and patient levels. A graphical user interface was designed and refined through an iterative process involving direct feedback from clinical end-users.
Additional components developed during the project include a change detection algorithm for multi-temporal lesion analysis, and an explanation module that enhances the interpretability of AI outputs through saliency maps and structured justifications. These features were embedded into the Cognitive Assistant to support clinical usability and decision-making.
In terms of project management and coordination, all planned deliverables and milestones were completed. The full system, comprising hardware, software, and data infrastructure, was deployed and validated in clinical settings.
From an exploitation standpoint, the project produced a set of Key Exploitable Results (KERs), including hardware components, AI models, data management tools, and user interfaces. Three patents were filed related to the liquid lens and image acquisition technologies. Dissemination activities were conducted at scale, with over 170 publications, active participation in major scientific events, and the release of two public datasets. Engagement with clinicians, researchers, and industry stakeholders was maintained through workshops, digital media, and targeted communication strategies. The outcomes of this phase have established a strong foundation for further deployment and post-project clinical studies.
Early efforts were directed towards the development of the high-resolution imaging module (HRIM), a critical component of the total body scanner. This included the design and validation of a custom liquid lens system, integrated with automated image stacking algorithms to enable non-contact dermoscopic imaging. The HRIM was successfully incorporated into a robotic scanning platform that enables whole-body imaging with precise lesion targeting. The full scanner system was completed, tested, and used in clinical trials.
In parallel, the project established a clinical data acquisition study, enrolling 496 patients and collecting a rich dataset comprising whole-body images, dermoscopic image stacks, clinical variables, and polygenic risk information. Image resolution ranged from 60–80 microns per pixel, allowing detailed visual analysis of pigmented skin lesions. A multi-layer annotation pipeline was implemented, combining algorithmic pre-annotations with expert dermatological validation.
Building on this dataset, a range of AI modules were developed to support skin lesion detection, classification, change tracking and risk estimation. These models were trained and validated using multimodal inputs, including image tiles, 3D surface reconstructions, and structured patient data. The resulting outputs were consolidated into a Cognitive Assistant, capable of producing risk scores at both lesion and patient levels. A graphical user interface was designed and refined through an iterative process involving direct feedback from clinical end-users.
Additional components developed during the project include a change detection algorithm for multi-temporal lesion analysis, and an explanation module that enhances the interpretability of AI outputs through saliency maps and structured justifications. These features were embedded into the Cognitive Assistant to support clinical usability and decision-making.
In terms of project management and coordination, all planned deliverables and milestones were completed. The full system, comprising hardware, software, and data infrastructure, was deployed and validated in clinical settings.
From an exploitation standpoint, the project produced a set of Key Exploitable Results (KERs), including hardware components, AI models, data management tools, and user interfaces. Three patents were filed related to the liquid lens and image acquisition technologies. Dissemination activities were conducted at scale, with over 170 publications, active participation in major scientific events, and the release of two public datasets. Engagement with clinicians, researchers, and industry stakeholders was maintained through workshops, digital media, and targeted communication strategies. The outcomes of this phase have established a strong foundation for further deployment and post-project clinical studies.
The iToBoS project has achieved a major advance in skin cancer diagnostics by delivering a fully integrated platform that combines non-contact total body imaging, multimodal AI analysis, and interpretable decision support. Central to the system are a custom-designed scanner, the AI Cognitive Assistant and a clinician-facing interface, which together offer unprecedented levels of precision, automation and personalisation beyond current diagnostic workflows.
A key innovation lies in the platform’s ability to integrate dermoscopic images with clinical, genetic, and phenotypic data, generating a holistic melanoma risk score tailored to each patient. This multimodal AI approach moves beyond isolated lesion assessment to support comprehensive, patient-level diagnostics.
The non-contact imaging system, equipped with liquid lenses, image stacking, and coma compensation, provides dermoscopy-quality images without skin contact. These innovations have led to the filing of three patents in optical and imaging technology.
The AI Cognitive Assistant brings together lesion classification, change detection, and risk estimation into a transparent and explainable interface, compliant with EU ethical guidelines. Its design prioritises clinician understanding, overcoming key limitations of current black-box AI tools.
Clinically, the system is expected to increase early melanoma detection, improve survival rates, and reduce long-term treatment costs through personalised diagnostics. Its modular architecture can also be extended to other dermatological conditions, expanding its utility and market reach.
Economically, iToBoS strengthens Europe’s position in AI and medical imaging, with 19 partners from 13 countries, including 10 companies (7 SMEs) that have expanded their expertise and are now well-positioned to enter new healthcare markets.
Dissemination has been extensive, with 61 journal articles, 111 conference contributions, and public resources such as SLICE-3D and the Kaggle Lesion Detection Challenge. The consortium has actively engaged the scientific community and SMEs through open-access initiatives and events.
In summary, iToBoS has laid the foundation for a new standard in skin cancer diagnostics, merging precision medicine, AI, and clinical usability into a scalable and impactful platform.
A key innovation lies in the platform’s ability to integrate dermoscopic images with clinical, genetic, and phenotypic data, generating a holistic melanoma risk score tailored to each patient. This multimodal AI approach moves beyond isolated lesion assessment to support comprehensive, patient-level diagnostics.
The non-contact imaging system, equipped with liquid lenses, image stacking, and coma compensation, provides dermoscopy-quality images without skin contact. These innovations have led to the filing of three patents in optical and imaging technology.
The AI Cognitive Assistant brings together lesion classification, change detection, and risk estimation into a transparent and explainable interface, compliant with EU ethical guidelines. Its design prioritises clinician understanding, overcoming key limitations of current black-box AI tools.
Clinically, the system is expected to increase early melanoma detection, improve survival rates, and reduce long-term treatment costs through personalised diagnostics. Its modular architecture can also be extended to other dermatological conditions, expanding its utility and market reach.
Economically, iToBoS strengthens Europe’s position in AI and medical imaging, with 19 partners from 13 countries, including 10 companies (7 SMEs) that have expanded their expertise and are now well-positioned to enter new healthcare markets.
Dissemination has been extensive, with 61 journal articles, 111 conference contributions, and public resources such as SLICE-3D and the Kaggle Lesion Detection Challenge. The consortium has actively engaged the scientific community and SMEs through open-access initiatives and events.
In summary, iToBoS has laid the foundation for a new standard in skin cancer diagnostics, merging precision medicine, AI, and clinical usability into a scalable and impactful platform.