Periodic Reporting for period 1 - CLASSICA (VALIDATING AI IN CLASSIFYING CANCER IN REAL-TIME SURGERY)
Periodo di rendicontazione: 2022-05-01 al 2023-10-31
CLASSICA is deploying cancer classification AI technology in the operating theatre. We will deliver and clinically validate an AI-based decision support technology, which allows rapid identification of the presence and distribution of cancer within any tumour. Validation will be carried out across several hospitals, surgical teams, and countries.
Colorectal cancer (CRC) is the third most common cancer type globally and the second most common cause of cancer death, leading to almost one million deaths annually. The project addresses a key clinical challenge: the treatment of significant rectal polyps, especially those that are sessile and larger than 2 cm. While smaller polyps are typically managed through routine endoscopic polypectomy and advanced cancers through established paradigms, these significant polyps may require advanced local excision, such as transanal endoscopic resection. CLASSICA addresses the unreliability of current methods for characterisation of these polyp, such as biopsies (unreliable for up to 20% of such lesions) and radiological assessments (tend to overestimate these lesions). This is problematic because such characterisation will influence the choice of surgical technique and potentially lead to unnecessary complications.
Our technology in CLASSICA leverages the rapid analysis of tissue fluorescence dynamics to distinguish between cancerous and non-cancerous tissues during surgeries. This approach is based on the variance in fluorescence intensity of tissues dyed with fluorescent Indocyanine Green (ICG) and illuminated by near-infrared (NIR) light. By analysing the intensity curves plotted over time from multiple video frames, the system can classify tissue types. This method is pivotal in providing real-time, AI-driven identification and classification of cancerous tissues, thereby aiming to enhance surgical accuracy and improve patient outcomes.
By integrating this technology into surgical practice, CLASSICA not only contributes to the field of medical technology but will also help ensure the patient proceeds to the optimum treatment pathway and reduce the need for further surgery. In essence, CLASSICA represents a significant stride in enhancing surgical care for CRC combining technological innovation with the expertise of surgeons to provide a more precise, reliable, and effective treatment approach.
Colorectal cancer (CRC) is the third most common cancer type globally and the second most common cause of cancer death, leading to almost one million deaths annually. The project addresses a key clinical challenge: the treatment of significant rectal polyps, especially those that are sessile and larger than 2 cm. While smaller polyps are typically managed through routine endoscopic polypectomy and advanced cancers through established paradigms, these significant polyps may require advanced local excision, such as transanal endoscopic resection. CLASSICA addresses the unreliability of current methods for characterisation of these polyp, such as biopsies (unreliable for up to 20% of such lesions) and radiological assessments (tend to overestimate these lesions). This is problematic because such characterisation will influence the choice of surgical technique and potentially lead to unnecessary complications.
Our technology in CLASSICA leverages the rapid analysis of tissue fluorescence dynamics to distinguish between cancerous and non-cancerous tissues during surgeries. This approach is based on the variance in fluorescence intensity of tissues dyed with fluorescent Indocyanine Green (ICG) and illuminated by near-infrared (NIR) light. By analysing the intensity curves plotted over time from multiple video frames, the system can classify tissue types. This method is pivotal in providing real-time, AI-driven identification and classification of cancerous tissues, thereby aiming to enhance surgical accuracy and improve patient outcomes.
By integrating this technology into surgical practice, CLASSICA not only contributes to the field of medical technology but will also help ensure the patient proceeds to the optimum treatment pathway and reduce the need for further surgery. In essence, CLASSICA represents a significant stride in enhancing surgical care for CRC combining technological innovation with the expertise of surgeons to provide a more precise, reliable, and effective treatment approach.
In the first 18 months of the project, CLASSICA has made good progress towards our aims.
Advanced tissue-tracking algorithms and feature extraction processes have been developed. Code and data from a previous prototype have been migrated to the current project framework. Additionally, our efforts have focused on developing and optimising a new AI pipeline and developing a user-friendly application. CLASSICA-Web, which facilitates efficient data management, annotation, and analysis has been deployed and is accessible to our sites in Ireland, Belgium, Austria, Italy, and the Netherlands.
Study 1, focusing on CLASSICA's generalisability and accuracy, has begun at multiple sites. Registered on ClinicalTrials.gov (Identifier: NCT05793554), this study has seen active patient recruitment and intra-operative video recordings across three of the five clinical sites.
We are in the preparatory phase for Studies 2 and 3, which will occur in real-time in operating rooms. These interventional studies, focusing on biopsy and resection, are vital for a comprehensive assessment of CLASSICA's validity, usability, safety, and performance. A prototype system (CLASSICA Insight) of the software that will be rolled out for use in the operating room (CLASSICA-OR) has also been developed and is being used for validation and assessment of videos available to date.
Standard Operating Protocols (SOPs) have been established, ensuring standardisation of data inputs across all sites. This is particularly evident in Study 1, where we have developed a detailed protocol for patient recruitment, ICG fluorescence assessment, administration, and NIR video recording.
Developed training materials include an educational video for surgeons and OR staff. This video demonstrates the standardised clinical method for capturing surgical footage, which has been integral to training surgeons and OR staff.
The groundwork for enhancing clinical guidelines, particularly for Transanal Minimally Invasive Surgery (TAMIS)/Transanal Endoscopic Microsurgery (TEMS) procedures, has been laid. This includes establishing the EAES Task Force and conducting preliminary legal and regulatory framework studies to shape guidelines that are practically applicable and widely accepted.
We have made significant progress in ensuring GDPR compliance and preparing for the classification of upcoming studies under MDR. This includes the implementation of pseudonymisation practices and preparing documentation for clinical investigations of medical devices.
Advanced tissue-tracking algorithms and feature extraction processes have been developed. Code and data from a previous prototype have been migrated to the current project framework. Additionally, our efforts have focused on developing and optimising a new AI pipeline and developing a user-friendly application. CLASSICA-Web, which facilitates efficient data management, annotation, and analysis has been deployed and is accessible to our sites in Ireland, Belgium, Austria, Italy, and the Netherlands.
Study 1, focusing on CLASSICA's generalisability and accuracy, has begun at multiple sites. Registered on ClinicalTrials.gov (Identifier: NCT05793554), this study has seen active patient recruitment and intra-operative video recordings across three of the five clinical sites.
We are in the preparatory phase for Studies 2 and 3, which will occur in real-time in operating rooms. These interventional studies, focusing on biopsy and resection, are vital for a comprehensive assessment of CLASSICA's validity, usability, safety, and performance. A prototype system (CLASSICA Insight) of the software that will be rolled out for use in the operating room (CLASSICA-OR) has also been developed and is being used for validation and assessment of videos available to date.
Standard Operating Protocols (SOPs) have been established, ensuring standardisation of data inputs across all sites. This is particularly evident in Study 1, where we have developed a detailed protocol for patient recruitment, ICG fluorescence assessment, administration, and NIR video recording.
Developed training materials include an educational video for surgeons and OR staff. This video demonstrates the standardised clinical method for capturing surgical footage, which has been integral to training surgeons and OR staff.
The groundwork for enhancing clinical guidelines, particularly for Transanal Minimally Invasive Surgery (TAMIS)/Transanal Endoscopic Microsurgery (TEMS) procedures, has been laid. This includes establishing the EAES Task Force and conducting preliminary legal and regulatory framework studies to shape guidelines that are practically applicable and widely accepted.
We have made significant progress in ensuring GDPR compliance and preparing for the classification of upcoming studies under MDR. This includes the implementation of pseudonymisation practices and preparing documentation for clinical investigations of medical devices.
Traditional methods of characterisation for significant rectal polyps are often unreliable. There exists an urgent clinical need for better characterisation methods to ensure “right first time” biopsies and surgery.
The following are key areas where CLASSICA will deliver results beyond the current state of the art:
- CLASSICA introduces cutting-edge AI algorithms for real-time tissue classification.
- By providing surgeons with real-time, AI-driven insights during operations, CLASSICA will empower them to make more informed decisions, potentially reducing the need for additional surgeries and improving patient outcomes.
- Our validation studies across multiple hospital sites are crucial in demonstrating the technology's effectiveness and adaptability in different clinical environments.
- CLASSICA is addressing the evolving regulatory and ethical landscape, and potential biases and liability concerns related to AI-assisted surgery. This includes compliance with GDPR and other regulations and the development of guidelines for AI in surgical care.
In terms of communication and exploitation, CLASSICA has laid a strong foundation. Intellectual property management is underway, with regular IP reviews and an engagement with the EU Horizon IP Scan initiative. Our comprehensive communication strategy has yielded substantial engagement, evidenced by a well-maintained project website, active social media presence, and a suite of effective promotional materials. Key achievements include publishing five journal articles and notable participation in major conferences.
The following are key areas where CLASSICA will deliver results beyond the current state of the art:
- CLASSICA introduces cutting-edge AI algorithms for real-time tissue classification.
- By providing surgeons with real-time, AI-driven insights during operations, CLASSICA will empower them to make more informed decisions, potentially reducing the need for additional surgeries and improving patient outcomes.
- Our validation studies across multiple hospital sites are crucial in demonstrating the technology's effectiveness and adaptability in different clinical environments.
- CLASSICA is addressing the evolving regulatory and ethical landscape, and potential biases and liability concerns related to AI-assisted surgery. This includes compliance with GDPR and other regulations and the development of guidelines for AI in surgical care.
In terms of communication and exploitation, CLASSICA has laid a strong foundation. Intellectual property management is underway, with regular IP reviews and an engagement with the EU Horizon IP Scan initiative. Our comprehensive communication strategy has yielded substantial engagement, evidenced by a well-maintained project website, active social media presence, and a suite of effective promotional materials. Key achievements include publishing five journal articles and notable participation in major conferences.