EIT Health LUCINDA (Early Lung Cancer Diagnosis with Artificial Intelligence and Big Data) is a consortium of leading clinicians & hospitals in the UK, the Netherlands and Germany (Oxford University Hospital, the University Medical Center Groningen, Heidelberg University Hospital & ThoraxKlinik Heidelberg, and the University of Oxford) and Optellum – a high-tech start up from Oxford, UK. This unique team of experts in Lung Cancer, Machine Learning and medical technology product development have united to address a huge and growing problem in Lung Cancer diagnosis, the management of patients presenting with indeterminate pulmonary nodules. Supported by EIT Heath, European Union’s flagship initiative driving healthcare innovation to market, the team have developed the world’s first image-based decision support software to improve patient management and reduce unnecessary follow-up procedures.
The team will be showcasing their work for the first time at IASLC 18th World Conference on Lung Cancer in Yokohama Japan on 15 to 18th October 2017.
Early detection of lung cancer by a Chest Computed Tomography (CT) scan, frequently performed for a variety of reasons ranging from screening for lung cancer to scanning for suspected cardiac disease or even following trauma, can dramatically improve survival rates. Such scans frequently identify pulmonary nodules, small opacities in the lung, typically less than 1cm in size. Up to 30% of all patients scanned have such small nodules, but the vary majority are harmless and will not cause problems to the patient. Unfortunately, radiologists frequently struggle to determine if a nodule is cancerous, leading to an indeterminate diagnosis which requires up to two year follow-up imaging to monitor growth. In some cases, additional biopsies and surgeries are performed to investigate nodules that ultimately turn out to be benign. Such additional procedures can increase patient stress, carry a risk of complications and present a huge and growing burden on limited healthcare system resources.
EIT Health have developed expert-level decision support software that can improve a doctor’s ability to correctly diagnose lung nodules. Their software, utilizing state-of-the-art deep learning, provides an objective risk score of nodule malignancy learned from a database of thousands of examples with known ground-truth diagnoses. The output enables clinicians to confidently stratify lung nodule patients earlier, potentially on the basis of only one or two scans.
“Our project consortium, comprising Europe’s leading institutes in lung cancer screening in Groningen and Heidelberg, along with experts in healthcare machine learning at Optellum and Oxford, is uniquely positioned to tackle this critically important problem,” comments Prof. Gleeson (Oxford), co-author of the 2015 British Thoracic Society guidelines for the management of pulmonary nodules. Prof. Gleeson continues, “We believe that this system will improve patient care and reduce the burden of managing indeterminate lung nodules in both incidental and screening settings.”
Members from the EIT Health LUCINDA team will be available at the educational exhibit, entitled EIT Health: AI & Lung Cancer in Yokohama (Booth 1114), to:
- Explain how image-based decision support with Deep Learning can enhance clinical workflows, with more consistent patient management & reduced false positives.
- Demonstrate the prototype AI software. Visitors can get hands on experience with the demonstration system and provide feedback to guide future developments, trials and validation studies.
About EIT Health LUCINDA
The academic partners are among the world-leading hospitals specializing in lung cancer research and clinical care, including Oxford University Hospitals, Heidelberg University Hospital and the University Medical Centre Groningen.
Optellum is a high-tech startup based in Oxford, UK developing the world’s first automated patient management and image-based risk stratification software for incidental and screen-detected nodules in CT. Their vision is to make significant improvements in lung cancer diagnosis and patient management from the current standard of care using Deep Learning. Optellum comprise a team of award-winning machine learning and imaging experts who met at Oxford’s world-renowned computer vision laboratory with track records of bringing innovative medical technology to market, including multiple trade-sales, IPO.
for more information contact: firstname.lastname@example.org
About the WCLC:
The World Conference on Lung Cancer (WCLC) is the world’s largest meeting dedicated to lung cancer and other thoracic malignancies, attracting over 6,000 researchers, physicians and specialists from more than 100 countries. The goal is to disseminate the latest scientific achievements; increase awareness, collaboration and understanding of lung cancer; and to help participants implement the latest developments across the globe. Organized under the theme of “Synergy to Conquer Lung Cancer,” the conference will cover a wide range of disciplines and unveil several research studies and clinical trial results. For more information, visit http://wclc2017.iaslc.org/.
The IASLC is the only global organization dedicated solely to the study of lung cancer and other thoracic malignancies.The organization’s multi-disciplinary membership allows for collaboration among stakeholders, with the goal of uncovering the best solutions for lung cancer patients around the world. Members of the IASLC and conference attendees are the world’s preeminent experts in lung cancer and other thoracic malignancies, including surgeons, oncologists, pulmonologists, radiologists, pathologists, epidemiologists, basic research scientists, nurses, allied health professionals and industry representatives.
The World Conference on Lung Cancer is the premier event for those in the lung cancer field to convene and collaborate. By providing a global stage for the latest scientific advancements and the highest-quality research, the conference advances the treatment of lung cancer and other thoracic malignancies worldwide.