Virtual Library

Start Your Search

Anthony P Reeves



Author of

  • +

    ES08 - Critical Concerns in Screening (ID 11)

    • Event: WCLC 2019
    • Type: Educational Session
    • Track: Screening and Early Detection
    • Presentations: 1
    • Now Available
    • +

      ES08.07 - System Approach to Screening Management (Now Available) (ID 3197)

      13:30 - 15:00  |  Presenting Author(s): Anthony P Reeves

      • Abstract
      • Presentation
      • Slides

      Abstract

      IASLC ES08 - Critical Concerns in Screening 2019

      System Approach to Screening Management

      Anthony P. Reeves

      School of Electrical and Computer Engineering

      Cornell University

      Screening seeks to identify a specific disease or set of diseases at an early stage where therapy can be most effective. It involves application of a medical test or tests to a group of asymptomatic individuals at-risk for the disease. Only a very small fraction of the tested population will be expected to have the target disease. Thus, a system for managing the screening process focuses on a single complex protocol and differs significantly from the more traditional medical practice that has a focus on symptomatic diseases and medical conditions. Very high compliance with the protocol and timeliness in follow up actions are critical to extract the maximum benefit of the screening process and avoid unnecessary actions on the majority of the participants that do not have the disease.

      System requirements for Lung Cancer Screening

      Screening involves detection of early stage asymptomatic disease and timely follow-up to provide the maximum therapeutic benefit of early stage detection. This requires a system to track participants throughout the screening process, from initial contact to documentation of screening results to follow-up. To maintain the highest degree of quality and timeliness, the screening management system should be comprehensive for all the digital data in the screening program and incorporate the screening protocol in its design.

      For lung cancer screening (LCS), the web-based I-ELCAP management system was implemented in 2000 [1] with integration of all screening functions into a single system, including: scheduling, data collection, follow-up, patient reports and QA reports. This system includes structured reports for all patient interactions and medical events. The screening protocol is built in to the system; hence, there are real-time checks on adherence to the screening protocol. Any deviations from the protocol, such as a missing report or appointment schedule are flagged for attention. In addition, the management system includes all acquired digital images linked to the patient records; physicians may review images from within the system. Finally, the system includes computer image analysis methods for automated pulmonary nodule detection and for nodule growth rate assessment.

      Additional findings and Computer Aided Diagnosis

      Since that early system implementation in 2000, the importance of additional findings for other organs visible in the chest CT scans have become apparent. The radiological structured reporting requirements have been increased to include findings of the heart, and the lungs (emphysema, COPD) which, with lung cancer, covers the three main causes of death for the high-risk screening population. The detailed reporting of the CT scan reading, especially once the initial baseline scan has been read, places an increased burden on the radiologist. To improve the program quality and to address the reading issues a number of additional automated computer analysis functions have been integrated into the system, Reeves et. al. (2017) [2]. These include measures for: coronary calcium, heart size, the aorta, pulmonary hypertension, emphysema, major airways, bone mineral density from thoracic vertebra, breast density, and liver density. In addition, an automated quality assessment of the CT scan itself is reported.

      The role for AI in screening management

      Recent advances in AI technology, including deep learning with convolutional neural networks, have increased the capabilities of computer aided diagnostics. A landmark paper by Gulshan et. al. (2016) [3] showed that an automated end-to-end review of eye fundus images for diabetic retinopathy to determine if a follow-up action was indicated could be effectively accomplished without requiring a human read of the images. Following this work a commercial product for this task is now available. A recent paper by Ardila et. al. (2019) [4] showed that, for LCS CT scans, a similar approach with a more complex system could be used for predicting cancer events in a manner similar to LungRADS. A challenge with this LCS study, compared to Gulshan diabetic retinopathy study, is the cost and reporting complexity of the former for training data. While the Gulshan study was prospective and trained on over 120,000 cases, the Ardila study was retrospective with a subset of the NLST data of around 10,000 cases and only considered lung cancer. These methods employ the natural advantage of computer analysis with respect to human readers in attention to detail and lack of fatigue. Further, modern AI methods when appropriately designed, can assimilate data from millions of cases, far beyond human capacity. Efficient large-scale documentation methods have been developed to address the data issue for LCS [2] in which over 25,000 cases have been documented for multiple diseases.

      These studies move us closer to the point where the majority of the CT image report for LCS could be automatically completed and the role of the physician focused to reviewing a small number of the most significant findings.

      References

      1. Reeves, A. P., Kostis, W. J., Yankelevitz, D. F., and Henschke, C. I. A web-based database system for multi-institutional research studies on lung cancer. RSNA 87th Scientific Meeting 221 (Nov. 2001), 372

      2. Reeves, A. P., Xie, Y., and Liu, S. Large-scale image region documentation for fully automated image biomarker algorithm development and evaluation. Journal of Medical Imaging 4, 2 (2017), 024505.

      3. Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., ... & Kim, R. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama, 316(22), 2402-2410.

      4. Ardila, D., Kiraly, A. P., Bharadwaj, S., Choi, B., Reicher, J. J., Peng, L., ... & Naidich, D. P. (2019). End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nature medicine, 1.

      Only Members that have purchased this event or have registered via an access code will be able to view this content. To view this presentation, please login, select "Add to Cart" and proceed to checkout. If you would like to become a member of IASLC, please click here.

      Only Active Members that have purchased this event or have registered via an access code will be able to view this content. To view this presentation, please login or select "Add to Cart" and proceed to checkout.

  • +

    OA06 - Refining Lung Cancer Screening (ID 131)

    • Event: WCLC 2019
    • Type: Oral Session
    • Track: Screening and Early Detection
    • Presentations: 1
    • Now Available
    • +

      OA06.03 - An Open Source Lung Screening Management System (Now Available) (ID 1467)

      11:00 - 12:30  |  Author(s): Anthony P Reeves

      • Abstract
      • Presentation
      • Slides

      Background

      Starting in 1992, the Early Lung Cancer Screening Project (ELCAP) investigators developed the ELCAP Management System (MS) to ensure high quality care and follow-up of the first 1,000 ELCAP participants. The resulting Lancet publication in 1999 created worldwide interest in screening and an updated web-based ELCAP MS was updated to be web-based and provided free of charge to participating institutions, together with the I-ELCAP protocol.

      Method

      The ELCAP MS was designed to be comprehensive and rapidly capture information on each participant to be used by coordinators, navigators, nurses, radiologists, and other medical professionals to ensure appropriate follow-up and care. It provides rapid documentation of telephone or other inquiries, registering, scheduling screening appointments, reporting results, diagnosis of lung cancer, and treatment, and archives all CT images for integrated access of image and patient information. It has been iteratively updated through user feedback, and supports medical reimbursement requirements and continuous quality improvement to minimize harms of lung screening across International ELCAP (I-ELCAP) sites.

      Result

      More than 81,000 participants in 80 institutions worldwide have contributed their LDCT findings and images. The MS has provided efficient data collection for rigorous assessment of screening outcomes which has resulted in some 300 publications and abstracts for protocol updating, comparisons, and continuous quality improvement.

      Having anticipated “open science”, the ELCAP MS has been translated into an open source MS that offers a reference standard for data elements (1,500 data fields, 267 required) for robust and efficient management of lung screening programs. This first open source translation has been adopted by the United States Veterans Administration (VA) and integrated into its VistA Electronic Healthcare System for deployment at 10 VA medical centers through a grant for VA Partnership to increase Access to Lung Screening (VA-PALS). The software is being certified by the Open Source Electronic Health Record Alliance (OSEHRA); source code is available on GitHub.

      Automated quantitative tools have been developed for identification and characterization of nodules, emphysema, major airways, calcification scoring of coronary arteries, aortic valve, thoracic aorta, breast tissue, liver, bone, and image quality. These tools are integrated into the ELCAP MS, and in the future will provide automatically-generated quantitative LDCT reports.

      Conclusion

      The ELCAP MS and I-ELCAP protocol have helped define current global standards for lung screening. Its developers have now made the ELCAP MS publicly available through OSEHRA for support of lung screening programs of any scale throughout the world.

      Only Members that have purchased this event or have registered via an access code will be able to view this content. To view this presentation, please login, select "Add to Cart" and proceed to checkout. If you would like to become a member of IASLC, please click here.

      Only Active Members that have purchased this event or have registered via an access code will be able to view this content. To view this presentation, please login or select "Add to Cart" and proceed to checkout.