Virtual Library

Start Your Search

Lyndsey C Pickup



Author of

  • +

    OA06 - Refining Lung Cancer Screening (ID 131)

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

      OA06.05 - Evaluation of a Deep Learning-Based Automatic Classifier for the Classification of Perifissural Nodules (Now Available) (ID 1928)

      11:00 - 12:30  |  Author(s): Lyndsey C Pickup

      • Abstract
      • Presentation
      • Slides

      Background

      Perifissural nodules (PFNs) comprise approximately 20% of screening-detected nodules and are almost certainly benign. Automatic PFN classification could therefore reduce the number of follow-up procedures required for nodule work-up. Prior work has shown some success in AI classification with limited datasets. Here we evaluate the performance of a new deep convolutional neural network (CNN) for PFN classification, trained on a dataset of nodules retrospectively collected from multiple European centers, including validation on an independent reader-study dataset.

      Method

      Data (1103 Patients, 1557 unique nodules and 3320 nodule images) were collected from three centers in the UK and the Netherlands. Each nodule was categorized into subtypes, including “PFN”, by on-site radiologists. Labels were reviewed centrally, overseen by a single clinician to ensure consistency between sites.

      A CNN classifier was trained to produce a score that classifies nodules as (typical) PFN or not, using five-fold cross validation. The PFN classifier was developed by “transfer learning” from an existing benign-vs-malignant AI trained on the US National Lung Screening Trial.

      To compare the CNN with human performance, independent validation was performed on a separate dataset of 158 benign patients (196 nodules/nodule images) from two of the sites. Three readers (two radiologists and a radiology resident) were asked to label each nodule as typical PFN, atypical PFN, or non-PFN. To match the AI training procedure, only the typical-PFN labels were used in the reader study, and compared to atypical/non-PFN classified nodules.

      Model performance was evaluated by area under the ROC curve (AUC). For the independent validation, Cohen’s kappa was used to measure both the model’s agreement with reader consensus (at least 2 in agreement) and inter-reader agreement. For Cohen’s kappa calculations the CNN score was binarized using a threshold determined from the internal validation data.

      Result

      The mean cross-validated AUC on the internal dataset was 92% (95% CI = 90.6–92.9). For the independent dataset, the classifier labelled 61/196 (31%) as typical PFNs, and reader consensus gave 45/196 (23%). Versus reader consensus, the AUC of the CNN on the reader-study dataset was 96% (95% CI 93.3–98.4). Both the classifier–reader agreement [(k=0.74) 90%] and the inter-reader agreement [(k=0.64–0.79) 88%-92%] were substantial.

      Conclusion

      The performance of the PFN classifier is similar to that of radiologists and is within the inter-reader variability of radiologists. This demonstrates the potential utility of CNN-based systems for automatic PFN classification.

      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.

  • +

    P1.11 - Screening and Early Detection (ID 177)

    • Event: WCLC 2019
    • Type: Poster Viewing in the Exhibit Hall
    • Track: Screening and Early Detection
    • Presentations: 1
    • Moderators:
    • Coordinates: 9/08/2019, 09:45 - 18:00, Exhibit Hall
    • +

      P1.11-02 - Acceleration of Lung Cancer Diagnosis: Utility Study for AI-Based Stratification of Pulmonary Nodules (ID 2752)

      09:45 - 18:00  |  Author(s): Lyndsey C Pickup

      • Abstract

      Background

      Lung cancer diagnostic pathway guidelines promote the use of risk stratification models. Artificial Intelligence (AI)-based risk models have been shown to achieve better diagnostic accuracy than clinical models like Mayo Clinic (Mayo) for particular clinical populations. The aim of this study is to examine whether this could translate into faster diagnosis for high-risk cancer patients.

      Method

      116 patients (116 nodules) have been collected from a retrospective consecutive cohort acquired at Vanderbilt University Hospital. Time to diagnosis (TTD) was defined as the number of days between the CT scan and diagnosis date. Mean TTD was calculated on the cohort on which TTD could be defined, and on a reduced group comprising of TTD >31 days only.

      Risk scores for each nodule were found using the Mayo model and an AI-based Lung Cancer Prediction model (LCP) based on CT images alone. A 65% risk of cancer was taken to be the threshold at which surgical intervention is indicated (according to ACCP guidelines).

      Result

      Seven patients were dropped due to negative TTD, and six for having no definitive diagnosis date. The eventual cohort contained 61 cancer patients and 42 controls. Mean TTD is 140 days (Interquartile Range – IQR 1-77 days). 25 patients have TTD=0, 60 are within 31 days (28 cancers, 32 controls) and 43 (33 cancers, 10 controls) are above 32 days.

      On the full cohort: Mayo risk score is >=65% for 15 cancers and 4 controls (sensitivity, 24.6%, specificity 90.5%), with a mean cancer TTD of 75 days. The LCP scores >=65% in 43 cancers and 10 controls (sensitivity, 70.5%, specificity 76.2%), mean cancer TTD 81 days.

      On the reduced group: Mayo >=65% for 7 cancers and 2 controls (sensitivity, 21.2%, specificity 80.0%) with mean cancer TTD 150 days. The LCP scores >=65% in 21 cancers and 4 controls (sensitivity, 63.6%, specificity 60.0%), with mean cancer TTD 156 days.

      Conclusion

      The LCP risk model could potentially accelerate the diagnosis in 40% more cancer patients who were not worked up fully in the month following a scan (the jump in sensitivity going from Mayo to LCP risk >=65% is 42.4%). For these patients, time to a cancer diagnosis and treatment could be shortened by up to 156 days compared to recommendations if applying the Mayo risk model.

  • +

    P2.11 - Screening and Early Detection (ID 178)

    • Event: WCLC 2019
    • Type: Poster Viewing in the Exhibit Hall
    • Track: Screening and Early Detection
    • Presentations: 1
    • Moderators:
    • Coordinates: 9/09/2019, 10:15 - 18:15, Exhibit Hall
    • +

      P2.11-46 - Could Malignancies Diagnosed During Round 2 of Screening Be Worked Up Sooner? (ID 2488)

      10:15 - 18:15  |  Author(s): Lyndsey C Pickup

      • Abstract
      • Slides

      Background

      A high proportion of cancers diagnosed during screening with low dose CT (LDCT) are Stage II or higher, with rates of 33% and 46% reported for NELSON (Horeweg et al., 2014) and (NLST, 2013) respectively, considering all screening rounds. Even in rounds after baseline in NLST, 34% of malignancies were diagnosed as Stage II+. In a retrospective analysis, we investigate the frequency with which cancers diagnosed at their second screening had already manifested at baseline, and whether they would have been ruled-in at their earlier appearance by an AI-based lung cancer (LCP) score and the Brock model (McWilliams, 2013).

      Method

      3914 subjects from the NLST with at least one solid or semi-solid nodule with a long-axis diameter >=6mm in the baseline LDCT were used in the analysis. Subjects either had benign findings or were diagnosed with cancer at baseline or at second screen. Malignancies diagnosed at second screen were manually checked for a nodule >=6mm in size at the same anatomical location in the baseline LDCT. Thresholds to rule-in malignancies using the LCP score and the Brock model were selected by matching the specificity to that (87.2%) reported for baseline LDCTs when applying LungRADS (Pinsky et al., 2015) at baseline, with a reported sensitivity of 84.9%.

      Result

      98 of the 147 cancers diagnosed at timepoint 1 were visible and >=6mm at baseline. 7 of the remaining 49 cancers that manifested as nodules <6mm in size were discarded from further analysis. The LCP score achieved sensitivities and 95% confidence intervals of 94.6% (90.5, 97.1) for baseline alone, 92.5% (86.4, 97.7), and 86.9% (82.1, 92.0) when including the early manifestations of the latter at baseline. Using Brock scores the sensitivities were 76.7% (68.9, 81.2) for baseline cancers, and 65.1% (59.2, 71.3) for baseline and early manifestations. This equated to LCP ruling in 68 (16 Stage II+) of the 98 early manifestations, and 38 early rule-ins (9 Stage II+) for Brock.

      roc_t01_aiscore_brock_y.png

      Conclusion

      Two thirds of cancers that were diagnosed at second screening manifest at baseline. Even so, many of the early manifestations could have triggered diagnostic work-up early, especially when the LCP score was utilised. Earlier manifestations appear to be more difficult to distinguish from benign nodules than cancers diagnosed at baseline. Future work will examine if size or radiological appearance made the nodules appear suspicious in earlier manifestations.

      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.