Virtual Library
Start Your Search
Samuel Kemp
Author of
-
+
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
-
+
P1.11-30 - Very Rapid Growth of Small Pulmonary Nodules Predicts Benignity (ID 704)
09:45 - 18:00 | Author(s): Samuel Kemp
- Abstract
Background
Growth of pulmonary nodules on repeat CT is used to identify malignant lesions, although very rapid growth is thought to imply an inflammatory process. Few data exist examining the optimum threshold at which rate of growth predicts a benign aetiology.
Method
Using an institutional CT database of small (<15mm) solid pulmonary nodules (n=784), we identified patients with antecedent (≥30 days prior) thin section (≤2mm) CT imaging and a final diagnosis of primary lung malignancy or a definite benign diagnosis based on pathology or longitudinal CT follow up data (n=137). Enlarging nodules (volume growth >25%) were identified (n=63) using semi-automated volumetry, and the volume doubling time (VDT) calculated. In cases where no nodule existed on the antecedent CT, a volume of 5mm3 was assigned, permitting the calculation of a ‘virtual’ VDT. Comparison of volume doubling time between benign and malignant nodules was made using Wilcoxon signed rank test. A receiver operator curve was constructed, and the optimum threshold of nodule growth rate predictive of benignity was calculated using the methods of Miller.
Result
The final study population consisted of 63 nodules in 57 patients [32/62 (50.8%) malignant, median age 67 years (range 34–85 years), male = 30/57 (52.6%)]. There was no difference in patient age nor in smoking status between groups, although patients with malignant diagnoses significantly more likely to be female (p < 0.001).
The median time between baseline (T1) and antecedent (T0) scans was 260 days (interquartile range 343 days). At baseline (T1), benign lesions (median diameter 10mm, median volume 380 mm3, range 10-4300mm3) were significantly smaller than malignant nodules (median diameter 13mm, median volume 890mm3, range 60-4250 mm3); p = 0.001.
24/31 benign lesions and 3/32 malignant lesions were not visible on the T0 scan, and were assigned a volume of 5mm3. The median benign lesion VDT was 70 days (interquartile range 270 days), malignant median VDT was 188 days (interquartile range 170 days); p = 0.2. The majority of lesions with very rapid growth (VDT < 90 days) were benign diagnoses (n= 17/24 [70.8%]). When examining these rapidly growing nodules, the optimal cut-point of the receiver-operator was a VDT of 50 days, AUC = 0.735. This provided 100% specificity for benign disease.
Conclusion
Our results confirm that very rapid nodule growth predicts benignity; a VDT of <50 days was 100% specific for benignity. Further work is required to validate these findings in other cohorts.
-
+
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
- Now Available
- Moderators:
- Coordinates: 9/09/2019, 10:15 - 18:15, Exhibit Hall
-
+
P2.11-13 - What Is the Impact of Localised Data When Training Deep Neural Networks for Lung Cancer Prediction? (Now Available) (ID 2485)
10:15 - 18:15 | Author(s): Samuel Kemp
- Abstract
Background
Deep neural networks (DNN) have been shown to offer a viable alternative for risk cancer prediction of indeterminate pulmonary nodules (IPNs). While the type of data used for training is known to impact performance, this issue has not been extensively studied. We present, for the first time, a study of the effect of including training data that matches the clinical pathway of the independent validation dataset, a nodule clinic of incidental findings.
Method
Two identical DNNs were trained on the task of diagnosis prediction of pulmonary nodules from CT images. The first one (DNNnlst) used purely screening data from the US National Lung Screening Trial (922 cancer and 14733 benign nodules), while the second one (DNNnlst+incidental) included data of incidentally detected nodules from European hospitals (1064 cancer and 7207 benign nodules). Both models were evaluated in an independent validation set of nodules coming from a referral center in the UK (Royal Brompton and Harefield Hospital, London) consisting of baseline scans of 406 cancer and 325 benign nodules. The models were compared in terms of AUC, as well as their ability to reclassify cancer patients with intermediate risk nodules. The Intermediate risk sub-population was defined by selecting patients with nodules in the size range of 8 to 15mm, and who were followed-up within a year with CT, referred to PET-CT, or referred to biopsy. Within this sub-population, a cancer prevalence of 30% was assumed. The operating points of the cancer prediction models were chosen by setting a cancer risk of 70%, corresponding to high-risk nodules in the guidelines of the British Thoracic Society.
Result
The DNNnlst and DNNnlst+incidental models achieved an AUC of 84.33 (95%CI: 81.49, 87.15) and 87.43 (95%CI: 84.79, 89.82) respectively on the entire validation set, showing an improvement in the discrimination capabilities (p < 0.01). For reference, using the nodule’s maximum axial diameter as a predictor led to an AUC of 79.07 (95%CI: 75.73, 82.73). Additionally, considering only the intermediate risk population of the data, all of which would require workup according to guidelines, the DNNnlst+incidental model correctly classified as high risk 34.34% more cases than the DNNnlst model (sensitivity 59.39% (95%CI: 47.68, 75.17) vs. 44.21% (95%CI: 20.98, 64.42)), an improvement significant at p < 0.05.
Conclusion
Although a DNN trained only on the US lung cancer screening data could have clinical utility in an incidental setting, exposing it to further incidental data can not only increase its discriminability, as expected, but also make it a potentially more effective tool for speeding up the diagnosis of cancer patients with intermediate risk nodules and reducing unnecessary workups.
