Abstract 463P
Background
T factor depends on consolidation diameter in lung adenocarcinoma. Adenocarcinoma with short consolidation diameter could be indicated for sublobar resection. However, measurement of consolidation diameter under lung window in 2D-CT could be problematic, as the outline is not clear. We evaluated the relationship between consolidation lesion under mediastinal window in 3D-CT and pathological invasiveness, and aimed to predict invasiveness using machine learning algorithm.
Methods
Ninety-five patients who underwent surgical resection of lung adenocarcinoma that is less than 20 mm in diameter and has consolidation were analyzed retrospectively, in our Hospital from 2010 to 2016. The total tumor diameter and the volume and diameter of consolidation were analyzed using thin-slice CT and 3D-CT. Preoperative FDG-PET and serum CEA were also measured. Preinvasive lesion and minimally invasive adenocarcinoma were classified as pathologically non-invasive group, and invasive adenocarcinoma was classified as pathologically invasive group. The statistical differences were assessed by the Mann-Whitney U test or chi-square test. We used two machine learning algorithm. Three logistic regression (LR) models were trained based on sex, total tumor diameter, SUVmax, CEA, and (1) consolidation diameter (LR-Cd), (2) consolidation volume (LR-Cv), (3) consolidation diameter and volume (LD-Cd+Cv). Similarly, three random forest (RF) models were trained (RF-Cd, RF-Cv, RF-Cd+Cv). Patients were split into a training set (n = 76) and test set (n = 19). Model performance was measured area under the curve (AUC), and compared using receiver-operating characteristics curve analysis on the test set.
Results
Twenty-six non-invasive adenocarcinomas and 69 invasive adenocarcinomas were evaluated. The consolidation diameter and volume, and SUVmax of invasive group were significantly greater than those of non-invasive group (p < 0.001). On the test set, AUC of LR-Cd, RF-Cd, LR-Cv, RF-Cv, LR-Cd+Cv and RF-Cd+Cv were 0.687, 0.703,0.628, 0.744, 0.628 and 0.744 respectively.
Conclusions
The pathological invasiveness could be predicted by using machine learning algorithm. Especially, higher AUCs were obtained in RF-Cv and RF-Cd+Cv model.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
9P - XRCC1 Arg194Trp, Palb2 T1100T (3300T>G), HMMR V353A, TNF aG308A polymorphisms as diagnostic and prognostic markers of breast cancer in the Kyrgyz ethnic group
Presenter: Aigul Semetei kyzy
Session: Poster display session
Resources:
Abstract
232P - Early Results from the Phase I Study of SY-1365, a Potent and Selective CDK7 inhibitor, in Patients with Ovarian Cancer and Advanced Solid Tumors
Presenter: Debra Richardson
Session: Poster display session
Resources:
Abstract
382P - Drug metabolizing enzymes pharmacogenomic: Biomarkers for improved chemotherapy in head and neck cancer squamous cell carcinoma
Presenter: Sunishtha Bhatia
Session: Poster display session
Resources:
Abstract
401P - Women in oncology: Alarming figures from India
Presenter: Sharada Mailankody
Session: Poster display session
Resources:
Abstract
416P - Multidisciplinary management of sarcomas of the head and neck: An institutional experience
Presenter: Kavitha Jain
Session: Poster display session
Resources:
Abstract
523P - Co-morbilities and survival of patients initially diagnosed with extensive-stage small cell lung cancer: Impact of hypertension, diabetes and chronic hepatitis B viral infection
Presenter: Weigang Xiu
Session: Poster display session
Resources:
Abstract
529P - Osimertinib for patients with EGFR-mutant advanced NSCLC and asymptomatic brain metastases: An open-label, two-arm, phase II study
Presenter: Roni Gillis
Session: Poster display session
Resources:
Abstract