Start Your Search
EP1.17 - Treatment of Early Stage/Localized Disease (ID 207)
- Event: WCLC 2019
- Type: E-Poster Viewing in the Exhibit Hall
- Track: Treatment of Early Stage/Localized Disease
- Presentations: 1
- Now Available
- Coordinates: 9/08/2019, 08:00 - 18:00, Exhibit Hall
EP1.17-35 - CBCT Radiomics May Predict Short-Term SBRT Effect in Early Stage Lung Cancer Patients (Now Available) (ID 501)
08:00 - 18:00 | Author(s): Yunyu Xu
This study aimed to determine whether radiomics features can be obtained from cone-beam CT (CBCT) through the linac based onboard-imaging systems.Method
Thirty consecutive patients with early stage lung cancer treated with stereotactic body radiation therapy (SBRT) (Total dose:50-60Gy, Fraction:5-8) were included. CBCT scan were performed before delivery of each SBRT treatment. Diagnostic CT scan before Radiation Therapy (diagnostic CT) and follow-up CT at one month after radiotherapy (follow-up CT) were analyzed. Primary tumors were delineated manually and modified on diagnostic CT, CBCT and follow-up CT. Tumor size on diagnostic CT and follow-up CT were used to calculate the reduction rate. The primary endpoint was average daily tumor reduction rate. Radiomics features were extracted from first fraction CBCT (CBCT first), last fraction CBCT (CBCT last) and diagnostic CT by Imaging Biomarker Explorer (IBEX) software. Radiomic features were selected using correlation coefficient and LASSO dimensionality reduction based on R.Result
A total of 222 radiomics features were obtained from CBCT first, CBCT last and diagnostic CT of each patient. Based on correlation coefficients>0.70 and with LASSO dimensionality reduction, 5, 4 and 5 features were selected in diagnostic CT, CBCT first and CBCT last, respectively. Comparing the features in three CT subsets, two features were same between diagnostic CT and CBCT first, three features were the same between diagnostic CT and CBCT last. Two features are common in all three CT imaging sets. (Table 1)
Table 1 Different characteristic values of different CT radiomics be predicted SBRT reduction rate.
Inverse Diff Moment Norm
A few radiomics features may be robust to the noise in daily CBCT images which are often considered of poor quality. Study with larger sample size are needed to verify this interesting finding.
OA06 - Refining Lung Cancer Screening (ID 131)
- Event: WCLC 2019
- Type: Oral Session
- Track: Screening and Early Detection
- Presentations: 1
- Now Available
- Moderators:Tomasz Grodzki, Lluis Esteban Tejero
- Coordinates: 9/09/2019, 11:00 - 12:30, Hilton Head (1978)
OA06.07 - Discrimination of Lung Invasive Adenocarcinoma with Micropapillary Pattern Based on CT Radiomics (Now Available) (ID 399)
11:00 - 12:30 | Author(s): Yunyu Xu
To develop and validate the radiomics nomogram on the discrimination of lung invasive adenocarcinoma (IAC) with micropapillary pattern from non-micropapillary pattern lesion and improve the diagnostic accuracy rate of lung invasive adenocarcinoma with micropapillary pattern before operations and provide guidance for follow-up treatments.Method
Forty-one pathologically confirmed lung invasive adenocarcinomas with micropapillary pattern from January 2014 to December 2018 were included. Eighty-two pathologically confirmed lung invasive adenocarcinomas without micropapillary pattern from January 2018 to December 2018 were collected. Select 86 patients (70%) randomly from the 123 patients as the primary cohort, and the other 37 patients (30%) were set as an independent validation cohort. Least absolute shrinkage and selection operator (Lasso) was used for feature selection based on contrast enhancement CT images and then radiomics signature building. ROC analysis and AUC were used to value the ability to identify the lung invasive adenocarcinomas with micropapillary pattern.Result
According to GrayLevelCooccurenceMatrix3, Intensity Histogram and Shape, nine hundred and eighty-five radiomics features were extracted by IBEX. And after data pre-processing such as eliminating missing items, strong correlation variables and multicollinear variables, the features were reduced to 40 features. Based on Mann-Whitney U Test, 28 features were figured out from the 40 features. Then Lasso was used to reduce the features to 3 features (10-1clusterprominenc, -333-4clusterprominence, 8-1contrast) as the most meaningful discriminators to build the radiomics signatures (Table 1). According to SPSS21.0 binary logistic regression analysis, ROC analysis and AUC show that the radiomics signature have effective discrimination performance of lung invasive adenocarcinoma with micropapillary pattern from non- micropapillary pattern lesion (AUC=0.766) and it reflects better in the independent validation cohort (AUC=0.807) (Figure 1).
Table 1 Three characteristic prediction parameters in radiomics label
prediction parameter P value U value W value AUC 10-1clusterprominence <0.005 765.000 4168.000 0.772 -333-4clusterpromise <0.005 790.000 4193.000 0.765 8-1contrast <0.005 919.000 4322.000 0.727
The radiomics signature established in this study have effective prediction of lung invasive adenocarcinoma with micropapillary pattern and non- micropapillary pattern lesion.