Virtual Library
Start Your Search
D. Yang
Author of
-
+
OA12 - SBRT and Other Issues in Early Stage NSCLC (ID 383)
- Event: WCLC 2016
- Type: Oral Session
- Track: Early Stage NSCLC
- Presentations: 1
- Moderators:D. De Ruysscher, M.R. Mueller
- Coordinates: 12/06/2016, 11:00 - 12:30, Strauss 2
-
+
OA12.05 - Noninvasive CT-Based Image Biopsy System (iBiopsy) for Early Stage Lung Adenocarcinoma (ID 6080)
11:45 - 11:55 | Author(s): D. Yang
- Abstract
- Presentation
Background:
CT screening programs frequently detect early stage lung adenocarcinoma. Recent studies show that distinct subtypes of lung adenocarcinoma are associated with different prognosis and suggest that treatment should be tailored to histological subtypes as identified in the new WHO Lung Tumor Classification. To develop this personalized approach, it is important to have reliable tools to diagnose tumors before treatment, preferably non-invasively through image analysis. We have developed a CT-image analysis system (iBiopsy) that uses computerized deep learning and artificial intelligence. To validate the accuracy of a noninvasive CT-based image biopsy system (iBiopsy) in differentiating early stage lung adenocarcinoma subtypes of atypical adenomatous hyperplasia (AAH), adenocaricnoma in situ (AIS), minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC).
Methods:
We retrospectively identified 365 eligible patients from Zhongshan Hopsital Fudan University, diagnosed with AAH, AIS, MIA or IAC by surgical pathological diagnosis. The last high definition CT scan prior to the surgery of the lesion was analyzed using the iBiopsy system, blinded to pathological result. Based on a pulmonary nodule image feature set (PNIFS) in combination with classified pattern models, such as R-SVM, all the pulmonary nodules were classified into four groups. For diagnosis efficacy, area under the curve (AUC) of Precision-Recall score (PRS), receiver operating characteristic (ROC) of a classification model were calculated in each group.
Results:
365 patients were included in the analysis. The classification recognition rate of the PNIFS was 80.03%. The average value of PRS is 0.92, the mean of ROC is 0.95, and it is more than 0.80 for the cross validation value.
Conclusion:
iBiopsy system allows the non-invasive imaged based stratification of pulmonary adenocarcinoma nodules into four groups, from AAH to IAC. Our result suggest that iBiopsy system could ultimate facilitate the diagnosis and precision management of pulmonary nodules.
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.
-
+
P2.06 - Poster Session with Presenters Present (ID 467)
- Event: WCLC 2016
- Type: Poster Presenters Present
- Track: Scientific Co-Operation/Research Groups (Clinical Trials in Progress should be submitted in this category)
- Presentations: 1
- Moderators:
- Coordinates: 12/06/2016, 14:30 - 15:45, Hall B (Poster Area)
-
+
P2.06-042 - Evaluate the Utility of the Computed Bioconductance Measurement in the Diagnosis of Lung Cancer (ID 6382)
14:30 - 14:30 | Author(s): D. Yang
- Abstract
Background:
Transcutaneous Computed Bioconductance (CB) has been shown to be different between malignant and benign lung lesions. We have launched a multicenter study to evaluate the utility of the Computed Bioconductance (CB) measurement following the CT scan in the diagnosis of lung cancer in Chinese population.
Methods:
In this multicenter study, we analyzed the result of a non-randomized prospective trail enrolling 123 patients with suspicious lung lesions studied by CT and CB. The pulmonary nodules or lesions confirmed by CT scan are greater than 4mm and smaller than 50mm. A CB test by BSP-E2-1000-A (Prolung Biotech Wuxi Co., Wuxi, China) was operated within these patients prior to an abnormal CT, then the tissue biopsy or surgical specimen would be conducted within 14 days. The detailed protocol could be found on ClinicalTrails.gov identifier NCT02726633.
Results:
Among the current 123 enrolling patients, 34（28%） cases were diagnosed of benign lesion, and 83 (67%) cases were diagnosed of malignant lesion depend on pathological diagnosis, 6 (5%) cases were eliminated due to patient refusal of biopsy. In malignant group, 32 (39%) cases were in stage I; 17 (20%) cased were in stage II and IIIA; 30 (36%) cases were in stage IIIB and IV. In addition, 10 (12%) cases were with EGFR mutation and all were adenocarcinoma. In benign group, 2 (6%) cases were diagnosed of tuberculosis and most other were inflammation and fibrosis lesion. The sex ratio was 45/78 (female vs. male). In addition, body mass index, lung functions test, serum tumor biomarker, nodule position and appearance, medical, treatment and smoking history were collected in the study. Among all cases, 31 had concomitant PET performed and standardized uptake value were collected.
Conclusion:
In this enrolling study, a pre-biopsy assessment of malignant probability with a CT-detected lung lesion, the method which combined CT and CB was evaluated at first time. This non-invasive risk-stratification technology could improve the diagnostic efficacy of lung cancer.
