scholarly journals PO-0956 Non Invasive Grading of Non-Small Cell Lung Cancer Using Machine Learning Models Based on Radiomics

2019 ◽  
Vol 133 ◽  
pp. S518
Author(s):  
S. Aouadi ◽  
R. Hammoud ◽  
T. Torfeh ◽  
N. Al-Hammadi
2020 ◽  
Vol 245 (16) ◽  
pp. 1428-1436
Author(s):  
Zhi-Jun Zhang ◽  
Xing-Guo Song ◽  
Li Xie ◽  
Kang-Yu Wang ◽  
You-Yong Tang ◽  
...  

Circulating exosomal microRNAs (ExmiRNAs) provide an ideal non-invasive method for cancer diagnosis. In this study, we evaluated two circulating ExmiRNAs in NSCLC patients as a diagnostic tool for early-stage non-small lung cancer (NSCLC). The exosomes were characterized by qNano, transmission electron microscopy, and Western blot, and the ExmiRNA expression was measured by microarrays. The differentially expressed miRNAs were verified by RT-qPCR using peripheral blood specimens from NSCLC patients ( n = 276, 0 and I stage: n = 104) and healthy donors ( n = 282). The diagnostic values were measured by receiver operating characteristic (ROC) analysis. The results show that the expression of both ExmiR-20b-5p and ExmiR-3187-5p was drastically reduced in NSCLC patients. The area under the ROC curve (AUC) was determined to be 0.818 and 0.690 for ExmiR-20b-5p and ExmiR-3187-5p, respectively. When these two ExmiRNAs were combined, the AUC increased to 0.848. When the ExmiRNAs were administered with either carcinoembryonic antigen (CEA) or cytokeratin-19-fragment (CYFRA21-1), the AUC was further improved to 0.905 and 0.894, respectively. Additionally, both ExmiR-20b-5p and ExmiR-3187-5p could be used to distinguish early stages NSCLC (0 and I stage) from the healthy controls. The ROC curves showed that the AUCs were 0.810 and 0.673, respectively. Combination of ExmiR-20b-5p and ExmiR-3187-5p enhanced the AUC to 0.838. When CEA and CYFRA21-1 were administered with the ExmiRNAs, the AUCs were improved to 0.930 and 0.928, respectively. In summary, circulating serum exosomal miR-20b-5p and miR-3187-5p could be used as effective, non-invasive biomarkers for the diagnosis of early-stage NSCLC, and the effects were further improved when the ExmiRNAs were combined. Impact statement The high mortality of non-small cell lung cancer (NSCLC) is mainly because the cancer has progressed to a more advanced stage before diagnosis. If NSCLC can be diagnosed at early stages, especially stage 0 or I, the overall survival rate will be largely improved by definitive treatment such as lobectomy. We herein validated two novel circulating serum ExmiRs as diagnostic biomarkers for early-stage NSCLC to fulfill the unmet medical need. Considering the number of specimens in this study, circulating serum exosomal miR-20b-5p and miR-3187-5p are putative NSCLC biomarkers, which need to be further investigated in a larger randomized controlled clinical trial.


2013 ◽  
Vol 7 (1) ◽  
pp. 7
Author(s):  
Ioannis Koukis ◽  
Ioannis Gkiozos ◽  
Ioannis Ntanos ◽  
Elias Kainis ◽  
Konstantinos N. Syrigos

Staging is of the utmost importance in the evaluation of a patient with non-small cell lung cancer (NSCLC) because it defines the actual extent of the disease. Accurate staging allows multidisciplinary oncology teams to plan the best surgical or medical treatment and to predict patient prognosis. Based on the recommendation of the International Association for the Study of Lung Cancer (IASLC), a tumor, node, and metastases (TNM) staging system is currently used for NSCLC. Clinical staging (c-TNM) is achieved via non-invasive modalities such as examination of case history, clinical assessment and radiological tests. Pathological staging (p-TNM) is based on histological examination of tissue specimens obtained with the aid of invasive techniques, either non-surgical or during the intervention. This review is a critical evaluation of the roles of current pre-operative staging modalities, both invasive and non-invasive. In particular, it focuses on new techniques and their role in providing accurate confirmation of patient TNM status. It also evaluates the surgical-pathological staging modalities used to obtain the true-pathological staging for NSCLC.


2019 ◽  
Vol 18 (1) ◽  
Author(s):  
Xue Bai ◽  
Guoping Shan ◽  
Ming Chen ◽  
Binbing Wang

Abstract Background Intensity-modulated radiotherapy (IMRT) and volumetric-modulated arc therapy (VMAT) are standard physical technologies of stereotactic body radiotherapy (SBRT) that are used for patients with non-small-cell lung cancer (NSCLC). The treatment plan quality depends on the experience of the planner and is limited by planning time. An automated planning process can save time and ensure a high-quality plan. This study aimed to introduce and demonstrate an automated planning procedure for SBRT for patients with NSCLC based on machine-learning algorithms. The automated planning was conducted in two steps: (1) determining patient-specific optimized beam orientations; (2) calculating the organs at risk (OAR) dose achievable for a given patient and setting these dosimetric parameters as optimization objectives. A model was developed using data of historical expertise plans based on support vector regression. The study cohort comprised patients with NSCLC who were treated using SBRT. A training cohort (N = 125) was used to calculate the beam orientations and dosimetric parameters for the lung as functions of the geometrical feature of each case. These plan–geometry relationships were used in a validation cohort (N = 30) to automatically establish the SBRT plan. The automatically generated plans were compared with clinical plans established by an experienced planner. Results All 30 automated plans (100%) fulfilled the dose criteria for OARs and planning target volume (PTV) coverage, and were deemed acceptable according to evaluation by experienced radiation oncologists. An automated plan increased the mean maximum dose for ribs (31.6 ± 19.9 Gy vs. 36.6 ± 18.1 Gy, P < 0.05). The minimum, maximum, and mean dose; homogeneity index; conformation index to PTV; doses to other organs; and the total monitor units showed no significant differences between manual plans established by experts and automated plans (P > 0.05). The hands-on planning time was reduced from 40–60 min to 10–15 min. Conclusion An automated planning method using machine learning was proposed for NSCLC SBRT. Validation results showed that the proposed method decreased planning time without compromising plan quality. Plans generated by this method were acceptable for clinical use.


2018 ◽  
Vol 15 (6) ◽  
pp. 2055-2058 ◽  
Author(s):  
N. Komal Kumar ◽  
D Vigneswari ◽  
M Kavya ◽  
K Ramya ◽  
T. Lakshmi Druthi

Sign in / Sign up

Export Citation Format

Share Document