Neural Networks for Nodal Staging of Non–Small Cell Lung Cancer with FDG PET and CT: Importance of Combining Uptake Values and Sizes of Nodes and Primary Tumor

7214 Background: The SUV is a measure for the preferential uptake of a radiopharmaceutical in a tumor compared with a homogenous distribution in a body. SUV can be based on the maximum value (SUVmax) or on the mean value in a region outlined by isodensity contours, e.g., 70% and 50%. The prognostic value of the different SUVs in non-small cell lung cancer (NSCLC) is not clear. We evaluated the prognostic value of SUVmax, SUV 70% and SUV 50% in patients (pts) with resectable NSCLC. Methods: All consecutive pts who underwent an attenuation corrected whole body FDG-PET scan were selected. All data were reconstructed iteratively. Only pts with stage I through IIIA NSCLC were included. By adjusting the isocontour in the region of interest, the SUVmax, SUV 70% and SUV 50% of the primary tumor were calculated. Cox regression analysis was used to calculate the relation between the different SUVs and survival. Results: Eighty-four pts (67 males, median age 64 years, range 38–86) were included. Histology was squamous cell carcinoma (n = 43), adenocarcinoma (n = 27), large cell carcinoma (n = 13), and 1 patient with bronchoalveolar carcinoma. Nineteen pts had stage IA, 28 stage IB, 4 stage IIA, 19 stage IIB, and 14 stage IIIA. Median (range) SUVmax, SUV 70%, and SUV 50% were 6.9 (1.6–32.5), 5.5 (1.0–23.2), and 4.5 (0.9–21.9), respectively. Analysis of residuals of SUVmax as a continuous variable suggests no cut-off point and no indication of time-dependency. By univariate analysis, all pts with a SUV higher than the median value had a worse survival than pts with a SUV lower than median (Hazard ratio’s for SUVmax, SUV70% and SUV 50% were 2.3 (p = 0.024), 2.5 (p = 0.015), and 2.7 (p = 0.010), respectively). Conclusions: SUVmax, SUV 70% and SUV 50% measured with FDG-PET have a similar prognostic impact. No cut-off point for SUVmax has been observed. No significant financial relationships to disclose.

Download Full-text

P1-055: Role of FDG-PET/CT in nodal staging with non-small cell lung cancer

Journal of Thoracic Oncology ◽

10.1097/01.jto.0000283670.43636.47 ◽

2007 ◽

Vol 2 (8) ◽

pp. S571-S572

Author(s):

Yuji Asato ◽

Motohiro Sato ◽

Moriyuki Kiyoshima ◽

Takayuki Kaburagi ◽

Tomoyuki Yokose ◽

...

Keyword(s):

Lung Cancer ◽

Small Cell Lung Cancer ◽

Cell Lung Cancer ◽

Fdg Pet ◽

Small Cell ◽

Nodal Staging ◽

Small Cell Lung ◽

Pet Ct ◽

Fdg Pet Ct

Download Full-text

Pre-Operative Prediction of Mediastinal Node Metastasis Using Radiomics Model Based on 18F-FDG PET/CT of the Primary Tumor in Non-Small Cell Lung Cancer Patients

Frontiers in Medicine ◽

10.3389/fmed.2021.673876 ◽

2021 ◽

Vol 8 ◽

Author(s):

Kai Zheng ◽

Xinrong Wang ◽

Chengzhi Jiang ◽

Yongxiang Tang ◽

Zhihui Fang ◽

...

Keyword(s):

Lung Cancer ◽

Small Cell Lung Cancer ◽

Cell Lung Cancer ◽

Primary Tumor ◽

Fdg Pet ◽

Small Cell ◽

Small Cell Lung ◽

Training Cohort ◽

Pet Ct ◽

Fdg Pet Ct

Purpose: We investigated whether a fluorine-18-fluorodeoxy glucose positron emission tomography/computed tomography (18F-FDG PET/CT)-based radiomics model (RM) could predict the pathological mediastinal lymph node staging (pN staging) in patients with non-small cell lung cancer (NSCLC) undergoing surgery.Methods: A total of 716 patients with a clinicopathological diagnosis of NSCLC were included in this retrospective study. The prediction model was developed in a training cohort that consisted of 501 patients. Radiomics features were extracted from the 18F-FDG PET/CT of the primary tumor. Support vector machine and extremely randomized trees were used to build the RM. Internal validation was assessed. An independent testing cohort contained the remaining 215 patients. The performances of the RM and clinical node staging (cN staging) in predicting pN staging (pN0 vs. pN1 and N2) were compared for each cohort. The area under the curve (AUC) of the receiver operating characteristic curve was applied to assess the model's performance.Results: The AUC of the RM [0.81 (95% CI, 0.771–0.848); sensitivity: 0.794; specificity: 0.704] for the predictive performance of pN1 and N2 was significantly better than that of cN in the training cohort [0.685 (95% CI, 0.644–0.728); sensitivity: 0.804; specificity: 0.568], (P-value = 8.29e-07, as assessed by the Delong test). In the testing cohort, the AUC of the RM [0.766 (95% CI, 0.702–0.830); sensitivity: 0.688; specificity: 0.704] was also significantly higher than that of cN [0.685 (95% CI, 0.619–0.747); sensitivity: 0.799; specificity: 0.568], (P = 0.0371, Delong test).Conclusions: The RM based on 18F-FDG PET/CT has a potential for the pN staging in patients with NSCLC, suggesting that therapeutic planning could be tailored according to the predictions.

Download Full-text