e20057 Background: Interstitial lung disease (ILD) is an independent risk factor for lung cancer. The incidence of ILD in lung cancer patients is 5–10%. Although CRT is the standard treatment for LA lung cancer and has potential for long-term disease-free survival or cure, the treatment is avoided in patients with ILD because of the risk of severe radiation pneumonitis or acute ILD exacerbation. ILA has recently been evaluated using high-resolution computed tomography (HRCT) to assess interstitial changes. The aim of this study was to determine the feasibility and efficacy of CRT for LA lung cancer patients with ILA. Methods: Patients who underwent CRT for LA lung cancer at Okayama University Hospital between 2012 and 2015 were reviewed retrospectively. HRCT prior to treatment was evaluated by one pulmonologist and two radiologists using sequential reading. Results: Of 74 patients, ILA was present in 25 (33.8%) and indeterminate ILA was present in 23 (31.1%); 26 patients (35.1%) did not have ILA. Patient characteristics are shown below. Desaturation at rest (SpO 2 < 95%) and honeycombing on HRCT were not observed in patients with ILA. Only one patient with ILA had a low vital capacity (VC% of predicted, < 80%). Severe radiation pneumonitis (≥ grade 2) occurred in 32.0% of patients with ILA and 19.2% of patients without ILA (P=0.35). All radiation pneumonitis was controllable and grade 4 or 5 was not observed. Using multivariate analyses, treatment > 20 Gy involving > 25% of the lung volume was a predictive factor for severe radiation pneumonitis, but not ILA. The 2-year survival percentages of patients with and without ILA were 56.8% and 72.5%, respectively (hazard ratio, 1.21; 95% confidence interval, 0.76–1.90; P=0.42). Conclusions: Although severe radiation pneumonitis tended to increase, CRT was appropriate for patients with ILA without desaturation, low VC, and honeycombing on HRCT. [Table: see text]
OBJECTIVE. This study evaluated the utility of a deep learning method for determining whether a small (≤ 4 cm) solid renal mass was benign or malignant on multiphase contrast-enhanced CT. MATERIALS AND METHODS. This retrospective study included 1807 image sets from 168 pathologically diagnosed small (≤ 4 cm) solid renal masses with four CT phases (unenhanced, corticomedullary, nephrogenic, and excretory) in 159 patients between 2012 and 2016. Masses were classified as malignant (n = 136) or benign (n = 32). The dataset was randomly divided into five subsets: four were used for augmentation and supervised training (48,832 images), and one was used for testing (281 images). The Inception-v3 architecture convolutional neural network (CNN) model was used. The AUC for malignancy and accuracy at optimal cutoff values of output data were evaluated in six different CNN models. Multivariate logistic regression analysis was also performed. RESULTS. Malignant and benign lesions showed no significant difference of size. The AUC value of corticomedullary phase was higher than that of other phases (corticomedullary vs excretory, p = 0.022). The highest accuracy (88%) was achieved in corticomedullary phase images. Multivariate analysis revealed that the CNN model of corticomedullary phase was a significant predictor for malignancy compared with other CNN models, age, sex, and lesion size. CONCLUSION. A deep learning method with a CNN allowed acceptable differentiation of small (≤ 4 cm) solid renal masses in dynamic CT images, especially in the corticomedullary image model.
Although chemoradiotherapy for locally advanced lung cancer has the potential for cure, treatment is avoided in patients with interstitial lung disease because of the risk for severe radiation pneumonitis. Interstitial lung abnormalities (ILA) can be evaluated using high-resolution computed tomography (HRCT) to assess interstitial changes. In this study, we retrospectively examined the feasibility and efficacy of chemoradiotherapy for locally advanced lung cancer patients with ILA.Patients who underwent chemoradiotherapy for locally advanced lung cancer at Okayama University Hospital between 2012 and 2015 were reviewed retrospectively. HRCT prior to treatment was evaluated by one pulmonologist and two radiologists using a sequential reading method.Of the 77 patients enrolled in this study, ILA was present in 25 (32.5%) and indeterminate ILA in 24 patients; 28 patients did not have ILA. Desaturation at rest (SpO2 < 95%) and honeycombing on HRCT were not observed in ILA patients. Only one patient with ILA had a low vital capacity (%VC < 80%). Severe radiation pneumonitis (≥Grade 2) occurred in 36.0% of the patients with ILA, but it was controllable; Grade 4 or 5 was not observed. Multivariate analysis showed that >25% of the lung volume receiving >20 Gy was risk factors of severe radiation pneumonitis, but ILA was not. The 2-year survival rates of patients with and without ILA were 56.8% and 74.1%, respectively, but the difference was not significant (P = 0.33).Chemoradiotherapy was feasible and effective in some patient population with ILA without desaturation, low VC and honeycombing on HRCT.
