Objective:To build a predictive model for symptomatic radiation pneumonitis(RP) using the pretreatment CT radiomics features, clinical and dosimetric data of lung cancer patients by using machine learning method.Methods:A retrospective analysis of 103 lung cancer patients who underwent radiotherapy in the Affiliated Hospital of Jiangnan University from November 2018 to April 2020 was performed. Total normal lung tissues were segmented as an interested volume in pretreatment CT images, and then 250 radiomics features were extracted. The correlations of RP and clinical or dosimetric features were firstly investigated with univariate analysis. Then all clinical data, dosimetric data and CT radiomics features were collected and considered as predictors for modeling of RP grade ≥ 2. Features were selected through LASSO machine learning method, and the predictive model was built. Finally, nomogram for risk of RP were obtained according to the selected features.Results:The result of univariate analysis showed that symptomatic RP was significantly correlated with lung dosimetric parameters including mean lung dose (MLD), V20 Gy and V30 Gy( t=2.20, 2.34 and 2.93, P<0.05). Four features, including lung dose volume percentage V30 Gyand three radiomics features, entropy feature of GLCM, mean and median feature of wavelet histogram were selected among all clinical, dosimetric features and radiomics features. AUC of the predicted model obtained from selected features reached 0.757. For convenient clinical use, the nomogram were obtained, and then personalized RP risk prediction and early intervention could be performed according to this nomogram. Conclusions:Pretreatment CT radiomics and dosimetric features can be used in predicting symptomatic RP, which will be useful for advanced intervention treatment.

Objective:To explore the efficacy of elective nodal irradiation (ENI) and involved field irradiation (IFI) combined with chemotherapy in treatment of esophageal cancer.Methods:A total of 104 patients with esophageal cancer in Affiliated Hospital of Jiangnan University from May 2018 to May 2020 were selected as subjects for prospective study. All patients were randomly divided into observation group and control group by lottery method with 52 cases in each group. The target volume of observation group was delineated with IFI, and the control group was delineated with ENI. The curative effects, the levels of serum tumor markers [carbohydrate antigen 50 (CA50), squamous cell carcinoma (SCC) and carcinoembryonic antigen (CEA)] before and after treatment, the 1-year overall survival (OS) rate, the incidence of adverse reactions and the scores of various dimensions of health survey summary (SF-36) after treatment were compared between the two groups.Results:The total effective rate in the observation group was 90.38% (47/52), the total effective rate in the control group was 84.62% (44/52), and the difference was not statistically significant ( χ2 = 0.79, P =0.374). There was no statistical difference in CA50, CEA, SCC levels between the two groups before and after treatment (all P > 0.05). After treatment, the CA50, CEA and SCC levels in the two groups were lower than those before treatment, and the differences were statistically significant (all P < 0.05). The 1-year OS rate of the observation group was 94.23%, the control group was 90.38%, and the difference in OS between the two groups was not statistically significant ( χ2 = 0.54, P = 0.462). The incidence of acute radiation esophagitis in the observation group was lower than that in the control group, and the difference was statistically significant ( P < 0.001). There was no statistical difference between the two groups in SF-36 scale scores of physical functioning, role-physical, bodily pain, mental health, vitality, social functioning, role-emotional, and general health after treatment (all P > 0.05). Conclusions:Both ENI and IFI are effective treatments for patients with esophageal cancer. There is no significant difference in the quality of life of patients between the two delineation methods, but the incidence of acute radiation esophagitis is lower in patients with IFI regimen.

Objective To compare the efficacy and safety of two concurrent chemoradiotherapy regimens between paclitaxel plus fluorouracil( TF) and cisplatin plus fluorouracil ( PF) in the treatment of locally advanced esophageal squamous carcinoma. Methods 103 patients with locally advanced esophagus carcinoma were treated in Affiliated Hospital of Jiangnan University from December 2014 to February 2016, and randomly assigned to either study group ( TF ) or control group ( PF ) according to random number table, of which 52 patients in the TF group while 51 patients in the PF group. The primary outcome was overall survival(OS), and secondary outcomes include progression-free survival(PFS), local progression-free survival( LPFS) and side effects. Results The 1-year OS for TF group was 76. 9％ versus 74. 5％ for PF group( P>0. 05 ) , and the 2-year OS for TF group was 59. 6％ versus 56. 9％ for PF group ( P >0. 05). The 1-year LPFS for TF group and PF group were 71. 2％ and 66. 7％ respectively(P>0. 05), and the 2-year LPFS for TF group and PF group were 61. 5％ and 58. 8％ respectively(P>0. 05). The 1-year PFS for TF group was 63. 5％ versus 62. 7％ for PF group ( P>0. 05 ) , and the 2-year PFS for TF group was 51. 9％ versus 39. 2％ for PF group ( P>0. 05 ) . The incidence rate of serious ( grade 3- 4 ) leukopenia for TF group was 36. 5％ versus 17. 6％ for PF group(χ2 =4. 642, P<0. 05). The incidence rate of serious (grade 3-4) acute radiation pneumonitis was 15. 4％ in the TF group, higher than that in the PF group with the rate of 3. 9％(χ2 =3. 859, P<0. 05), while the incidence rate of severe nausea and vomiting for PF group was 17. 6％ versus 1. 9％ for TF group(χ2 =7. 262, P <0. 05). The difference between the two groups was statistically significant. Conclusions Patients who were treated with two concurrent chemoradiotherapy regimens showed no difference in OS, PFS and LPFS. The regimen on the basis of Paclitaxel has higher risk of adverse effects incidence rates of hematological toxicity and acute radiation pneumonitis, while digestive system toxicity must be concerned when concurrent chemoradiotherapy is performed on the basis of cisplatin plus fluorouracil.