Objective To develop a combined model integrating radiomics and 3D deep learning features for improving the predictive efficacy of overall survival in non-small cell lung cancer(NSCLC)patients undergoing radiotherapy,thereby providing a foundation for optimizing individualized radiotherapy strategies.Methods A retrospective analysis was conducted on 522 NSCLC patients from 3 centers.Radiomics features were extracted from the tumor region of interest on radiotherapy planning CT scans,and a 3D-SE-ResNet was constructed to extract deep learning features.Following feature extraction,features were selected via univariate Cox analysis and Lasso-Cox regression,and a combined model was established by fusing the two feature types through principal component analysis.The discriminative ability of the model was evaluated using the concordance index(C-index)and the area under the receiver operating characteristic curve(AUC),while the risk stratification efficacy was verified by Kaplan-Meier survival analysis.Results The predictive performance of deep learning features was significantly superior to that of radiomics features(C-index:0.73 vs 0.65).The combined model achieved the highest predictive performance in the training set,internal test set,and external test set(C-index:0.74,0.69,0.72 respectively),with higher AUC values for predicting 1-year,2-year,and 3-year OS than either single model.Kaplan-Meier analysis showed significant differences in survival between the high-and low-risk groups(Log-rank test,P<0.001),and calibration curves indicated good consistency between predicted and actual survival outcomes.Conclusion The combined model integrating radiomics and 3D deep learning features can accurately predict survival outcomes in NSCLC patients undergoing radiotherapy.The multi-center validation results support its potential application in prognosis stratification for individualized radiotherapy.

Objective To develop a combined model integrating radiomics and 3D deep learning features for improving the predictive efficacy of overall survival in non-small cell lung cancer(NSCLC)patients undergoing radiotherapy,thereby providing a foundation for optimizing individualized radiotherapy strategies.Methods A retrospective analysis was conducted on 522 NSCLC patients from 3 centers.Radiomics features were extracted from the tumor region of interest on radiotherapy planning CT scans,and a 3D-SE-ResNet was constructed to extract deep learning features.Following feature extraction,features were selected via univariate Cox analysis and Lasso-Cox regression,and a combined model was established by fusing the two feature types through principal component analysis.The discriminative ability of the model was evaluated using the concordance index(C-index)and the area under the receiver operating characteristic curve(AUC),while the risk stratification efficacy was verified by Kaplan-Meier survival analysis.Results The predictive performance of deep learning features was significantly superior to that of radiomics features(C-index:0.73 vs 0.65).The combined model achieved the highest predictive performance in the training set,internal test set,and external test set(C-index:0.74,0.69,0.72 respectively),with higher AUC values for predicting 1-year,2-year,and 3-year OS than either single model.Kaplan-Meier analysis showed significant differences in survival between the high-and low-risk groups(Log-rank test,P<0.001),and calibration curves indicated good consistency between predicted and actual survival outcomes.Conclusion The combined model integrating radiomics and 3D deep learning features can accurately predict survival outcomes in NSCLC patients undergoing radiotherapy.The multi-center validation results support its potential application in prognosis stratification for individualized radiotherapy.

Objective To propose a deep learning neural network approach for transforming megavoltage computed tomography(MVCT)images of cervical cancer into pseudo kilovoltage computed tomography(kVCT)images with high signal-to-noise ratio and contrast-to-noise ratio,thus providing three-dimensional anatomical images and localization information required for adaptive radiotherapy of cervical cancer,and guiding the accelerator to achieve precise treatment.Methods The MVCT and kVCT images of 54 patients treated with cervical cancer radiotherapy were collected,with 44 cases randomly selected as the training set,and the remaining 10 cases as the test set.A cyclic generative adversarial network with gating mechanism and multi-channel data input was used to synthesize pseudo-kVCT images from MVCT images.The network training results were evaluated with imaging quality evaluation parameters,such as mean absolute error(MAE),peak signal-to-noise ratio(PSNR),and structural similarity index(SSIM).Results The MAE,PSNR,and SSIM of MVCT imagesvspseudo-kVCT(5:5)images were(24.9±0.7)HUvs(17.8±0.3)HU,(29.8±0.2)dBvs(30.7±0.2)dB,and 0.841±0.007 vs 0.898±0.003,respectively.Conclusion The generated pseudo-kVCT images have advantages in noise reduction and contrast enhancement,and can reduce the need for additional MV-kVCT electron density calibration in dose calculations.The dose calculation ability of pseudo-kVCT is comparable to that of MVCT,providing a possibility for the application of pseudo-kVCT images in image-guided adaptive radiotherapy.

Objective:To investigate the value of 18F-FDG PET/CT combined with conventional imaging modalities in the evaluation of the depth of tumor invasion, regional lymph node metastasis, distant organ and lymph node metastasis (TNM staging), and the adjacent structure invasion of rectal cancer. Methods:Fifty-four patients (28 males, 26 females, age (65.8±11.0) years) with pathologically confirmed rectal cancer admitted to the Affiliated Qingdao Central Hospital of Qingdao University between September 2019 and June 2021 were retrospectively analyzed. 18F-FDG PET/CT examination, conventional imaging modalities including high-resolution MRI (HR-MRI), chest CT plain scan, upper abdominal MRI or CT plain scan+ enhanced examination were performed within 2 weeks before or after the rectal cancer being confirmed. The TNM staging and adjacent structural invasions including circumferential resection margin (CRM), extramural vascular invasion (EMVI), anal sphincter complex involvement were evaluated by 18F-FDG PET/CT and conventional imaging modalities separately or in combination, and those results based on imaging were compared with the pathological results or clinical follow-up results. χ2 test was used to compare the differences of diagnostic sensitivity, specificity and accuracy between the 18F-FDG PET/CT or conventional imaging modalities and combined examination. Results:The accuracy for T staging and the sensitivity and accuracy for N staging of the combined examination were 96.30%(52/54), 98.65%(73/74) and 93.91%(185/197), respectively, which were significantly higher than those of 18F-FDG PET/CT (85.19%(46/54), 66.22%(49/74), 81.73%(161/197); χ2 values: 3.97, 26.88, 13.66, all P<0.05). The specificity (91.06%, 112/123) and accuracy of the combined examination for N staging were higher than those of the conventional imaging modalities (77.24%(95/123), 83.76%(165/197); χ2 values: 8.81, 10.23, both P<0.05). The sensitivity and accuracy of the combined examination for M staging were higher than those of the conventional imaging modalities (97.01%(65/67) vs 73.13%(49/67), 95.95%(71/74) vs 68.92%(51/74); χ2 values: 15.05, 18.66, both P<0.001). The sensitivities of the combined examination in evaluating CRM and EMVI were 100%(22/22) and 95.00%(19/20), and the accuracies were 98.15%(53/54) and 96.30%(52/54), all of which were higher than those of 18F-FDG PET/CT (CRM: 54.55%(12/22), 74.07%(40/54); EVMI: 30.00%(6/20), 74.07%(40/54); χ2 values: 12.94, 13.08, 18.03, 10.56, all P<0.01). The accuracy of the combined examination in evaluating EMVI was higher than that of the conventional imaging modalities (85.19%(46/54); χ2=3.97, P=0.046). Conclusion:18F-FDG PET/CT combined with conventional imaging modalities can improve the diagnostic efficacy for TNM staging and assessment of adjacent structural invasion in rectal cancer.

Objective To analyze the current status,research hotspots and development trends in the field of immune responses in the microenvironment after spinal cord injury(SCI). Methods Literatrues about immune responses in the microenvironment after SCI were searched from CNKI and the Web of Science Core Collection,from inception to March,2024.VOSviewer and CiteSpace were used to conduct a vi-sual analysis of authors,countries,institutions,journals,co-cited references and keywords. Results A total of 152 Chinese and 455 English studies were included.The number of publications increased annually,and China and the United States were leading research efforts in this field.In the Chinese literature,Zhu Yue was the most prolific author,and China Medical University was the leading institution.In the English literature,Phil-lip Popovich was the most prolific and highly cited author,and Ohio State University was the leading institution.Journal of Neuroscience and Experimental Neurology were identified as key journals.The research hotspots in both languages focused on immune activation,inflammatory response and functional recovery.Researches on stem cell transplantation,macrophage and traditional Chinese medicine were particularly prominent in the regu-lation of immune responses after SCI. Conclusion Immune responses in the microenvironment have emerged as a central focus in SCI research.The emphasis of current researches is shifting from mechanistic exploration to the investigation of immunomodulatory strate-gies,with several cutting-edge technologies showing significant potential in this regard.Moving forward,increas-ing collaboration across regions and institutions are essential to promote information sharing,accelerate scientific progress,and facilitate clinical translation,ultimately enhance patient rehabilitation outcomes.

Objective:To investigate the clinical effect of minimally invasive plate osteosynthesis (MIPO) through anterolateral approach in treatment of middle-distal humeral shaft fracture.Methods:A retrospective case series study was conducted to analyze the clinical data of 21 patients with middle-distal humeral shaft fracture admitted to 7th Medical Center of Chinese PLA General Hospital from August 2015 to March 2018, including 12 males and 9 females, aged 18-68 years [(31.3±3.6)years]. All were closed fracture. According to AO classification, the fracture were classified as type A in 6 patients, type B in 10 and type C in 5. All patients were treated with anterolateral minimally invasive plate fixation. The operation time, intraoperative blood loss and hospital stay were recorded. The fracture healing was observed after operation. The visual analogue scale (VAS), University of California at Los Angeles (UCLA) shoulder rating scale, and Mayo elbow performance score (MEPS) were used to evaluate the effectiveness before operation and at 2 weeks, 3 months and 12 months after operation.Results:All patients were followed up for 12-26 months [(18.2±2.4)months]. The operation time was 50-82 minutes [(68.2±19.4)minutes], with intraoperative blood loss of 40-95 ml [(60.2±21.3)ml]. The hospital stay was 6-16 days [(6.8±1.2)days]. There was no iatrogenic vascular or nerve injury during operation. The patients with radial nerve injury before operation were all adventitia contusion. The nerve function returned to normal within 3 months after operation. All fractures were healed within 5-10 months [(5.3±1.2)months]. At 2 weeks, 3 months and 12 months after operation, the VAS [(3.6±0.8)points, (2.1±0.4)points, (1.8±0.3)points] was lower than that before operation [(8.3±1.6)points] ( P<0.05); UCLA shoulder rating scale [(31.2±1.5)points, (33.6±0.8)points, (34.6±0.5)points] was higher than that before operation [(28.4±2.3)points] ( P<0.05); and MEPS [(80.2±3.4)points, (93.4±2.2)points, (96.4±3.5)points] was higher than that before operation [(60.5±4.5)points] ( P<0.05). At the last follow-up, the UCLA shoulder rating scale and MEPS showed excellent results. Conclusion:For middle and lower humeral shaft fracture especially for the fracture line relatively distal to the shaft, MIPO technique through anterolateral approach can attain satisfactory results in terms of pain, range of motion of shoulder and elbow joint, and joint function.

To assure the clinical quality and requirement of CT shelter used in field environment, the factors related with the practical application were studied. The evaluation indicators of CT equipment were investigated. Based on the technical modification of vehicle shelter CT, the scanning conditions of shelter CT were analyzed. Moreover, the comparative study was done between shelter CT and common CT in hospitals. In result, in order to meet maneuverability application in the field, vehicle shelter CT was restrictive by the field conditions, traffic impacts and running requirement. The application of vehicle shelter CT was affected by the factors, such as mechanical stabilization, moving precision, power fluctuations and variations of temperature and humidity, etc. The results were helpful to improve the clinical quality of vehicle shelter CT and made a base for the quality control study in the future.
Humidity ; Temperature ; Tomography, X-Ray Computed ; instrumentation

To assure the clinical quality and requirement of CT shelter used in field environment, the factorsrelated with the practical application were studied. The evaluation indicators of CT equipment were investigated. Based on the technical modification of vehicle shelter CT, the scanning conditions of shelter CT were analyzed. Moreover, the comparative study was done between shelter CT and common CT in hospitals. In result, in order to meet maneuverability application in the field, vehicle shelterCT was restrictive by the field conditions, traffic impacts and running requirement. The application of vehicle shelter CT was affected by the factors, such as mechanical stabilization, moving precision, power fluctuations and variations of temperature and humidity, etc. The results were helpful to improve the clinical quality of vehicle shelter CT and made a base for the quality control study inthe future.

Objective To analyze the impact of parotid's position and volume changing on radiation dose for head and neck cancer treated with TomoTherapy.Methods Totally 12 patients with head and neck cancer were treated with TomoTherapy.Before the treatment,the dose distribution was recalculated with MVCT images,which would obtain the parameters of position,volume and actual radiation dose for parotids.Results The volume of parotids in Plan2 was significantly lower than in Plan1,and the percentage reduction was 29.06％ and 31.78％ for left and right parotid,respectively (Z =6.77,3.06,P ＜ 0.05).Distance between the COM (center of mass) of parotids and the midline of body was significantly smaller in Plan2 than in Plan1,and the percentage reduction was 6.72％ and 6.19％ (t =5.14,5.80,P ＜ 0.05) at left and right side,respectively.Average dose and V26 for both parotids were higher than those in Plan1,increasing by an average of 37.74％,25.08％ (Z =-6.03,-5.31,P ＜ 0.05) for left parotid and 30.45％,19.33％ (Z =-5.43,-3.26,P ＜0.05) for right parotid,respectively.Conclusions The actual radiation dose to parotids was significantly increased during the radiation therapy for patients with head and neck cancer.There was a linear correlation between the decrease of distance between the COM of parotids and the midline of body and the percentage increase of parotids' radiation dose.No correlation between the reduction of parotids' volume and dose to parotids.In order to reduce the parotids' radiation dose,modification of treatment plan at the appropriate time is essential.