Objective To observe the performance of ConvNeXt architecture model(SC2-Net)integrated with feedforward attention(FA)for segmentation of pancreas from abdominal CT images.Methods 3D abdominal CT images of 80 healthy adults(Dataset 1)and 68 patients with pancreatic lesions(Dataset 2)were included.ConvNeXt network model was established and enhanced by introducing a FA mechanism,a scalable convolution block(SCB)and a feature gating(FG)module into the encoder section.The performance of the model for segmenting pancreas were comparatively evaluated with other models(Swin UNETR,nnFormer,UNETR,TransBTS models based on Transformer and 3D UX-NET model based on ConvNeXt),while conduct ablation experiments were performed on the added modules.Results SC2-Net accurately segmented pancreas from abdominal CT images,with Dice similarity coefficient(DSC),95％Hausdorff distance(HD95)and the mean surface distance(MSD)of 0.92±0.01,(1.08±0.05)mm and(2.12±0.01)mm in Dataset 1,respectively.The DSC and HD95 of SC2-Net segmentation of pancreas were both superior to those of other models.In Dataset 2,SC 2-Net achieved DSC,HD95 and MSD of 0.82±0.03,(3.35±0.36)mm and(0.87±0.15)mm,respectively,surpassing all other models.SC2-Net achieved complete pancreas segmentation in both datasets,whereas other models demonstrated under-segmentation or mis-segmentation.FA module significantly improved segmentation performance when integrated into the baseline network.Conclusion SC2-Net could improve segmentation of pancreas from abdominal CT images.

Objective To investigate the feasibility and accuracy of convolutional neural networks for automatically delineating the pancreatic cancer gross target volume(GTV)in pancreatic enhanced CT.Methods The localizable enhanced CT images of 114 patients with pancreatic cancer were retrospectively selected,in which the GTV was manually delineated using AccuContour.The imaging data were then import to AccuLearning and randomly divided as the training set,validation set and test set at a ratio of 8:1:1.Flex and Segresnet were used to train the automatic segmentation model,with each network structure trained continuously 3 times using fixed training parameters.The model was evaluated in terms of Dice similarity coefficient(DSC),95%Hausdorff distance(HD95),average symmetric surface distance(ASSD)and relative volume difference(RVD).Results In the model training phase,Flex-3 test results in Flex group were the worst,with a minimum DSC of 0.14%and an average DSC of 56.30%,while Flex-1 performed well,achieving a minimum DSC of 47.90%and an average DSC of 67.35%.Meanwhile,Segresnet-2 in Segresnet group had the worst test results,with a minimum DSC of 0.00%and an average DSC of 42.46%,while Segresnet-3 test results were better,with a minimum DSC of 42.65%and an average DSC of 63.28%.In the fixed testing phase,the best results among all were as follows:average DSC and RVD values of 63.88%and 29.41%in Segresnet-3 group,average ASSD value of 4.43 mm in Segresnet-2 group,and average HD95 value of 12.87 mm in Segresnet-1 group.Conclusion Both Flex and Segresnet architectures of convolutional neural network can be used for the automatic pancreatic tumor GTV segmentation training,with Segresnet performing better in comprehensive evaluation.

In recent years, the application of artificial intelligence technology in rectal cancer radiotherapy has become increasingly significant. By constructing models from patient clinical information, accurate prediction of dose distribution, treatment effect, and toxic side effects of rectal cancer can be achieved. This allows optimizing the radiotherapy plan, ensuring the dose is focused on the tumor target area while reducing the radiation damage to the bladder, rectum, and other surrounding tissues. Thus, it can achieve precision and personalization in radiotherapy. In this review, the construction method of artificial intelligence predictive models was described, and the value of different predictive factors to the model was systematically analyzed, including patient clinical data, radiomics, and dosimetry. Moreover, the application and limitations of artificial intelligence predictive models in radiotherapy were summarized. This information can serve as a reference for the clinical application of artificial intelligence predictive models in rectal cancer radiotherapy.

Objective To investigate the feasibility and accuracy of convolutional neural networks for automatically delineating the pancreatic cancer gross target volume(GTV)in pancreatic enhanced CT.Methods The localizable enhanced CT images of 114 patients with pancreatic cancer were retrospectively selected,in which the GTV was manually delineated using AccuContour.The imaging data were then import to AccuLearning and randomly divided as the training set,validation set and test set at a ratio of 8:1:1.Flex and Segresnet were used to train the automatic segmentation model,with each network structure trained continuously 3 times using fixed training parameters.The model was evaluated in terms of Dice similarity coefficient(DSC),95%Hausdorff distance(HD95),average symmetric surface distance(ASSD)and relative volume difference(RVD).Results In the model training phase,Flex-3 test results in Flex group were the worst,with a minimum DSC of 0.14%and an average DSC of 56.30%,while Flex-1 performed well,achieving a minimum DSC of 47.90%and an average DSC of 67.35%.Meanwhile,Segresnet-2 in Segresnet group had the worst test results,with a minimum DSC of 0.00%and an average DSC of 42.46%,while Segresnet-3 test results were better,with a minimum DSC of 42.65%and an average DSC of 63.28%.In the fixed testing phase,the best results among all were as follows:average DSC and RVD values of 63.88%and 29.41%in Segresnet-3 group,average ASSD value of 4.43 mm in Segresnet-2 group,and average HD95 value of 12.87 mm in Segresnet-1 group.Conclusion Both Flex and Segresnet architectures of convolutional neural network can be used for the automatic pancreatic tumor GTV segmentation training,with Segresnet performing better in comprehensive evaluation.

Objective To observe the performance of ConvNeXt architecture model(SC2-Net)integrated with feedforward attention(FA)for segmentation of pancreas from abdominal CT images.Methods 3D abdominal CT images of 80 healthy adults(Dataset 1)and 68 patients with pancreatic lesions(Dataset 2)were included.ConvNeXt network model was established and enhanced by introducing a FA mechanism,a scalable convolution block(SCB)and a feature gating(FG)module into the encoder section.The performance of the model for segmenting pancreas were comparatively evaluated with other models(Swin UNETR,nnFormer,UNETR,TransBTS models based on Transformer and 3D UX-NET model based on ConvNeXt),while conduct ablation experiments were performed on the added modules.Results SC2-Net accurately segmented pancreas from abdominal CT images,with Dice similarity coefficient(DSC),95％Hausdorff distance(HD95)and the mean surface distance(MSD)of 0.92±0.01,(1.08±0.05)mm and(2.12±0.01)mm in Dataset 1,respectively.The DSC and HD95 of SC2-Net segmentation of pancreas were both superior to those of other models.In Dataset 2,SC 2-Net achieved DSC,HD95 and MSD of 0.82±0.03,(3.35±0.36)mm and(0.87±0.15)mm,respectively,surpassing all other models.SC2-Net achieved complete pancreas segmentation in both datasets,whereas other models demonstrated under-segmentation or mis-segmentation.FA module significantly improved segmentation performance when integrated into the baseline network.Conclusion SC2-Net could improve segmentation of pancreas from abdominal CT images.

Objective To analyze the correlation between morphological and dosimetric parameters in patients with esophageal cancer at different locations using multi-to-multi double screening stepwise regression method,and to make simple predictions.Methods A retrospective analysis was conducted on 105 patients with advanced esophageal cancer who underwent radiotherapy at the First Affiliated Hospital of Fujian Medical University from 2019 to 2021.Morphological parameters of organs-at-risk were collected from CT images,and intensity-modulated radiotherapy plans were developed using Raystation4.7.The prescription doses for PTV-G and PTV-C were 60 Gy/30 F and 54 Gy/30 F,respectively.Multi-to-multi double screening stepwise regression method was employed to analyze the correlation between morphological and dosimetric parameters in esophageal cancer patients,and some preliminary predictions were provided.Results The dosimetric volume parameters of the lungs and heart were correlated with PTV-G volume,PTV-G length,PTV-G cross-sectional area,left and right lung volumes,lung length and total lung volume(P<0.05).For upper thoracic esophageal cancer,dosimetric volume parameters of the lungs and heart were correlated with PTV-G volume,PTV-G length,and right lung volume(P<0.05).For middle thoracic esophageal cancer,dosimetric volume parameters of the lungs,heart,and spinal cord were correlated with PTV-G volume,PTV-G length,PTV-G cross-sectional area,left and right lung volumes,and lung length(P<0.05).For lower thoracic esophageal cancer,dosimetric volume parameters of the lungs,heart,and spinal cord were correlated with PTV-G volume,PTV-G length,right lung volume,and lung length(P<0.05).Conclusion For patients with tumors at different locations,both overall and segmental analyses should be considered to balance therapeutic effect and side effects of radiotherapy,thereby maximizing the benefits for tumor patients.

Objective To analyze the correlation between morphological and dosimetric parameters in patients with esophageal cancer at different locations using multi-to-multi double screening stepwise regression method,and to make simple predictions.Methods A retrospective analysis was conducted on 105 patients with advanced esophageal cancer who underwent radiotherapy at the First Affiliated Hospital of Fujian Medical University from 2019 to 2021.Morphological parameters of organs-at-risk were collected from CT images,and intensity-modulated radiotherapy plans were developed using Raystation4.7.The prescription doses for PTV-G and PTV-C were 60 Gy/30 F and 54 Gy/30 F,respectively.Multi-to-multi double screening stepwise regression method was employed to analyze the correlation between morphological and dosimetric parameters in esophageal cancer patients,and some preliminary predictions were provided.Results The dosimetric volume parameters of the lungs and heart were correlated with PTV-G volume,PTV-G length,PTV-G cross-sectional area,left and right lung volumes,lung length and total lung volume(P<0.05).For upper thoracic esophageal cancer,dosimetric volume parameters of the lungs and heart were correlated with PTV-G volume,PTV-G length,and right lung volume(P<0.05).For middle thoracic esophageal cancer,dosimetric volume parameters of the lungs,heart,and spinal cord were correlated with PTV-G volume,PTV-G length,PTV-G cross-sectional area,left and right lung volumes,and lung length(P<0.05).For lower thoracic esophageal cancer,dosimetric volume parameters of the lungs,heart,and spinal cord were correlated with PTV-G volume,PTV-G length,right lung volume,and lung length(P<0.05).Conclusion For patients with tumors at different locations,both overall and segmental analyses should be considered to balance therapeutic effect and side effects of radiotherapy,thereby maximizing the benefits for tumor patients.

Objective:To study the influence of intensive magnet fields on radiation dose measurement, and to demonstrate the feasibility of measuring magnet field correction factor by a combination of medical linac with variable magnet fields in view of needing for accurate measurement of the doses from reference beam arising in MR image-guided radiotherapy.Methods:A photon radiation field and a variable field with 6 MV nominal high voltage were produced by using conventional medical electron linear accelerator equipped with a pair of electromagnets with magnetic field strength up to 1.5 T. Both PTW30013 and PTW31010 ionization chambers were used to test the responses of ionization chambers under different magnetic field strengths at four orientations in which the angles between ionization chamber axis and magnetic field direction were 0°, 180°, 90° and 270°, respectively. The magnetic factors, kB, M was calculated and compared with the reported values in literature. Results:The response of ionization chamber was proportional to the magnetic field strength before it reached to a peak around 1 T, and then fell down as the magnetic field continued to rise. When the magnetic field was 0.35 T, the magnetic factors of PTW31010 were 0.988 2±0.000 3 and 0.997 4±0.000 4 corresponding to 90° and 0° directions, the discrepancy between 0° scenario and literature was 0.05% ± 0.04%. When the magnetic field reached 1.5 T, the magnetic factor of PTW30013 was 0.958 9±0.000 5 at the situation of 90°, which was 0.60% ± 0.05% different from the literature value.Conclusions:Conventional 6 MV medical accelerator equipped with electromagnet can be used to measure the magnetic field factor of reference dosimetry for MRIgRT.

Objective:To study the clinical efficacy of laparoscopic radical cholecystectomy in the treatment of stage Ⅲ gallbladder cancer.Methods:The clinical characteristics and postoperative follow-up data of 184 patients (male 66, and female 118) who underwent radical cholecystectomy for stage Ⅲ gallbladder cancer at Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, from May 2015 to May 2022, were retrospectively analyzed. The age was (67.0±8.6) years old (range 38 to 85 years old). There were 71 patients in the laparoscopic group and 113 in the open group. The general medical data, surgery-related indicators and complications were analyzed. Follow-up was completed by outpatient visits and by telephone.Results:The laparoscopic group showed better postoperative alanine aminotransferase [67.5 (40.0, 138.5) vs. 104.0 (45.0, 252.2) U/L] and aspartate aminotransferase [41.5 (26.0, 71.2) vs. 53.0 (30.2, 153.5) U/L] recovery, higher albumin levels [32.05 (30.18, 35.20) vs. 30.50 (27.70, 33.50) g/L], earlier abdominal drainage tube removal [8.00(6.00, 10.25) vs. 10.00(6.00, 13.00)d], shorter hospital stay [10.00(8.00, 15.25) vs. 14.00(9.00, 19.00) d] and lower incidences of complications [(14.1%(10/71) vs. 31.9%(36/113)] when compared with the open group (all P<0.05). The 1 year (49.1% vs 61.0%), 2 years (24.0% vs. 28.5%), 3 years (16.0% vs. 14.5%) overall survival ( P=0.640), and the 3 years progression-free survival (18.3% vs. 15.0%, P=0.463) showed no significant difference between the 2 groups. Conclusion:Laparoscopic surgery for AJCC TNM stage Ⅲ gallbladder cancer showed comparable results with open surgery. When compared with open surgery, laparoscopic radical resection of gallbladder cancer had the advantages of earlier removal of abdominal drainage tube, lower incidence of postoperative complications, and shorter hospital stay.

Objective:To study the effect of preoperative transcatheter arterial chemoembolization (TACE) on postoperative complications after hepatectomy in patients with hepatocellular carcinoma (HCC) by propensity score matching analysis.Methods:Of 1 666 patients with HCC undergoing hepatectomy in Tongji Hospital, Tongji Medical College of Huazhong University of Science and Technology and Tianyou Hospital of Wuhan University of Science and Technology from March 2015 to March 2021 were retrospectively screened. Of 262 patients were enrolled, including 236 males and 26 females, aged (50.3±11.8) years. Of 131 patients were enrolled in both the single surgery group and the combined group (preoperative TACE + surgical resection). Factors affecting the complications after hepatectomy in patients with HCC were analyzed using univariate and multivariate logistic regression method.Results:After matching the propensity score, the incidence of postoperative complications in the single surgery group was 22.1% (29/131), lower than that in the combined group [41.2% (54/131), χ 2=11.02, P<0.001]. The incidence of bile leakage in the single surgery group [2.3% (3/131)] was also lower than that in the combined group [(9.2% (12/131), χ 2=5.73, P=0.017]. Multivariate logistic regression analysis showed that the combined group ( OR=2.43, 95% CI: 1.28-4.61, P=0.007) had an increased incidence of postoperative complications, so did patients with a preoperative alpha-fetoprotein > 400 μg/L, anatomic hepatectomy, long operation time, and hilar occlusion. Conclusion:Preoperative TACE could be a risk factor for postoperative complications in patients with HCC, especially for the postoperative biliary leakage.