Search

Background and purpose: Deep learning methods can be used for automatic segmentation and detection of lymphocytes on pathological images. This study aimed to assess the performance of using variational autoencoding pre-training method for lymphocyte infiltration detection on pathological images, as well as the impact of removing tumor necrosis regions on model performance. Methods: Using variational autoencoding (VAE) pre-training method, pre-training was performed on a large number of unlabeled pathological images from the Cancer Genome Atlas (TCGA) database (TCGA-COAD and TCGA-READ) to obtain an auto-encoding pre-training model, and then a classifier model of lymphocyte infiltration was trained on the public data samples. To avoid confusion with necrotic regions, a Unet segmentation model for tumor necrotic regions was trained to remove the influence of tumor necrotic regions on lymphocyte identification. Results: The lymphocyte infiltration detection model pre-trained with the VAE model had an area under curve (AUC) of 0.979 (95% CI: 0.978-0.980), an accuracy of 92.5% (95% CI: 92.3%-92.6%), a kappa value of 0.849, sensitivity of 0.908, specificity of 0.941, precision of 0.939, recall of 0.908, and F1 of 0.923 under the receiver operating characteristic (ROC) curve on the training set. The AUC for the validation set was 0.968 (95% CI: 0.964-0.972), the accuracy was 91.3% (95% CI: 90.6%-92.0%), kappa value was 0.826, sensitivity was 0.898, specificity was 0.928, precision was 0.925, recall was 0.898, and F1 was 0.912. The results of Resnet18 model on the labeled dataset were as follows: accuracy of the validation set was 83.2 % (95% CI: 82.2%-84.1%), kappa value was 0.664, sensitivity was 0.823, specificity was 0.840, precision was 0.838, recall was 0.823 and F1 was 0.830. The Unet model that segmented the necrotic regions of the tumors had a final DICE of 0.78 for the training set, and 0.76 for the validation. After removing the necrotic region, the predictive performance of the pre-trained lymphocyte infiltration detection model using the VAE proposed in this article was improved to some extent, with the AUC on the validation set increasing from 0.968 (95% CI: 0.964-0.972) to 0.971 (95% CI: 0.968-0.975). The accuracy was 92.4% (95% CI: 91.7%-93.0%), kappa value was 0.849, sensitivity was 0.928, specificity was 0.921, precision was 0.921, recall was 0.928, and F1 was 0.925. Conclusion: Using the variational autoencoding model pre-training method to classify the pathological pictures of lymphocyte infiltration can obtain better model performance compared with direct training, and removing the influence of tumor necrosis areas through Unet can further improve the performance of the model.

Background and Purpose: In recent years, domestic radiotherapy equipment and related software have made great progress, and testing the functionality and stability of the equipment and software is an essential step. This paper focused on comparing the differences in intensity-modulated radiation therapy (IMRT) plans dosimetry and organ at risk (OAR) volume calculations for common cancers between uRT-treatment planning system (TPS) and Monaco-TPS, and to evaluate the feasibility of dose calculation for Infinity linac (linear accelerator, Elekta, Sweden) using uRT-TPS. Methods: Twenty cases of rectal cancer, lung cancer, breast cancer and nasopharyngeal carcinoma were selected. The IMRT plans were completed in uRT-TPS and Monaco-TPS. The dose uniformity and conformity, mean dose, maximum dose of planning target volume (PTV) and OAR between two plans under the same prescribed dose of PTV were compared. And the pass rates of two TPS plans validated at the same linear accelerator were compared. Meanwhile, monitor units (MU), source skin distance (SSD) and the volume of OAR in uRT-TPS and Monaco-TPS were compared. Results: Wonderful plans that met the clinical requirements were obtained in uRT-TPS and Monaco-TPS. Comparable uniformity and conformability was received in PTV, and the maximum dose of PTV was reduced by 1.1 Gy for uRT-TPS (P = 0.006). For breast cancer and lung cancer, the dose in lung was lower for Monaco-TPS (P95%) for both plans met the clinical requirements. The region of interest in uRT-TPS was smaller compared with Monaco-TPS (P

Background and purpose: The incidence of pancreatic cancer has increased annually. Intensity-modulated radiotherapy (IMRT) has been widely used in the treatment of pancreatic cancer, however most dosimetric studies for pancreatic cancer have prescribed doses less than 60 Gy. The purpose of this study was to investigate the feasibility and dosimetric differences between coplanar IMRT (CO-IMRT) and non-coplanar IMRT (NC-IMRT) when using 75 Gy simultaneous integrated boost for patients with locally advanced pancreatic cancer (LAPC). Methods: Ten patients with LAPC treated with simultaneous integrated boost at Fudan University Shanghai Cancer Center from January 2018 to December 2021 were included. The prescribed dose for the planning target volume (PTV)50 Gy was 50 Gy in 25 fractions, and 75 Gy in 25 fractions for the simultaneous integrated boost PTV75 Gy. CO-IMRT and NC-IMRT plans were designed for each patient separately, with identical number of fields, prescription doses and OAR constrains for the same patient. The PTV dose distribution, conformability index (CI), homogeneity index (HI), indices to organs at risk (OAR) for multiple end points, beam-on time and monitor units (MU) were analyzed. We evaluated whether the PTV met clinical requirements and quantitative analysis of normal tissue effects in the clinic (QUANTEC) limits, and compared dosimetric differences between the two plans. Results: Both CO-IMRT and NC-IMRT could achieve the required dose coverage of PTV and meet the QUANTEC dose limits for OAR. The differences in CI, HI, beam-on time and MU between the two plans were not statistically significant (P>0.05). NC-IMRT was significantly decreased left kidney Dmean[(10.15±1.53) Gy vs (9.29±1.78) Gy, P0.05). Conclusion: In the treatment of LAPC using 75 Gy simultaneous integrated boost, both CO-IMRT and NC-IMRT can achieve excellent PTV coverage and meet the OAR constraints in all patients. Without affecting the quality of PTV coverage, NC-IMRT has more advantages in the dose distribution of OAR, which can better protect the OAR and reduce the toxicity to the gastrointestinal tract, liver and kidneys.

To evaluate the clinical applicability of deep learning based auto-segmentation of organs at risk (OARs) based on geometric and dosimetric indices. In this study, a total of 35 patients with rectal cancer who received radiotherapy in the Fudan University Shanghai Cancer Center were enrolled, and an in-house developed deep learning system was used to automatically segment OARs. Taking manual delineation as reference, the geometric evaluation indices included the dice similarity coefficient (DSC), jaccard similarity coefficient (JSC), hausdorff distance (HD), and mean distance to agreement (MDA). For each case, the treatment planning was optimized based on the auto-segmented OARs. The plan optimization and evaluation process was consistent with clinical procedure, recorded as Plan_FD. The dosimetric differences between Plan_FD and the original clinical treatment plan (recorded as Plan_Treat) were compared through dose-volume parameters and three-dimensional gamma analysis. The auto-segmented and manually delineated OARs were not only highly overlapping in three-dimensional space with an average value of DSC greater than 0.85 but also well matched in edge details with an average value of MDA less than 2.8 mm. In the dosimetric evaluation, a statistically significant difference was observed only for the bladder (p < 0.05); the dose-volume parameters of the other OARs and PTV were not statistically significant. Three-dimensional γ analysis (3 mm / 3 % standard) was performed on Plan_FD and Plan_Treat, where the percentage of points with γ ≤ 1.0 was (91.63 ± 6.27) %. Deep learning-based auto-segmentation of OARs has a high geometric similarity with manual delineation. The auto-segmented OARs have no significant impact on treatment planning and dose distribution, and have the potential to be directly applied to clinical treatment planning.

Objective: This study aims to investigate the prevalence of depression, anxiety and insomnia in pregnant Chinese women, and to explore the related risk factors across multiple fields. Method: The participants were 2120 women (Mage = 30.24 years, range = 19–47) from 12 provinces in China. Bivariate correlation and logistic regression analyses were used to explore the risk factors. Chi-square tests and t tests were used to examine whether there were significant differences in mental health status between pregnant women in different periods of gestation. Results: The overall prevalence rates of depression, anxiety and insomnia among pregnant Chinese women were 10.0%, 3.8% and 3.3%, respectively. Risk factors for the mental health of pregnant women were identified across demographic, maternal, physiological, and psychological domains. Among these, severe mobility restrictions and fear of childbirth were found to be the strongest predictors. Conclusions: The prevalence of depression, anxiety and insomnia among pregnant women is low. Pregnant women with a seriously impaired ability to move and fear of childbirth are more likely to experience mental health problems. KEY POINTS: What is already known about this topic: Depression, anxiety, and insomnia are common mental health problems among pregnant women. Prevalence rates vary significantly across different countries and regions. Particularly in a large country like China, prevalence rates differ substantially among different regions. While risk factors for mental health of pregnant women span multiple domains, such as physiological and demographic domains, the most influential factors remain unclear. What this topic adds: A large-scale study from 12 provinces in China showed relatively low prevalence rates of depression, anxiety, and insomnia among pregnant women. Among the numerous factors influencing mental health, severe mobility restrictions and fear of childbirth emerged as the most robust predictors. [ABSTRACT FROM AUTHOR]

Introduction: This study primarily aims to investigate the suitability of Halcyon in the context of cervical-thoracic esophageal cancer by exploring the dosimetric quality and delivery efficiency of Halcyon plans with different arc configurations. Additionally, it compares these findings with the dosimetric indices and delivery efficiency of TrueBeam and TomoTherapy accelerators, focusing on their capability to optimize protection for organs at risk (OARs) while maintaining efficient treatment delivery strategies. Methods: This retrospective study involved 26 patients diagnosed with cervical-thoracic esophageal cancer, and new radiotherapy plans were created using Halcyon, TrueBeam, and TomoTherapy. Dose volume histogram (DVH) metrics and delivery efficiency for plans involving different arc numbers on Halcyon (2, 3, and 4 arcs) were compared with those from TrueBeam and TomoTherapy. T-tests were employed to evaluate differences in organ protection among the accelerators. Results: The Halcyon plans, especially those with 4 arcs, provided superior protection for organs at risk, including the heart, lungs, and spinal cord, while maintaining excellent delivery efficiency. Compared to TrueBeam 2arc plans and TomoTherapy helical plans, Halcyon plans with 3 arcs also showed slight advantages. Although TomoTherapy offered better uniformity in dose distribution, it did not demonstrate a clear advantage over the other accelerators in terms of OAR protection or treatment efficiency. Furthermore, despite the lack of clear advantages in TrueBeam 2arc plans with flattening filter (FF), TrueBeam with flattening filter free (FFF) plans may hold potential in the treatment. Conclusion: Halcyon, particularly with 4 arcs, offers an optimal balance between reducing toxicity to organs at risk and maintaining treatment efficiency, making it a preferred choice in cervical thoracic esophageal cancer radiotherapy. The findings highlight the need for careful selection of radiotherapy accelerators based on specific clinical goals, with Halcyon showing potential advantages in scenarios where both treatment efficiency and OAR protection are paramount. [ABSTRACT FROM AUTHOR]

The active distribution network (ADN) can obtain measurement data, estimate system states, and control distributed energy resources (DERs) and flexible loads to ensure voltage stability. However, the ADN is more vulnerable to cyber attacks due to the recent wave of digitization and automation efforts. In this article, false data injection (FDI) attacks are focused on and they are classified into two types, that is, type I attacks on measurement data and type II attacks on control commands. After studying the impact of these two FDI attacks on the ADN, a new threat is revealed called coordinated FDI attack, which can maximize the voltage deviation by coordinating type I and type II FDI attacks. From the attacker's perspective, the scheme of CFDI is proposed and an algorithm is developed to find the optimal attack strategy. The feasibility of CFDI attacks has been validated on a smart distribution testbed. Moreover, simulation results on an ADN benchmark have demonstrated that CFDI attacks could cause remarkable voltage deviation that may deteriorate the stability of the distribution network. Moreover, the impact of CFDI attacks is higher than pure type I or type II attacks. To mitigate the threat, some countermeasures against CFDI attacks are also proposed. [ABSTRACT FROM AUTHOR]

Background: Undetermined lung nodules are common in locally advanced rectal cancer (LARC) and lack precise risk stratification. This study aimed to develop a radiomic‐based score (Rad‐score) to distinguish metastasis and predict overall survival (OS) in patients with LARC and lung nodules. Methods: Retrospective data from two institutions (July 10, 2006—September 24, 2015) was used to develop and validate the Rad‐score for distinguishing lung nodule malignancy. The prognostic value of the Rad‐score was investigated in LARC cohorts, leading to the construction and validation of a clinical and radiomic score (Cli‐Rad‐score) that incorporates both clinical and radiomic information for the purpose of improving personalized clinical prognosis prediction. Descriptive statistics, survival analysis, and model comparison were performed to assess the results. Results: The Rad‐score demonstrated great performance in distinguishing malignancy, with C‐index values of 0.793 [95% CI: 0.729–0.856] in the training set and 0.730 [95% CI: 0.666–0.874] in the validation set. In independent LARC cohorts, Rad‐score validation achieved C‐index values of 0.794 [95% CI: 0.737–0.851] and 0.747 [95% CI: 0.615–0.879]. Regarding prognostic prediction, Rad‐score effectively stratified patients. Cli‐Rad‐score outperformed the clinicopathological information alone in risk stratification, as evidenced by significantly higher C‐index values (0.735 vs. 0.695 in the internal set and 0.618 vs. 0.595 in the external set). Conclusions: CT‐based radiomics could serve as a reliable and powerful tool for lung nodule malignancy distinction and prognostic prediction in LARC patients. Rad‐score predicts prognosis independently. Incorporation of Cli‐Rad‐score significantly enhances the persionalized clinical prognostic capacity in LARC patients with lung nodules. [ABSTRACT FROM AUTHOR]