Purpose
To develop a method for predicting optimal dose distributions, given the planning image and segmented anatomy, by applying deep learning techniques to a database of previously optimized and ...approved Intensity‐modulated radiation therapy treatment plans.
Methods
Eighty cases of early‐stage nasopharyngeal cancer (NPC) were included in the study. Seventy cases were chosen randomly as the training set and the remaining as the test set. The inputs were the images with structures, with each target and organs at risk (OARs) assigned a unique label. The outputs were dose maps, including coarse dose maps and converted fine dose maps (FDM) from convolution. Two types of input images with structures were used in the model building. One type of input included the images (with associated structures) without manipulation. The second type of input involved modifying the image gray label with information from radiation beam geometry. ResNet101 was chosen as the deep learning network for both. The accuracy of predicted dose distributions was evaluated against the corresponding dose as used in the clinic. A global three‐dimensional gamma analysis was calculated for the evaluation.
Results
The proposed model trained with the two different sets of input images and structures could both predict patient‐specific dose distributions accurately. For the out‐of‐field dose distributions, the model obtained from the input with radiation geometry performed better (dose difference in %, 4.7 ± 6.1% vs 5.5 ± 7.9%, P < 0.05). The mean Gamma pass rates of dose distributions predicted with both types of input were comparable for most OARs (P > 0.05), except for the bilateral optic nerves and the optic chiasm.
Conclusions
The proposed system with radiation geometry added to the input is a promising method to generate patient‐specific dose distributions for radiotherapy. It can be applied to obtain the dose distributions slice‐by‐slice for planning quality assurance and for guiding automated planning.
Style transfer describes the rendering of an image's semantic content as different artistic styles. Recently, generative adversarial networks (GANs) have emerged as an effective approach in style ...transfer by adversarially training the generator to synthesize convincing counterfeits. However, traditional GAN suffers from the mode collapse issue, resulting in unstable training and making style transfer quality difficult to guarantee. In addition, the GAN generator is only compatible with one style, so a series of GANs must be trained to provide users with choices to transfer more than one kind of style. In this paper, we focus on tackling these challenges and limitations to improve style transfer. We propose adversarial gated networks (Gated-GAN) to transfer multiple styles in a single model. The generative networks have three modules: an encoder, a gated transformer, and a decoder. Different styles can be achieved by passing input images through different branches of the gated transformer. To stabilize training, the encoder and decoder are combined as an auto-encoder to reconstruct the input images. The discriminative networks are used to distinguish whether the input image is a stylized or genuine image. An auxiliary classifier is used to recognize the style categories of transferred images, thereby helping the generative networks generate images in multiple styles. In addition, Gated-GAN makes it possible to explore a new style by investigating styles learned from artists or genres. Our extensive experiments demonstrate the stability and effectiveness of the proposed model for multi-style transfer.
Insomnia disorder (ID) has become the second-most common mental disorder. Despite burgeoning evidence for increased high-frequency electroencephalography (EEG) activity and cortical hyperarousal in ...ID, the detailed spectral features of this disorder during wakefulness and different sleep stages remain unclear. Therefore, we adopted a meta-analytic approach to systematically assess existing evidence on EEG spectral features in ID. Hedges's g was calculated by 148 effect sizes from 24 studies involving 977 participants. Our results demonstrate that, throughout wakefulness and sleep, patients with ID exhibited increased beta band power, although such increases sometimes extended into neighboring frequency bands. Patients with ID also exhibited increased theta and gamma power during wakefulness, as well as increased alpha and sigma power during rapid eye movement (REM) sleep. In addition, ID was associated with decreased delta power and increased theta, alpha, and sigma power during NREM sleep. The EEG measures of absolute and relative power have similar sensitivity in detecting spectral features of ID during wakefulness and REM sleep; however, relative power appeared to be a more sensitive biomarker during NREM sleep. Our study is the first statistics-based review to quantify EEG power spectra across stages of sleep and wakefulness in patients with ID.
Radiotherapy is one of the main treatment methods for nasopharyngeal carcinoma (NPC). It requires exact delineation of the nasopharynx gross tumor volume (GTVnx), the metastatic lymph node gross ...tumor volume (GTVnd), the clinical target volume (CTV), and organs at risk in the planning computed tomography images. However, this task is time-consuming and operator dependent. In the present study, we developed an end-to-end deep deconvolutional neural network (DDNN) for segmentation of these targets.
The proposed DDNN is an end-to-end architecture enabling fast training and testing. It consists of two important components: an encoder network and a decoder network. The encoder network was used to extract the visual features of a medical image and the decoder network was used to recover the original resolution by deploying deconvolution. A total of 230 patients diagnosed with NPC stage I or stage II were included in this study. Data from 184 patients were chosen randomly as a training set to adjust the parameters of DDNN, and the remaining 46 patients were the test set to assess the performance of the model. The Dice similarity coefficient (DSC) was used to quantify the segmentation results of the GTVnx, GTVnd, and CTV. In addition, the performance of DDNN was compared with the VGG-16 model.
The proposed DDNN method outperformed the VGG-16 in all the segmentation. The mean DSC values of DDNN were 80.9% for GTVnx, 62.3% for the GTVnd, and 82.6% for CTV, whereas VGG-16 obtained 72.3, 33.7, and 73.7% for the DSC values, respectively.
DDNN can be used to segment the GTVnx and CTV accurately. The accuracy for the GTVnd segmentation was relatively low due to the considerable differences in its shape, volume, and location among patients. The accuracy is expected to increase with more training data and combination of MR images. In conclusion, DDNN has the potential to improve the consistency of contouring and streamline radiotherapy workflows, but careful human review and a considerable amount of editing will be required.
The conversion of serine and glycine that is accomplished by serine hydroxymethyltransferase 2 (SHMT2) in mitochondria is significantly upregulated in various cancers to support cancer cell ...proliferation. In this study, we observed that SHMT2 is acetylated at K95 in colorectal cancer (CRC) cells. SIRT3, the major deacetylase in mitochondria, is responsible for SHMT2 deacetylation. SHMT2-K95-Ac disrupts its functional tetramer structure and inhibits its enzymatic activity. SHMT2-K95-Ac also promotes its degradation via the K63-ubiquitin-lysosome pathway in a glucose-dependent manner. TRIM21 acts as an E3 ubiquitin ligase for SHMT2. SHMT2-K95-Ac decreases CRC cell proliferation and tumor growth in vivo through attenuation of serine consumption and reduction in NADPH levels. Finally, SHMT2-K95-Ac is significantly decreased in human CRC samples and is inversely associated with increased SIRT3 expression, which is correlated with poorer postoperative overall survival. Our study reveals the unknown mechanism of SHMT2 regulation by acetylation which is involved in colorectal carcinogenesis.
Despite a good and overall prognosis, papillary thyroid cancer (PTC) can still affect the quality of life of many patients, and can even be life-threatening due to its invasiveness and metastasis. ...Emerging studies demonstrate that circular RNAs (circRNAs) participate in the regulation of various cancers. However, the circRNA profile in invasive PTC is still not well understood.
Competing endogenous RNA (ceRNA) microarrays were performed to determine circRNAs contributed to the tumorigenesis and invasiveness of PTC. Bioinformatics methods were used to narrow down the candidate circRNAs. Quantitative real-time polymerase chain reaction (qRT-PCR) assays revealed a significant upregulation of hsa_circ_0058124 in PTC tissue and a close correlation with a poor prognosis for PTC patients. RNA fluorescence in situ hybridization and Cell fractionation assay were used to investigate the subcellular location of hsa_circ_0058124. Then, we examined the functions of hsa_circ_0058124 in PTC by cell proliferation, cell cycle, apoptosis, migration and invasion assay. Mechanistically, RNA sequencing and GSEA analysis were applied to predict the downstream pathway of hsa_circ_0058124. Dual-luciferase report assays were used to explore the potential miRNA sponge role of hsa_circ_0058124. Western blotting, cell proliferation, cell cycle, cell apoptosis, migration and invasion, and mouse xenograft assay were used to validate the effects of hsa_circ_0058124/NOTCH3/GATAD2A axis on PTC progression.
In the current study, a novel hsa_circ_0058124 on 2q35 was identified and explored in PTC. Hsa_circ_0058124 is associated with the malignant features and poor outcomes of PTC patients. Hsa_circ_0058124 acts as an oncogenic driver that promotes PTC cell proliferation, tumorigenicity, tumor invasion, and metastasis, which functions as a competing endogenous RNA to modulate miRNA-218-5p and its target gene NUMB expression, and consequently with repression of the NOTCH3/GATAD2A signaling axis in vitro and in vivo.
This study unveils a novel biomarker panel consisting of the hsa_circ_0058124/NOTCH3/GATAD2A axis which is critical for PTC tumorigenesis and invasiveness and may represent a novel therapeutic target for intervening in PTC progression.
Internal leakage diagnosis in a hydraulic cylinder is a key technique for the maintenance of hydraulic systems. However, it is difficult to diagnose the internal leakage under different low loads. To ...solve this problem, a novel fault diagnosis method based on the optimization deep belief network (DBN) combined with the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique is proposed to treat the collected AE signals. The raw AE signals are decomposed into a set of intrinsic mode functions (IMFs) by using CEEMDAN. Subsequently, according to the decreasing order of the Pearson correlation coefficient values, the first five IMFs are selected for signal reconstruction to suppress the abnormal interference from noise. The reconstructed signals are regarded as the input of the optimization DBN, and the particle swarm optimization simulated annealing (PSOSA) algorithm is adopted to identify the four internal leakage levels. The experimental results show that the proposed method exhibits a higher classification accuracy than other methods under different low loads. This result validates the effectiveness and superiority of the proposed approach to realize internal leakage diagnoses under different low loads.
Protein/subunit vaccines often require external adjuvants to induce protective immunity. Due to the safety concern of chemical adjuvants, physical adjuvants were recently explored to boost ...vaccination. Physical adjuvants use physical energies rather than chemicals to stimulate tissue stress and endogenous danger signal release to boost vaccination. Here we present the safety and potency of non-invasive radiofrequency treatment to boost intradermal vaccination in murine models. We show non-invasive radiofrequency can increase protein antigen-induced humoral and cellular immune responses with adjuvant effects comparable to widely used chemical adjuvants. Radiofrequency adjuvant can also safely boost pandemic 2009 H1N1 influenza vaccination with adjuvant effects comparable to MF59-like AddaVax adjuvant. We find radiofrequency adjuvant induces heat shock protein 70 (HSP70) release and activates MyD88 to mediate the adjuvant effects. Physical radiofrequency can potentially be a safe and potent adjuvant to augment protein/subunit vaccine-induced humoral and cellular immune responses.
Internal leakage is the most common failure of hydraulic cylinder; when it increases, it decreases volumetric efficiency, pressure and speed of the hydraulic cylinder, and can seriously affect the ...normal operation of the hydraulic cylinder, so it is important to measure it, especially to measure it online. Firstly, the principle of internal leakage online measurement is proposed, including the online measurement system, the fixed mode of the strain gauge and the mathematical model of the flow-strain signal conversion. Secondly, an experimental system is established to collect internal leakages and strain values, and the data is processed. Finally, the convolutional neural network (CNN), BP neural network (BPNN), Radial Basis Function Network (RBF), and Support Vector Regression (SVR) are used to predict the hydraulic cylinder leakage; the comparison of experimental results show that the CNN has high accuracy and high efficiency. This study provides a new idea for online measurement of small flow on other hydraulic components.
Display omitted
The majority of vaccines have been delivered into the muscular tissue. Skin contains large amounts of antigen-presenting cells and has been recognized as a more immunogenic site for ...vaccine delivery. Intradermal delivery has been approved to improve influenza vaccine efficacy and spare influenza vaccine doses. In response to the recent monkeypox outbreak, intradermal delivery has been also approved to stretch the limited monkeypox vaccine doses to immunize more people at risk. Incorporation of vaccine adjuvants is promising to further increase intradermal vaccine efficacy and spare more vaccine doses. Yet, intradermal vaccination is associated with more significant local reactions than intramuscular vaccination. Thus, adjuvants suitable to boost intradermal vaccination need to have a good local safety without inducing overt local reactions. This review introduces currently approved adjuvants in licensed human vaccines and their relative reactogenicity for intradermal delivery and then introduces emerging chemical and physical adjuvants with a good local safety to boost intradermal vaccination. The rational to develop physical adjuvants, the types of physical adjuvants, and the unique advantages of physical adjuvants to boost intradermal vaccination are also introduced in this review.