OFIDA: Object-focused image data augmentation with attention-driven graph convolutional networks.

Image data augmentation plays a crucial role in data augmentation (DA) by increasing the quantity and diversity of labeled training data. However, existing methods have limitations. Notably, techniques like image manipulation, erasing, and mixing can distort images, compromising data quality. Accurate representation of objects without confusion is a challenge in methods like auto augment and feature augmentation. Preserving fine details and spatial relationships also proves difficult in certain techniques, as seen in deep generative models. To address these limitations, we propose OFIDA, an object-focused image data augmentation algorithm. OFIDA implements one-to-many enhancements that not only preserve essential target regions but also elevate the authenticity of simulating real-world settings and data distributions. Specifically, OFIDA utilizes a graph-based structure and object detection to streamline augmentation. Specifically, by leveraging graph properties like connectivity and hierarchy, it captures object essence and context for improved comprehension in real-world scenarios. Then, we introduce DynamicFocusNet, a novel object detection algorithm built on the graph framework. DynamicFocusNet merges dynamic graph convolutions and attention mechanisms to flexibly adjust receptive fields. Finally, the detected target images are extracted to facilitate one-to-many data augmentation. Experimental results validate the superiority of our OFIDA method over state-of-the-art methods across six benchmark datasets.

Trade-offs between leaf stoichiometric characteristics and photosynthetic traits of Larix gmelinii and its differences among provenances.

Variations and trade-offs between leaf stoichiometric characteristics and photosynthetic traits are indicative of ecological adaptation strategies of plants and their responses to environment changes. In a common garden of Maoershan, we measured leaf stoichiometric characteristics (carbon content (C), nitrogen content (N), phosphorus content (P), C/N, C/P, N/P) and photosynthetic traits (maximum net photosynthetic rate (Amax), maximum electron transport rate (Jmax), maximum carboxylation rate (Vmax)) of Larix gmelinii from 17 geographical provenances. We examined the provenance differences in stoichiometric characteristics and photosynthetic traits, and analyzed their trade-offs and influencing factors. The results showed leaf stoichiometric characteristics and photosynthetic traits significantly differed among provenances. The climatic factors of seed-source sites explained 54.8% and 67.2% of the variation in stoichiometric characteristics and photosynthetic traits, respectively. Aridity index (AI) of seed-source sites was positively correlated with C, N, P, Amax, Jmax, Vmax, but negatively with C/N, C/P, and N/P. Results of redundancy analysis showed that stoichiometric characteristics accounted for 75.0% of the variation in photosynthetic traits. Amax, Jmax, Vmax were positively correlated with C, N, P, and negatively correlated with C/N, C/P, N/P. The provenance differences in stoichiometric characteristics, photosynthetic traits, and their synergistic relationship suggested the long-term adaptation of trees to the climate of seed-source sites. These findings were of great significance for understanding ecological adaptation strategies of trees in response to climate change.

Provenance variation of root C, N, P, and K stoichiometric characteristics under different diameter classes of Larix gmelinii.

For exploring the difference of root stoichiometric characteristics among diameter classes and provenances, we examined the contents and stoichiometric ratios of carbon (C), nitrogen (N), phosphorus (P), and potassium (K) in three diameter classes of roots (0-1, 1-2 and 2-5 mm, respectively) of 39-year-old Larix gmelinii grown in a common garden. The results showed that root element contents and their stoichiometric ratios had significant difference among three diameter classes of roots. C content, C:N, C:P, C:K were the lowest, and N, P, K contents, N:P, and N:K were the highest in 0-1 mm diameter class roots. Compared with the 1-2 and 2-5 mm diameter class roots, 0-1 mm diameter class roots had different seasonal dynamics, which might be caused by the fact that 0-1 mm diameter class roots are absorptive roots and the other diameter class roots are transport roots. There was no provenance difference in C content among all diameter class roots, while significant provenance differences were found in N, K contents, C:N, and C:K in 0-1 mm diameter class roots, and great provenance differences for in P content, C:P, N:P, and N:K in 0-1 and 1-2 mm diameter class roots. N content, K content, C:P, N:P, and N:K in 0-1 mm diameter class roots had positive correlation with the aridity index of seed-source sites, while the P content, C:N and C:K had negative correlations. The stoichiometric characteristics were related with the diameter (or function) of roots, and had significant provenance differences in 0-1 mm (absorptive root) and 1-2 mm diameter class roots, which might be attributed to their genotypic adaptation to the environment of seed-source sites.

A total variation prior unrolling approach for computed tomography reconstruction.

BACKGROUND: With the rapid development of deep learning technology, deep neural networks can effectively enhance the performance of computed tomography (CT) reconstructions. One kind of commonly used method to construct CT reconstruction networks is to unroll the conventional iterative reconstruction (IR) methods to convolutional neural networks (CNNs). However, most unrolling methods primarily unroll the fidelity term of IR methods to CNNs, without unrolling the prior terms. The prior terms are always directly replaced by neural networks. PURPOSE: In conventional IR methods, the prior terms play a vital role in improving the visual quality of reconstructed images. Unrolling the hand-crafted prior terms to CNNs may provide a more specialized unrolling approach to further improve the performance of CT reconstruction. In this work, a primal-dual network (PD-Net) was proposed by unrolling both the data fidelity term and the total variation (TV) prior term, which effectively preserves the image edges and textures in the reconstructed images. METHODS: By further deriving the Chambolle-Pock (CP) algorithm instance for CT reconstruction, we discovered that the TV prior updates the reconstructed images with its divergences in each iteration of the solution process. Based on this discovery, CNNs were applied to yield the divergences of the feature maps for the reconstructed image generated in each iteration. Additionally, a loss function was applied to the predicted divergences of the reconstructed image to guarantee that the CNNs' results were the divergences of the corresponding feature maps in the iteration. In this manner, the proposed CNNs seem to play the same roles in the PD-Net as the TV prior in the IR methods. Thus, the TV prior in the CP algorithm instance can be directly unrolled to CNNs. RESULTS: The datasets from the Low-Dose CT Image and Projection Data and the Piglet dataset were employed to assess the effectiveness of our proposed PD-Net. Compared with conventional CT reconstruction methods, our proposed method effectively preserves the structural and textural information in reference to ground truth. CONCLUSIONS: The experimental results show that our proposed PD-Net framework is feasible for the implementation of CT reconstruction tasks. Owing to the promising results yielded by our proposed neural network, this study is intended to inspire further development of unrolling approaches by enabling the direct unrolling of hand-crafted prior terms to CNNs.

Artifact-Assisted multi-level and multi-scale feature fusion attention network for low-dose CT denoising.

BACKGROUND AND OBJECTIVE: Since low-dose computed tomography (LDCT) images typically have higher noise that may affect accuracy of disease diagnosis, the objective of this study is to develop and evaluate a new artifact-assisted feature fusion attention (AAFFA) network to extract and reduce image artifact and noise in LDCT images. METHODS: In AAFFA network, a feature fusion attention block is constructed for local multi-scale artifact feature extraction and progressive fusion from coarse to fine. A multi-level fusion architecture based on skip connection and attention modules is also introduced for artifact feature extraction. Specifically, long-range skip connections are used to enhance and fuse artifact features with different depth levels. Then, the fused shallower features enter channel attention for better extraction of artifact features, and the fused deeper features are sent into pixel attention for focusing on the artifact pixel information. Besides, an artifact channel is designed to provide rich artifact features and guide the extraction of noise and artifact features. The AAPM LDCT Challenge dataset is used to train and test the network. The performance is evaluated by using both visual observation and quantitative metrics including peak signal-noise-ratio (PSNR), structural similarity index (SSIM) and visual information fidelity (VIF). RESULTS: Using AAFFA network improves the averaged PSNR/SSIM/VIF values of AAPM LDCT images from 43.4961, 0.9595, 0.3926 to 48.2513, 0.9859, 0.4589, respectively. CONCLUSIONS: The proposed AAFFA network is able to effectively reduce noise and artifacts while preserving object edges. Assessment of visual quality and quantitative index demonstrates the significant improvement compared with other image denoising methods.

A Dual-Encoder-Single-Decoder Based Low-Dose CT Denoising Network.

Generative adversarial networks (GAN) have shown great potential for image quality improvement in low-dose CT (LDCT). In general, the shallow features of generator include more shallow visual information such as edges and texture, while the deep features of generator contain more deep semantic information such as organization structure. To improve the network's ability to categorically deal with different kinds of information, this paper proposes a new type of GAN with dual-encoder- single-decoder structure. In the structure of the generator, firstly, a pyramid non-local attention module in the main encoder channel is designed to improve the feature extraction effectiveness by enhancing the features with self-similarity; Secondly, another encoder with shallow feature processing module and deep feature processing module is proposed to improve the encoding capabilities of the generator; Finally, the final denoised CT image is generated by fusing main encoder's features, shallow visual features, and deep semantic features. The quality of the generated images is improved due to the use of feature complementation in the generator. In order to improve the adversarial training ability of discriminator, a hierarchical-split ResNet structure is proposed, which improves the feature's richness and reduces the feature's redundancy in discriminator. The experimental results show that compared with the traditional single-encoder- single-decoder based GAN, the proposed method performs better in both image quality and medical diagnostic acceptability. Code is available in https://github.com/hanzefang/DESDGAN.

Correlation between the anatomical morphology of palatal rugae and sex / Correlación entre la morfología anatómica de las rugas palatinas y el sexo

SUMMARY: To investigate the correlation between the anatomical morphology of palatal rugae and sex. The study sample consisted of 120 students studying from Shanxi Medical University, of which 60 were females and 60 were males. The digital model of the palatal rugae was obtained by the 3 Shape TRIOS intraoral scanner. And the shapes of palatal rugae were recorded. Association between palatal rugae shape and sex were tested using Chi-square analysis. And logistic regression analysis (LRA) was carried out to calculate the accuracy of gender prediction using rugae shapes. There was a statistically significant difference between males and females in terms of the distribution of wavy and circular palate rugae. The use of logistic regression analysis obtained a sex predictive value of 65 % when all the rugae shapes were analyzed. Digital images of the palatal rugae morphology contribute to more accurate and convenient for data collection and transformation. It was found that rugae patterns can moderately identify the sex of the specific population when multivariate statistics such as LRA is applied. The palatal rugae morphology can be utilized as an assistant measure for sex identification.

RESUMEN: Investigar la correlación entre la morfología anatómica de las rugas palatinas y el sexo. En la muestra de este estudio se incluyeron 120 estudiantes de la Universidad Médica de Shanxi, (60 mujeres y 60 hombres). El modelo digital de las rugas palatinas se obtuvo mediante escáner intraoral 3 Shape TRIOS, y se registraron las formas de las rugas palatinas. La asociación entre la forma de las rugas palatinas y el sexo se evaluó mediante un análisis de Chi-cuadrado; para calcular la precisión de la predicción de sexo se llevó a cabo un análisis de regresión logística (ARL) Se observó una diferencia estadísticamente significativa entre hombres y mujeres en términos de la distribución de las rugas palatinas onduladas y circulares. El uso de análisis de regresión logística obtuvo un valor predictivo de sexo del 65 % cuando se analizaron todas las formas de las rugas. Las imágenes digitales de la morfología de las rugas palatinas contribuyen a una recopilación de datos más precisa. En este análisis se determinó que los patrones de rugas pueden identificar relativamente el sexo de una población específica, cuando se aplican estadísticas multivariadas como ARL. La morfología de las rugas palatinas se puede utilizar como medida de ayuda para la identificación de sexo.

Prognostic Significance of Gene Signature of Tertiary Lymphoid Structures in Patients With Lung Adenocarcinoma.

BACKGROUND: Lung adenocarcinoma (LUAD) is a highly mortal cancer. Tertiary lymphoid structures (TLS) are ectopic lymphoid organs with similar morphological and molecular characters to secondary lymphoid organ. The aim of this study is to investigate the prognostic effect of a gene signature associated with TLSs, including B-cell-specific genes. METHODS: Clinical data of 515 LUAD patients in the TGCA cohort were used to examine the relationship of TLS signature with immune microenvironment, tumor mutational burden (TMB), and driver gene mutations. Patients were divided into the TLS signature high group and TLS signature low group, and comparative analysis of survival and its influencing factors between the two groups was performed. The resulting data were then validated in the GSE37745 cohort. RESULTS: TLS signature high group had significantly better overall survival (OS) and progression-free interval (PFI) as well as significantly higher infiltration of immune cell subsets, cancer immune cycle (CIC) signature except for immunogram score2 (IGS2), and expression of major checkpoint genes than the TLS signature low group. Notably, while TLS signature was not markedly associated with TMB and mutation frequencies of driver genes, there were significant differences in overall survival of patients with given mutation status of EGFR, KRAS, BRAF and TP53 genes between the TLS signature high and low groups. CONCLUSION: This study provided evidence that LUAD patients with high TLS signature had a favorable immune microenvironment and better prognosis, suggesting that TLS signature is an independent positive prognostic factor for LUAD patients.

Artifact and Detail Attention Generative Adversarial Networks for Low-Dose CT Denoising.

Generative adversarial networks are being extensively studied for low-dose computed tomography denoising. However, due to the similar distribution of noise, artifacts, and high-frequency components of useful tissue images, it is difficult for existing generative adversarial network-based denoising networks to effectively separate the artifacts and noise in the low-dose computed tomography images. In addition, aggressive denoising may damage the edge and structural information of the computed tomography image and make the denoised image too smooth. To solve these problems, we propose a novel denoising network called artifact and detail attention generative adversarial network. First, a multi-channel generator is proposed. Based on the main feature extraction channel, an artifacts and noise attention channel and an edge feature attention channel are added to improve the denoising network's ability to pay attention to the noise and artifacts features and edge features of the image. Additionally, a new structure called multi-scale Res2Net discriminator is proposed, and the receptive field in the module is expanded by extracting the multi-scale features in the same scale of the image to improve the discriminative ability of discriminator. The loss functions are specially designed for each sub-channel of the denoising network corresponding to its function. Through the cooperation of multiple loss functions, the convergence speed, stability, and denoising effect of the network are accelerated, improved, and guaranteed, respectively. Experimental results show that the proposed denoising network can preserve the important information of the low-dose computed tomography image and achieve better denoising effect when compared to the state-of-the-art algorithms.

Circular RNA circSLC25A16 contributes to the glycolysis of non-small-cell lung cancer through epigenetic modification.

Growing evidence has highlighted the roles of circular RNAs (circRNAs) in non-small-cell lung cancer (NSCLC), however, their roles in NSCLC glycolysis remains poorly understood. CircRNAs microarray profiles discovered a novel exon-derived circRNA, circSLC25A16 (hsa_circ_0018534), in NSCLC tissue samples. In NSCLC samples, high-expression of circSLC25A16 was associated with unfavorable prognosis. Cellular experiments revealed that circSLC25A16 accelerated the glycolysis and proliferation of NSCLC cells. Besides, circSLC25A16 knockdown repressed the in vivo growth by xenograft assays. RNA-fluorescence in situ hybridization (RNA-FISH) illustrated that circSLC25A16 and miR-488-3p were both located in cytoplasm. Mechanistic experiments demonstrated that circSLC25A16 interacts with miR-488-3p/HIF-1α, which activates lactate dehydrogenase A (LDHA) by facilitating its transcription. Collectively, present research reveals the crucial function of circSLC25A16 on NSCLC glycolysis through miR-488-3p/HIF-1α/LDHA, suggesting the underlying pathogenesis for NSCLC and providing a therapeutic strategy for precise treatment.

Research on correction method of palatal rugae morphology in forensic digital identification system / Investigación sobre el método de corrección de la morfología de las rugas palatinas en sistema digital de identificación forense

SUMMARY: Palatal rugae is an irregular soft tissue, which is located in the front third of the hard palate, and is asymmetrically distributed from the middle suture to the sides. The difference, stability and extensive characteristics of palatal rugae morphology have gradually make it a characteristic indicator of forensic identification. However, a mature digital palatal rugae identification system has not yet been established at present. Feature extraction is the premise of palatal rugae image recognition. In order to obtain palatal rugae feature information in all directions and improve the reliability of forensic identification, it is necessary to collect palatal rugae images from a plurality of different angles. When the collected images are sent to the recognition system, the diversity of angles will often cause problems such as error recognition. If the tilted images are not rotated properly, it will make the forensic identification face many difficulties. To solve the problem of image skew caused by the diversity of acquisition angle, an algorithm based on orientation vector to correct the tilted palatal rugae images was proposed in this paper. Firstly, the criteria for standard palatal rugae image and the selection rules for feature points were set; Secondly, characterizing feature points according to the rules, and fitting two lines and find their direction vector; Finally, to obtain the corrected images, the tilted images were rotated by the angle determined by the two direction vectors. Simulation results show that the proposed algorithm can correct the tilted palatal rugae images collected from different angles and has strong robustness.

RESUMEN: Las rugas palatinas son tejidos blandos irregulares, que se ubican en el tercio frontal del paladar duro y se distribuyen asimétricamente desde la sutura mediana hacia los lados. La diferencia, la estabilidad y las características extensivas de la morfología de las rugas palatinas la han convertido gradualmente en un indicador característico de la identificación forense. Sin embargo, un sistema de identificación de rugas palatinas digitales maduras todavía no se ha establecido en la actualidad. La extracción de características es la premisa del reconocimiento de imágenes de las rugas palatinas. Para obtener información sobre las características de las rugas palatinas en todas las direcciones, y mejorar la confiabilidad de la identificación forense, es necesario recopilar imágenes de las rugas palatinas desde una pluralidad de ángulos diferentes. Cuando las imágenes recogidas se envían al sistema de reconocimiento, la diversidad de ángulos a menudo causará problemas como el reconocimiento de errores. Si las imágenes inclinadas no se giran correctamente, la identificación forense se enfrentará a muchas dificultades. Para resolver el problema del sesgo de la imagen causado por la diversidad del ángulo de adquisición, en este documento se propuso un algoritmo basado en el vector de orientación para corregir las imágenes de las arrugas palatinas inclinadas. En primer lugar, se establecieron los criterios para la imagen de las rugas palatinas estándar, y las reglas de selección para los puntos de características. En segundo lugar, se determinaron puntos de características según las reglas, y se ajustaron dos líneas y encontrar la dirección del vector. Finalmente, para obtener las imágenes corregidas, las imágenes inclinadas se giraron según el ángulo determinado por la dirección de dos vectores. Los resultados de la simulación muestran que el algoritmo propuesto puede corregir las imágenes de rugas palatinas inclinadas recopiladas desde diferentes ángulos y tiene una gran robustez.

Hemolymphangioma in the posterior mediastinum: a case report and literature review.

Hemolymphangioma of the thorax is a very rare benign tumor. There were only three reports of this disease until 2016. Herein, we report a case of hemolymphangioma of the thorax with pleural effusion. A 57-year-old woman had been admitted to hospital. Computed tomography also demonstrated a heterogenous mass in the posterior mediastinum and suspected invasion to the artery. Surgery was performed. The mediastinal tumor was soft. The pathological diagnosis was a hemolymphangioma of the posterior mediastinum. Her postoperative course was uneventful and she was discharged on the fifth day after surgery. Major symptoms are chest tightness and short of breath due to the tumor and pleural effusion. However, we experienced a case of hemolymphangioma of the thorax with pleural effusion. This disease is a very rare entity, but should be considered when patients have mass and pleural effusion in the thorax.

Low-dose CT statistical iterative reconstruction via modified MRF regularization.

It is desirable to reduce the excessive radiation exposure to patients in repeated medical CT applications. One of the most effective ways is to reduce the X-ray tube current (mAs) or tube voltage (kVp). However, it is difficult to achieve accurate reconstruction from the noisy measurements. Compared with the conventional filtered back-projection (FBP) algorithm leading to the excessive noise in the reconstructed images, the approaches using statistical iterative reconstruction (SIR) with low mAs show greater image quality. To eliminate the undesired artifacts and improve reconstruction quality, we proposed, in this work, an improved SIR algorithm for low-dose CT reconstruction, constrained by a modified Markov random field (MRF) regularization. Specifically, the edge-preserving total generalized variation (TGV), which is a generalization of total variation (TV) and can measure image characteristics up to a certain degree of differentiation, was introduced to modify the MRF regularization. In addition, a modified alternating iterative algorithm was utilized to optimize the cost function. Experimental results demonstrated that images reconstructed by the proposed method could not only generate high accuracy and resolution properties, but also ensure a higher peak signal-to-noise ratio (PSNR) in comparison with those using existing methods.

Median prior constrained TV algorithm for sparse view low-dose CT reconstruction.

It is known that lowering the X-ray tube current (mAs) or tube voltage (kVp) and simultaneously reducing the total number of X-ray views (sparse view) is an effective means to achieve low-dose in computed tomography (CT) scan. However, the associated image quality by the conventional filtered back-projection (FBP) usually degrades due to the excessive quantum noise. Although sparse-view CT reconstruction algorithm via total variation (TV), in the scanning protocol of reducing X-ray tube current, has been demonstrated to be able to result in significant radiation dose reduction while maintain image quality, noticeable patchy artifacts still exist in reconstructed images. In this study, to address the problem of patchy artifacts, we proposed a median prior constrained TV regularization to retain the image quality by introducing an auxiliary vector m in register with the object. Specifically, the approximate action of m is to draw, in each iteration, an object voxel toward its own local median, aiming to improve low-dose image quality with sparse-view projection measurements. Subsequently, an alternating optimization algorithm is adopted to optimize the associative objective function. We refer to the median prior constrained TV regularization as "TV_MP" for simplicity. Experimental results on digital phantoms and clinical phantom demonstrated that the proposed TV_MP with appropriate control parameters can not only ensure a higher signal to noise ratio (SNR) of the reconstructed image, but also its resolution compared with the original TV method.