SG-Transunet: A segmentation-guided Transformer U-Net model for KRAS gene mutation status identification in colorectal cancer.

Accurately identifying the Kirsten rat sarcoma virus (KRAS) gene mutation status in colorectal cancer (CRC) patients can assist doctors in deciding whether to use specific targeted drugs for treatment. Although deep learning methods are popular, they are often affected by redundant features from non-lesion areas. Moreover, existing methods commonly extract spatial features from imaging data, which neglect important frequency domain features and may degrade the performance of KRAS gene mutation status identification. To address this deficiency, we propose a segmentation-guided Transformer U-Net (SG-Transunet) model for KRAS gene mutation status identification in CRC. Integrating the strength of convolutional neural networks (CNNs) and Transformers, SG-Transunet offers a unique approach for both lesion segmentation and KRAS mutation status identification. Specifically, for precise lesion localization, we employ an encoder-decoder to obtain segmentation results and guide the KRAS gene mutation status identification task. Subsequently, a frequency domain supplement block is designed to capture frequency domain features, integrating it with high-level spatial features extracted in the encoding path to derive advanced spatial-frequency domain features. Furthermore, we introduce a pre-trained Xception block to mitigate the risk of overfitting associated with small-scale datasets. Following this, an aggregate attention module is devised to consolidate spatial-frequency domain features with global information extracted by the Transformer at shallow and deep levels, thereby enhancing feature discriminability. Finally, we propose a mutual-constrained loss function that simultaneously constrains the segmentation mask acquisition and gene status identification process. Experimental results demonstrate the superior performance of SG-Transunet over state-of-the-art methods in discriminating KRAS gene mutation status.

Health related quality of life in pediatric hematological malignancies patients and survivors: A meta-analysis of comparative studies.

BACKGROUND: Pediatric patients with hematologic malignancies (HM) and survivors are at high risk for numerous negative effects including decreased health-related quality of life (HRQOL). In order to understand the association between HM and QOL, we conducted this meta-analysis to systematically compare QOL between pediatric HM patients and survivors and controls. METHOD: The PubMed, EMBASE, Web of Science and the Cochrane Library databases were systematically searched. Data were analyzed using the random-effects model. RESULTS: Of 6586 unique articles identified, 30 were included in this meta-analysis. Studies described 12 different HRQOL tools. Different QOL measures varied in their association with quality of life. When compared with Non-HM group, the Pediatric Quality of Life Inventory (PedsQL) has a moderate effect size (standard mean difference, SMD = 0.50, 95% CI: 0.32, 0.68; P < 0.001). When compared with health controls, it has a large effect size (SMD = -1.00, 95% CI: -1.47, -0.53; P < 0.001). In addition, Health utilities index mark (HUI), and the Pediatric Oncology Quality of Life Scale (POQOLS) have a large (SMD = -0.81, 95% CI: -1.29, -0.33; P = 0.001) and a small (SMD = -0.10, 95% CI: -0.42, 0.22; P = 0.534) effect sizes when comparing overall controls. CONCLUSION: Pediatric HM patients and survivors had lower QOL compared with healthy controls and higher QOL compared with Non-HM controls in most domains. Considering the negative impact of poor QOL on daily life and functional outcomes, future research should focus on proposing effective measures to improve QOL of this population.

Triad3A-Mediated K48-Linked ubiquitination and degradation of TLR9 impairs mitochondrial bioenergetics and exacerbates diabetic cardiomyopathy.

INTRODUCTION: Targeted protein degradation represents a promising therapeutic approach, while diabetic cardiomyopathy (DCM) arises as a consequence of aberrant insulin secretion and impaired glucose and lipid metabolism in the heart.. OBJECTIVES: Considering that the Toll-like receptor 9 (TLR9) signaling pathway plays a pivotal role in regulating energy metabolism, safeguarding cardiomyocytes, and influencing glucose uptake, the primary objective of this study was to investigate the impact of TLR9 on diabetic cardiomyopathy (DCM) and elucidate its underlying mechanism. METHODS: Mouse model of DCM was established using intraperitoneal injection of STZ, and mice were transfected with adeno-associated virus serotype 9-TLR9 (AAV9-TLR9) to assess the role of TLR9 in DCM. To explore the mechanism of TLR9 in regulating DCM disease progression, we conducted interactome analysis and employed multiple molecular approaches. RESULTS: Our study revealed a significant correlation between TLR9 expression and mouse DCM. TLR9 overexpression markedly mitigated cardiac dysfunction, myocardial fibrosis, oxidative stress, and apoptosis in DCM, while inflammation levels remained relatively unaffected. Mechanistically, TLR9 overexpression positively modulated mitochondrial bioenergetics and activated the AMPK-PGC1a signaling pathway. Furthermore, we identified Triad3A as an interacting protein that facilitated TLR9's proteasomal degradation through K48-linked ubiquitination. Inhibiting Triad3A expression improved cardiac function and pathological changes in DCM by enhancing TLR9 activity. CONCLUSIONS: The findings of this study highlight the critical role of TLR9 in maintaining cardiac function and mitigating pathological alterations in diabetic cardiomyopathy. Triad3A-mediated regulation of TLR9 expression and function has significant implications for understanding the pathogenesis of DCM. Targeting TLR9 and its interactions with Triad3A may hold promise for the development of novel therapeutic strategies for diabetic cardiomyopathy. Further research is warranted to fully explore the therapeutic potential of TLR9 modulation in the context of cardiovascular diseases.

Association of cooking fuel use with risk of cancer and all-cause mortality among Chinese elderly people: a prospective cohort study.

When cooking with biomass and fossil fuels, their incomplete burning can lead to air pollution, which can trigger pernicious effects on people's health, especially among the elderly, who are more vulnerable to toxic and harmful environmental damage. This study explored the association between different cooking fuel types and the risk of cancer and all-cause mortality among seniors constructing Cox regression models. Data were obtained by linking waves of 6, 7, and 8 of the Chinese Longitudinal Healthy Longevity Survey, which included a total of 7269 participants who were 65 years old and over. Cooking fuels were categorized as either biomass, fossil, or clean fuels. And the effects of switching cooking fuels on death risk were also investigated using Cox regression models. The results indicate that, compared with the users of clean fuels, individuals using biomass or fossil fuels were at a greater death risk for cancer [HR (95% CI): biomass, 1.13 (1.05-1.20); fossil, 1.16 (1.06-1.25)] and all causes [HR (95% CI): biomass, 1.29 (1.16-1.42); fossil, 1.32 (1.22-1.50)]. Furthermore, compared with sustained users of biomass fuels, individuals converting from biomass to clean fuels significantly reduced death risk for cancer [HR (95% CI): 0.81 (0.72-0.95)] and all causes [HR (95% CI): 0.76 (0.64-0.93)]. Similarly, all-cause death risk [HR (95% CI): 0.77 (0.62-0.93)] was noticeably reduced among these participants converting from fossil to clean fuels than persistent users of fossil fuels. Subgroup analyses revealed that males had a greater cancer and all-cause death risk when exposed to unclean fuels. These findings can inform the development of policies and the implementation of measures related to cooking fuel use to promote the health of older people and reduce the burden of disease on society.

Multi-scale dense selective network based on border modeling for lung nodule segmentation.

PURPOSE: Accurate quantification of pulmonary nodules helps physicians to accurately diagnose and treat lung cancer. We try to improve the segmentation efficiency of irregular nodules while maintaining the segmentation accuracy of simple types of nodules. METHODS: In this paper, we obtain the unique edge part of pulmonary nodules and process it as a single branch stream, i.e., border stream, to explicitly model the nodule edge information. We propose a multi-scale dense selective network based on border modeling (BorDenNet). Its overall framework consists of a dual-branch encoder-decoder, which achieves parallel processing of classical image stream and border stream. We design a dense attention module to facilitate a strongly coupled status of feature images to focus on key regions of pulmonary nodules. Then, during the process of model decoding, the multi-scale selective attention module is proposed to establish long-range correlation relationships between different scale features, which further achieves finer feature discrimination and spatial recovery. We introduce border context enhancement module to mutually fuse and enhance the edge-related voxel features contained in the image stream and border stream and finally achieve the accurate segmentation of pulmonary nodules. RESULTS: We evaluate the BorDenNet rigorously on the lung public dataset LIDC-IDRI. For the segmentation of the target nodules, the average Dice score is 92.78[Formula: see text], the average sensitivity is 91.37[Formula: see text], and the average Hausdorff distance is 3.06 mm. We further test on a private dataset from Shanxi Provincial People's Hospital, which verifies the excellent generalization of BorDenNet. Our BorDenNet relatively improves the segmentation efficiency for multi-type nodules such as adherent pulmonary nodules and ground-glass pulmonary nodules. CONCLUSION: Accurate segmentation of irregular pulmonary nodules can obtain important clinical parameters, which can be used as a guide for clinicians and improve clinical efficiency.

Static-Dynamic coordinated Transformer for Tumor Longitudinal Growth Prediction.

Accurate prediction of the tumor's future imaging features can provide its complete growth evolution and more detailed clinical parameters. The existing longitudinal models tend to lose detailed growth information and make it difficult to model the complete tumor development process. In this paper, we propose the Static-Dynamic coordinated Transformer for Tumor Longitudinal Growth Prediction (SDC-Transformer). To extract the static high-level features of tumors in each period, and to further explore the dynamic growth associations and expansion trend of tumors between different periods. Aiming at the insensitivity to local pixel information of the Transformer, we propose the Local Adaptive Transformer Module to facilitate a strongly coupled status of feature images, which ensures the characterization of tumor complex growth trends. Faced with the dynamic changes brought about by tumor growth, we introduce the Dynamic Growth Estimation Module to predict the future growth trend of the tumor. As a core part of SDC-Transformer, we design the Enhanced Deformable Convolution to enrich the sampling space of tumor growth pixels. And a novel Cascade Self-Attention is performed under multi-growth imaging to obtain dynamic growth relationships between periods and use dual cascade operations to predict the tumor's future expansion trajectories and growth contours. Our SDC-Transformer is rigorously trained and tested on longitudinal tumor data composed of the National Lung Screening Trial (NLST) and collaborative Shanxi Provincial People's Hospital. The RMSE, Dice, Recall, and Specificity of the longitudinal prediction results reach 11.32, 89.31%, 90.57%, and 89.64%, respectively. This result shows that our proposed SDC-Transformer model can achieve accurate longitudinal prediction of tumors, which will help physicians to establish specific treatment plans and accurately diagnose lung cancer. The code will be released soon.

A multitask dual-stream attention network for the identification of KRAS mutation in colorectal cancer.

PURPOSE: It is of great significance to accurately identify the KRAS gene mutation status for patients in tumor prognosis and personalized treatment. Although the computer-aided diagnosis system based on deep learning has gotten all-round development, its performance still cannot meet the current clinical application requirements due to the inherent limitations of small-scale medical image data set and inaccurate lesion feature extraction. Therefore, our aim is to propose a deep learning model based on T2 MRI of colorectal cancer (CRC) patients to identify whether KRAS gene is mutated. METHODS: In this research, a multitask attentive model is proposed to identify KRAS gene mutations in patients, which is mainly composed of a segmentation subnetwork and an identification subnetwork. Specifically, at first, the features extracted by the encoder of segmentation model are used as guidance information to guide the two attention modules in the identification network for precise activation of the lesion area. Then the original image of the lesion and the segmentation result are concatenated for feature extraction. Finally, features extracted from the second step are combined with features activated by the attention modules to identify the gene mutation status. In this process, we introduce the interlayer loss function to encourage the similarity of the two subnetwork parameters and ensure that the key features are fully extracted to alleviate the overfitting problem caused by small data set to some extent. RESULTS: The proposed identification model is benchmarked primarily using 15-fold cross validation. Three hundred and eighty-two images from 36 clinical cases were used to test the model. For the identification of KRAS mutation status, the average accuracy is 89.95 ± 1.23%, the average sensitivity is 89.29 ± 1.79%, the average specificity is 90.53 ± 2.45%, and the average area under the curve (AUC) is 95.73 ± 0.52%. For segmentation of lesions, the average dice is 88.11 ± 0.86%. CONCLUSIONS: We developed a novel deep learning-based model to identify the KRAS status in CRC. We demonstrated the excellent properties of the proposed identification through comparison with ground truth gene mutation status of 36 clinical cases. And all these results show that the novel method has great potential for clinical application.

Elevated LINC00909 Promotes Tumor Progression of Ovarian Cancer via Regulating the miR-23b-3p/MRC2 Axis.

Ovarian cancer (OC), the third common gynecologic malignancy, contributes to the most cancer-caused mortality in women. However, 70% of patients with OC are diagnosed at an advanced stage, of which the 5-year survival is less than 30%. Long noncoding RNAs (long ncRNAs or lncRNA), a type of RNA with exceeding 200 nucleotides in length but no protein-coding capability, have been demonstrated to involve the pathogenesis of various cancers and show considerable potential in the diagnosis of OC. In this study, we found that the LINC00909 expression in tumor and serum specimens of OC patients was elevated, determined by real-time quantitative, and droplet digital PCR. In receiver operating characteristic (ROC) analysis, our results revealed that serum LINC00909 distinguished cancers from normal ovarian tissue with 87.8% of sensitivity and 69.6% of specificity (AUC, 81.2%) and distinguished serous ovarian cancer from normal ovarian tissue with 90.0% of sensitivity and 75.9% of specificity (AUC, 84.5%). Furthermore, we observed that the tumor and serum LINC00909 level was positively associated with the International Federation of Gynecology and Obstetrics (FIGO) stage and the Eastern Cooperative Oncology Group (ECOG) score (reflecting patients' performance status). Also, patients with low serum LINC00909 level showed a longer overall (hazard ratio, HR = 1.874, p = 0.0004) and progression-free (HR = 1.656, p = 0.0017) survival. Functional assays indicated that the elevation of LINC00909 expression contributes to cell proliferation, migration, and invasion capability of ovarian cancer cells. Besides, we demonstrated that LINC00909 functions as a competing endogenous RNA (ceRNA) of MRC2 mRNA by sponging miR-23-3p, and thereby promotes epithelial-to-mesenchymal transition (EMT) of ovarian cancer cells. Therefore, we highlight that the LINC00909/miR-23b-3p/MRC2 axis is implicated in the pathogenesis of ovarian cancer, and serum LINC00909 may be a promising biomarker for the diagnosis of OC.

Spatial-Frequency dual-branch attention model for determining KRAS mutation status in colorectal cancer with T2-weighted MRI.

BACKGROUND AND OBJECTIVE: Identifying the KRAS mutation status accurately in medical images is very important for the diagnosis and treatment of colorectal cancer. Despite the substantial progress achieved by existing methods, it remains challenging due to limited annotated dataset, large intra-class variances, and a high degree of inter-class similarities. METHODS: To tackle these challenges, we propose a spatial-frequency dual-branch attention model (SF-DBAM) to determine the KRAS mutation status of colorectal cancer patients using a limited T2-weighted MRI dataset. The dataset contains 169 wild-type patients (2151 images) and 137 mutation-type patients (1666 images). The first branch utilizes part of the pre-trained Xception model to capture spatial-domain information and alleviate the small-scale dataset problem. The second branch builds frequency-domain information into cube columns using block-based discrete cosine transform and channel rearrangement. Then the cube columns are fed into convolutional long short-term memory (convLSTM) to explore the effective information between the reconstructed frequency-domain channels. Also, we design a channel enhanced attention module (CEAM) at the end of each branch to make them focus on the lesion areas. Finally, we concatenate the two branches and output the classified results through fully connected layers. RESULTS: The proposed method achieves 88.03% overall accuracy with AUC of 94.27% and specificity of 90.75% in 10-fold cross-validation, which is better than the current non-invasive methods for determining KRAS mutation status. CONCLUSIONS: We believe that the proposed method can assist physicians to diagnose the KRAS mutation status in patients with colorectal cancer, and other medical problems can benefit from the spatial and frequency domains information.

Metformin Antagonizes Ovarian Cancer Cells Malignancy Through MSLN Mediated IL-6/STAT3 Signaling.

BACKGROUND: Ovarian cancer is the most lethal gynecological malignancy, and chemotherapy remains the cornerstone for ovarian cancer management. Due to the unsatisfactory prognosis, a better understanding of the underlying molecular carcinogenesis is urgently required. METHODS: Assays for determining cell growth, cell motility, and apoptosis were employed to evaluate the potential antitumor effects of metformin against ovarian cancer cells. Molecular biological methods were employed to explore the underlying mechanism. Human ovarian cancer samples and Gene Expression Profiling Interactive Analysis (GEPIA) dataset were used for uncovering the clinical significances of mesothelin (MSLN) on ovarian cancer. RESULTS: In the present work, we found that metformin treatment led to cell growth and cell migration inhibition, and induced cell apoptosis. Metformin administration also impaired cancer cell stemness and the capillary-like structure formation capacity of SKOV3 cells. On mechanism, metformin treatment remarkably reduced mesothelin (MSLN) expression, downregulated IL-6/STAT3 signaling activity, subsequently resulted in VEGF and TGFß1 expression. We also observed an oncogenic function of MSLN on ovarian cancer. CONCLUSIONS: Collectively, our findings suggested that metformin exerts anticancer effects by suppressing ovarian cancer cell malignancy, which attributed to MSLN inhibition mediated IL6/STAT3 signaling and VEGF and TGFß1 downregulation.

Multi-channel multi-task deep learning for predicting EGFR and KRAS mutations of non-small cell lung cancer on CT images.

BACKGROUND: Predicting the mutation statuses of 2 essential pathogenic genes [epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma (KRAS)] in non-small cell lung cancer (NSCLC) based on CT is valuable for targeted therapy because it is a non-invasive and less costly method. Although deep learning technology has realized substantial computer vision achievements, CT imaging being used to predict gene mutations remains challenging due to small dataset limitations. METHODS: We propose a multi-channel and multi-task deep learning (MMDL) model for the simultaneous prediction of EGFR and KRAS mutation statuses based on CT images. First, we decomposed each 3D lung nodule into 9 views. Then, we used the pre-trained inception-attention-resnet model for each view to learn the features of the nodules. By combining 9 inception-attention-resnet models to predict the types of gene mutations in lung nodules, the models were adaptively weighted, and the proposed MMDL model could be trained end-to-end. The MMDL model utilized multiple channels to characterize the nodule more comprehensively and integrate patient personal information into our learning process. RESULTS: We trained the proposed MMDL model using a dataset of 363 patients collected by our partner hospital and conducted a multi-center validation on 162 patients in The Cancer Imaging Archive (TCIA) public dataset. The accuracies for the prediction of EGFR and KRAS mutations were, respectively, 79.43% and 72.25% in the training dataset and 75.06% and 69.64% in the validation dataset. CONCLUSIONS: The experimental results demonstrated that the proposed MMDL model outperformed the latest methods in predicting EGFR and KRAS mutations in NSCLC.

MicroRNA-155 expression inversely correlates with pathologic stage of gastric cancer and it inhibits gastric cancer cell growth by targeting cyclin D1.

PURPOSE: MicroRNAs (miRs) have been frequently reported dysregulating in tumors and playing a crucial role in tumor development and progression. However, the expression of miR-155 and its role in gastric cancer (GC) are still obscure. METHODS: qRT-PCR was applied to detect miR-155 expression in 60 matched GC samples and four GC cell lines, and the relationship between miR-155 levels and clinicopathological features of GC was analyzed. Next, the effects of miR-155 on GC cell growth were evaluated by gain- and loss-of-function analysis. Finally, the target gene(s) of miR-155 in GC cells were explored. RESULTS: Our results revealed that miR-155 levels were significantly lower in both GC tissues and GC cell lines than in their normal controls, and its expression inversely correlated with tumor size and the pathologic stage. Moreover, our study showed that enforced expression of miR-155 impaired GC cell proliferation, promoted G1 phase arrest and induced apoptosis in vitro. In addition, we identified cyclin D1 as the direct target of miR-155, and knockdown of cyclin D1 partially phenocopied the role of miR-155 in GC cells. CONCLUSIONS: Our findings suggest that miR-155 may act as a potential diagnostic marker for early-stage GC and may represent a novel therapeutic target for GC treatment.

CYP1A1 genetic polymorphisms and uterine leiomyoma risk: a meta-analysis.

BACKGROUND: Some studies assessed the association between CYP1A1 MspI and Ile462Val polymorphisms and uterine leiomyoma (UL) risk. However, the results were controversial. We did this meta-analysis to determine the association between CYP1A1 MspI and Ile462Val polymorphisms and UL risk. MATERIALS AND METHODS: We searched databases containing PubMed, Springer Link, EMBASE, Chinese National Knowledge Infrastructure (CNKI) up to 11 October 2014. Pooled ORs and 95% CIs were used to assess the strength of the associations. RESULTS: In total, 9 case-control studies with 2157 UL cases and 2197 healthy controls were included in this meta-analysis. CYP1A1 Ile462Val polymorphism was significantly associated with UL risk (OR = 2.29, 95% CI 1.75-2.99, P < 0.00001). In the subgroup analysis by race, significantly increased risks were found in the Asians (OR = 2.76, 95% CI 1.86-4.09, P < 0.00001) and Caucasians (OR = 1.87, 95% CI 1.30-2.68, P = 0.0007). However, MspI polymorphism was not significantly associated with UL risk (OR = 1.15, 95% CI 0.90-1.47, P = 0.27). In the subgroup analysis by race, no significant association was found in the Asians (OR = 1.15, 95% CI 0.86-1.54, P = 0.35). CONCLUSION: In summary, the results of the meta-analysis suggested that CYP1A1 Ile462Val polymorphism was significantly associated with UL risk.

MicroRNA-155 induces differentiation of RAW264.7 cells into dendritic-like cells.

MicroRNA (miRNA, miR)-155 is the most promising pro-inflammatory miRNA molecule. Lipopolysaccharide (LPS) and oxidized low-density lipoprotein (oxLDL) are the most well-known foreign antigens, initiating immune responses against infection and the development of atherosclerosis (AS), respectively. To explore whether miR-155 is involved in regulating LPS- and oxLDL-initiated inflammations, we investigated the level of miR-155 in both LPS- and oxLDL-treated RAW264.7 cells, assessed whether miR-155 induce morphologic changes of the cells and how did it regulate the production of surface markers and cytokines. The results showed that the level of miR-155 was significantly increased by LPS and was modestly increased by oxLDL. Moreover, RAW264.7 cells displayed morphological transformations from macrophage-like cells into DC-like cells when miR-155 was over-expressed. Furthermore, the gain- and loss-of-function studies demonstrated that miR-155 induced the expression of the surface markers (including MHC-II, MHC-I, CD86, and CD83) and pro-inflammatory cytokines (including interleukin (IL)-12, IL-6, and IL-1b) in both LPS- and oxLDL-treated RAW264.7 cells. Additionally, miR-155 induced the expression of CD36 in oxLDL-treated RAW264.7 cells. In conclusion, up-regulated miR-155 is able to induce morphological and phenotypic changes, and the expression of pro-inflammatory cytokines in both LPS- and oxLDL-treated RAW264.7 cells. Therefore, our study suggests that miR-155 is one important regulator involved in enhancing both LPS- and oxLDL-initiated inflammations, which is critical for the progression of immune responses as well as for the development of AS.