Multi-view attribute learning and context relationship encoding enhanced segmentation of lung tumors from CT images.

Graph convolutional neural networks (GCN) have shown the promise in medical image segmentation due to the flexibility of representing diverse range of image regions using graph nodes and propagating knowledge via graph edges. However, existing methods did not fully exploit the various attributes of image nodes and the context relationship among their attributes. We propose a new segmentation method with multi-similarity view enhancement and node attribute context learning (MNSeg). First, multiple views were formed by measuring the similarities among the image nodes, and MNSeg has a GCN based multi-view image node attribute learning (MAL) module to integrate various node attributes learnt from multiple similarity views. Each similarity view contains the specific similarities among all the image nodes, and it was integrated with the node attributes from all the channels to form the enhanced attributes of image nodes. Second, the context relationships among the attributes of image nodes are formulated by a transformer-based context relationship encoding (CRE) strategy to propagate these relationships across all the image nodes. During the transformer-based learning, the relationships were estimated based on the self-attention on all the image nodes, and then they were encoded into the learned node features. Finally, we design an attention at attribute category level (ACA) to discriminate and fuse the learnt diverse information from MAL, CRE, and the original node attributes. ACA identifies the more informative attribute categories by adaptively learn their importance. We validate the performance of MNSeg on a public lung tumor CT dataset and an in-house non-small cell lung cancer (NSCLC) dataset collected from the hospital. The segmentation results show that MNSeg outperformed the compared segmentation methods in terms of spatial overlap and the shape similarities. The ablation studies demonstrated the effectiveness of MAL, CRE, and ACA. The generalization ability of MNSeg was proved by the consistent improved segmentation performances using different 3D segmentation backbones.

Topological structure and global features enhanced graph reasoning model for non-small cell lung cancer segmentation from CT.

Objective.Accurate and automated segmentation of lung tumors from computed tomography (CT) images is critical yet challenging. Lung tumors are of various sizes and locations and have indistinct boundaries adjacent to other normal tissues.Approach.We propose a new segmentation model that can integrate the topological structure and global features of image region nodes to address the challenges. Firstly, we construct a weighted graph with image region nodes. The graph topology reflects the complex spatial relationships among these nodes, and each node has its specific attributes. Secondly, we propose a node-wise topological feature learning module based on a new graph convolutional autoencoder (GCA). Meanwhile, a node information supplementation (GNIS) module is established by integrating specific features of each node extracted by a convolutional neural network (CNN) into each encoding layer of GCA. Afterwards, we construct a global feature extraction model based on multi-layer perceptron (MLP) to encode the features learnt from all the image region nodes which are crucial complementary information for tumor segmentation.Main results.Ablation study results over the public lung tumor segmentation dataset demonstrate the contributions of our major technical innovations. Compared with other segmentation methods, our new model improves the segmentation performance and has generalization ability on different 3D image segmentation backbones. Our model achieved Dice of 0.7827, IoU of 0.6981, and HD of 32.1743 mm on the public dataset 2018 Medical Segmentation Decathlon challenge, and Dice of 0.7004, IoU of 0.5704 and HD of 64.4661 mm on lung tumor dataset from Shandong Cancer Hospital.Significance. The novel model improves automated lung tumor segmentation performance especially the challenging and complex cases using topological structure and global features of image region nodes. It is of great potential to apply the model to other CT segmentation tasks.

Graph based multi-scale neighboring topology deep learning for kidney and tumor segmentation.

Objective.Effective learning and modelling of spatial and semantic relations between image regions in various ranges are critical yet challenging in image segmentation tasks.Approach.We propose a novel deep graph reasoning model to learn from multi-order neighborhood topologies for volumetric image segmentation. A graph is first constructed with nodes representing image regions and graph topology to derive spatial dependencies and semantic connections across image regions. We propose a new node attribute embedding mechanism to formulate topological attributes for each image region node by performing multi-order random walks (RW) on the graph and updating neighboring topologies at different neighborhood ranges. Afterwards, multi-scale graph convolutional autoencoders are developed to extract deep multi-scale topological representations of nodes and propagate learnt knowledge along graph edges during the convolutional and optimization process. We also propose a scale-level attention module to learn the adaptive weights of topological representations at multiple scales for enhanced fusion. Finally, the enhanced topological representation and knowledge from graph reasoning are integrated with content features before feeding into the segmentation decoder.Main results.The evaluation results over public kidney and tumor CT segmentation dataset show that our model outperforms other state-of-the-art segmentation methods. Ablation studies and experiments using different convolutional neural networks backbones show the contributions of major technical innovations and generalization ability.Significance.We propose for the first time an RW-driven MCG with scale-level attention to extract semantic connections and spatial dependencies between a diverse range of regions for accurate kidney and tumor segmentation in CT volumes.

The optimal neoadjuvant chemotherapy regimen for locally advanced gastric and gastroesophageal junction adenocarcinoma: a systematic review and Bayesian network meta-analysis.

BACKGROUND: Neoadjuvant chemotherapy (NAC) for locally advanced gastric and gastroesophageal junction adenocarcinoma (LAGC) has been recommended in several guidelines. However, there is no global consensus about the optimum of NAC regimens. We aimed to determine the optimal NAC regimen for LAGC. METHODS: A systematic review and Bayesian network meta-analysis was performed. The literature search was conducted from inception to June 2022. The odds ratio (OR) value and 95% confidence interval (95% CI) were used for assessment of R0 resection rate and pathological complete response rate (pCR) as primary outcomes. The hazard ratio (HR) value and 95% CI were interpreted for the assessment of overall survival (OS) and disease-free survival (DFS) as second outcomes. The risk ratio (RR) value and 95% CI were used for safety assessment. RESULTS: Twelve randomized controlled trials were identified with 3846 eligible participants. The network plots for R0 resectability, OS, and DFS constituted closed loops. The regimens of TPF (taxane and platinum plus fluoropyrimidine), ECF (epirubicin and cisplatin plus fluorouracil), and PF (platinum plus fluoropyrimidine) showed a meaningful improvement of R0 resectability, as well as OS and/or DFS, compared with surgery (including surgery-alone and surgery plus postoperative adjuvant chemotherapy). Importantly, among these regimens, TPF regimen showed significant superiority in R0 resection rate (versus ECF regimen), OS (versus ECF regimen), DFS (versus PF and ECF regimens), and pCR (versus PF regimen). CONCLUSIONS: The taxane-based triplet regimen of TPF is likely the optimal neoadjuvant chemotherapy regimen for LAGC patients.

Convolutional bi-directional learning and spatial enhanced attentions for lung tumor segmentation.

BACKGROUND AND OBJECTIVE: Accurate lung tumor segmentation from computed tomography (CT) is complex due to variations in tumor sizes, shapes, patterns and growing locations. Learning semantic and spatial relations between different feature channels, image regions and positions is critical yet challenging. METHODS: We propose a new segmentation method, PRCS, by learning and integrating multi-channel contextual relations, and spatial and position dependencies across image regions. Firstly, to extract contextual relationships between different deep image feature tensor channels, we propose a new convolutional bi-directional gated recurrent unit based module for forward and backward learning. Secondly, a novel cross-channel region-level attention mechanism is proposed to discriminate the contributions of different local regions and associated features in the global learning process. Finally, spatial and position dependencies are formulated by a new position-enhanced self-attention mechanism. The new attention can measure the diverse contributions of other positions to a target position and obtain an enhanced adaptive feature vector for the target position. RESULTS: Our model outperformed seven state-of-the-art segmentation methods on both public and in-house lung tumor datasets in terms of spatial overlapping and shape similarity. Ablation study results proved the effectiveness of three technical innovations and generalization ability on different 3D CNN segmentation backbones. CONCLUSION: The proposed model enhanced the learning and propagation of contextual, spatial and position relations in 3D volumes, improving lung tumours' segmentation performance with large variations and indistinct boundaries. PRCS provides an effective automated approach to support precision diagnosis and treatment planning of lung cancer.

Network pharmacology study of Citrus reticulata and Pinellia ternata in the treatment of non-small cell lung cancer.

It has been recognized that Citrus reticulata and Pinellia ternata have a good therapeutic effect on NSCLC. However, the potential mechanism of C. reticulata and P. ternata in the treatment of NSCLC based on network pharmacology analysis is not clear. The "Drug-Component-Target-Disease" network was constructed by Cytoscape, and the protein interaction (PPI) network was constructed by STRING. Our study indicated that 18 active ingredients of C. reticulata and P. Ternata were screened from the TCMSP database, and 56 target genes of C. reticulata and P. Ternata for the treatment of NSCLC were identified, and we constructed the "Drug-Component-Target-Disease" network. In this study, we screened 56 PPI core genes to establish a PPI network. We concluded that the network pharmacology mechanism of the effect of C. reticulata and P. Ternata  on NSCLC may be closely related to the protein expressed by TP53, ESR1, FOS, NCOA3 and MAPK8, and these may play the therapeutic roles by regulating the IL-17 signaling pathway, antigen processing and presentation, microRNAs in cancer and endocrine resistance.

Association of 25-hydroxyvitamin D level with survival outcomes in female breast cancer patients: A meta-analysis.

Conflicting results have been reported on the association of blood vitamin D level with prognosis in women with breast cancer. This meta-analysis aimed to evaluate the association between blood 25-hydroxyvitamin D level and survival outcomes in female breast cancer patients. Two authors independently searched PubMed and Embase databases from their inception to August 25, 2020. Prospective or retrospective cohort studies evaluating the association between blood 25-hydroxyvitamin D level and survival outcomes in women with breast cancer were included. Outcome measures included overall survival (OS), breast cancer-specific survival (BCSS), and disease-free survival (DFS). Twelve studies involving 8574 female breast cancer patients were identified and analyzed. When compared the lowest with the highest category of 25-hydroxyvitamin D level, the pooled adjusted hazard ratio (HR) was 1.57 (95 % confidence interval [CI] 1.35-1.83) for OS, 1.98 (95 % CI 1.55-2.53) for DFS, and 1.44 (95 % CI 1.14-1.81) for BCSS. This meta-analysis indicates that lower blood 25-hydroxyvitamin D level is significantly associated with reduced survival among female breast cancer patients. Additional clinical trials are required to investigate whether vitamin D supplement can improve survival outcomes in these patients.

Nano-realgar suppresses lung cancer stem cell growth by repressing metabolic reprogramming.

BACKGROUND: Recent studies in cancer biology suggest that metabolic glucose reprogramming is a potential target for cancer treatment. However, little is known about drug intervention in the glucose metabolism of cancer stem cells (CSCs) and its related underlying mechanisms. METHODS: The crude realgar powder was Nano-grinded to meets the requirements of Nano-pharmaceutical preparations, and Nano-realgar solution (NRS) was prepared for subsequent experiments. Isolation and characterization of lung cancer stem cells (LCSCs) was performed by magnetic cell sorting (MACS) and immunocytochemistry, respectively. Cell viability and intracellular glucose concentration were detected by MTT assay and glucose oxidase (GOD) kit. Protein expressions related to metabolic reprogramming was detected by ELISA assay. Determination of the expression of HIF-1α and PI3K/Akt/mTOR pathways was carried out by RT-PCR and western blotting analysis. A subcutaneous tumor model in BALB/c-nu mice was successfully established to evaluate the effects of Nano-realgar on tumor growth and histological structure, and the expression of HIF-1α in tumor tissues was measured by immunofluorescence. RESULTS: Nano-realgar inhibits cell viability and induces glucose metabolism in LCSCs, and inhibits protein expression related to metabolic reprogramming in a time- and dose-dependent manner. Nano-realgar downregulated the expression of HIF-1α and PI3K/Akt/mTOR pathways in vitro and in vivo. Nano-realgar inhibits tumor growth and changes the histological structure of tumors through in vivo experiments and consequently inhibits the constitutive activation of HIF-1α signaling. CONCLUSIONS: These results reveal that Nano-realgar inhibits tumor growth in vitro and in vivo by repressing metabolic reprogramming. This inhibitory effect potentially related to the downregulation HIF-1α expression via PI3K/Akt/mTOR pathway.

Apoptosis induction by alantolactone in breast cancer MDA-MB-231 cells through reactive oxygen species-mediated mitochondrion-dependent pathway.

Alantolactone is a sesquiterpene lactone isolated from Inula helenium L. Although alantolactone possesses anti-inflammation and apoptosis-induction activities, the underlying mechanism of anti-cancer effect on human breast cancer cells remains largely unknown. In this study, we explored the possibility of alantolactone as an apoptosis-inducing cytotoxic agent using MDA-MB-231 cells as in vitro model. Alantolactone significantly induced its apoptosis, demonstrated by cell cycle analysis, annexin V-APC/7-AAD double staining and dUTP nick end labeling. Additionally, alantolactone triggered the mitochondrial-mediated caspase cascade apoptotic pathway, which was confirmed by increased Bax/Bcl-2 ratio, loss of MMP, release of cytc from mitochondria to cytoplasm, activation of caspase 9/3, and subsequent cleavage of PARP. Z-VAD-FMK partially prevented apoptosis induced by alantolactone. Alantolactone provoked the production of ROS, while NAC (a scavenger of ROS) reversed alantolactone-mediated depolarization of MMP and apoptosis. Alantolactone modulated the activities of MAPKs. As expected, cotreatment with SB203580, SP600125 or U0126 could reduced the apoptotic rate. Furthermore, alantolactone decreased the protein expressions of p-NF-kB p65 and p-STAT3, increased p-c-Jun level in a dose-dependent manner. These findings suggested that alantolactone possessed anticancer activity via ROS-mediated mitochondrial dysfunction involving MAPK pathway, and had an effect on the transcription factors of NF-kB, AP-1 and STAT3.

Dual-stage deep learning framework for pigment epithelium detachment segmentation in polypoidal choroidal vasculopathy.

Worldwide, polypoidal choroidal vasculopathy (PCV) is a common vision-threatening exudative maculopathy, and pigment epithelium detachment (PED) is an important clinical characteristic. Thus, precise and efficient PED segmentation is necessary for PCV clinical diagnosis and treatment. We propose a dual-stage learning framework via deep neural networks (DNN) for automated PED segmentation in PCV patients to avoid issues associated with manual PED segmentation (subjectivity, manual segmentation errors, and high time consumption).The optical coherence tomography scans of fifty patients were quantitatively evaluated with different algorithms and clinicians. Dual-stage DNN outperformed existing PED segmentation methods for all segmentation accuracy parameters, including true positive volume fraction (85.74 ± 8.69%), dice similarity coefficient (85.69 ± 8.08%), positive predictive value (86.02 ± 8.99%) and false positive volume fraction (0.38 ± 0.18%). Dual-stage DNN achieves accurate PED quantitative information, works with multiple types of PEDs and agrees well with manual delineation, suggesting that it is a potential automated assistant for PCV management.

Saliency-Based Lesion Segmentation Via Background Detection in Dermoscopic Images.

The segmentation of skin lesions in dermoscopic images is a fundamental step in automated computer-aided diagnosis of melanoma. Conventional segmentation methods, however, have difficulties when the lesion borders are indistinct and when contrast between the lesion and the surrounding skin is low. They also perform poorly when there is a heterogeneous background or a lesion that touches the image boundaries; this then results in under- and oversegmentation of the skin lesion. We suggest that saliency detection using the reconstruction errors derived from a sparse representation model coupled with a novel background detection can more accurately discriminate the lesion from surrounding regions. We further propose a Bayesian framework that better delineates the shape and boundaries of the lesion. We also evaluated our approach on two public datasets comprising 1100 dermoscopic images and compared it to other conventional and state-of-the-art unsupervised (i.e., no training required) lesion segmentation methods, as well as the state-of-the-art unsupervised saliency detection methods. Our results show that our approach is more accurate and robust in segmenting lesions compared to other methods. We also discuss the general extension of our framework as a saliency optimization algorithm for lesion segmentation.

DeepGene: an advanced cancer type classifier based on deep learning and somatic point mutations.

BACKGROUND: With the developments of DNA sequencing technology, large amounts of sequencing data have become available in recent years and provide unprecedented opportunities for advanced association studies between somatic point mutations and cancer types/subtypes, which may contribute to more accurate somatic point mutation based cancer classification (SMCC). However in existing SMCC methods, issues like high data sparsity, small volume of sample size, and the application of simple linear classifiers, are major obstacles in improving the classification performance. RESULTS: To address the obstacles in existing SMCC studies, we propose DeepGene, an advanced deep neural network (DNN) based classifier, that consists of three steps: firstly, the clustered gene filtering (CGF) concentrates the gene data by mutation occurrence frequency, filtering out the majority of irrelevant genes; secondly, the indexed sparsity reduction (ISR) converts the gene data into indexes of its non-zero elements, thereby significantly suppressing the impact of data sparsity; finally, the data after CGF and ISR is fed into a DNN classifier, which extracts high-level features for accurate classification. Experimental results on our curated TCGA-DeepGene dataset, which is a reformulated subset of the TCGA dataset containing 12 selected types of cancer, show that CGF, ISR and DNN all contribute in improving the overall classification performance. We further compare DeepGene with three widely adopted classifiers and demonstrate that DeepGene has at least 24% performance improvement in terms of testing accuracy. CONCLUSIONS: Based on deep learning and somatic point mutation data, we devise DeepGene, an advanced cancer type classifier, which addresses the obstacles in existing SMCC studies. Experiments indicate that DeepGene outperforms three widely adopted existing classifiers, which is mainly attributed to its deep learning module that is able to extract the high level features between combinatorial somatic point mutations and cancer types.

A likelihood and local constraint level set model for liver tumor segmentation from CT volumes.

In computed tomography of liver tumors there is often heterogeneous density, weak boundaries, and the liver tumors are surrounded by other abdominal structures with similar densities. These pose limitations to accurate the hepatic tumor segmentation. We propose a level set model incorporating likelihood energy with the edge energy. The minimization of the likelihood energy approximates the density distribution of the target and the multimodal density distribution of the background that can have multiple regions. In the edge energy formulation, our edge detector preserves the ramp associated with the edges for weak boundaries. We compared our approach to the Chan-Vese and the geodesic level set models and the manual segmentation performed by clinical experts. The Chan-Vese model was not successful in segmenting hepatic tumors and our model outperformed the geodesic level set model. Our results on 18 clinical datasets showed that our algorithm had a Jaccard distance error of 14.4 ± 5.3%, relative volume difference of -8.1 ± 2.1%, average surface distance of 2.4 ± 0.8 mm, RMS surface distance of 2.9 ± 0.7 mm, and the maximum surface distance of 7.2 ± 3.1 mm.

A new energy framework with distribution descriptors for image segmentation.

Segmentation of the target object(s) from images that have multiple complicated regions, mixture intensity distributions or are corrupted by noise poses a challenge for the level set models. In addition, the conventional piecewise smooth level set models normally require prior knowledge about the number of image segments. To address these problems, we propose a novel segmentation energy function with two distribution descriptors to model the background and the target. The single background descriptor models the heterogeneous background with multiple regions. Then, the target descriptor takes into account the intensity distribution and incorporates local spatial constraint. Our descriptors, which have more complete distribution information, construct the unique energy function to differentiate the target from the background and are more tolerant of image noise. We compare our approach to three other level set models: 1) the Chan-Vese; 2) the multiphase level set; and 3) the geodesic level set. This comparison using 260 synthetic images with varying levels and types of image noise and medical images with more complicated backgrounds showed that our method outperforms these models for accuracy and immunity to noise. On an additional set of 300 synthetic images, our model is also less sensitive to the contour initialization as well as to different types and levels of noise.

Automated liver segmentation for whole-body low-contrast CT images from PET-CT scanners.

Accurate objective automated liver segmentation in PET-CT studies is important to improve the identification and localization of hepatic tumor. However, this segmentation is an extremely challenging task from the low-contrast CT images captured from PET-CT scanners because of the intensity similarity between liver and adjacent loops of bowel, stomach and muscle. In this paper, we propose a novel automated three-stage liver segmentation technique for PET-CT whole body studies, where: 1) the starting liver slice is automatically localized based on the liver - lung relations; 2) the "masking" slice containing the biggest liver section is localized using the ratio of liver ROI size to the right half of abdomen ROI size; 3) the liver segmented from the "masking" slice forms the initial estimation or mask for the automated liver segmentation. Our experimental results from clinical PET-CT studies show that this method can automatically segment the liver for a range of different patients, with consistent objective selection criteria and reproducible accurate results.