Unsupervised stain augmentation enhanced glomerular instance segmentation on pathology images.

PURPOSE: In pathology images, different stains highlight different glomerular structures, so a supervised deep learning-based glomerular instance segmentation model trained on individual stains performs poorly on other stains. However, it is difficult to obtain a training set with multiple stains because the labeling of pathology images is very time-consuming and tedious. Therefore, in this paper, we proposed an unsupervised stain augmentation-based method for segmentation of glomerular instances. METHODS: In this study, we successfully realized the conversion between different staining methods such as PAS, MT and PASM by contrastive unpaired translation (CUT), thus improving the staining diversity of the training set. Moreover, we replaced the backbone of mask R-CNN with swin transformer to further improve the efficiency of feature extraction and thus achieve better performance in instance segmentation task. RESULTS: To validate the method presented in this paper, we constructed a dataset from 216 WSIs of the three stains in this study. After conducting in-depth experiments, we verified that the instance segmentation method based on stain augmentation outperforms existing methods across all metrics for PAS, PASM, and MT stains. Furthermore, ablation experiments are performed in this paper to further demonstrate the effectiveness of the proposed module. CONCLUSION: This study successfully demonstrated the potential of unsupervised stain augmentation to improve glomerular segmentation in pathology analysis. Future research could extend this approach to other complex segmentation tasks in the pathology image domain to further explore the potential of applying stain augmentation techniques in different domains of pathology image analysis.

Realization of high-performance biosensor through sandwich analysis utilizing weak value amplification.

A label-free optical sandwich immunoassay sensor, utilizing weak value amplification and total internal reflection, was devised for real-time, high-sensitivity analysis and detection of low-concentration targets. 3D printed channels and sodium chloride solution were employed to ensure reproducibility, reliability, and stability of the measurements for calibration. The sandwich structure demonstrated enhanced responsiveness in the proposed optical biosensor through a comparative analysis of the direct assay and sandwich assay for detecting alpha-fetoprotein (AFP) at the same concentration. By optimizing the binding sequences of the coating antibody, target, and detection antibody in the sandwich method, a more suitable sandwich sensing approach based on weak value amplification was achieved. With this approach, the limit of detection (LOD) of 6.29 ng/mL (pM level) for AFP in PBS solution was achieved. AFP testing and regeneration experiments in human serum have proved the feasibility of our methods in detecting complex samples and the reusability of sensing chips. Additionally, the method demonstrated excellent selectivity for unpaired antigens. The efficacy of this methodology was evaluated by simultaneously detecting AFP, carcinoembryonic antigen (CEA), and CA15-3 on a singular sensor chip. In conclusion, the label-free sandwich immunoassay sensing scheme holds promise for advancing the proposed optical sensors based on weak value amplification in early diagnosis and prevention applications. Compared to other biomarker detection methods, it will be easier to promote in practical applications.

Global attention based GNN with Bayesian collaborative learning for glomerular lesion recognition.

BACKGROUND: Glomerular lesions reflect the onset and progression of renal disease. Pathological diagnoses are widely regarded as the definitive method for recognizing these lesions, as the deviations in histopathological structures closely correlate with impairments in renal function. METHODS: Deep learning plays a crucial role in streamlining the laborious, challenging, and subjective task of recognizing glomerular lesions by pathologists. However, the current methods treat pathology images as data in regular Euclidean space, limiting their ability to efficiently represent the complex local features and global connections. In response to this challenge, this paper proposes a graph neural network (GNN) that utilizes global attention pooling (GAP) to more effectively extract high-level semantic features from glomerular images. The model incorporates Bayesian collaborative learning (BCL), enhancing node feature fine-tuning and fusion during training. In addition, this paper adds a soft classification head to mitigate the semantic ambiguity associated with a purely hard classification. RESULTS: This paper conducted extensive experiments on four glomerular datasets, comprising a total of 491 whole slide images (WSIs) and 9030 images. The results demonstrate that the proposed model achieves impressive F1 scores of 81.37%, 90.12%, 87.72%, and 98.68% on four private datasets for glomerular lesion recognition. These scores surpass the performance of the other models used for comparison. Furthermore, this paper employed a publicly available BReAst Carcinoma Subtyping (BRACS) dataset with an 85.61% F1 score to further prove the superiority of the proposed model. CONCLUSION: The proposed model not only facilitates precise recognition of glomerular lesions but also serves as a potent tool for diagnosing kidney diseases effectively. Furthermore, the framework and training methodology of the GNN can be adeptly applied to address various pathology image classification challenges.

Introducing π-HelixNovo for practical large-scale de novo peptide sequencing.

De novo peptide sequencing is a promising approach for novel peptide discovery, highlighting the performance improvements for the state-of-the-art models. The quality of mass spectra often varies due to unexpected missing of certain ions, presenting a significant challenge in de novo peptide sequencing. Here, we use a novel concept of complementary spectra to enhance ion information of the experimental spectrum and demonstrate it through conceptual and practical analyses. Afterward, we design suitable encoders to encode the experimental spectrum and the corresponding complementary spectrum and propose a de novo sequencing model $\pi$-HelixNovo based on the Transformer architecture. We first demonstrated that $\pi$-HelixNovo outperforms other state-of-the-art models using a series of comparative experiments. Then, we utilized $\pi$-HelixNovo to de novo gut metaproteome peptides for the first time. The results show $\pi$-HelixNovo increases the identification coverage and accuracy of gut metaproteome and enhances the taxonomic resolution of gut metaproteome. We finally trained a powerful $\pi$-HelixNovo utilizing a larger training dataset, and as expected, $\pi$-HelixNovo achieves unprecedented performance, even for peptide-spectrum matches with never-before-seen peptide sequences. We also use the powerful $\pi$-HelixNovo to identify antibody peptides and multi-enzyme cleavage peptides, and $\pi$-HelixNovo is highly robust in these applications. Our results demonstrate the effectivity of the complementary spectrum and take a significant step forward in de novo peptide sequencing.

DeepTree: Pathological Image Classification Through Imitating Tree-Like Strategies of Pathologists.

Digitization of pathological slides has promoted the research of computer-aided diagnosis, in which artificial intelligence analysis of pathological images deserves attention. Appropriate deep learning techniques in natural images have been extended to computational pathology. Still, they seldom take into account prior knowledge in pathology, especially the analysis process of lesion morphology by pathologists. Inspired by the diagnosis decision of pathologists, we design a novel deep learning architecture based on tree-like strategies called DeepTree. It imitates pathological diagnosis methods, designed as a binary tree structure, to conditionally learn the correlation between tissue morphology, and optimizes branches to finetune the performance further. To validate and benchmark DeepTree, we build a dataset of frozen lung cancer tissues and design experiments on a public dataset of breast tumor subtypes and our dataset. Results show that the deep learning architecture based on tree-like strategies makes the pathological image classification more accurate, transparent, and convincing. Simultaneously, prior knowledge based on diagnostic strategies yields superior representation ability compared to alternative methods. Our proposed methodology helps improve the trust of pathologists in artificial intelligence analysis and promotes the practical clinical application of pathology-assisted diagnosis.

Polyamine-producing bacteria inhibit the absorption of Cd by spinach and alter the bacterial community composition of rhizosphere soil.

Polyamines (PAs) are small aliphatic nitrogenous bases with strong biological activity that participate in plant stress response signaling and the alleviation of damage from stress. Herein, the effects of the PA-producing bacterium Bacillus megaterium N3 and PAs on the immobilization of Cd and inhibition of Cd absorption by spinach and the underlying mechanisms were studied. A solution test showed that strain N3 secreted spermine and spermidine in the presence of Cd. Both strain N3 and the PAs (spermine+spermidine) immobilized Cd and increased the pH of the solution. Untargeted metabolomics results showed that strain N3 secreted PAs, N1-acetylspermidine, 3-indolepropionic acid, indole-3-acetaldehyde, cysteinyl-gamma-glutamate, and choline, which correlated with plant growth promotion and Cd immobilization. A pot experiment showed that rhizosphere soil inoculation with strain N3 and PAs improved spinach dry weight and reduced spinach Cd absorption compared with the control. These positive effects were likely due to the increase in rhizosphere soil pH and NH4+-N and PA contents, which can be attributed primarily to Cd immobilization. Moreover, inoculation with strain N3 more effectively inhibited the absorption of Cd by spinach than spraying PAs, mainly because strain N3 enabled a better relative abundance of bacteria (Microvirga, Pedobacter, Bacillus, Brevundimonas, Pseudomonas, Serratia, Devosid, and Aminobacter), that have been reported to have the ability to resist heavy metals and produce PAs. Strain N3 regulated the structure of rhizosphere functional bacterial communities and inhibited Cd uptake by spinach. These results provide a theoretical basis for the prevention of heavy metal absorption by vegetables using PA-producing bacteria.

Effects of atorvastatin in suppressing pulmonary vascular remodeling in rats with chronic obstructive pulmonary disease.

OBJECTIVE: To investigate the effects of atorvastatin calcium on pulmonary vascular remodeling, the authors explored the regulatory mechanism of Histone Deacetylation Enzyme-2 (HDAC2) in rats with Chronic Obstructive Pulmonary Disease (COPD), and provided a new direction for drug treatment in the progression of vascular remodeling. METHODS: Eighteen female SD rats were randomly divided into control (Group S1), COPD (Group S2), and atorvastatin calcium + COPD (Group S3) groups. A COPD rat model was established by passive smoking and intratracheal injection of Lipopolysaccharide (LPS). Haematoxylin and eosin staining and Victoria Blue + Van Gibson staining were used to observe pathological changes in the lung tissue. The pulmonary vascular inflammation score was calculated, and the degree of pulmonary vascular remodeling was evaluated. The ratio of Muscular Arteries in lung tissue (MA%), the ratio of the vessel Wall Area to the vessel total area (WA%), and the ratio of the vessel Wall Thickness to the vascular outer diameter (WT%) were measured using imaging software. The expression of HDAC2 was measured using western blotting, ELISA (Enzyme-Linked Immunosorbent Assay), and qPCR (Real-time PCR). RESULTS: Compared with the control group, the degree of pulmonary vascular inflammation and pulmonary vascular remodeling increased in rats with COPD. The WT%, WA%, and lung inflammation scores increased significantly; the expression of HDAC2 and HDAC2mRNA in the serum and lung tissue decreased, and the level of Vascular Endothelial Growth Factor (VEGF) in the lung tissues increased (p < 0.05). Compared with the COPD group, the lung tissues from rats in the atorvastatin group had fewer inflammatory cells, and the vascular pathological changes were significantly relieved. The WT%, WA%, and lung inflammation scores decreased significantly; the expression of HDAC2 and HDAC2mRNA in the serum and lung tissues increased, and the level of VEGF in the lung tissues decreased (p < 0.05). CONCLUSION: The present study revealed that atorvastatin calcium could regulate the contents and expression of HDAC2 in serum and lung tissues and inhibit the production of VEGF, thereby regulating pulmonary vascular remodeling in a rat model with COPD.

Differential Responses of Bacterial and Fungal Communities to Siderophore Supplementation in Soil Affected by Tobacco Bacterial Wilt (Ralstonia solanacearum).

Siderophores secreted by microorganisms can promote ecological efficiency and could be used to regulate the unbalanced microbial community structure. The influence of the siderophore activity of Trichoderma yunnanense strain 2-14F2 and Beauveria pseudobassiana strain (2-8F2) on the physiological/biochemical functions and community structure of soil microbes affected by tobacco bacterial wilt (TBW) was studied. DNS Colorimetry and Biolog-eco plates were used to quantify the impacts of strain siderophores on soil enzyme activities and microbial metabolism. Based on Illumina MiSeq high-throughput sequencing, the soil 16S rDNA and ITS sequences were amplified to dissect the response characteristics of alpha/beta diversity and the structure/composition of a soil microbial community toward siderophores. The KEGG database was used to perform the PICRUSt functional prediction of the microbial community. We found that siderophores of 2-14F2 and 2-8F2, at certain concentrations, significantly increased the activities of sucrase (S-SC) and urease (S-UE) in the TBW soil and enhanced the average well color development (AWCD, carbon source utilization capacity) of the microbial community. The metabolic capacity of the diseased soil to amino acids, carbohydrates, polymers, aromatics, and carboxylic acids also increased significantly. The response of the bacterial community to siderophore active metabolites was more significant in alpha diversity, while the beta diversity of the fungal community responded more positively to siderophores. The relative abundance of Actinobacteria, Chloroflexi, and Acidobacteria increased and was accompanied by reductions in Proteobacteria and Firmicutes. LEfSe analysis showed that Pseudonocardiaceae, Gemmatimonas, Castellaniella, Chloridiumand and Acrophialophora altered the most under different concentrations of siderophore active metabolites. The PICRUSt functional prediction results showed that siderophore increased the abundance of the redox-related enzymes of the microbial community in TBW soil. The BugBase phenotypic prediction results showed that the siderophore activity could decrease the abundance of pathogenic bacteria. The study concludes that siderophore activity could decrease the abundance of pathogenic bacteria and regulate the composition of the microbial community in TBW soil. The activities of sucrase (S-SC) and urease (S-UE) in TBW soil were significantly increased. Overall, the siderophore regulation of community structures is a sustainable management strategy for soil ecosystems.

miR-199a-3p promotes gastric cancer progression by promoting its stemness potential via DDR2 mediation.

BACKGROUND: Peritoneal metastasis (PM) is an independent prognostic factor in gastric cancer (GC), however, the underlying mechanisms of PM occurrence remain unclear. METHOD: The roles of DDR2 were investigated in GC and its potential relationship to PM, and orthotopic implants into nude mice were performed to assess the biological effects of DDR2 on PM. RESULTS: Herein, DDR2 level is more significantly observed to elevate in PM lesion than the primary lesion. GC with DDR2-high expression evokes a worse overall survival (OS) in TCGA, similar results of the gloomy OS with high DDR2 levels are clarified via the stratifying stage of TNM. The conspicuously increased expression of DDR2 was found in GC cell lines, luciferase reporter assays verified that miR-199a-3p directly targeted DDR2 gene, which was correlated to tumor progression. We ulteriorly observed DDR2 participated in GC stemness maintenance via mediating pluripotency factor SOX2 expression and implicated in autophagy and DNA damage of cancer stem cells (CSCs). In particular, DDR2 dominated EMT programming through recruiting NFATc1-SOX2 complex to Snai1 in governing cell progression, controlling by DDR2-mTOR-SOX2 axis in SGC-7901 CSCs. Furthermore, DDR2 promoted the tumor peritoneal dissemination in gastric xenograft mouse model. CONCLUSION: Phenotype screens and disseminated verifications incriminating in GC exposit the miR-199a-3p-DDR2-mTOR-SOX2 axis as a clinically actionable target for tumor PM progression. The herein-reported DDR2-based underlying axis in GC represents novel and potent tools for studying the mechanisms of PM.

Unique DUOX2+ACE2+ small cholangiocytes are pathogenic targets for primary biliary cholangitis.

Cholangiocytes play a crucial role in bile formation. Cholangiocyte injury causes cholestasis, including primary biliary cholangitis (PBC). However, the etiology of PBC remains unclear despite being characterized as an autoimmune disease. Using single-cell RNA sequencing (scRNA-seq), fluorescence-activated-cell-sorting, multiplex immunofluorescence (IF) and RNAscope analyses, we identified unique DUOX2+ACE2+ small cholangiocytes in human and mouse livers. Their selective decrease in PBC patients was associated with the severity of disease. Moreover, proteomics, scRNA-seq, and qPCR analyses indicated that polymeric immunoglobulin receptor (pIgR) was highly expressed in DUOX2+ACE2+ cholangiocytes. Serum anti-pIgR autoantibody levels were significantly increased in PBC patients, regardless of positive and negative AMA-M2. Spatial transcriptomics and multiplex IF revealed that CD27+ memory B and plasma cells accumulated in the hepatic portal tracts of PBC patients. Collectively, DUOX2+ACE2+ small cholangiocytes are pathogenic targets in PBC, and preservation of DUOX2+ACE2+ cholangiocytes and targeting anti-pIgR autoantibodies may be valuable strategies for therapeutic interventions in PBC.

Expression site agnostic histopathology image segmentation framework by self supervised domain adaption.

MOTIVATION: With the sites of antigen expression different, the segmentation of immunohistochemical (IHC) histopathology images is challenging, due to the visual variances. With H&E images highlighting the tissue structure and cell distribution more broadly, transferring more salient features from H&E images can achieve considerable performance on expression site agnostic IHC images segmentation. METHODS: To the best of our knowledge, this is the first work that focuses on domain adaptive segmentation for different expression sites. We propose an expression site agnostic domain adaptive histopathology image semantic segmentation framework (ESASeg). In ESASeg, multi-level feature alignment encodes expression site invariance by learning generic representations of global and multi-scale local features. Moreover, self-supervision enhances domain adaptation to perceive high-level semantics by predicting pseudo-labels. RESULTS: We construct a dataset with three IHCs (Her2 with membrane stained, Ki67 with nucleus stained, GPC3 with cytoplasm stained) with different expression sites from two diseases (breast and liver cancer). Intensive experiments on tumor region segmentation illustrate that ESASeg performs best across all metrics, and the implementation of each module proves to achieve impressive improvements. CONCLUSION: The performance of ESASeg on the tumor region segmentation demonstrates the efficiency of the proposed framework, which provides a novel solution on expression site agnostic IHC related tasks. Moreover, the proposed domain adaption and self-supervision module can improve feature domain adaption and extraction without labels. In addition, ESASeg lays the foundation to perform joint analysis and information interaction for IHCs with different expression sites.

An accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images.

BACKGROUND: Determining the origin of bone metastatic cancer (OBMC) is of great significance to clinical therapeutics. It is challenging for pathologists to determine the OBMC with limited clinical information and bone biopsy. METHODS: We designed a regional multiple-instance learning algorithm to predict the OBMC based on hematoxylin-eosin (H&E) staining slides alone. We collected 1041 cases from eight different hospitals and labeled 26,431 regions of interest to train the model. The performance of the model was assessed by ten-fold cross validation and external validation. Under the guidance of top3 predictions, we conducted an IHC test on 175 cases of unknown origins to compare the consistency of the results predicted by the model and indicated by the IHC markers. We also applied the model to identify whether there was tumor or not in a region, as well as distinguishing squamous cell carcinoma, adenocarcinoma, and neuroendocrine tumor. FINDINGS: In the within-cohort, our model achieved a top1-accuracy of 91.35% and a top3-accuracy of 97.75%. In the external cohort, our model displayed a good generalizability with a top3-accuracy of 97.44%. The top1 consistency between the results of the model and the immunohistochemistry markers was 83.90% and the top3 consistency was 94.33%. The model obtained an accuracy of 98.98% to identify whether there was tumor or not and an accuracy of 93.85% to differentiate three types of cancers. INTERPRETATION: Our model demonstrated good performance to predict the OBMC from routine histology and had great potential for assisting pathologists with determining the OBMC accurately. FUNDING: National Science Foundation of China (61875102 and 61975089), Natural Science Foundation of Guangdong province (2021A15-15012379 and 2022A1515 012550), Science and Technology Research Program of Shenzhen City (JCYJ20200109110606054 and WDZC20200821141349001), and Tsinghua University Spring Breeze Fund (2020Z99CFZ023).

Unsupervised domain adaptive tumor region recognition for Ki67 automated assisted quantification.

PURPOSE: Ki67 is a protein associated with tumor proliferation and metastasis in breast cancer and acts as an essential prognostic factor. Clinical work requires recognizing tumor regions on Ki67-stained whole-slide images (WSIs) before quantitation. Deep learning has the potential to provide assistance but largely relies on massive annotations and consumes a huge amount of time and energy. Hence, a novel tumor region recognition approach is proposed for more precise Ki67 quantification. METHODS: An unsupervised domain adaptive method is proposed, which combines adversarial and self-training. The model trained on labeled hematoxylin and eosin (H&E) data and unlabeled Ki67 data can recognize tumor regions in Ki67 WSIs. Based on the UDA method, a Ki67 automated assisted quantification system is developed, which contains foreground segmentation, tumor region recognition, cell counting, and WSI-level score calculation. RESULTS: The proposed UDA method achieves high performance in tumor region recognition and Ki67 quantification. The AUC reached 0.9915, 0.9352, and 0.9689 on the validation set and internal and external test sets, respectively, substantially exceeding baseline (0.9334, 0.9167, 0.9408) and rivaling the fully supervised method (0.9950, 0.9284, 0.9652). The evaluation of automated quantification on 148 WSIs illustrated statistical agreement with pathological reports. CONCLUSION: The model trained by the proposed method is capable of accurately recognizing Ki67 tumor regions. The proposed UDA method can be readily extended to other types of immunohistochemical staining images. The results of automated assisted quantification are accurate and interpretable to provide assistance to both junior and senior pathologists in their interpretation.

AI-Powered Segmentation of Invasive Carcinoma Regions in Breast Cancer Immunohistochemical Whole-Slide Images.

AIMS: The automation of quantitative evaluation for breast immunohistochemistry (IHC) plays a crucial role in reducing the workload of pathologists and enhancing the objectivity of diagnoses. However, current methods face challenges in achieving fully automated immunohistochemistry quantification due to the complexity of segmenting the tumor area into distinct ductal carcinoma in situ (DCIS) and invasive carcinoma (IC) regions. Moreover, the quantitative analysis of immunohistochemistry requires a specific focus on invasive carcinoma regions. METHODS AND RESULTS: In this study, we propose an innovative approach to automatically identify invasive carcinoma regions in breast cancer immunohistochemistry whole-slide images (WSIs). Our method leverages a neural network that combines multi-scale morphological features with boundary features, enabling precise segmentation of invasive carcinoma regions without the need for additional H&E and P63 staining slides. In addition, we introduced an advanced semi-supervised learning algorithm, allowing efficient training of the model using unlabeled data. To evaluate the effectiveness of our approach, we constructed a dataset consisting of 618 IHC-stained WSIs from 170 cases, including four types of staining (ER, PR, HER2, and Ki-67). Notably, the model demonstrated an impressive intersection over union (IoU) score exceeding 80% on the test set. Furthermore, to ascertain the practical utility of our model in IHC quantitative evaluation, we constructed a fully automated Ki-67 scoring system based on the model's predictions. Comparative experiments convincingly demonstrated that our system exhibited high consistency with the scores given by experienced pathologists. CONCLUSIONS: Our developed model excels in accurately distinguishing between DCIS and invasive carcinoma regions in breast cancer immunohistochemistry WSIs. This method paves the way for a clinically available, fully automated immunohistochemistry quantitative scoring system.

Effects of atorvastatin in suppressing pulmonary vascular remodeling in rats with chronic obstructive pulmonary disease

Abstract Objective To investigate the effects of atorvastatin calcium on pulmonary vascular remodeling, the authors explored the regulatory mechanism of Histone Deacetylation Enzyme-2 (HDAC2) in rats with Chronic Obstructive Pulmonary Disease (COPD), and provided a new direction for drug treatment in the progression of vascular remodeling. Methods Eighteen female SD rats were randomly divided into control (Group S1), COPD (Group S2), and atorvastatin calcium + COPD (Group S3) groups. A COPD rat model was established by passive smoking and intratracheal injection of Lipopolysaccharide (LPS). Haematoxylin and eosin staining and Victoria Blue + Van Gibson staining were used to observe pathological changes in the lung tissue. The pulmonary vascular inflammation score was calculated, and the degree of pulmonary vascular remodeling was evaluated. The ratio of Muscular Arteries in lung tissue (MA%), the ratio of the vessel Wall Area to the vessel total area (WA%), and the ratio of the vessel Wall Thickness to the vascular outer diameter (WT%) were measured using imaging software. The expression of HDAC2 was measured using western blotting, ELISA (Enzyme-Linked Immunosorbent Assay), and qPCR (Real-time PCR). Results Compared with the control group, the degree of pulmonary vascular inflammation and pulmonary vascular remodeling increased in rats with COPD. The WT%, WA%, and lung inflammation scores increased significantly; the expression of HDAC2 and HDAC2mRNA in the serum and lung tissue decreased, and the level of Vascular Endothelial Growth Factor (VEGF) in the lung tissues increased (p< 0.05). Compared with the COPD group, the lung tissues from rats in the atorvastatin group had fewer inflammatory cells, and the vascular pathological changes were significantly relieved. The WT%, WA%, and lung inflammation scores decreased significantly; the expression of HDAC2 and HDAC2mRNA in the serum and lung tissues increased, and the level of VEGF in the lung tissues decreased (p< 0.05). Conclusion The present study revealed that atorvastatin calcium could regulate the contents and expression of HDAC2 in serum and lung tissues and inhibit the production of VEGF, thereby regulating pulmonary vascular remodeling in a rat model with COPD.

Using Sparse Patch Annotation for Tumor Segmentation in Histopathological Images.

Tumor segmentation is a fundamental task in histopathological image analysis. Creating accurate pixel-wise annotations for such segmentation tasks in a fully-supervised training framework requires significant effort. To reduce the burden of manual annotation, we propose a novel weakly supervised segmentation framework based on sparse patch annotation, i.e., only small portions of patches in an image are labeled as 'tumor' or 'normal'. The framework consists of a patch-wise segmentation model called PSeger, and an innovative semi-supervised algorithm. PSeger has two branches for patch classification and image classification, respectively. This two-branch structure enables the model to learn more general features and thus reduce the risk of overfitting when learning sparsely annotated data. We incorporate the idea of consistency learning and self-training into the semi-supervised training strategy to take advantage of the unlabeled images. Trained on the BCSS dataset with only 25% of the images labeled (five patches for each labeled image), our proposed method achieved competitive performance compared to the fully supervised pixel-wise segmentation models. Experiments demonstrate that the proposed solution has the potential to reduce the burden of labeling histopathological images.

[Research progress on three-dimensional printed interbody fusion cage].

Spinal fusion is a standard operation for treating moderate and severe intervertebral disc diseases. In recent years, the proportion of three-dimensional printing interbody fusion cage in spinal fusion surgery has gradually increased. In this paper, the research progress of molding technology and materials used in three-dimensional printing interbody fusion cage at present is summarized. Then, according to structure layout, three-dimensional printing interbody fusion cages are classified into five types: solid-porous-solid (SPS) type, solid-porous-frame (SPF) type, frame-porous-frame (FPF) type, whole porous cage (WPC) type and others. The optimization process of three-dimensional printing interbody fusion cage and the advantages and disadvantages of each type are analyzed and summarized in depth. The clinical application of various types of 3D printed interbody fusion cage was introduced and summarized later. Lastly, combined with the latest research progress and achievements, the future research direction of three-dimensional printing interbody fusion cage in molding technology, application materials and coating materials is prospected in order to provide some reference for scholars engaged in interbody fusion cage research and application.

Unpaired Stain Transfer Using Pathology-Consistent Constrained Generative Adversarial Networks.

Pathological examination is the gold standard for the diagnosis of cancer. Common pathological examinations include hematoxylin-eosin (H&E) staining and immunohistochemistry (IHC). In some cases, it is hard to make accurate diagnoses of cancer by referring only to H&E staining images. Whereas, the IHC examination can further provide enough evidence for the diagnosis process. Hence, the generation of virtual IHC images from H&E-stained images will be a good solution for current IHC examination hard accessibility issue, especially for some low-resource regions. However, existing approaches have limitations in microscopic structural preservation and the consistency of pathology properties. In addition, pixel-level paired data is hard available. In our work, we propose a novel adversarial learning method for effective Ki-67-stained image generation from corresponding H&E-stained image. Our method takes fully advantage of structural similarity constraint and skip connection to improve structural details preservation; and pathology consistency constraint and pathological representation network are first proposed to enforce the generated and source images hold the same pathological properties in different staining domains. We empirically demonstrate the effectiveness of our approach on two different unpaired histopathological datasets. Extensive experiments indicate the superior performance of our method that surpasses the state-of-the-art approaches by a significant margin. In addition, our approach also achieves a stable and good performance on unbalanced datasets, which shows our method has strong robustness. We believe that our method has significant potential in clinical virtual staining and advance the progress of computer-aided multi-staining histology image analysis.

Effective Immunohistochemistry Pathology Microscopy Image Generation Using CycleGAN.

Immunohistochemistry detection technology is able to detect more difficult tumors than regular pathology detection technology only with hematoxylin-eosin stained pathology microscopy images, - for example, neuroendocrine tumor detection. However, making immunohistochemistry pathology microscopy images costs much time and money. In this paper, we propose an effective immunohistochemistry pathology microscopic image-generation method that can generate synthetic immunohistochemistry pathology microscopic images from hematoxylin-eosin stained pathology microscopy images without any annotation. CycleGAN is adopted as the basic architecture for the unpaired and unannotated dataset. Moreover, multiple instances learning algorithms and the idea behind conditional GAN are considered to improve performance. To our knowledge, this is the first attempt to generate immunohistochemistry pathology microscopic images, and our method can achieve good performance, which will be very useful for pathologists and patients when applied in clinical practice.