Partial-Label Contrastive Representation Learning for Fine-grained Biomarkers Prediction from Histopathology Whole Slide Images.

In the domain of histopathology analysis, existing representation learning methods for biomarkers prediction from whole slide images (WSI) face challenges due to the complexity of tissue subtypes and label noise problems. This paper proposed a novel partial-label contrastive representation learning approach to enhance the discrimination of histopathology image representations for fine-grained biomarkers prediction. We designed a partial-label contrastive clustering (PLCC) module for partial-label disambiguation and a dynamic clustering algorithm to sample the most representative features of each category to the clustering queue during the contrastive learning process. We conducted comprehensive experiments on three gene mutation prediction datasets, including USTC-EGFR, BRCA-HER2, and TCGA-EGFR. The results show that our method outperforms 9 existing methods in terms of Accuracy, AUC, and F1 Score. Specifically, our method achieved an AUC of 0.950 in EGFR mutation subtyping of TCGA-EGFR and an AUC of 0.853 in HER2 0/1+/2+/3+ grading of BRCA-HER2, which demonstrates its superiority in fine-grained biomarkers prediction from histopathology whole slide images. The source code is available at https://github.com/WkEEn/PLCC.

Masked hypergraph learning for weakly supervised histopathology whole slide image classification.

BACKGROUND AND OBJECTIVES: Graph neural network (GNN) has been extensively used in histopathology whole slide image (WSI) analysis due to the efficiency and flexibility in modelling relationships among entities. However, most existing GNN-based WSI analysis methods only consider the pairwise correlation of patches from one single perspective (e.g. spatial affinity or embedding similarity) yet ignore the intrinsic non-pairwise relationships present in gigapixel WSI, which are likely to contribute to feature learning and downstream tasks. The objective of this study is therefore to explore the non-pairwise relationships in histopathology WSI and exploit them to guide the learning of slide-level representations for better classification performance. METHODS: In this paper, we propose a novel Masked HyperGraph Learning (MaskHGL) framework for weakly supervised histopathology WSI classification. Compared with most GNN-based WSI classification methods, MaskHGL exploits the non-pairwise correlations between patches with hypergraph and global message passing conducted by hypergraph convolution. Concretely, multi-perspective hypergraphs are first built for each WSI, then hypergraph attention is introduced into the jointed hypergraph to propagate the non-pairwise relationships and thus yield more discriminative node representation. More importantly, a masked hypergraph reconstruction module is devised to guide the hypergraph learning which can generate more powerful robustness and generalization than the method only using hypergraph modelling. Additionally, a self-attention-based node aggregator is also applied to explore the global correlation of patches in WSI and produce the slide-level representation for classification. RESULTS: The proposed method is evaluated on two public TCGA benchmark datasets and one in-house dataset. On the public TCGA-LUNG (1494 WSIs) and TCGA-EGFR (696 WSIs) test set, the area under receiver operating characteristic (ROC) curve (AUC) were 0.9752±0.0024 and 0.7421±0.0380, respectively. On the USTC-EGFR (754 WSIs) dataset, MaskHGL achieved significantly better performance with an AUC of 0.8745±0.0100, which surpassed the second-best state-of-the-art method SlideGraph+ 2.64%. CONCLUSIONS: MaskHGL shows a great improvement, brought by considering the intrinsic non-pairwise relationships within WSI, in multiple downstream WSI classification tasks. In particular, the designed masked hypergraph reconstruction module promisingly alleviates the data scarcity and greatly enhances the robustness and classification ability of our MaskHGL. Notably, it has shown great potential in cancer subtyping and fine-grained lung cancer gene mutation prediction from hematoxylin and eosin (H&E) stained WSIs.

Histopathology language-image representation learning for fine-grained digital pathology cross-modal retrieval.

Large-scale digital whole slide image (WSI) datasets analysis have gained significant attention in computer-aided cancer diagnosis. Content-based histopathological image retrieval (CBHIR) is a technique that searches a large database for data samples matching input objects in both details and semantics, offering relevant diagnostic information to pathologists. However, the current methods are limited by the difficulty of gigapixels, the variable size of WSIs, and the dependence on manual annotations. In this work, we propose a novel histopathology language-image representation learning framework for fine-grained digital pathology cross-modal retrieval, which utilizes paired diagnosis reports to learn fine-grained semantics from the WSI. An anchor-based WSI encoder is built to extract hierarchical region features and a prompt-based text encoder is introduced to learn fine-grained semantics from the diagnosis reports. The proposed framework is trained with a multivariate cross-modal loss function to learn semantic information from the diagnosis report at both the instance level and region level. After training, it can perform four types of retrieval tasks based on the multi-modal database to support diagnostic requirements. We conducted experiments on an in-house dataset and a public dataset to evaluate the proposed method. Extensive experiments have demonstrated the effectiveness of the proposed method and its advantages to the present histopathology retrieval methods. The code is available at https://github.com/hudingyi/FGCR.

Structural characteristics and stability analysis of coconut oil body and its application for loading ß-carotene.

In this work, we investigated structural characteristics and stability analysis of the coconut oil body (COB) and its application for loading ß-carotene (ß-CA). The COB contained neutral lipids (81.1 ± 2.1 %), membrane proteins (0.6 ± 0.0 %), and moistures (18.3 ± 3.2 %), in which the molecular weights of membrane proteins ranged from 12 kDa to 40 kDa, as analyzed by the SDS-PAGE. The COB exhibited a small droplet diameter (5.1 ± 0.3 µm) with a monomodal diameter distribution, as reflected by the dynamic light scattering. The COB showed stable states at alkaline pH values (pH 8-10) and instability against ionic strengths (50-200 mmol/L) and thermal treatment (30-90℃) after analyzing the instability indexes. COB-based emulsions were favorable for the loading and retention of ß-CA, as reflected by free fatty acids release rates and bioaccessibility in the simulated gastrointestinal digestion. This study will contribute to using the coconut oil bodies for loading bioactive nutraceuticals to enhance their bioaccessibility.

A Key-Points Based Anchor-Free Cervical Cell Detector.

Cervical cell detection is crucial to cervical cytology screening at early stage. Currently most cervical cell detection methods use anchor-based pipeline to achieve the localization and classification of cells, e.g. faster R-CNN and YOLOv3. However, the anchors generally need to be pre-defined before training and the detection performance is inevitably sensitive to these pre-defined hyperparameters (e.g. number of anchors, anchor size and aspect ratios). More importantly, these preset anchors fail to conform to the cells with different morphology at inference phase. In this paper, we present a key-points based anchor-free cervical cell detector based on YOLOv3. Compared with the conventional YOLOv3, the proposed method applies a key-points based anchor-free strategy to represent the cells in the initial prediction phase instead of the preset anchors. Therefore, it can generate more desirable cell localization effect through refinement. Furthermore, PAFPN is applied to enhance the feature hierarchy. GIoU loss is also introduced to optimize the small cell localization in addition to focal loss and smooth L1 loss. Experimental results on cervical cytology ROI datasets demonstrate the effectiveness of our method for cervical cell detection and the robustness to different liquid-based preparation styles (i.e. drop-slide, membrane-based and sedimentation).

Kernel Attention Transformer for Histopathology Whole Slide Image Analysis and Assistant Cancer Diagnosis.

Transformer has been widely used in histopathology whole slide image analysis. However, the design of token-wise self-attention and positional embedding strategy in the common Transformer limits its effectiveness and efficiency when applied to gigapixel histopathology images. In this paper, we propose a novel kernel attention Transformer (KAT) for histopathology WSI analysis and assistant cancer diagnosis. The information transmission in KAT is achieved by cross-attention between the patch features and a set of kernels related to the spatial relationship of the patches on the whole slide images. Compared to the common Transformer structure, KAT can extract the hierarchical context information of the local regions of the WSI and provide diversified diagnosis information. Meanwhile, the kernel-based cross-attention paradigm significantly reduces the computational amount. The proposed method was evaluated on three large-scale datasets and was compared with 8 state-of-the-art methods. The experimental results have demonstrated the proposed KAT is effective and efficient in the task of histopathology WSI analysis and is superior to the state-of-the-art methods.

Autofluorescence imaging-assisted medical thoracoscopy in the diagnosis of malignant pleural disease.

BACKGROUND: Medical thoracoscopy (MT) does not always provide a conclusive diagnosis of pleural diseases because the endoscopic appearance of pleural diseases can be misleading. Autofluorescence imaging (AFI) is an effective assistive diagnostic tool. However, its clinical application for pleural disease remains controversial. OBJECTIVES: This prospective study evaluated the clinical usefulness of AFI-assisted MT for diagnosis of malignant pleural diseases. METHODS: Patients with unexplained pleural effusion admitted to our clinics between December 2018 and September 2021 were enrolled. We performed white-light thoracoscopy (WLT) first, and then AFI, during MT. Images of endoscopic real-time lesions were recorded under both modes. Pleural biopsy specimens were analyzed pathologically. Between-groups differences in diagnostic sensitivity, specificity, positive-predictive value (PPV), and negative-predictive value (NPV) were assessed using 95% confidence intervals (CI). Receiver operating characteristic curves and decision curve analyses were employed to analyze the diagnostic efficiency of these two modes. RESULTS: Of 126 eligible patients, 73 cases were diagnosed with malignant pleural disease. A total of 1292 biopsy specimens from 492 pleural sites were examined for pathological changes. The diagnostic sensitivity, PPV, and NPV of AFI were 99.7%, 58.2%, and 99.2%, respectively. AFI was significantly superior to WLT, which had a sensitivity of 79.7%, PPV of 50.7%, and NPV of 62.8%. Subgroup analysis showed that the AFI type III pattern was significantly more specific for pleural malignant disease than that of WLT. CONCLUSIONS: AFI could further improve the diagnostic efficacy of MT by providing better visualization, convenience, and safety.

Significantly Enhanced Crystallization of Poly(ethylene succinate-co-1,2-propylene succinate) by Cellulose Nanocrystals as an Efficient Nucleating Agent.

Poly(ethylene succinate-co-1,2-propylene succinate) (PEPS) is a novel aliphatic biodegradable polyester with good mechanical properties. Due to the presence of methyl as a side group, the crystallization rate of PEPS is remarkably slower than that of the poly(ethylene succinate) homopolymer. To promote the potential application of PEPS, the effect of cellulose nanocrystals (CNC) on the crystallization behavior, crystalline morphology, and crystal structure of PEPS was investigated in this research with the aim of increasing the crystallization rate. CNC enhanced both the melt crystallization behavior of PEPS during the cooling process and the overall crystallization rate during the isothermal crystallization process. The crystallization rate of PEPS became faster with an increase in CNC content. The crystalline morphology study directly confirmed the heterogeneous nucleating agent role of CNC. The crystal structure of PEPS remained unchanged in the composites. On the basis of the interfacial energy, the nucleation mechanism of PEPS in the composites was further discussed by taking into consideration the induction of CNC.

Rapid large-scale preparation of polysaccharides from jackfruit peel waste by high-speed countercurrent chromatography and their antioxidant and hypoglycemic activities.

Polysaccharides with antioxidant and hypoglycemic activities were first isolated from jackfruit (Artocarpus heterophyllus Lam.) peel through the one-step high-speed countercurrent chromatography. The separation process was completed using the polymer two-phase aqueous system constituted by PEG1000-K2 HPO4 -KH2 PO4 -H2 O (0.8:1.25:1.25:6.5, w/w). For every separation process, two main polysaccharides, namely, fraction-1 and fraction-2 (165 and 225 mg, respectively) were obtained from a 2.0 g crude sample. As suggested by high-performance gel permeation chromatography, jackfruit peel polysaccharides had the mean molecular weight values of 113.3 and 174.3 kDa, separately. Physicochemical analysis suggested that two polysaccharides were dominant in galacturonic acid, galactose, rhamnose, arabinose, glucose, mannose, as well as fucose, which were highly esterified. Biological activity analysis showed that fraction-1 exhibited stronger antioxidant activity in vitro and hypoglycemic activity in streptozotocin-induced diabetic mice compared with fraction-2. The results suggest that polysaccharide fraction-1 may be developed as a potential functional food supplement.

Encoding histopathology whole slide images with location-aware graphs for diagnostically relevant regions retrieval.

Content-based histopathological image retrieval (CBHIR) has become popular in recent years in histopathological image analysis. CBHIR systems provide auxiliary diagnosis information for pathologists by searching for and returning regions that are contently similar to the region of interest (ROI) from a pre-established database. It is challenging and yet significant in clinical applications to retrieve diagnostically relevant regions from a database consisting of histopathological whole slide images (WSIs). In this paper, we propose a novel framework for regions retrieval from WSI database based on location-aware graphs and deep hash techniques. Compared to the present CBHIR framework, both structural information and global location information of ROIs in the WSI are preserved by graph convolution and self-attention operations, which makes the retrieval framework more sensitive to regions that are similar in tissue distribution. Moreover, benefited from the graph structure, the proposed framework has good scalability for both the size and shape variation of ROIs. It allows the pathologist to define query regions using free curves according to the appearance of tissue. Thirdly, the retrieval is achieved based on the hash technique, which ensures the framework is efficient and adequate for practical large-scale WSI database. The proposed method was evaluated on an in-house endometrium dataset with 2650 WSIs and the public ACDC-LungHP dataset. The experimental results have demonstrated that the proposed method achieved a mean average precision above 0.667 on the endometrium dataset and above 0.869 on the ACDC-LungHP dataset in the task of irregular region retrieval, which are superior to the state-of-the-art methods. The average retrieval time from a database containing 1855 WSIs is 0.752 ms. The source code is available at https://github.com/zhengyushan/lagenet.

Baseline neutrophil-lymphocyte ratio is associated with outcomes in patients with castration-resistant prostate cancer treated with Docetaxel in South China.

ABSTRACT: The aim of this study is to investigate the association between baseline neutrophil-to-lymphocyte ratio (NLR) and progression-free survival (PFS), overall survival (OS) and radiological response in castration-resistant prostate cancer patients treated with docetaxel.Forty-one prostate cancer patients who were treated with docetaxel were selected. Univariable and multivariable Cox regression models were used to predict the association of baseline NLR as a dichotomous variable with PFS and OS after chemotherapy initiation.In Kaplan-Meier analysis, the median PFS (9.8 vs 7.5 months, P = .039, Fig. 1) and OS (17.6 vs 14.2 months, P = .021, Fig. 2) was higher in patients who did not have an elevated NLR than in those with an elevated NLR. In univariate analysis, the pretreatment NLR was significantly associated with PFS (P = .049) and OS (P = .023). In multivariable analysis, patients with a NLR of >3 were at significantly higher risk of tumor progress (hazard ratio 2.458; 95% confidence interval 1.186-5.093; P = .016) and death (hazard ratio 3.435; 95% CI 1.522-7.750; P = .003)than patients with a NLR of ⩽3.NLR may be an independent predictor of PFS and OS in castration-resistant prostate cancer patients treated with docetaxel. The findings require validation in further prospective, big sample-sized studies.

Cervical cell classification with graph convolutional network.

BACKGROUND AND OBJECTIVE: Cervical cell classification has important clinical significance in cervical cancer screening at early stages. In contrast with the conventional classification methods which depend on hand-crafted or engineered features, Convolutional Neural Network (CNN) generally classifies cervical cells via learned deep features. However, the latent correlations of images may be ignored during CNN feature learning and thus influence the representation ability of CNN features. METHODS: We propose a novel cervical cell classification method based on Graph Convolutional Network (GCN). It aims to explore the potential relationship of cervical cell images for improving the classification performance. The CNN features of all the cervical cell images are firstly clustered and the intrinsic relationships of images can be preliminarily revealed through the clustering. To further capture the underlying correlations existed among clusters, a graph structure is constructed. GCN is then applied to propagate the node dependencies and thus yield the relation-aware feature representation. The GCN features are finally incorporated to enhance the discriminative ability of CNN features. RESULTS: Experiments on the public cervical cell image dataset SIPaKMeD from International Conference on Image Processing in 2018 demonstrate the feasibility and effectiveness of the proposed method. In addition, we introduce a large-scale Motic liquid-based cytology image dataset which provides the large amount of data, some novel cell types with important clinical significance and staining difference and thus presents a great challenge for cervical cell classification. We evaluate the proposed method under two conditions of the consistent staining and different staining. Experimental results show our method outperforms the existing state-of-arts methods according to the quantitative metrics (i.e. accuracy, sensitivity, specificity, F-measure and confusion matrices). CONCLUSIONS: The intrinsic relationship exploration of cervical cells contributes significant improvements to the cervical cell classification. The relation-aware features generated by GCN effectively strengthens the representational power of CNN features. The proposed method can achieve the better classification performance and also can be potentially used in automatic screening system of cervical cytology.

Diagnostic Regions Attention Network (DRA-Net) for Histopathology WSI Recommendation and Retrieval.

The development of whole slide imaging techniques and online digital pathology platforms have accelerated the popularization of telepathology for remote tumor diagnoses. During a diagnosis, the behavior information of the pathologist can be recorded by the platform and then archived with the digital case. The browsing path of the pathologist on the WSI is one of the valuable information in the digital database because the image content within the path is expected to be highly correlated with the diagnosis report of the pathologist. In this article, we proposed a novel approach for computer-assisted cancer diagnosis named session-based histopathology image recommendation (SHIR) based on the browsing paths on WSIs. To achieve the SHIR, we developed a novel diagnostic regions attention network (DRA-Net) to learn the pathology knowledge from the image content associated with the browsing paths. The DRA-Net does not rely on the pixel-level or region-level annotations of pathologists. All the data for training can be automatically collected by the digital pathology platform without interrupting the pathologists' diagnoses. The proposed approaches were evaluated on a gastric dataset containing 983 cases within 5 categories of gastric lesions. The quantitative and qualitative assessments on the dataset have demonstrated the proposed SHIR framework with the novel DRA-Net is effective in recommending diagnostically relevant cases for auxiliary diagnosis. The MRR and MAP for the recommendation are respectively 0.816 and 0.836 on the gastric dataset. The source code of the DRA-Net is available at https://github.com/zhengyushan/dpathnet.

Identification of the key genes and pathways involved in the tumorigenesis and prognosis of kidney renal clear cell carcinoma.

Kidney renal clear cell carcinoma (KIRC) is the most common renal cell carcinoma (RCC). However, patients with KIRC usually have poor prognosis due to limited biomarkers for early detection and prognosis prediction. In this study, we analysed key genes and pathways involved in KIRC from an array dataset including 26 tumour and 26 adjacent normal tissue samples. Weighted gene co-expression network analysis (WGCNA) was performed with the WGCNA package, and 20 modules were characterized as having the highest correlation with KIRC. The upregulated genes in the tumour samples are involved in the innate immune response, whereas the downregulated genes contribute to the cellular catabolism of glucose, amino acids and fatty acids. Furthermore, the key genes were evaluated through a protein-protein interaction (PPI) network combined with a co-expression network. The comparatively lower expression of AGXT, PTGER3 and SLC12A3 in tumours correlates with worse prognosis in KIRC patients, while higher expression of ALOX5 predicts reduced survival. Our integrated analysis illustrated the hub genes involved in KIRC tumorigenesis, shedding light on the development of prognostic markers. Further understanding of the function of the identified KIRC hub genes could provide deep insights into the molecular mechanisms of KIRC.

Ultrasonic microwave-assisted extraction coupled with macroporous resin chromatography for the purification of antioxidant phenolics from waste jackfruit (Artocarpus heterophyllus Lam.) peels.

An efficient ultrasonic microwave-assisted extraction (UMAE) coupled with macroporous resin chromatography technique was successfully used for the extraction and purification of antioxidant phenolics from jackfruit by-products (peels). After optimization by single factor experiments and response surface methodology, the optimum extraction conditions for UMAE were: ethanol concentration 63%, solvent-to-solid ratio 34 mL/g, microwave power 160 W and irradiation time 20 min. Under the optimal condition, the phenolics extraction yield was 8.14 mg GAE/g DW. After the purification by macroporous resin AB-8, the purity of antioxidant phenolics from UMAE extracts improved from 13.59 to 49.07%. Furthermore, ABTS radical scavenging activities were also significantly increased from 35.95 ± 2.21 to 162.36 ± 10.26 mg TE/g. HPLC analysis revealed that gallic acid, chlorogenic acid, and catechin were three dominant antioxidant phenolics in jackfruit peels. All of the results demonstrated that waste jackfruit peels could be utilized as a good source of phenolics with strong antioxidant activities in food and pharmaceutical industry.

N-Doped Graphene/Melamine Formaldehyde Composite Carbon Foam as a Binder-Free Electrode for Supercapacitors.

A N-doped graphene/melamine formaldehyde composite carbon foam (G/C) with a porous structure was prepared by a physical foaming method and high-temperature carbonization. Samples of the G/C with various graphene content (i.e., 0%, 1% and 2%) were synthesized and characterized by X-ray diffraction (XRD), X-ray photoelectron spectroscopy (XPS) and field-emission scanning electron microscopy (FESEM). The XPS and TEM analyses show that the as-prepared G2%/C foam has the highest nitrogen content of 14.7%, with an apparent porous structure. The electrochemical performances of the G/C samples were investigated by charge-discharge cycles. The G2%/C exhibits a high capacitance of 619.3 Fg-1 at a current density of 0.5 Ag-1. The N-doped graphene/melamine formaldehyde composite carbon foam is a promising electric double-layer capacitor material for binder-free electrodes with excellent properties for supercapacitors.

The role of thymus preservation in parathyroid gland function and surgical completeness after bilateral central lymph node dissection for papillary thyroid cancer: A randomized controlled study.

BACKGROUND: The clinical value of thymus preservation during thyroid carcinoma surgery remains unclear. The aim of this study is to explore the role of bilateral thymus preservation in parathyroid glands (PGs) function and surgical completeness in total thyroidectomy (TT) with bilateral central lymph node dissection (CLND). MATERIALS AND METHODS: Fifty-four consecutive patients who underwent TT and bilateral CLND were assigned to the thymus preservation (TP) group (n = 27) and the bilateral thymectomy (BT) group (n = 27). Surgical completeness was evaluated by the number of lymph nodes dissected, serum Tg level and ultrasound findings postoperatively. RESULTS: Incidental parathyroidectomy was more common in the BT group (29.6% vs 7.4%, p = 0.038). Patients in the BT group had higher risks of neuromuscular symptoms (63.0% vs 29.6%, P = 0.014) and transient hypoparathyroidism (70.4% vs 25.9%, P = 0.001). The incidence of persistent hypoparathyroidism failed to show a significant difference between the TP and BT groups (0 vs 14.8%, P = 0.111). However, those with transient hypoparathyroidism in the BT group had a lower level of serum PTH at 3 weeks postoperatively (p = 0.001). There was no significant difference in the number of lymph nodes dissected (5.89 ±â€¯3.12 vs 8.56 ±â€¯6.93, P = 0.077) and preablation sTg level (1.82 ±â€¯2.18 vs 1.42 ±â€¯1.56 ng/ml, P = 0.775) between the TP and BT groups. No metastatic lymph nodes were found on sonography at 3 months postoperatively in both groups. CONCLUSION: Thymus preservation had benefits on protecting PGs and promoting rapid clinical resolution of hypoparathyroidism. It had no effects on oncologic completeness of TT with bilateral CLND.

Adaptive color deconvolution for histological WSI normalization.

BACKGROUND AND OBJECTIVE: Color consistency of histological images is significant for developing reliable computer-aided diagnosis (CAD) systems. However, the color appearance of digital histological images varies across different specimen preparations, staining, and scanning situations. This variability affects the diagnosis and decreases the accuracy of CAD approaches. It is important and challenging to develop effective color normalization methods for digital histological images. METHODS: We proposed a novel adaptive color deconvolution (ACD) algorithm for stain separation and color normalization of hematoxylin-eosin-stained whole slide images (WSIs). To avoid artifacts and reduce the failure rate of normalization, multiple prior knowledges of staining are considered and embedded in the ACD model. To improve the capacity of color normalization for various WSIs, an integrated optimization is designed to simultaneously estimate the parameters of the stain separation and color normalization. The solving of ACD model and application of the proposed method involves only pixel-wise operation, which makes it very efficient and applicable to WSIs. RESULTS: The proposed method was evaluated on four WSI-datasets including breast, lung and cervix cancers and was compared with 6 state-of-the-art methods. The proposed method achieved the most consistent performance in color normalization according to the quantitative metrics. Through a qualitative assessment for 500 WSIs, the failure rate of normalization was 0.4% and the structure and color artifacts were effectively avoided. Applied to CAD methods, the area under receiver operating characteristic curve for cancer image classification was improved from 0.842 to 0.914. The average time of solving the ACD model is 2.97 s. CONCLUSIONS: The proposed ACD model has prone effective for color normalization of hematoxylin-eosin-stained WSIs in various color appearances. The model is robust and can be applied to WSIs containing different lesions. The proposed model can be efficiently solved and is effective to improve the performance of cancer image recognition, which is adequate for developing automatic CAD programs and systems based on WSIs.

Histopathological Whole Slide Image Analysis Using Context-Based CBIR.

Histopathological image classification (HIC) and content-based histopathological image retrieval (CBHIR) are two promising applications for the histopathological whole slide image (WSI) analysis. HIC can efficiently predict the type of lesion involved in a histopathological image. In general, HIC can aid pathologists in locating high-risk cancer regions from a WSI by providing a cancerous probability map for the WSI. In contrast, CBHIR was developed to allow searches for regions with similar content for a region of interest (ROI) from a database consisting of historical cases. Sets of cases with similar content are accessible to pathologists, which can provide more valuable references for diagnosis. A drawback of the recent CBHIR framework is that a query ROI needs to be manually selected from a WSI. An automatic CBHIR approach for a WSI-wise analysis needs to be developed. In this paper, we propose a novel aided-diagnosis framework of breast cancer using whole slide images, which shares the advantages of both HIC and CBHIR. In our framework, CBHIR is automatically processed throughout the WSI, based on which a probability map regarding the malignancy of breast tumors is calculated. Through the probability map, the malignant regions in WSIs can be easily recognized. Furthermore, the retrieval results corresponding to each sub-region of the WSIs are recorded during the automatic analysis and are available to pathologists during their diagnosis. Our method was validated on fully annotated WSI data sets of breast tumors. The experimental results certify the effectiveness of the proposed method.