LncRNA MSC-AS1 regulates SNIP1 SUMOylation-mediated EMT by binding to SENP1 to promote intestinal fibrosis in Crohn's disease.

As a common complication of Crohn's disease (CD), the mechanism underlying CD intestinal fibrosis remains unclear. Studies have shown that epithelial-mesenchymal transition (EMT) is a key step in the development of intestinal fibrosis in CD. It is currently known that the long non-coding RNA (lncRNA) MSC-AS1 plays an important role in regulating the secretion of inflammatory mediators and EMT; however, its role in intestinal fibrosis remains unclear. MSC-AS1 was significantly upregulated in the CD intestinal tissue and intestinal tissue of mice treated with 2,4,6-trinitrobenzenesulfonic acid. Downregulation of its expression can inhibit EMT and alleviates intestinal fibrosis by regulating SNIP1. In addition, MSC-AS1 directly interacted with SENP1, blocking the deSUMOylation of SNIP1 and inhibiting its activity. Furthermore, we found that SENP1 enhanced the expression of SNIP1 and reduced intestinal fibrosis. In summary, MSC-AS1 regulates EMT through the SENP1/SNIP1 axis to promote fibrosis, and may be considered a potential molecular target for the treatment of CD and intestinal fibrosis.

SwinHR: Hemodynamic-powered hierarchical vision transformer for breast tumor segmentation.

Accurate and automated segmentation of breast tumors in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a critical role in computer-aided diagnosis and treatment of breast cancer. However, this task is challenging, due to random variation in tumor sizes, shapes, appearances, and blurred boundaries of tumors caused by inherent heterogeneity of breast cancer. Moreover, the presence of ill-posed artifacts in DCE-MRI further complicate the process of tumor region annotation. To address the challenges above, we propose a scheme (named SwinHR) integrating prior DCE-MRI knowledge and temporal-spatial information of breast tumors. The prior DCE-MRI knowledge refers to hemodynamic information extracted from multiple DCE-MRI phases, which can provide pharmacokinetics information to describe metabolic changes of the tumor cells over the scanning time. The Swin Transformer with hierarchical re-parameterization large kernel architecture (H-RLK) can capture long-range dependencies within DCE-MRI while maintaining computational efficiency by a shifted window-based self-attention mechanism. The use of H-RLK can extract high-level features with a wider receptive field, which can make the model capture contextual information at different levels of abstraction. Extensive experiments are conducted in large-scale datasets to validate the effectiveness of our proposed SwinHR scheme, demonstrating its superiority over recent state-of-the-art segmentation methods. Also, a subgroup analysis split by MRI scanners, field strength, and tumor size is conducted to verify its generalization. The source code is released on (https://github.com/GDPHMediaLab/SwinHR).

A robust and efficient AI assistant for breast tumor segmentation from DCE-MRI via a spatial-temporal framework.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) allows screening, follow up, and diagnosis for breast tumor with high sensitivity. Accurate tumor segmentation from DCE-MRI can provide crucial information of tumor location and shape, which significantly influences the downstream clinical decisions. In this paper, we aim to develop an artificial intelligence (AI) assistant to automatically segment breast tumors by capturing dynamic changes in multi-phase DCE-MRI with a spatial-temporal framework. The main advantages of our AI assistant include (1) robustness, i.e., our model can handle MR data with different phase numbers and imaging intervals, as demonstrated on a large-scale dataset from seven medical centers, and (2) efficiency, i.e., our AI assistant significantly reduces the time required for manual annotation by a factor of 20, while maintaining accuracy comparable to that of physicians. More importantly, as the fundamental step to build an AI-assisted breast cancer diagnosis system, our AI assistant will promote the application of AI in more clinical diagnostic practices regarding breast cancer.

MRI-based Quantification of Intratumoral Heterogeneity for Predicting Treatment Response to Neoadjuvant Chemotherapy in Breast Cancer.

Background Breast cancer is highly heterogeneous, resulting in different treatment responses to neoadjuvant chemotherapy (NAC) among patients. A noninvasive quantitative measure of intratumoral heterogeneity (ITH) may be valuable for predicting treatment response. Purpose To develop a quantitative measure of ITH on pretreatment MRI scans and test its performance for predicting pathologic complete response (pCR) after NAC in patients with breast cancer. Materials and Methods Pretreatment MRI scans were retrospectively acquired in patients with breast cancer who received NAC followed by surgery at multiple centers from January 2000 to September 2020. Conventional radiomics (hereafter, C-radiomics) and intratumoral ecological diversity features were extracted from the MRI scans, and output probabilities of imaging-based decision tree models were used to generate a C-radiomics score and ITH index. Multivariable logistic regression analysis was used to identify variables associated with pCR, and significant variables, including clinicopathologic variables, C-radiomics score, and ITH index, were combined into a predictive model for which performance was assessed using the area under the receiver operating characteristic curve (AUC). Results The training data set was comprised of 335 patients (median age, 48 years [IQR, 42-54 years]) from centers A and B, and 590, 280, and 384 patients (median age, 48 years [IQR, 41-55 years]) were included in the three external test data sets. Molecular subtype (odds ratio [OR] range, 4.76-8.39 [95% CI: 1.79, 24.21]; all P < .01), ITH index (OR, 30.05 [95% CI: 8.43, 122.64]; P < .001), and C-radiomics score (OR, 29.90 [95% CI: 12.04, 81.70]; P < .001) were independently associated with the odds of achieving pCR. The combined model showed good performance for predicting pCR to NAC in the training data set (AUC, 0.90) and external test data sets (AUC range, 0.83-0.87). Conclusion A model that combined an index created from pretreatment MRI-based imaging features quantitating ITH, C-radiomics score, and clinicopathologic variables showed good performance for predicting pCR to NAC in patients with breast cancer. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Rauch in this issue.

CXCL8 as a Potential Biomarker for Crohn's Disease is Associated with Immune Infiltration and RNA Methylation.

TRP channels have an important role in regulating the function of gastrointestinal epithelial cells. The aim of this study was to investigate the molecular mechanisms of genes associated with TRP channels in Crohn's disease (CD) by bioinformatics approach and to identify potential key biomarkers. In our study, we identified TRP channel-related differentially expressed genes (DEGs) based on the GSE95095 dataset and the TRP channel-related gene set from the GeneCards database. Hub genes (CXCL8, HIF1A, NGF, JUN, IL1A) were identified by the PPI network and validated by the external GSE52746 dataset. Immune infiltration analysis revealed that CXCL8 was significantly correlated with B cells memory, NK cells activated, Mast cells resting, Mast cells activated, and Neutrophils. GSEA of CXCL8 results showed inositol phosphate metabolism, RNA polymerase, propanoate metabolism, MAPK signaling pathway, base excision repair, and Calcium signaling pathway. In addition, we constructed a lncRNA-miRNA-mRNA ceRNA network and a drug-gene interaction network. Finally, we performed in vitro experiments to verify that LPS induced CXCL8 expression in HT-29 cells and that knockdown of CXCL8 inhibited the inflammatory stimulatory effects of LPS. This study reveals that CXCL8 plays an important role in the pathogenesis of Crohn's disease and is expected to be a novel biomarker.

CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer With Modality-Correlated Cross-Attention for Brain Tumor Segmentation.

Brain tumor segmentation (BTS) in magnetic resonance image (MRI) is crucial for brain tumor diagnosis, cancer management and research purposes. With the great success of the ten-year BraTS challenges as well as the advances of CNN and Transformer algorithms, a lot of outstanding BTS models have been proposed to tackle the difficulties of BTS in different technical aspects. However, existing studies hardly consider how to fuse the multi-modality images in a reasonable manner. In this paper, we leverage the clinical knowledge of how radiologists diagnose brain tumors from multiple MRI modalities and propose a clinical knowledge-driven brain tumor segmentation model, called CKD-TransBTS. Instead of directly concatenating all the modalities, we re-organize the input modalities by separating them into two groups according to the imaging principle of MRI. A dual-branch hybrid encoder with the proposed modality-correlated cross-attention block (MCCA) is designed to extract the multi-modality image features. The proposed model inherits the strengths from both Transformer and CNN with the local feature representation ability for precise lesion boundaries and long-range feature extraction for 3D volumetric images. To bridge the gap between Transformer and CNN features, we propose a Trans&CNN Feature Calibration block (TCFC) in the decoder. We compare the proposed model with six CNN-based models and six transformer-based models on the BraTS 2021 challenge dataset. Extensive experiments demonstrate that the proposed model achieves state-of-the-art brain tumor segmentation performance compared with all the competitors.

HoVer-Trans: Anatomy-Aware HoVer-Transformer for ROI-Free Breast Cancer Diagnosis in Ultrasound Images.

Ultrasonography is an important routine examination for breast cancer diagnosis, due to its non-invasive, radiation-free and low-cost properties. However, the diagnostic accuracy of breast cancer is still limited due to its inherent limitations. Then, a precise diagnose using breast ultrasound (BUS) image would be significant useful. Many learning-based computer-aided diagnostic methods have been proposed to achieve breast cancer diagnosis/lesion classification. However, most of them require a pre-define region of interest (ROI) and then classify the lesion inside the ROI. Conventional classification backbones, such as VGG16 and ResNet50, can achieve promising classification results with no ROI requirement. But these models lack interpretability, thus restricting their use in clinical practice. In this study, we propose a novel ROI-free model for breast cancer diagnosis in ultrasound images with interpretable feature representations. We leverage the anatomical prior knowledge that malignant and benign tumors have different spatial relationships between different tissue layers, and propose a HoVer-Transformer to formulate this prior knowledge. The proposed HoVer-Trans block extracts the inter- and intra-layer spatial information horizontally and vertically. We conduct and release an open dataset GDPH&SYSUCC for breast cancer diagnosis in BUS. The proposed model is evaluated in three datasets by comparing with four CNN-based models and three vision transformer models via five-fold cross validation. It achieves state-of-the-art classification performance (GDPH&SYSUCC AUC: 0.924, ACC: 0.893, Spec: 0.836, Sens: 0.926) with the best model interpretability. In the meanwhile, our proposed model outperforms two senior sonographers on the breast cancer diagnosis when only one BUS image is given (GDPH&SYSUCC-AUC ours: 0.924 vs. reader1: 0.825 vs. reader2: 0.820).

LINC01116 modulates EMT process via binding with AGO1 mRNA in oesophageal squamous cell carcinoma.

Recent researches have uncovered that long non-coding RNAs (lncRNAs) are closely correlated with the development of different diseases, while biological functions and hidden molecular mechanisms of antisense lncRNAs in oesophageal squamous cell carcinoma (OSCC) remain unclear. Here, we identified upregulation of LINC01116 in RNA sequencing data, online database, and in OSCC and intraepithelial neoplasia (IEN) specimens. Functionally, LINC01116 facilitates OSCC advancement and metastasis in vitro and vivo. Mechanistically, elevated expression of LINC01116 in OSCC cells other than tumor stroma and cytoplasmic enables it to activate AGO1 expression via complementary binding with AGO1 mRNA to facilitate EMT process of OSCC.

Using Machine Learning Methods to Assess Lymphovascular Invasion and Survival in Breast Cancer: Performance of Combining Preoperative Clinical and MRI Characteristics.

BACKGROUND: Preoperative assessment of lymphovascular invasion (LVI) in invasive breast cancer (IBC) is of high clinical relevance for treatment decision-making and prognosis. PURPOSE: To investigate the associations of preoperative clinical and magnetic resonance imaging (MRI) characteristics with LVI and disease-free survival (DFS) by using machine learning methods in patients with IBC. STUDY TYPE: Retrospective. POPULATION: Five hundred and seventy-five women (range: 24-79 years) with IBC who underwent preoperative MRI examinations at two hospitals, divided into the training (N = 386) and validation datasets (N = 189). FIELD STRENGTH/SEQUENCE: Axial fat-suppressed T2-weighted turbo spin-echo sequence and dynamic contrast-enhanced with fat-suppressed T1-weighted three-dimensional gradient echo imaging. ASSESSMENT: MRI characteristics (clinical T stage, breast edema score, MRI axillary lymph node status, multicentricity or multifocality, enhancement pattern, adjacent vessel sign, and increased ipsilateral vascularity) were reviewed independently by three radiologists. Logistic regression (LR), eXtreme Gradient Boosting (XGBoost), k-Nearest Neighbor (KNN), and Support Vector Machine (SVM) algorithms were used to establish the models by combing preoperative clinical and MRI characteristics for assessing LVI status in the training dataset, and the methods were further applied in the validation dataset. The LVI score was calculated using the best-performing of the four models to analyze the association with DFS. STATISTICAL TESTS: Chi-squared tests, variance inflation factors, receiver operating characteristics (ROC), Kaplan-Meier curve, log-rank, Cox regression, and intraclass correlation coefficient were performed. The area under the ROC curve (AUC) and hazard ratios (HR) were calculated. A P-value <0.05 was considered statistically significant. RESULTS: The model established by the XGBoost algorithm had better performance than LR, SVM, and KNN models, achieving an AUC of 0.832 (95% confidence interval [CI]: 0.789, 0.876) in the training dataset and 0.838 (95% CI: 0.775, 0.901) in the validation dataset. The LVI score established by the XGBoost model was an independent indicator of DFS (adjusted HR: 2.66, 95% CI: 1.22-5.80). DATA CONCLUSION: The XGBoost model based on preoperative clinical and MRI characteristics may help to investigate the LVI status and survival in patients with IBC. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

A reciprocal learning strategy for semisupervised medical image segmentation.

BACKGROUND: Semisupervised strategy has been utilized to alleviate issues from segmentation applications due to challenges in collecting abundant annotated segmentation masks, which is an essential prerequisite for training high-performance 3D convolutional neural networks (CNNs) . PURPOSE: Existing semisupervised segmentation methods are mainly concerned with how to generate the pseudo labels with regularization but not evaluate the quality of the pseudo labels explicitly. To alleviate this problem, we offer a simple yet effective reciprocal learning strategy for semisupervised volumetric medical image segmentation, which generates more reliable pseudo labels for the unannotated data. METHODS: Our proposed reciprocal learning is achieved through a pair of networks, one as a teacher network and the other as a student network. The student network learns from pseudo labels generated by the teacher network. In addition, the teacher network autonomously optimizes its parameters based on the reciprocal feedback signals from the student's performance on the annotated images. The efficacy of the proposed method is evaluated on three medical image data sets, including 82 pancreas computed tomography (CT) scans (training/testing: 62/20), 100 left atrium gadolinium-enhanced magnetic resonance (MR) scans (training/testing: 80/20), and 200 breast cancer MR scans (training/testing: 68/132). The comparison methods include mean teacher (MT) model, uncertainty-aware MT (UA-MT) model, shape-aware adversarial network (SASSNet), and transformation-consistent self-ensembling model (TCSM). The evaluation metrics are Dice similarity coefficient (Dice), Jaccard index (Jaccard), 95% Hausdorff distance (95HD), and average surface distance (ASD). The Wilcoxon signed-rank test is used to conduct the statistical analyses. RESULTS: By utilizing 20% labeled data and 80% unlabeled data for training, our proposed method achieves an average Dice of 84.77%/90.46%/78.53%, Jaccard of 73.71%/82.67%/69.00%, ASD of 1.58/1.90/0.57, and 95HD of 6.24/5.97/4.34 on pancreas/left atrium/breast data sets, respectively. These results outperform several cutting-edge semisupervised approaches, showing the feasibility of our method for the challenging semisupervised segmentation applications. CONCLUSIONS: The proposed reciprocal learning strategy is a general semisupervised solution and has the potential to be applied for other 3D segmentation tasks.

Axillary ultrasound after neoadjuvant therapy reduces the false-negative rate of sentinel lymph node biopsy in patients with cytologically node-positive breast cancer.

OBJECTIVES: This study aimed to determine whether post-neoadjuvant therapy (NAT) axillary ultrasound (AUS) could reduce the false-negative rate (FNR) of sentinel lymph node biopsy (SLNB). We also performed subgroup analyses to identify the appropriate patient for SLNB. METHODS: A total of 220 patients with cytologically proven axillary node-positive breast cancer who underwent both SLNB and axillary lymph node dissection (ALND) after NAT were included. We calculated the FNR of SLNB. In the case of post-NAT AUS results available, AUS was classified as negative or positive. Then the FNR of post-NAT AUS combined with SLNB was evaluated. Subgroup analyses based on the number of sentinel lymph nodes removed, molecular subtypes, and the clinical N stage were also performed. RESULTS: The overall axillary lymph node pathological complete response rate was 45.5% (100/220). The FNR of SLNB alone was 15.8% (95%CI: 9.2 to 22.5%). Post-NAT AUS results were available for 181 patients. When combined negative post-NAT AUS results and SLNB, the FNR was reduced to 7.5% (95%CI: 2.4 to 12.7%). Subgroup analyses of the FNR for SLNB alone and negative post-NAT AUS combined with SLNB were shown as follows: in cases patients with less than three sentinel lymph nodes (SLNs) and at least three SLNs removed, the FNR was decreased from 24.5 to 13.2%, and 9.0 to 5.0%, respectively. The FNR was decreased from 20.8 to 10.5% in HR+/HER2+subgroup, 21.4 to 16.7% in HR-/HER2+subgroup, 15.9 to 7.0% in HR+/HER2- subgroup, and 0% in HR-/HER2- subgroup, respectively. For cN1 patients, the FNR was decreased from 18.1 to 12.1% while 17.1 to 3.6% for cN2 patients and 0% for cN3 patients. CONCLUSION: Using negative post-NAT AUS may help to decrease the FNR and improve patient selection for SLNB.

Computerized tumor-infiltrating lymphocytes density score predicts survival of patients with resectable lung adenocarcinoma.

A high abundance of tumor-infiltrating lymphocytes (TILs) has a positive impact on the prognosis of patients with lung adenocarcinoma (LUAD). We aimed to develop and validate an artificial intelligence-driven pathological scoring system for assessing TILs on H&E-stained whole-slide images of LUAD. Deep learning-based methods were applied to calculate the densities of lymphocytes in cancer epithelium (DLCE) and cancer stroma (DLCS), and a risk score (WELL score) was built through linear weighting of DLCE and DLCS. Association between WELL score and patient outcome was explored in 793 patients with stage I-III LUAD in four cohorts. WELL score was an independent prognostic factor for overall survival and disease-free survival in the discovery cohort and validation cohorts. The prognostic prediction model-integrated WELL score demonstrated better discrimination performance than the clinicopathologic model in the four cohorts. This artificial intelligence-based workflow and scoring system could promote risk stratification for patients with resectable LUAD.

Multi-scale pathology image texture signature is a prognostic factor for resectable lung adenocarcinoma: a multi-center, retrospective study.

BACKGROUND: Tumor histomorphology analysis plays a crucial role in predicting the prognosis of resectable lung adenocarcinoma (LUAD). Computer-extracted image texture features have been previously shown to be correlated with outcome. However, a comprehensive, quantitative, and interpretable predictor remains to be developed. METHODS: In this multi-center study, we included patients with resectable LUAD from four independent cohorts. An automated pipeline was designed for extracting texture features from the tumor region in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) at multiple magnifications. A multi-scale pathology image texture signature (MPIS) was constructed with the discriminative texture features in terms of overall survival (OS) selected by the LASSO method. The prognostic value of MPIS for OS was evaluated through univariable and multivariable analysis in the discovery set (n = 111) and the three external validation sets (V1, n = 115; V2, n = 116; and V3, n = 246). We constructed a Cox proportional hazards model incorporating clinicopathological variables and MPIS to assess whether MPIS could improve prognostic stratification. We also performed histo-genomics analysis to explore the associations between texture features and biological pathways. RESULTS: A set of eight texture features was selected to construct MPIS. In multivariable analysis, a higher MPIS was associated with significantly worse OS in the discovery set (HR 5.32, 95%CI 1.72-16.44; P = 0.0037) and the three external validation sets (V1: HR 2.63, 95%CI 1.10-6.29, P = 0.0292; V2: HR 2.99, 95%CI 1.34-6.66, P = 0.0075; V3: HR 1.93, 95%CI 1.15-3.23, P = 0.0125). The model that integrated clinicopathological variables and MPIS had better discrimination for OS compared to the clinicopathological variables-based model in the discovery set (C-index, 0.837 vs. 0.798) and the three external validation sets (V1: 0.704 vs. 0.679; V2: 0.728 vs. 0.666; V3: 0.696 vs. 0.669). Furthermore, the identified texture features were associated with biological pathways, such as cytokine activity, structural constituent of cytoskeleton, and extracellular matrix structural constituent. CONCLUSIONS: MPIS was an independent prognostic biomarker that was robust and interpretable. Integration of MPIS with clinicopathological variables improved prognostic stratification in resectable LUAD and might help enhance the quality of individualized postoperative care.

The value of magnetic resonance imaging-based tumor shape features for assessing microsatellite instability status in endometrial cancer.

Background: Microsatellite instability (MSI) status can be used for the classification and risk stratification of endometrial cancer (EC). This study aimed to investigate whether magnetic resonance imaging (MRI)-based tumor shape features can help assess MSI status in EC before surgery. Methods: The medical records of 88 EC patients with MSI status were retrospectively reviewed. Quantitative and subjective shape features based on MRI were used to assess MSI status. Variables were compared using the Student's t-test, χ2 test, or Wilcoxon rank-sum test where appropriate. Univariate and multivariate analyses were performed by the logistic regression model. The area under the curve (AUC) was used to estimate the discrimination performance of variables. Results: There were 23 patients with MSI, and 65 patients with microsatellite stability (MSS) in this study. Eccentricity and shape type showed significant differences between MSI and MSS (P=0.039 and P=0.033, respectively). The AUC values of eccentricity, shape type, and the combination of 2 features for assessing MSI were 0.662 [95% confidence interval (CI): 0.554-0.770], 0.627 (95% CI: 0.512-0.743), and 0.727 (95% CI: 0.613-0.842), respectively. Considering the International Federation of Gynecology and Obstetrics (FIGO) staging, eccentricity maintained a significant difference in stages I-II (P=0.039), while there was no statistical difference in stages III-IV (P=0.601). Conclusions: It is possible that MRI-based tumor shape features, including eccentricity and shape type, could be promising markers for assessing MSI status. The features may aid in the preliminary screening of EC patients with MSI.

Multiple-parameter MRI after neoadjuvant systemic therapy combining clinicopathologic features in evaluating axillary pathologic complete response in patients with clinically node-positive breast cancer.

OBJECTIVE: This study aimed to evaluate axillary pathologic complete response (pCR) after neoadjuvant systemic therapy (NST) in clinically node-positive breast cancer (BC) patients based on post-NST multiple-parameter MRI and clinicopathological characteristics. METHODS: In this retrospective study, females with clinically node-positive BC who received NST and followed by surgery between January 2017 and September 2021 were included. All axillary lymph nodes (ALNs) on MRI were matched with pathology by ALN markers or sizes. MRI morphological parameters, signal intensity curve (TIC) patterns and apparent diffusion coefficient (ADC) values of post-NST ALNs were measured. The clinicopathological characteristics was also collected and analyzed. Univariable and multivariable logistic regression analyses were performed to evaluate the independent predictors of axillary pCR. RESULTS: Pathologically confirmed 137 non-pCR ALNs in 71 patients and 87 pCR ALNs in 87 patients were included in this study. Cortical thickness, fatty hilum, and TIC patterns of ALNs, hormone receptor, and human epidermal growth factor receptor 2 (HER2) status were significantly different between the two groups (all, p < 0.05). There was no significant difference for ADC values (p = 0.875). On multivariable analysis, TIC patterns (odds ratio [OR], 2.67, 95% confidence interval [CI]: 1.33, 5.34, p = 0.006), fatty hilum (OR, 2.88, 95% CI:1.39, 5.98, p = 0.004), hormone receptor (OR, 8.40, 95% CI: 2.48, 28.38, p = 0.001) and HER2 status (OR, 8.57, 95% CI: 3.85, 19.08, p < 0.001) were identified as independent predictors associated with axillary pCR. The area under the curve of the multivariate analysis using these predictors was 0.85 (95% CI: 0.79, 0.91). CONCLUSION: Combining post-NST multiple-parameter MRI and clinicopathological characteristics allowed more accurate identification of BC patients who had received axillary pCR after NST. ADVANCES IN KNOWLEDGE: A combined model incorporated multiple-parameter MRI and clinicopathologic features demonstrated good performance in evaluating axillary pCR preoperatively and non-invasively.

Histopathological Tissue Segmentation of Lung Cancer with Bilinear CNN and Soft Attention.

Automatic tissue segmentation in whole-slide images (WSIs) is a critical task in hematoxylin and eosin- (H&E-) stained histopathological images for accurate diagnosis and risk stratification of lung cancer. Patch classification and stitching the classification results can fast conduct tissue segmentation of WSIs. However, due to the tumour heterogeneity, large intraclass variability and small interclass variability make the classification task challenging. In this paper, we propose a novel bilinear convolutional neural network- (Bilinear-CNN-) based model with a bilinear convolutional module and a soft attention module to tackle this problem. This method investigates the intraclass semantic correspondence and focuses on the more distinguishable features that make feature output variations relatively large between interclass. The performance of the Bilinear-CNN-based model is compared with other state-of-the-art methods on the histopathological classification dataset, which consists of 107.7 k patches of lung cancer. We further evaluate our proposed algorithm on an additional dataset from colorectal cancer. Extensive experiments show that the performance of our proposed method is superior to that of previous state-of-the-art ones and the interpretability of our proposed method is demonstrated by Grad-CAM.

Automated whole-slide images assessment of immune infiltration in resected non-small-cell lung cancer: towards better risk-stratification.

BACKGROUND: High immune infiltration is associated with favourable prognosis in patients with non-small-cell lung cancer (NSCLC), but an automated workflow for characterizing immune infiltration, with high validity and reliability, remains to be developed. METHODS: We performed a multicentre retrospective study of patients with completely resected NSCLC. We developed an image analysis workflow for automatically evaluating the density of CD3+ and CD8+ T-cells in the tumour regions on immunohistochemistry (IHC)-stained whole-slide images (WSIs), and proposed an immune scoring system "I-score" based on the automated assessed cell density. RESULTS: A discovery cohort (n = 145) and a validation cohort (n = 180) were used to assess the prognostic value of the I-score for disease-free survival (DFS). The I-score (two-category) was an independent prognostic factor after adjusting for other clinicopathologic factors. Compared with a low I-score (two-category), a high I-score was associated with significantly superior DFS in the discovery cohort (adjusted hazard ratio [HR], 0.54; 95% confidence interval [CI] 0.33-0.86; P = 0.010) and validation cohort (adjusted HR, 0.57; 95% CI 0.36-0.92; P = 0.022). The I-score improved the prognostic stratification when integrating it into the Cox proportional hazard regression models with other risk factors (discovery cohort, C-index 0.742 vs. 0.728; validation cohort, C-index 0.695 vs. 0.685). CONCLUSION: This automated workflow and immune scoring system would advance the clinical application of immune microenvironment evaluation and support the clinical decision making for patients with resected NSCLC.

Multi-layer pseudo-supervision for histopathology tissue semantic segmentation using patch-level classification labels.

Tissue-level semantic segmentation is a vital step in computational pathology. Fully-supervised models have already achieved outstanding performance with dense pixel-level annotations. However, drawing such labels on the giga-pixel whole slide images is extremely expensive and time-consuming. In this paper, we use only patch-level classification labels to achieve tissue semantic segmentation on histopathology images, finally reducing the annotation efforts. We propose a two-step model including a classification and a segmentation phases. In the classification phase, we propose a CAM-based model to generate pseudo masks by patch-level labels. In the segmentation phase, we achieve tissue semantic segmentation by our propose Multi-Layer Pseudo-Supervision. Several technical novelties have been proposed to reduce the information gap between pixel-level and patch-level annotations. As a part of this paper, we introduce a new weakly-supervised semantic segmentation (WSSS) dataset for lung adenocarcinoma (LUAD-HistoSeg). We conduct several experiments to evaluate our proposed model on two datasets. Our proposed model outperforms five state-of-the-art WSSS approaches. Note that we can achieve comparable quantitative and qualitative results with the fully-supervised model, with only around a 2% gap for MIoU and FwIoU. By comparing with manual labeling on a randomly sampled 100 patches dataset, patch-level labeling can greatly reduce the annotation time from hours to minutes. The source code and the released datasets are available at: https://github.com/ChuHan89/WSSS-Tissue.