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

SC-Net: Symmetrical conical network for colorectal pathology image segmentation

BACKGROUND AND OBJECTIVE

Image segmentation of histopathology of colorectal cancer is a core task of computer aided medical image diagnosis system. Existing convolutional neural networks generally extract multi-scale information in linear flow structures by inserting multi-branch modules, which is difficult to extract heterogeneous semantic information under multi-level and different receptive field and tough to establish context dependency among different receptive field features.

METHODS

To address these issues, we propose a symmetric spiral progressive feature fusion encoder-decoder network called the Symmetric Conical Network (SC-Net). First, we design a Multi-scale Feature Extraction Block (MFEB) matching with the Symmetric Conical Network to obtain multi-branch heterogeneous semantic information under different receptive fields, so as to enrich the diversity of extracted feature information. The encoder is composed of MFEB through spiral and multi-branch arrangement to enhance context dependence between different information flow. Secondly, the information loss of contour, color and others in high-level semantic information through causally stacking MFEB, the Feature Mapping Layer (FML) is designed to map low-level features to high-level semantic features along the down-sampling branch and solve the problem of insufficient global feature extraction in deep levels.

RESULTS

The SC-Net was evaluated on our self-constructed colorectal cancer dataset, a publicly available breast cancer dataset and a polyp dataset. The results revealed that the mDice of segmentation reached 0.8611, 0.7259 and 0.7144. We compare our model with the state-of-art semantic segmentation UNet++, PSPNet, Attention U-Net, R2U-Net and other advanced segmentation networks. The experimental results demonstrate that we achieve the most advanced performance.

CONCLUSIONS

The results indicate that the proposed SC-Net excels in segmenting H&E stained pathology images, effectively preserving morphological features and spatial information even in scenarios with weak texture, poor contrast, and variations in appearance.

SG-MIAN: Self-guided multiple information aggregation network for image-level weakly supervised skin lesion segmentation

Nowadays, skin disease is becoming one of the most malignant diseases that threaten people's health. Computer aided diagnosis based on deep learning has become a widely used technology to assist medical professionals in diagnosis, and segmentation of lesion areas is one of the most important steps in it. However, traditional medical image segmentation methods rely on numerous pixel-level labels for fully supervised training, and such labeling process is time-consuming and requires professional competence. In order to reduce the costs of pixel-level labeling, we proposed a method only using image-level label to segment skin lesion areas. Due to the lack of lesion's spatial and intensity information in image-level labels, and the wide distribution range of irregular shape and different texture on skin lesions, the algorithm must pay great attention to the automatic lesion localization and perception of lesion boundary. In this paper, we proposed a Self-Guided Multiple Information Aggregation Network (SG-MIAN). Our backbone network MIAN utilizes the Multiple Spatial Perceptron (MSP) solely using classification information as guidance to discriminate the key classification features of lesion areas, and thereby performing more accurate localization and activation of lesion areas. Additionally, adjunct to MSP, we also proposed an Auxiliary Activation Structure (AAS) and two auxiliary loss functions to further self-guided boundary correction, achieving the goal of accurate boundary activation. To verify the effectiveness of the proposed method, we conducted extensive experiments using the HAM10000 dataset and the PH2dataset, which demonstrated superior performance compared to most existing weakly supervised segmentation methods.

DEPICTER: Deep representation clustering for histology annotation

Automatic segmentation of histopathology whole-slide images (WSI) usually involves supervised training of deep learning models with pixel-level labels to classify each pixel of the WSI into tissue regions such as benign or cancerous. However, fully supervised segmentation requires large-scale data manually annotated by experts, which can be expensive and time-consuming to obtain. Non-fully supervised methods, ranging from semi-supervised to unsupervised, have been proposed to address this issue and have been successful in WSI segmentation tasks. But these methods have mainly been focused on technical advancements in algorithmic performance rather than on the development of practical tools that could be used by pathologists or researchers in real-world scenarios. In contrast, we present DEPICTER (Deep rEPresentatIon ClusTERing), an interactive segmentation tool for histopathology annotation that produces a patch-wise dense segmentation map at WSI level. The interactive nature of DEPICTER leverages self- and semi-supervised learning approaches to allow the user to participate in the segmentation producing reliable results while reducing the workload. DEPICTER consists of three steps: first, a pretrained model is used to compute embeddings from image patches. Next, the user selects a number of benign and cancerous patches from the multi-resolution image. Finally, guided by the deep representations, label propagation is achieved using our novel seeded iterative clustering method or by directly interacting with the embedding space via feature space gating. We report both real-time interaction results with three pathologists and evaluate the performance on three public cancer classification dataset benchmarks through simulations. The code and demos of DEPICTER are publicly available at https://github.com/eduardchelebian/depicter.

Modern Image-Guided Surgery: A Narrative Review of Medical Image Processing and Visualization

Medical image analysis forms the basis of image-guided surgery (IGS) and many of its fundamental tasks. Driven by the growing number of medical imaging modalities, the research community of medical imaging has developed methods and achieved functionality breakthroughs. However, with the overwhelming pool of information in the literature, it has become increasingly challenging for researchers to extract context-relevant information for specific applications, especially when many widely used methods exist in a variety of versions optimized for their respective application domains. By being further equipped with sophisticated three-dimensional (3D) medical image visualization and digital reality technology, medical experts could enhance their performance capabilities in IGS by multiple folds. The goal of this narrative review is to organize the key components of IGS in the aspects of medical image processing and visualization with a new perspective and insights. The literature search was conducted using mainstream academic search engines with a combination of keywords relevant to the field up until mid-2022. This survey systemically summarizes the basic, mainstream, and state-of-the-art medical image processing methods as well as how visualization technology like augmented/mixed/virtual reality (AR/MR/VR) are enhancing performance in IGS. Further, we hope that this survey will shed some light on the future of IGS in the face of challenges and opportunities for the research directions of medical image processing and visualization.

Preparing Data for Artificial Intelligence in Pathology with Clinical-Grade Performance

The pathology is decisive for disease diagnosis but relies heavily on experienced pathologists. In recent years, there has been growing interest in the use of artificial intelligence in pathology (AIP) to enhance diagnostic accuracy and efficiency. However, the impressive performance of deep learning-based AIP in laboratory settings often proves challenging to replicate in clinical practice. As the data preparation is important for AIP, the paper has reviewed AIP-related studies in the PubMed database published from January 2017 to February 2022, and 118 studies were included. An in-depth analysis of data preparation methods is conducted, encompassing the acquisition of pathological tissue slides, data cleaning, screening, and subsequent digitization. Expert review, image annotation, dataset division for model training and validation are also discussed. Furthermore, we delve into the reasons behind the challenges in reproducing the high performance of AIP in clinical settings and present effective strategies to enhance AIP's clinical performance. The robustness of AIP depends on a randomized collection of representative disease slides, incorporating rigorous quality control and screening, correction of digital discrepancies, reasonable annotation, and sufficient data volume. Digital pathology is fundamental in clinical-grade AIP, and the techniques of data standardization and weakly supervised learning methods based on whole slide image (WSI) are effective ways to overcome obstacles of performance reproduction. The key to performance reproducibility lies in having representative data, an adequate amount of labeling, and ensuring consistency across multiple centers. Digital pathology for clinical diagnosis, data standardization and the technique of WSI-based weakly supervised learning will hopefully build clinical-grade AIP.

Weakly supervised joint whole-slide segmentation and classification in prostate cancer

The identification and segmentation of histological regions of interest can provide significant support to pathologists in their diagnostic tasks. However, segmentation methods are constrained by the difficulty in obtaining pixel-level annotations, which are tedious and expensive to collect for whole-slide images (WSI). Though several methods have been developed to exploit image-level weak-supervision for WSI classification, the task of segmentation using WSI-level labels has received very little attention. The research in this direction typically require additional supervision beyond image labels, which are difficult to obtain in real-world practice. In this study, we propose WholeSIGHT, a weakly-supervised method that can simultaneously segment and classify WSIs of arbitrary shapes and sizes. Formally, WholeSIGHT first constructs a tissue-graph representation of WSI, where the nodes and edges depict tissue regions and their interactions, respectively. During training, a graph classification head classifies the WSI and produces node-level pseudo-labels via post-hoc feature attribution. These pseudo-labels are then used to train a node classification head for WSI segmentation. During testing, both heads simultaneously render segmentation and class prediction for an input WSI. We evaluate the performance of WholeSIGHT on three public prostate cancer WSI datasets. Our method achieves state-of-the-art weakly-supervised segmentation performance on all datasets while resulting in better or comparable classification with respect to state-of-the-art weakly-supervised WSI classification methods. Additionally, we assess the generalization capability of our method in terms of segmentation and classification performance, uncertainty estimation, and model calibration. Our code is available at: https://github.com/histocartography/wholesight.

Computerized tertiary lymphoid structures density on H&E-images is a prognostic biomarker in resectable lung adenocarcinoma

The increased amount of tertiary lymphoid structures (TLSs) is associated with a favorable prognosis in patients with lung adenocarcinoma (LUAD). However, evaluating TLSs manually is an experience-dependent and time-consuming process, which limits its clinical application. In this multi-center study, we developed an automated computational workflow for quantifying the TLS density in the tumor region of routine hematoxylin and eosin (H&E)-stained whole-slide images (WSIs). The association between the computerized TLS density and disease-free survival (DFS) was further explored in 802 patients with resectable LUAD of three cohorts. Additionally, a Cox proportional hazard regression model, incorporating clinicopathological variables and the TLS density, was established to assess its prognostic ability. The computerized TLS density was an independent prognostic biomarker in patients with resectable LUAD. The integration of the TLS density with clinicopathological variables could support individualized clinical decision-making by improving prognostic stratification.

DFTNet: Dual-Path Feature Transfer Network for Weakly Supervised Medical Image Segmentation

Medical image segmentation has long suffered from the problem of expensive labels. Acquiring pixel-level annotations is time-consuming, labor-intensive, and relies on extensive expert knowledge. Bounding box annotations, in contrast, are relatively easy to acquire. Thus, in this paper, we explore to segment images through a novel Dual-path Feature Transfer design with only bounding box annotations. Specifically, a Target-aware Reconstructor is proposed to extract target-related features by reconstructing the pixels within the bounding box through the channel and spatial attention module. Then, a sliding Feature Fusion and Transfer Module (FFTM) fuses the extracted features from Reconstructor and transfers them to guide the Segmentor for segmentation. Finally, we present the Confidence Ranking Loss (CRLoss) which dynamically assigns weights to the loss of each pixel based on the network's confidence. CRLoss mitigates the impact of inaccurate pseudo-labels on performance. Extensive experiments demonstrate that our proposed model achieves state-of-the-art performance on the Medical Segmentation Decathlon (MSD) Brain Tumour and PROMISE12 datasets.

Artificial intelligence-quantified tumour-lymphocyte spatial interaction predicts disease-free survival in resected lung adenocarcinoma: A graph-based, multicentre study

BACKGROUND AND OBJECTIVE

A high degree of lymphocyte infiltration is related to superior outcomes amongst patients with lung adenocarcinoma. Recent evidence indicates that the spatial interactions between tumours and lymphocytes also influence the anti-tumour immune responses, but the spatial analysis at the cellular level remains insufficient.

METHODS

We proposed an artificial intelligence-quantified Tumour-Lymphocyte Spatial Interaction score (TLSI-score) by calculating the ratio between the number of spatial adjacent tumour-lymphocyte and the number of tumour cells based on topology cell graph constructed using H&E-stained whole-slide images. The association of TLSI-score with disease-free survival (DFS) was explored in 529 patients with lung adenocarcinoma across three independent cohorts (D1, 275; V1, 139; V2, 115).

RESULTS

After adjusting for pTNM stage and other clinicopathologic risk factors, a higher TLSI-score was independently associated with longer DFS than a low TLSI-score in the three cohorts [D1, adjusted hazard ratio (HR), 0.674; 95% confidence interval (CI) 0.463-0.983; p = 0.040; V1, adjusted HR, 0.408; 95% CI 0.223-0.746; p = 0.004; V2, adjusted HR, 0.294; 95% CI 0.130-0.666; p = 0.003]. By integrating the TLSI-score with clinicopathologic risk factors, the integrated model (full model) improves the prediction of DFS in three independent cohorts (C-index, D1, 0.716 vs. 0.701; V1, 0.666 vs. 0.645; V2, 0.708 vs. 0.662) CONCLUSIONS: TLSI-score shows the second highest relative contribution to the prognostic prediction model, next to the pTNM stage. TLSI-score can assist in the characterising of tumour microenvironment and is expected to promote individualized treatment and follow-up decision-making in clinical practice.

Weakly supervised semantic segmentation of histological tissue via attention accumulation and pixel-level contrast learning

Objective. Histopathology image segmentation can assist medical professionals in identifying and diagnosing diseased tissue more efficiently. Although fully supervised segmentation models have excellent performance, the annotation cost is extremely expensive. Weakly supervised models are widely used in medical image segmentation due to their low annotation cost. Nevertheless, these weakly supervised models have difficulty in accurately locating the boundaries between different classes of regions in pathological images, resulting in a high rate of false alarms Our objective is to design a weakly supervised segmentation model to resolve the above problems.Approach. The segmentation model is divided into two main stages, the generation of pseudo labels based on class residual attention accumulation network (CRAANet) and the semantic segmentation based on pixel feature space construction network (PFSCNet). CRAANet provides attention scores for each class through the class residual attention module, while the Attention Accumulation (AA) module overlays the attention feature maps generated in each training epoch. PFSCNet employs a network model containing an inflated convolutional residual neural network and a multi-scale feature-aware module as the segmentation backbone, and proposes dense energy loss and pixel clustering modules are based on contrast learning to solve the pseudo-labeling-inaccuracy problem.Main results. We validate our method using the lung adenocarcinoma (LUAD-HistoSeg) dataset and the breast cancer (BCSS) dataset. The results of the experiments show that our proposed method outperforms other state-of-the-art methods on both datasets in several metrics. This suggests that it is capable of performing well in a wide variety of histopathological image segmentation tasks.Significance. We propose a weakly supervised semantic segmentation network that achieves approximate fully supervised segmentation performance even in the case of incomplete labels. The proposed AA and pixel-level contrast learning also make the edges more accurate and can well assist pathologists in their research.

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.

Fast and scalable search of whole-slide images via self-supervised deep learning

The adoption of digital pathology has enabled the curation of large repositories of gigapixel whole-slide images (WSIs). Computationally identifying WSIs with similar morphologic features within large repositories without requiring supervised training can have significant applications. However, the retrieval speeds of algorithms for searching similar WSIs often scale with the repository size, which limits their clinical and research potential. Here we show that self-supervised deep learning can be leveraged to search for and retrieve WSIs at speeds that are independent of repository size. The algorithm, which we named SISH (for self-supervised image search for histology) and provide as an open-source package, requires only slide-level annotations for training, encodes WSIs into meaningful discrete latent representations and leverages a tree data structure for fast searching followed by an uncertainty-based ranking algorithm for WSI retrieval. We evaluated SISH on multiple tasks (including retrieval tasks based on tissue-patch queries) and on datasets spanning over 22,000 patient cases and 56 disease subtypes. SISH can also be used to aid the diagnosis of rare cancer types for which the number of available WSIs is often insufficient to train supervised deep-learning models.