Liver Dataset Research Articles

Adaptive wavelet-VNet for single-sample test time adaptation in medical image segmentation.

In medical image segmentation, a domain gap often exists between training and testing datasets due to different scanners or imaging protocols, which leads to performance degradation in deep learning-based segmentation models. Given the high cost of manual labeling and the need for privacy protection, it is often challenging to annotate the testing (target) domain data for model fine-tuning or to collect data from different domains to train domain generalization models. Therefore, using only unlabeled target domain data for test-time adaptation (TTA) presents a more practical but challenging solution. To improve the segmentation accuracy of deep learning-based models on unseen datasets, and especially to enhance the efficiency and stability of TTA for individual samples from heterogeneous domains. In this study, we proposed to dynamically adapt a wavelet-VNet (WaVNet) to unseen target domains with a hybrid objective function, based on each unlabeled test sample during the test time. We embedded multiscale wavelet coefficients into a V-Net encoder and adaptively adjusted the spatial and spectral features according to the input, and the model parameters were optimized by three loss functions. We integrated a shape-aware loss to focus on the foreground segmentations, a Refine loss to correct the incomplete and noisy segmentations caused by domain shifts, and an entropy loss to promote the global consistency of the segmentations. We evaluated the proposed method on multidomain liver and prostate segmentation datasets to assess its advantages over other TTA methods. For the source domain model training of the liver dataset, we used 15 3D MR image samples for training and 5 for validation. Correspondingly, for the prostate dataset, we used 22 3D MR image samples for training and 7 for validation. In the target domain, we used a single 3D MR image sample for adaptation and testing. The total number of testing samples is 60 in the liver dataset (for 3 different domains) and 116 in the prostate dataset (for 6 different domains). The proposed method showed the highest segmentation accuracy among all methods, achieving a mean(±SD) Dice coefficient (DSC) of 78.10±5.23% and a mean 95th Hausdorff distance (HD95) of 15.52±5.84mm on the liver dataset; and a mean DSC of 80.02±3.89% and a mean HD95 of 9.18±3.47mm on the prostate dataset. The DSC is 11.67% (in absolute terms) and 15.27% higher than that of the baseline (no adaptation) method, for the liver and the prostate datasets, respectively. The proposed adaptive WaVNet enhanced the image segmentation accuracy from unseen domains during the test time via unsupervised learning and multi-objective optimization. It can benefit clinical applications where data are scarce or with changing data distributions, including online adaptive radiotherapy. The code will be released at: https://github.com/sanny1226/WaVNet.

Robust and smooth Couinaud segmentation via anatomical structure-guided point-voxel network

Precise Couinaud segmentation from preoperative liver computed tomography (CT) is crucial for surgical planning and lesion examination. However, this task is challenging as it is defined based on vessel structures, and there is no intensity contrast between adjacent Couinaud segments in CT images. To solve this challenge, we design a multi-scale point-voxel fusion framework, which can more effectively model the spatial relationship of points and the semantic information of the image, producing robust and smooth Couinaud segmentations. Specifically, we first segment the liver and vessels from the CT image and generate 3D liver point clouds and voxel grids embedded with the vessel structure. Then, our method with two input-specific branches extracts complementary feature representations from points and voxels, respectively. The local attention module adaptively fuses features from the two branches at different scales to balance the contribution of different branches in learning more discriminative features. Furthermore, we propose a novel distance loss at the feature level to make the features in the segment more compact, thereby improving the certainty of segmentation between segments. Our experimental results on three public liver datasets demonstrate that our proposed method outperforms several state-of-the-art methods by large margins. Specifically, in out-of-distribution (OOD) testing of LiTS dataset, our method exceeded the voxel-based 3D UNet by approximately 20% in Dice score, and outperformed the point-based PointNet2Plus by approximately 8% in Dice score. Our code and manual annotations of the public datasets presented in this paper are available online: https://github.com/xukun-zhang/Couinaud-Segmentation.

Exploring Generalizable Distillation for Efficient Medical Image Segmentation.

Efficient medical image segmentation aims to provide accurate pixel-wise predictions with a lightweight implementation framework. However, existing lightweight networks generally overlook the generalizability of the cross-domain medical segmentation tasks. In this paper, we propose Generalizable Knowledge Distillation (GKD), a novel framework for enhancing the performance of lightweight networks on cross-domain medical segmentation by generalizable knowledge distillation from powerful teacher networks. Considering the domain gaps between different medical datasets, we propose the Model-Specific Alignment Networks (MSAN) to obtain the domain-invariant representations. Meanwhile, a customized Alignment Consistency Training (ACT) strategy is designed to promote the MSAN training. Based on the domain-invariant vectors in MSAN, we propose two generalizable distillation schemes, Dual Contrastive Graph Distillation (DCGD) and Domain-Invariant Cross Distillation (DICD). In DCGD, two implicit contrastive graphs are designed to model the intra-coupling and inter-coupling semantic correlations. Then, in DICD, the domain-invariant semantic vectors are reconstructed from two networks (i.e., teacher and student) with a crossover manner to achieve simultaneous generalization of lightweight networks, hierarchically. Moreover, a metric named Fréchet Semantic Distance (FSD) is tailored to verify the effectiveness of the regularized domain-invariant features. Extensive experiments conducted on the Liver, Retinal Vessel and Colonoscopy segmentation datasets demonstrate the superiority of our method, in terms of performance and generalization ability on lightweight networks.

Comparing regularized Kelvinlet functions and the finite element method for registration of medical images to sparse organ data

Image-guided surgery collocates patient-specific data with the physical environment to facilitate surgical decision making. Unfortunately, these guidance systems commonly become compromised by intraoperative soft-tissue deformations. Nonrigid image-to-physical registration methods have been proposed to compensate for deformations, but clinical utility requires compatibility of these techniques with data sparsity and temporal constraints in the operating room. While finite element models can be effective in sparse data scenarios, computation time remains a limitation to widespread deployment. This paper proposes a registration algorithm that uses regularized Kelvinlets, which are analytical solutions to linear elasticity in an infinite domain, to overcome these barriers. This algorithm is demonstrated and compared to finite element-based registration on two datasets: a phantom liver deformation dataset and an in vivo breast deformation dataset. The regularized Kelvinlets algorithm resulted in a significant reduction in computation time compared to the finite element method. Accuracy as evaluated by target registration error was comparable between methods. Average target registration errors were 4.6 ± 1.0 and 3.2 ± 0.8 mm on the liver dataset and 5.4 ± 1.4 and 6.4 ± 1.5 mm on the breast dataset for the regularized Kelvinlets and finite element method, respectively. Limitations of regularized Kelvinlets include the lack of organ-specific geometry and the assumptions of linear elasticity and infinitesimal strain. Despite limitations, this work demonstrates the generalizability of regularized Kelvinlets registration on two soft-tissue elastic organs. This method may improve and accelerate registration for image-guided surgery, and it shows the potential of using regularized Kelvinlets on medical imaging data.

Multimodal parallel attention network for medical image segmentation

Medical image segmentation is a crucial aspect of medical image processing, and has been widely used in the detection and clinical diagnosis for brain, lung, liver, heart and other diseases. In this paper, we propose a novel multimodal parallel attention network, called MPA-Net, for medical image segmentation. MPA-Net is divided into two parts. The first part extracts more high-dimensional features by improved network structure, which contains the skip connection, the output of the multimodal parallel attention and the output of the previous upsampling layer. The second part incorporates a multimodal parallel attention mechanism, encompassing feature parallel attention, spatial parallel attention and channel parallel attention. This mechanism facilitates the effective fusion of high-dimensional and low-dimensional features, leading to enhanced context information. Experimental results on Kagglelung dataset, Liver dataset, Cell dataset, Drive dataset and Kvasir-SEG dataset show that MPA-Net has achieved better segmentation performance than that of other baseline methods, on lung, liver, cell contour, retinal vessel and polyps.

Segmentation of liver CT images based on weighted medical transformer model.

Deep convolutional neural networks have made significant strides in the field of medical image segmentation. Although existing convolutional structures enhance performance by leveraging local image information, they often lose the interdependence information between contexts. Therefore, the article utilizes the multi-attention mechanism of the Transformer structure to more comprehensively express relationships between contexts and introduced the Transformer network architecture into the field of medical image segmentation. Most models based on this Transformer structure typically require large datasets for training. However, in the medical field, the limited size of datasets makes training models with the Transformer structure challenging. To address this, the article propose a Weighted Medical Transformer (WMT) model that imposes low requirements on dataset quantity. The weighting mechanism in the WMT model aims to improve the issue of inaccurate relative positional coding when dealing with small medical datasets. Additionally, a coarse-grained and fine-grained segmentation mechanism is introduced, focusing on both the detailed aspects within image blocks and the boundary information connecting blocks. Experimental results on a liver dataset demonstrate that the model achieves F1 and IoU scores of 88.48% and 79.41%, respectively. Results on the MoNuSeg dataset show comparable high F1 and IoU scores of 79.58% and 66.19%, respectively. The model's accuracy surpasses that of U-Net++ and U-Net models. Compared to other models, this approach is applicable to scenarios with limited datasets, exhibiting high execution efficiency and accuracy.

Mining cholesterol genes from thousands of mouse livers identifies aldolase C as a regulator of cholesterol biosynthesis

The availability of genome-wide transcriptomic and proteomic datasets is ever-increasing and often not used beyond initial publication. Here, we applied module-based coexpression network analysis to a comprehensive catalog of 35 mouse genome-wide liver expression datasets (encompassing more than 3800 mice) with the goal of identifying and validating unknown genes involved in cholesterol metabolism. From these 35 datasets, we identified a conserved module of genes enriched with cholesterol biosynthetic genes. Using a systematic approach across the 35 datasets, we identified three genes (Rdh11, Echdc1, and Aldoc) with no known role in cholesterol metabolism. We then performed functional validation studies and show that each gene is capable of regulating cholesterol metabolism. For the glycolytic gene, Aldoc, we demonstrate that it contributes to de novo cholesterol biosynthesis and regulates cholesterol and triglyceride levels in mice. As Aldoc is located within a genome-wide significant genome-wide association studies locus for human plasma cholesterol levels, our studies establish Aldoc as a causal gene within this locus. Through our work, we develop a framework for leveraging mouse genome-wide liver datasets for identifying and validating genes involved in cholesterol metabolism.

Single-cell, single-nucleus, and spatial transcriptomics characterization of the immunological landscape in the healthy and PSC human liver

Primary sclerosing cholangitis (PSC) is an immune-mediated cholestatic liver disease for which there is an unmet need to understand the cellular composition of the affected liver and how it underlies disease pathogenesis. We aimed to generate a comprehensive atlas of the PSC liver using multi-omic modalities and protein-based functional validation. We employed single-cell and single-nucleus RNA sequencing (47,156 cells and 23,000 nuclei) and spatial transcriptomics (one sample by 10x Visium and five samples with Nanostring GeoMx DSP) to profile the cellular ecosystem in 10 PSC livers. Transcriptomic profiles were compared to 24 neurologically deceased donor livers (107,542 cells) and spatial transcriptomics controls, as well as 18,240 cells and 20,202 nuclei from three PBC livers. Flow cytometry was performed to validate PSC-specific differences in immune cell phenotype and function. PSC explants with parenchymal cirrhosis and prominent periductal fibrosis contained a population of cholangiocyte-like hepatocytes that were surrounded by diverse immune cell populations. PSC-associated biliary, mesenchymal, and endothelial populations expressed chemokine and cytokine transcripts involved in immune cell recruitment. Additionally, expanded CD4+ T cells and recruited myeloid populations in the PSC liver expressed the corresponding receptors to these chemokines and cytokines, suggesting potential recruitment. Tissue-resident macrophages, by contrast, were reduced in number and exhibited a dysfunctional and downregulated inflammatory response to lipopolysaccharide and interferon-γ stimulation. We present a comprehensive atlas of the PSC liver and demonstrate an exhaustion-like phenotype of myeloid cells and markers of chronic cytokine expression in late-stage PSC lesions. This atlas expands our understanding of the cellular complexity of PSC and has potential to guide the development of novel treatments. Primary sclerosing cholangitis (PSC) is a rare liver disease characterized by chronic inflammation and irreparable damage to the bile ducts, which eventually results in liver failure. Due to a limited understanding of the underlying pathogenesis of disease, treatment options are limited. To address this, we sequenced healthy and diseased livers to compare the activity, interactions, and localization of immune and non-immune cells. This revealed that hepatocytes lining PSC scar regions co-express cholangiocyte markers, whereas immune cells infiltrate the scar lesions. Of these cells, macrophages, which typically contribute to tissue repair, were enriched in immunoregulatory genes and demonstrated a lack of responsiveness to stimulation. These cells may be involved in maintaining hepatic inflammation and could be a target for novel therapies.

CSSNet: Cascaded spatial shift network for multi-organ segmentation

Multi-organ segmentation is vital for clinical diagnosis and treatment. Although CNN and its extensions are popular in organ segmentation, they suffer from the local receptive field. In contrast, MultiLayer-Perceptron-based models (e.g., MLP-Mixer) have a global receptive field. However, these MLP-based models employ fully connected layers with many parameters and tend to overfit on sample-deficient medical image datasets. Therefore, we propose a Cascaded Spatial Shift Network, CSSNet, for multi-organ segmentation. Specifically, we design a novel cascaded spatial shift block to reduce the number of model parameters and aggregate feature segments in a cascaded way for efficient and effective feature extraction. Then, we propose a feature refinement network to aggregate multi-scale features with location information, and enhance the multi-scale features along the channel and spatial axis to obtain a high-quality feature map. Finally, we employ a self-attention-based fusion strategy to focus on the discriminative feature information for better multi-organ segmentation performance. Experimental results on the Synapse (multiply organs) and LiTS (liver & tumor) datasets demonstrate that our CSSNet achieves promising segmentation performance compared with CNN, MLP, and Transformer models. The source code will be available at https://github.com/zkyseu/CSSNet.

Dual regulation of NEMO by Nrf2 and miR-125a inhibits ferroptosis and protects liver from endoplasmic reticulum stress-induced injury.

Rationale: The surge of severe liver damage underscores the necessity for identifying new targets and therapeutic agents. Endoplasmic reticulum (ER) stress induces ferroptosis with Gα12 overexpression. NF-κB essential modulator (NEMO) is a regulator of inflammation and necroptosis. Nonetheless, the regulatory basis of NEMO de novo synthesis and its impact on hepatocyte ferroptosis need to be established. This study investigated whether Nrf2 transcriptionally induces IKBKG (the NEMO gene) for ferroptosis inhibition and, if so, how NEMO induction protects hepatocytes against ER stress-induced ferroptosis. Methods: Experiments were conducted using human liver tissues, hepatocytes, and injury models, incorporating NEMO overexpression and Gα12 gene modulations. RNA sequencing, immunoblotting, immunohistochemistry, reporter assays, and mutation analyses were done. Results: NEMO downregulation connects closely to ER and oxidative stress, worsening liver damage via hepatocyte ferroptosis. NEMO overexpression protects hepatocytes from ferroptosis by promoting glutathione peroxidase 4 (GPX4) expression. This protective role extends to oxidative and ER stress. Similar shifts occur in nuclear factor erythroid-2-related factor-2 (Nrf2) expression alongside NEMO changes. Nrf2 is newly identified as an IKBKG (NEMO gene) transactivator. Gα12 changes, apart from Nrf2, impact NEMO expression, pointing to post-transcriptional control. Gα12 reduction lowers miR-125a, an inhibitor of NEMO, while overexpression has the opposite effect. NEMO also counters ER stress, which triggers Gα12 overexpression. Gα12's significance in NEMO-dependent hepatocyte survival is confirmed via ROCK1 inhibition, a Gα12 downstream kinase, and miR-125a. The verified alterations or associations within the targeted entities are validated in human liver specimens and datasets originating from livers subjected to exposure to other injurious agents. Conclusions: Hepatic injury prompted by ER stress leads to the suppression of NEMO, thereby facilitating ferroptosis through the inhibition of GPX4. IKBKG is transactivated by Nrf2 against Gα12 overexpression responsible for the increase of miR-125a, an unprecedented NEMO inhibitor, resulting in GPX4 induction. Accordingly, the induction of NEMO mitigates ferroptotic liver injury.

Deep Power-aware Tunable Weighting for Ultrasound Microvascular Imaging.

Ultrasound microvascular imaging (UMI), including ultrafast power Doppler imaging (uPDI) and ultrasound localization microscopy (ULM), obtains blood flow information through plane wave transmissions at high frame rates. However, low signal-to-noise ratio of plane waves causes low image quality. Adaptive beamformers have been proposed to suppress noise energy to achieve higher image quality accompanied by increasing computational complexity. Deep learning (DL) leverages powerful hardware capabilities to enable rapid implementation of noise suppression at the cost of flexibility. To enhance the applicability of DL-based methods, in this work, we propose a deep power-aware tunable (DPT) weighting (i.e., postfilter) for delay-and-sum (DAS) beamforming to improve UMI by enhancing plane wave images. The model, called Yformer is a hybrid structure combining convolution and Transformer. With the DAS beamformed and compounded envelope image as input, Yformer can estimate both noise power and signal power. Furthermore, we utilize the obtained powers to compute pixel-wise weights by introducing a tunable noise control factor, which is tailored for improving the quality of different UMI applications. In vivo experiments on the rat brain demonstrate that Yformer can accurately estimate the powers of noise and signal with the structural similarity index (SSIM) higher than 0.95. The performance of the DPT weighting is comparable to that of superior adaptive beamformer in uPDI with low computational cost. The DPT weighting was then applied to four different datasets of ULM, including public simulation, public rat brain, private rat brain, and private rat liver datasets, showing excellent generalizability using the model trained by the private rat brain dataset only. In particular, our method indirectly improves the resolution of liver ULM from 25.24 μm to 18.77 μm by highlighting small vessels. In addition, the DPT weighting exhibits more details of blood vessels with faster processing, which has the potential to facilitate the clinical applications of high-quality UMI.

SCorP: Statistics-Informed Dense Correspondence Prediction Directly from Unsegmented Medical Images.

Statistical shape modeling (SSM) is a powerful computational framework for quantifying and analyzing the geometric variability of anatomical structures, facilitating advancements in medical research, diagnostics, and treatment planning. Traditional methods for shape modeling from imaging data demand significant manual and computational resources. Additionally, these methods necessitate repeating the entire modeling pipeline to derive shape descriptors (e.g., surface-based point correspondences) for new data. While deep learning approaches have shown promise in streamlining the construction of SSMs on new data, they still rely on traditional techniques to supervise the training of the deep networks. Moreover, the predominant linearity assumption of traditional approaches restricts their efficacy, a limitation also inherited by deep learning models trained using optimized/established correspondences. Consequently, representing complex anatomies becomes challenging. To address these limitations, we introduce SCorP, a novel framework capable of predicting surface-based correspondences directly from unsegmented images. By leveraging the shape prior learned directly from surface meshes in an unsupervised manner, the proposed model eliminates the need for an optimized shape model for training supervision. The strong shape prior acts as a teacher and regularizes the feature learning of the student network to guide it in learning image-based features that are predictive of surface correspondences. The proposed model streamlines the training and inference phases by removing the supervision for the correspondence prediction task while alleviating the linearity assumption. Experiments on the LGE MRI left atrium dataset and Abdomen CT-1K liver datasets demonstrate that the proposed technique enhances the accuracy and robustness of image-driven SSM, providing a compelling alternative to current fully supervised methods.

Interval Type-3 Fuzzy Inference System Design for Medical Classification Using Genetic Algorithms

An essential aspect of healthcare is receiving an appropriate and opportune disease diagnosis. In recent years, there has been enormous progress in combining artificial intelligence to help professionals perform these tasks. The design of interval Type-3 fuzzy inference systems (IT3FIS) for medical classification is proposed in this work. This work proposed a genetic algorithm (GA) for the IT3FIS design where the fuzzy inputs correspond to attributes relational to a particular disease. This optimization allows us to find some main fuzzy inference systems (FIS) parameters, such as membership function (MF) parameters and the fuzzy if-then rules. As a comparison against the proposed method, the results achieved in this work are compared with Type-1 fuzzy inference systems (T1FIS), Interval Type-2 fuzzy inference systems (IT2FIS), and General Type-2 fuzzy inference systems (GT2FIS) using medical datasets such as Haberman’s Survival, Cryotherapy, Immunotherapy, PIMA Indian Diabetes, Indian Liver, and Breast Cancer Coimbra dataset, which achieved 75.30, 87.13, 82.04, 77.76, 71.86, and 71.06, respectively. Also, cross-validation tests were performed. Instances established as design sets are used to design the fuzzy inference systems, the optimization technique seeks to reduce the classification error using this set, and finally, the testing set allows the validation of the real performance of the FIS.

A Multistage Rigid-Affine-Deformable Network for Three-Dimensional Multimodal Medical Image Registration

Multimodal image registration is an important component of medical image processing, allowing the integration of complementary information from various imaging modalities to improve clinical applications like diagnosis and treatment planning. We proposed a novel multistage neural network for three-dimensional multimodal medical image registration, which addresses the challenge of larger rigid deformations commonly present in medical images due to variations in patient positioning in different scanners and rigid anatomical structures. This multistage network combines rigid, affine and deformable transformations in three stages. The network was trained unsupervised with Mutual Information and Gradient L2 loss. We compared the results of our proposed multistage network with a rigid-affine-deformable registration with the classical registration method NiftyReg as a baseline and a multistage network, which combines affine and deformable transformation, as a benchmark. To evaluate the performance of the proposed multistage network, we used four three-dimensional multimodal in vivo datasets: three renal MR datasets consisting of T1-weighted and T2-weighted MR scans and one liver dataset containing CT and T1-weighted MR scans. Experimental results showed that combining rigid, affine and deformable transformations in a multistage network leads to registration results with a high structural similarity, overlap of the corresponding structures (Dice: 76.7 ± 12.5, 61.1 ± 14.0, 64.8 ± 16.2, 68.1 ± 24.6 for the four datasets) and a low level of image folding (|J| ≤ 0: less than or equal to 1.1%), resulting in a medical plausible registration result.

Liver segmentation using Mnet for cirrhosis

Liver biopsies for diagnosing cirrhosis, the last stage of chronic liver disease was analysed using imaging and it could able to determine the severity level of the disease. Liver lesions can be segmented for evaluation of tumor burden, therapeutic strategy, prognosis, and follow-up on the efficacy of therapy. Automatic technologies for malignancy identification and segmentation are preferable because manual segmentation is a laborious process that is prone to error. We thus propose an M-Net approach to cirrhosis of the liver segmentation. The liver datasets are collected initially as raw data, which, due to the existence of noise, must be normalized before the investigation can begin. With the help of the Bilateral Filter and the Wavelet Transform, we can get rid of the noise and improve the de-noised image. The Gabor Filter is used for feature extraction. Hybrid Genetic Algorithm (HGA) is used to pick the best feature subsets for classification. Ensemble Deep Convolutional Neural Network (EDCNN) method is applied to the classification process. MATLAB, a simulation program, is used to conduct the entire inquiry. In terms of accuracy, our system has outperformed the most sophisticated automatic techniques.

DeepHistoNet: A robust deep-learning model for the classification of hepatocellular, lung, and colon carcinoma.

In recent days, non-communicable diseases (NCDs) require more attention since they require specialized infrastructure for treatment. As per the cancer population registry estimate, nearly 800,000 new cancer cases will be detected yearly. The statistics alarm the need for early cancer detection and diagnosis. Cancer identification can be made either through manual efforts or by computer-aided algorithms. Manual efforts-based cancer detection is labor intensive and also offers more time complexity. In contrast, computer-aided algorithms offer feasibility in reducing time and manual efforts. With the motivation to develop a computer-aided diagnosis system for NCD, we developed a cancer detection methodology. In the present article, a deep learning (DL)-based cancer identification model is developed. In DL-based architectures, the features are generally extracted using convolutional neural networks. The proposed attention-guided, densely connected residual, and dilated convolution deep neural network called DeepHistoNet acquire precise patterns for classification. Experimentation has been carried out on Kasturba Medical College (KMC), TCGA-LIHC, and LC25000 datasets to prove the robustness of the model. Performance evaluation metrics like F1-score, sensitivity, specificity, recall, and accuracy validate the experimentation. Experimental results demonstrate that the proposed DeepHistoNet model outperforms the other state-of-the-art methods. The proposed model has been able to classify the KMC liver dataset with 97.1% accuracy and 0.9867 value of area under the curve-receiver operating characteristic curve (AUC-ROC), which is the best result obtained compared to the state-of-the-art techniques. The performance of the DeepHistoNet has been even better on the LC25000 dataset. On the LC25000 dataset, the proposed model achieved 99.8% classification accuracy. To our knowledge, DeepHistoNet is a novel approach for multiple histopathological image classification. RESEARCH HIGHLIGHTS: A novel robust DL model is proposed for histopathological image carcinoma classification. The precise patterns for accurate classification are extracted using dense cross-connected residual blocks. Spatial attention is provided to the network so that the spatial information is not lost during the feature extraction. DeepHistoNet is trained and evaluated on the liver, lung, and colon histopathology datasets to demonstrate its resilience. The results are promising and outperform state-of-the-art techniques. The proposed methodology has obtained the AUC-ROC value of 0.9867 with a classification accuracy of 97.1% on the KMC dataset. The proposed DeepHistoNet has classified the LC25000 dataset with 99.8% accuracy. The results are the best obtained till date.

SECP-Net: SE-Connection Pyramid Network for Segmentation of Organs at Risk with Nasopharyngeal Carcinoma.

Nasopharyngeal carcinoma (NPC) is a kind of malignant tumor. The accurate and automatic segmentation of computed tomography (CT) images of organs at risk (OAR) is clinically significant. In recent years, deep learning models represented by U-Net have been widely applied in medical image segmentation tasks, which can help to reduce doctors' workload. In the OAR segmentation of NPC, the sizes of the OAR are variable, and some of their volumes are small. Traditional deep neural networks underperform in segmentation due to the insufficient use of global and multi-size information. Therefore, a new SE-Connection Pyramid Network (SECP-Net) is proposed. For extracting global and multi-size information, the SECP-Net designs an SE-connection module and a pyramid structure for improving the segmentation performance, especially that of small organs. SECP-Net also uses an auto-context cascaded structure to further refine the segmentation results. Comparative experiments are conducted between SECP-Net and other recent methods on a private dataset with CT images of the head and neck and a public liver dataset. Five-fold cross-validation is used to evaluate the performance based on two metrics; i.e., Dice and Jaccard similarity. The experimental results show that SECP-Net can achieve SOTA performance in these two challenging tasks.

Graph-based automatic detection and classification of lesion changes in pairs of CT studies for oncology follow-up.

Radiological follow-up of oncology patients requires the quantitative analysis of lesion changes in longitudinal imaging studies, which is time-consuming, requires expertise, and is subject to variability. This paper presents a comprehensive graph-based method for the automatic detection and classification of lesion changes in current and prior CT scans. The inputs are the current and prior CT scans and their organ and lesion segmentations. Classification of lesion changes is formalized as bipartite graph matching where lesion pairings are computed by adaptive overlap-based lesion matching. Six types of lesion changes are computed by connected components analysis. The method was evaluated on 208 pairs of lung and liver CT scans from 57 patients with 4600 lesions, 1713 lesion matchings and 2887 lesion changes. Ground-truth lesion segmentations, lesion matchings and lesion changes were created by an expert radiologist. Our method yields a lesion matching rate accuracy of 99.7% (394/395) and 95.0% (1252/1318) for the lung and liver datasets. Precision and recall are > 0.99 and 0.94 and 0.95 (respectively) for the detection of lesion changes. The analysis of lesion changes helped the radiologist detect 48 missed lesions and 8 spurious lesions in the input ground-truth lesion datasets. The classification of lesion classification provides the clinician with a readily accessible and intuitive identification and classification of the lesion changes and their patterns in support of clinical decision making. Comprehensive automatic computer-aided lesion matching and analysis of lesion changes may improve quantitative follow-up and evaluation of disease status, assessment of treatment efficacy and response to therapy.

Duke Liver Dataset: A Publicly Available Liver MRI Dataset with Liver Segmentation Masks and Series Labels.

The Duke Liver Dataset contains 2146 abdominal MRI series from 105 patients, including a majority with cirrhotic features, and 310 image series with corresponding manually segmented liver masks.

Pan-precancer and cancer DNA methylation profiles revealed significant tissue specificity of interrupted biological processes in tumorigenesis

ABSTRACT DNA methylation (DNAme) alterations are known to initiate from the precancerous stage of tumorigenesis. Herein, we investigated the global and local patterns of DNAme perturbations in tumorigenesis by analysing the genome-wide DNAme profiles of the cervix, colorectum, stomach, prostate, and liver at precancerous and cancer stages. We observed global hypomethylation in tissues of both two stages, except for the cervix, whose global DNAme level in normal tissue was lower than that of the other four tumour types. For alterations shared by both stages, there were common hyper-methylation (sHyperMethyl) and hypo-methylation (sHypoMethyl) changes, of which the latter type was more frequently identified in all tissues. Biological pathways interrupted by sHyperMethyl and sHypoMethyl alterations demonstrated significant tissue specificity. DNAme bidirectional chaos indicated by the enrichment of both sHyperMethyl and sHypoMethyl changes in the same pathway was observed in most tissues and was a common phenomenon, particularly in liver lesions. Moreover, for the same enriched pathways, different tissues may be affected by distinct DNAme types. For the PI3K−Akt signalling pathway, sHyperMethyl enrichment was observed in the prostate dataset, but sHypoMethyl enrichment was observed in the colorectum and liver datasets. Nevertheless, they did not show an increased possibility in survival prediction of patients in comparison with other DNAme types. Additionally, our study demonstrated that gene-body DNAme changes of tumour suppressor genes and oncogenes may persist from precancerous lesions to the tumour. Overall, we demonstrate the tissue specificity and commonality of cross-stage alterations in DNA methylation profiles in multi-tissue tumorigenesis.