Dilated-Inception Net: Multi-Scale Feature Aggregation for Cardiac Right Ventricle Segmentation

Transforming pulmonary health care: the role of artificial intelligence in diagnosis and treatment

INTRODUCTION

Respiratory diseases like pneumonia, asthma, and COPD are major global health concerns, significantly impacting morbidity and mortality rates worldwide.

AREAS COVERED

A selective search on PubMed, Google Scholar, and ScienceDirect (up to 2024) focused on AI in diagnosing and treating respiratory conditions like asthma, pneumonia, and COPD. Studies were chosen for their relevance to prediction models, AI-driven diagnostics, and personalized treatments. This narrative review highlights technological advancements, clinical applications, and challenges in integrating AI into standard practice, with emphasis on predictive tools, deep learning for imaging, and patient outcomes.

EXPERT OPINION

Despite these advancements, significant challenges remain in fully integrating AI into pulmonary health care. The need for large, diverse datasets to train AI models is critical, and concerns around data privacy, algorithmic transparency, and potential biases must be carefully managed. Regulatory frameworks also need to evolve to address the unique challenges posed by AI in health care. However, with continued research and collaboration between technology developers, clinicians, and policymakers, AI has the potential to revolutionize pulmonary health care, ultimately leading to more effective, efficient, and personalized care for patients.

Targeted therapy and deep learning insights into microglia modulation for spinal cord injury

Spinal cord injury (SCI) is a devastating condition that can cause significant motor and sensory impairment. Microglia, the central nervous system's immune sentinels, are known to be promising therapeutic targets in both SCI and neurodegenerative diseases. The most effective way to deliver medications and control microglial inflammation is through nanovectors; however, because of the variability in microglial morphology and the lack of standardized techniques, it is still difficult to precisely measure their activation in preclinical models. This problem is especially important in SCI, where the intricacy of the glia response following traumatic events necessitates the use of a sophisticated method to automatically discern between various microglial cell activation states that vary over time and space as the secondary injury progresses. We address this issue by proposing a deep learning-based technique for quantifying microglial activation following drug-loaded nanovector treatment in a preclinical SCI model. Our method uses a convolutional neural network to segment and classify microglia based on morphological characteristics. Our approach's accuracy and efficiency are demonstrated through evaluation on a collection of histology pictures from injured and intact spinal cords. This robust computational technique has potential for analyzing microglial activation across various neuropathologies and demonstrating the usefulness of nanovectors in modifying microglia in SCI and other neurological disorders. It has the ability to speed development in this crucial sector by providing a standardized and objective way to compare therapeutic options.

Coreference Resolution Based on High-Dimensional Multi-Scale Information

Coreference resolution is a key task in Natural Language Processing. It is difficult to evaluate the similarity of long-span texts, which makes text-level encoding somewhat challenging. This paper first compares the impact of commonly used methods to improve the global information collection ability of the model on the BERT encoding performance. Based on this, a multi-scale context information module is designed to improve the applicability of the BERT encoding model under different text spans. In addition, improving linear separability through dimension expansion. Finally, cross-entropy loss is used as the loss function. After adding BERT and span BERT to the module designed in this article, F1 increased by 0.5% and 0.2%, respectively.

DECTNet: Dual Encoder Network combined convolution and Transformer architecture for medical image segmentation

Automatic and accurate segmentation of medical images plays an essential role in disease diagnosis and treatment planning. Convolution neural networks have achieved remarkable results in medical image segmentation in the past decade. Meanwhile, deep learning models based on Transformer architecture also succeeded tremendously in this domain. However, due to the ambiguity of the medical image boundary and the high complexity of physical organization structures, implementing effective structure extraction and accurate segmentation remains a problem requiring a solution. In this paper, we propose a novel Dual Encoder Network named DECTNet to alleviate this problem. Specifically, the DECTNet embraces four components, which are a convolution-based encoder, a Transformer-based encoder, a feature fusion decoder, and a deep supervision module. The convolutional structure encoder can extract fine spatial contextual details in images. Meanwhile, the Transformer structure encoder is designed using a hierarchical Swin Transformer architecture to model global contextual information. The novel feature fusion decoder integrates the multi-scale representation from two encoders and selects features that focus on segmentation tasks by channel attention mechanism. Further, a deep supervision module is used to accelerate the convergence of the proposed method. Extensive experiments demonstrate that, compared to the other seven models, the proposed method achieves state-of-the-art results on four segmentation tasks: skin lesion segmentation, polyp segmentation, Covid-19 lesion segmentation, and MRI cardiac segmentation.

ELTS-Net: An enhanced liver tumor segmentation network with augmented receptive field and global contextual information

The liver is one of the organs with the highest incidence rate in the human body, and late-stage liver cancer is basically incurable. Therefore, early diagnosis and lesion location of liver cancer are of important clinical value. This study proposes an enhanced network architecture ELTS-Net based on the 3D U-Net model, to address the limitations of conventional image segmentation methods and the underutilization of image spatial features by the 2D U-Net network structure. ELTS-Net expands upon the original network by incorporating dilated convolutions to increase the receptive field of the convolutional kernel. Additionally, an attention residual module, comprising an attention mechanism and residual connections, replaces the original convolutional module, serving as the primary components of the encoder and decoder. This design enables the network to capture contextual information globally in both channel and spatial dimensions. Furthermore, deep supervision modules are integrated between different levels of the decoder network, providing additional feedback from deeper intermediate layers. This constrains the network weights to the target regions and optimizing segmentation results. Evaluation on the LiTS2017 dataset shows improvements in evaluation metrics for liver and tumor segmentation tasks compared to the baseline 3D U-Net model, achieving 95.2% liver segmentation accuracy and 71.9% tumor segmentation accuracy, with accuracy improvements of 0.9% and 3.1% respectively. The experimental results validate the superior segmentation performance of ELTS-Net compared to other comparison models, offering valuable guidance for clinical diagnosis and treatment.

Semi-Supervised Representation Learning for Segmentation on Medical Volumes and Sequences

Benefiting from the massive labeled samples, deep learning-based segmentation methods have achieved great success for two dimensional natural images. However, it is still a challenging task to segment high dimensional medical volumes and sequences, due to the considerable efforts for clinical expertise to make large scale annotations. Self/semi-supervised learning methods have been shown to improve the performance by exploiting unlabeled data. However, they are still lack of mining local semantic discrimination and exploitation of volume/sequence structures. In this work, we propose a semi-supervised representation learning method with two novel modules to enhance the features in the encoder and decoder, respectively. For the encoder, based on the continuity between slices/frames and the common spatial layout of organs across subjects, we propose an asymmetric network with an attention-guided predictor to enable prediction between feature maps of different slices of unlabeled data. For the decoder, based on the semantic consistency between labeled data and unlabeled data, we introduce a novel semantic contrastive learning to regularize the feature maps in the decoder. The two parts are trained jointly with both labeled and unlabeled volumes/sequences in a semi-supervised manner. When evaluated on three benchmark datasets of medical volumes and sequences, our model outperforms existing methods with a large margin of 7.3% DSC on ACDC, 6.5% on Prostate, and 3.2% on CAMUS when only a few labeled data is available. Further, results on the M&M dataset show that the proposed method yields improvement without using any domain adaption techniques for data from unknown domain. Intensive evaluations reveal the effectiveness of representation mining, and superiority on performance of our method. The code is available at https://github.com/CcchenzJ/BootstrapRepresentation.

Deep Learning for Medical Image-Based Cancer Diagnosis

(1) Background: The application of deep learning technology to realize cancer diagnosis based on medical images is one of the research hotspots in the field of artificial intelligence and computer vision. Due to the rapid development of deep learning methods, cancer diagnosis requires very high accuracy and timeliness as well as the inherent particularity and complexity of medical imaging. A comprehensive review of relevant studies is necessary to help readers better understand the current research status and ideas. (2) Methods: Five radiological images, including X-ray, ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission computed tomography (PET), and histopathological images, are reviewed in this paper. The basic architecture of deep learning and classical pretrained models are comprehensively reviewed. In particular, advanced neural networks emerging in recent years, including transfer learning, ensemble learning (EL), graph neural network, and vision transformer (ViT), are introduced. Five overfitting prevention methods are summarized: batch normalization, dropout, weight initialization, and data augmentation. The application of deep learning technology in medical image-based cancer analysis is sorted out. (3) Results: Deep learning has achieved great success in medical image-based cancer diagnosis, showing good results in image classification, image reconstruction, image detection, image segmentation, image registration, and image synthesis. However, the lack of high-quality labeled datasets limits the role of deep learning and faces challenges in rare cancer diagnosis, multi-modal image fusion, model explainability, and generalization. (4) Conclusions: There is a need for more public standard databases for cancer. The pre-training model based on deep neural networks has the potential to be improved, and special attention should be paid to the research of multimodal data fusion and supervised paradigm. Technologies such as ViT, ensemble learning, and few-shot learning will bring surprises to cancer diagnosis based on medical images.

Deep Learning Segmentation of the Right Ventricle in Cardiac MRI: The M&Ms Challenge

In recent years, several deep learning models have been proposed to accurately quantify and diagnose cardiac pathologies. These automated tools heavily rely on the accurate segmentation of cardiac structures in MRI images. However, segmentation of the right ventricle is challenging due to its highly complex shape and ill-defined borders. Hence, there is a need for new methods to handle such structure's geometrical and textural complexities, notably in the presence of pathologies such as Dilated Right Ventricle, Tricuspid Regurgitation, Arrhythmogenesis, Tetralogy of Fallot, and Inter-atrial Communication. The last MICCAI challenge on right ventricle segmentation was held in 2012 and included only 48 cases from a single clinical center. As part of the 12th Workshop on Statistical Atlases and Computational Models of the Heart (STACOM 2021), the M&Ms-2 challenge was organized to promote the interest of the research community around right ventricle segmentation in multi-disease, multi-view, and multi-center cardiac MRI. Three hundred sixty CMR cases, including short-axis and long-axis 4-chamber views, were collected from three Spanish hospitals using nine different scanners from three different vendors, and included a diverse set of right and left ventricle pathologies. The solutions provided by the participants show that nnU-Net achieved the best results overall. However, multi-view approaches were able to capture additional information, highlighting the need to integrate multiple cardiac diseases, views, scanners, and acquisition protocols to produce reliable automatic cardiac segmentation algorithms.

ICUnet++: an Inception-CBAM network based on Unet++ for MR spine image segmentation

In recent years, more attention paid to the spine caused by related diseases, spinal parsing (the multi-class segmentation of vertebrae and intervertebral disc) is an important part of the diagnosis and treatment of various spinal diseases. The more accurate the segmentation of medical images, the more convenient and quick the clinicians can evaluate and diagnose spinal diseases. Traditional medical image segmentation is often time consuming and energy consuming. In this paper, an efficient and novel automatic segmentation network model for MR spine images is designed. The proposed Inception-CBAM Unet++ (ICUnet++) model replaces the initial module with the Inception structure in the encoder-decoder stage base on Unet++ , which uses the parallel connection of multiple convolution kernels to obtain the features of different receptive fields during in the feature extraction. According to the characteristics of the attention mechanism, Attention Gate module and CBAM module are used in the network to make the attention coefficient highlight the characteristics of the local area. To evaluate the segmentation performance of network model, four evaluation metrics, namely intersection over union (IoU), dice similarity coefficient(DSC), true positive rate(TPR), positive predictive value(PPV) are used in the study. The published SpineSagT2Wdataset3 spinal MRI dataset is used during the experiments. In the experiment results, IoU reaches 83.16%, DSC is 90.32%, TPR is 90.40%, and PPV is 90.52%. It can be seen that the segmentation indicators have been significantly improved, which reflects the effectiveness of the model.

Acoustic-Based Deep Learning Architectures for Lung Disease Diagnosis: A Comprehensive Overview

Lung auscultation has long been used as a valuable medical tool to assess respiratory health and has gotten a lot of attention in recent years, notably following the coronavirus epidemic. Lung auscultation is used to assess a patient's respiratory role. Modern technological progress has guided the growth of computer-based respiratory speech investigation, a valuable tool for detecting lung abnormalities and diseases. Several recent studies have reviewed this important area, but none are specific to lung sound-based analysis with deep-learning architectures from one side and the provided information was not sufficient for a good understanding of these techniques. This paper gives a complete review of prior deep-learning-based architecture lung sound analysis. Deep-learning-based respiratory sound analysis articles are found in different databases including the Plos, ACM Digital Libraries, Elsevier, PubMed, MDPI, Springer, and IEEE. More than 160 publications were extracted and submitted for assessment. This paper discusses different trends in pathology/lung sound, the common features for classifying lung sounds, several considered datasets, classification methods, signal processing techniques, and some statistical information based on previous study findings. Finally, the assessment concludes with a discussion of potential future improvements and recommendations.

Motion correction for native myocardial T1 mapping using self-supervised deep learning registration with contrast separation

In myocardial T₁ mapping, undesirable motion poses significant challenges because uncorrected motion can affect T₁ estimation accuracy and cause incorrect diagnosis. In this study, we propose and evaluate a motion correction method for myocardial T₁ mapping using self-supervised deep learning based registration with contrast separation (SDRAP). A sparse coding based method was first proposed to separate the contrast component from T₁ -weighted (T1w) images. Then, a self-supervised deep neural network with cross-correlation (SDRAP-CC) or mutual information as the registration similarity measurement was developed to register contrast separated images, after which signal fitting was performed on the motion corrected T1w images to generate motion corrected T₁ maps. The registration network was trained and tested in 80 healthy volunteers with images acquired using the modified Look-Locker inversion recovery (MOLLI) sequence. The proposed SDRAP was compared with the free form deformation (FFD) registration method regarding (1) Dice similarity coefficient (DSC) and mean boundary error (MBE) of myocardium contours, (2) T₁ value and standard deviation (SD) of T₁ fitting, (3) subjective evaluation score for overall image quality and motion artifact level, and (4) computation time. Results showed that SDRAP-CC achieved the highest DSC of 85.0 ± 3.9% and the lowest MBE of 0.92 ± 0.25 mm among the methods compared. Additionally, SDRAP-CC performed the best by resulting in lower SD value (28.1 ± 17.6 ms) and higher subjective image quality scores (3.30 ± 0.79 for overall quality and 3.53 ± 0.68 for motion artifact) evaluated by a cardiologist. The proposed SDRAP took only 0.52 s to register one slice of MOLLI images, achieving about sevenfold acceleration over FFD (3.7 s/slice).

A U-snake based deep learning network for right ventricle segmentation

PURPOSE

Ventricular segmentation is of great importance for the heart condition monitoring. However, manual segmentation is time-consuming, cumbersome and subjective. Many segmentation methods perform poorly due to the complex structure and uncertain shape of the right ventricle, so we combine deep learning to achieve automatic segmentation.

METHOD

This paper proposed a method named U-Snake network which is based on the improvement of deep snake⁵ together with level set⁸ to segment the right ventricular in the MR images. U-snake aggregates the information of each receptive field which is learned by circular convolution of multiple different dilation rates. At the same time, we also added dice loss functions and transferred the result of U-Snake to the level set so as to further enhance the effect of small object segmentation. our method is tested on the test1 and test2 datasets in the Right Ventricular Segmentation Challenge, which shows the effectiveness.

RESULTS

The experiment showed that we have obtained good result in the right ventricle segmentation challenge(RVSC). The highest segmentation accuracy on the right ventricular test set 2 reached a dice coefficient of 0.911, and the segmentation speed reached 5fps.

CONCLUSIONS

Our method, a new deep learning network named U-snake, has surpassed the previous excellent ventricular segmentation method based on mathematical theory and other classical deep learning methods, such as Residual U-net²⁷ , Inception cnn³³ , Dilated cnn²⁹ , etc. However, it can only be used as an auxiliary tool instead of replacing the work of human beings. This article is protected by copyright. All rights reserved.

Adaptive multi-scale feature fusion based U-net for fracture segmentation in coal rock images

Accurate segmentation of fractures in coal rock CT images is important for the development of coalbed methane. However, due to the large variation of fracture scale and the similarity of gray values between weak fractures and the surrounding matrix, it remains a challenging task. And there is no published dataset of coal rock, which make the task even harder. In this paper, a novel adaptive multi-scale feature fusion method based on U-net (AMSFF-U-net) is proposed for fracture segmentation in coal rock CT images. Specifically, encoder and decoder path consist of residual blocks (ReBlock), respectively. The attention skip concatenation (ASC) module is proposed to capture more representative and distinguishing features by combining the high-level and low-level features of adjacent layers. The adaptive multi-scale feature fusion (AMSFF) module is presented to adaptively fuse different scale feature maps of encoder path; it can effectively capture rich multi-scale features. In response to the lack of coal rock fractures training data, we applied a set of comprehensive data augmentation operations to increase the diversity of training samples. These extensive experiments are conducted via seven state-of-the-art methods (i.e., FCEM, U-net, Res-Unet, Unet++, MSN-Net, WRAU-Net and ours). The experiment results demonstrate that the proposed AMSFF-U-net can achieve better segmentation performance in our works, particularly for weak fractures and tiny scale fractures.

Automatic Left Ventricle Segmentation from Short-Axis Cardiac MRI Images Based on Fully Convolutional Neural Network

Background: Left ventricle (LV) segmentation using a cardiac magnetic resonance imaging (MRI) dataset is critical for evaluating global and regional cardiac functions and diagnosing cardiovascular diseases. LV clinical metrics such as LV volume, LV mass and ejection fraction (EF) are frequently extracted based on the LV segmentation from short-axis MRI images. Manual segmentation to assess such functions is tedious and time-consuming for medical experts to diagnose cardiac pathologies. Therefore, a fully automated LV segmentation technique is required to assist medical experts in working more efficiently. Method: This paper proposes a fully convolutional network (FCN) architecture for automatic LV segmentation from short-axis MRI images. Several experiments were conducted in the training phase to compare the performance of the network and the U-Net model with various hyper-parameters, including optimization algorithms, epochs, learning rate, and mini-batch size. In addition, a class weighting method was introduced to avoid having a high imbalance of pixels in the classes of image’s labels since the number of background pixels was significantly higher than the number of LV and myocardium pixels. Furthermore, effective image conversion with pixel normalization was applied to obtain exact features representing target organs (LV and myocardium). The segmentation models were trained and tested on a public dataset, namely the evaluation of myocardial infarction from the delayed-enhancement cardiac MRI (EMIDEC) dataset. Results: The dice metric, Jaccard index, sensitivity, and specificity were used to evaluate the network’s performance, with values of 0.93, 0.87, 0.98, and 0.94, respectively. Based on the experimental results, the proposed network outperforms the standard U-Net model and is an advanced fully automated method in terms of segmentation performance. Conclusion: This proposed method is applicable in clinical practice for doctors to diagnose cardiac diseases from short-axis MRI images.

A Novel Framework with Weighted Decision Map Based on Convolutional Neural Network for Cardiac MR Segmentation

For diagnosing cardiovascular disease, an accurate segmentation method is needed. There are several unre-solved issues in the complex field of cardiac magnetic resonance imaging, some of which have been partially addressed by using deep neural networks. To solve two problems of over-segmentation and under-segmentation of anatomical shapes in the short-axis view from different cardiac magnetic resonance sequences, we propose a novel two-stage framework with a weighted decision map based on convolutional neural networks to segment the myocardium (Myo), left ventricle (LV), and right ventricle (RV) simultaneously. The framework comprises a deci-sion map extractor and a cardiac segmenter. A cascaded U-Net++ is used as a decision map extractor to acquire the decision map that decides the category of each pixel. Cardiac segmenter is a multiscale dual-path feature ag-gregation network (MDFA-Net) which consists of a densely connected network and an asymmetric encoding and decoding network. The input to the cardiac seg-menter is derived from processed original images weighted by the output of the decision map extractor. We conducted experiments on two datasets of mul-ti-sequence cardiac magnetic resonance segmentation challenge 2019 (MS-CMRSeg 2019) and myocardial pa-thology segmentation challenge 2020 (MyoPS 2020). Test results obtained on MyoPS 2020 show that proposed method with average Dice coefficient of 84.70%, 86.00% and 86.31% in the segmentation task of Myo, LV, and RV, respectively.

Anatomical knowledge based level set segmentation of cardiac ventricles from MRI

This paper represents a novel level set framework for segmentation of cardiac left ventricle (LV) and right ventricle (RV) from magnetic resonance images based on anatomical structures of the heart. We first propose a level set approach to recover the endocardium and epicardium of LV by using a bi-layer level set (BILLS) formulation, in which the endocardium and epicardium are represented by the 0-level set and k-level set of a level set function. Furthermore, the recovery of LV endocardium and epicardium is achieved by a level set evolution process, called convexity preserving bi-layer level set (CP-BILLS). During the CP-BILLS evolution, the 0-level set and k-level set simultaneously evolve and move toward the true endocardium and epicardium under the guidance of image information and the impact of the convexity preserving mechanism as well. To eliminate the manual selection of the k-level, we develop an algorithm for automatic selection of an optimal k-level. As a result, the obtained endocardial and epicardial contours are convex and consistent with the anatomy of cardiac ventricles. For segmentation of the whole ventricle, we extend this method to the segmentation of RV and myocardium of both left and right ventricles by using a convex shape decomposition (CSD) structure of cardiac ventricles based on anatomical knowledge. Experimental results demonstrate promising performance of our method. Compared with some traditional methods, our method exhibits superior performance in terms of segmentation accuracy and algorithm stability. Our method is comparable with the state-of-the-art deep learning-based method in terms of segmentation accuracy and algorithm stability, but our method has no need for training and the manual segmentation of the training data.

TSU-net: Two-stage multi-scale cascade and multi-field fusion U-net for right ventricular segmentation

Accurate segmentation of the right ventricle from cardiac magnetic resonance images (MRI) is a critical step in cardiac function analysis and disease diagnosis. It is still an open problem due to some difficulties, such as a large variety of object sizes and ill-defined borders. In this paper, we present a TSU-net network that grips deeper features and captures targets of different sizes with multi-scale cascade and multi-field fusion in the right ventricle. TSU-net mainly contains two major components: Dilated-Convolution Block (DB) and Multi-Layer-Pool Block (MB). DB extracts and aggregates multi-scale features for the right ventricle. MB mainly relies on multiple effective field-of-views to detect objects at different sizes and fill boundary features. Different from previous networks, we used DB and MB to replace the convolution layer in the encoding layer, thus, we can gather multi-scale information of right ventricle, detect different size targets and fill boundary information in each encoding layer. In addition, in the decoding layer, we used DB to replace the convolution layer, so that we can aggregate the multi-scale features of the right ventricle in each decoding layer. Furthermore, the two-stage U-net structure is used to further improve the utilization of DB and MB through a two-layer encoding/decoding layer. Our method is validated on the RVSC, a public right ventricular data set. The results demonstrated that TSU-net achieved an average Dice coefficient of 0.86 on endocardium and 0.90 on the epicardium, thereby outperforming other models. It effectively assists doctors to diagnose the disease and promotes the development of medical images. In addition, we also provide an intuitive explanation of our network, which fully explain MB and TSU-net's ability to detect targets of different sizes and fill in boundary features.

Evaluation of Effect of Curcumin on Psychological State of Patients with Pulmonary Hypertension by Magnetic Resonance Image under Deep Learning

This research aimed to evaluate the right ventricular segmentation ability of magnetic resonance imaging (MRI) images based on deep learning and evaluate the influence of curcumin (Cur) on the psychological state of patients with pulmonary hypertension (PH). The heart MRI images were detected based on the You Only Look Once (YOLO) algorithm, and then the MRI image right ventricle segmentation algorithm was established based on the convolutional neural network (CNN) algorithm. The segmentation effect of the right ventricle in cardiac MRI images was evaluated regarding intersection-over-union (IOU), Dice coefficient, accuracy, and Jaccard coefficient. 30 cases of PH patients were taken as the research object. According to different treatments, they were rolled into control group (conventional treatment) and Cur group (conventional treatment + Cur), with 15 cases in each group. Changes in the scores of the self-rating anxiety scale (SAS) and self-rating depression scale (SDS) of the two groups of patients before and after treatment were analyzed. It was found that the average IOU of the heart target detection frame of the MRI image and the true bounding box before correction was 0.7023, and the IOU after correction was 0.9016. The Loss of the MRI image processed by the CNN algorithm was 0.05, which was greatly smaller than those processed by other algorithms. The Dice coefficient, Jaccard coefficient, and accuracy of the MRI image processed by CNN were 0.89, 0.881, and 0.994, respectively. The MRI images of PH patients showed that the anterior wall of the right ventricle was notably thickened, and the main pulmonary artery was greatly widened. After treatment, the SAR and SDS scores of the two groups were lower than those before treatment (P < 0.05), and the SAR and SDS scores of the curcumin group were lower than those of the control group (P < 0.05). To sum up, the right ventricular segmentation ability of MRI images based on deep learning was improved, and Cur can remarkably alleviate the psychological state of PH patients, which provided a reference for the diagnosis and treatment for PH patients.

Multiscale attention guided U-Net architecture for cardiac segmentation in short-axis MRI images

BACKGROUND AND OBJECTIVE

Automatic cardiac segmentation plays an utmost role in the diagnosis and quantification of cardiovascular diseases.

METHODS

This paper proposes a new cardiac segmentation method in short-axis Magnetic Resonance Imaging (MRI) images, called attention U-Net architecture with input image pyramid and deep supervised output layers (AID), which can fully-automatically learn to pay attention to target structures of various sizes and shapes. During each training process, the model continues to learn how to emphasize the desired features and suppress irrelevant areas in the original images, effectively improving the accuracy of cardiac segmentation. At the same time, we introduce the Focal Tversky Loss (FTL), which can effectively solve the problem of high imbalance in the amount of data between the target class and the background class during cardiac image segmentation. In order to obtain a better representation of intermediate features, we add a multi-scale input pyramid to the attention network.

RESULTS

The proposed cardiac segmentation technique is tested on the public Left Ventricle Segmentation Challenge (LVSC) dataset, which is shown to achieve 0.75, 0.87 and 0.92 for Jaccard Index, Sensitivity and Specificity, respectively. Experimental results demonstrate that the proposed method is able to improve the segmentation accuracy compared with the standard U-Net, and achieves comparable performance to the most advanced fully-automated methods.

CONCLUSIONS

Given its effectiveness and advantages, the proposed method can facilitate cardiac segmentation in short-axis MRI images in clinical practice.

Scale-adaptive deep network for deformable image registration

PURPOSE

Multiresolution hierarchical strategy is typically used in conventional optimization-based image registration to capture varying magnitudes of deformations while avoiding undesirable local minima. A rough concept of the scale is captured in deep networks by the reception field of kernels, and it has been realized to be both desirable and challenging to capture convolutions of different scales simultaneously in registration networks. In this study, we propose a registration network that is conscious of and self-adaptive to deformation of various scales to improve registration performance.

METHODS

Dilated inception modules (DIMs) are proposed to incorporate receptive fields of different sizes in a computationally efficient way. Scale adaptive modules (SAMs) are proposed to guide and adjust shallow features using convolutional kernels with spatially adaptive dilation rate learned from deep features. DIMs and SAMs are integrated into a registration network which takes a U-net structure. The network is trained in an unsupervised setting and completes registration with a single evaluation run.

RESULTS

Experiment with two-dimensional (2D) cardiac MRIs showed that the adaptive dilation rate in SAM corresponded well to the deformation scale. Evaluated with left ventricle segmentation, our method achieved a Dice coefficient of (0.93 ± 0.02), significantly better than SimpleElastix and networks without DIM or SAM. The average surface distance was less than 2 mm, comparable to SimpleElastix without statistical significance. Experiment with synthetic data demonstrated the effectiveness of DIMs and SAMs, which led to a significant reduction in target registration error (TRE) based on dense deformation field. The three-dimensional (3D) version of the network achieved a 2.52 mm mean TRE on anatomical landmarks in DIR-Lab thoracic 4DCTs, lower than SimpleElastix and networks without DIM or SAM with statistical significance. The average registration times were 0.002 s for 2D images with size 256 × 256 and 0.42 s for 3D images with size 256 × 256 × 96.

CONCLUSIONS

The introduction and integration of DIMs and SAMs addressed the heterogeneous scale problem in an efficient and self-adaptive way. The proposed method provides an alternative to the inefficient multiresolution registration setups.

Deep Learning for Cardiac Image Segmentation: A Review

Deep learning has become the most widely used approach for cardiac image segmentation in recent years. In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound and major anatomical structures of interest (ventricles, atria, and vessels). In addition, a summary of publicly available cardiac image datasets and code repositories are included to provide a base for encouraging reproducible research. Finally, we discuss the challenges and limitations with current deep learning-based approaches (scarcity of labels, model generalizability across different domains, interpretability) and suggest potential directions for future research.