Esophageal optical coherence tomography image synthesis using an adversarially learned variational autoencoder

Endoscopic optical coherence tomography (OCT) imaging offers a non-invasive way to detect esophageal lesions on the microscopic scale, which is of clinical potential in the early diagnosis and treatment of esophageal cancers. Recent studies focused on applying deep learning-based methods in esophageal OCT image analysis and achieved promising results, which require a large data size. However, traditional data augmentation techniques generate samples that are highly correlated and sometimes far from reality, which may not lead to a satisfied trained model. In this paper, we proposed an adversarial learned variational autoencoder (AL-VAE) to generate high-quality esophageal OCT samples. The AL-VAE combines the generative adversarial network (GAN) and variational autoencoder (VAE) in a simple yet effective way, which preserves the advantages of VAEs, such as stable training and nice latent manifold, and requires no extra discriminators. Experimental results verified the proposed method achieved better image quality in generating esophageal OCT images when compared with the state-of-the-art image synthesis network, and its potential in improving deep learning model performance was also evaluated by esophagus segmentation.     

Connectivity-based deep learning approach for segmentation of the epithelium in in vivo human esophageal OCT images

Optical coherence tomography (OCT) is used for diagnosis of esophageal diseases such as Barrett’s esophagus. Given the large volume of OCT data acquired, automated analysis is needed. Here we propose a bilateral connectivity-based neural network for in vivo human esophageal OCT layer segmentation. Our method, connectivity-based CE-Net (Bicon-CE), defines layer segmentation as a combination of pixel connectivity modeling and pixel-wise tissue classification. Bicon-CE outperformed other widely used neural networks and reduced common topological prediction issues in tissues from healthy patients and from patients with Barrett’s esophagus. This is the first end-to-end learning method developed for automatic segmentation of the epithelium in in vivo human esophageal OCT images.     

Retinal layer segmentation in optical coherence tomography (OCT) using a 3D deep-convolutional regression network for patients with age-related macular degeneration

Introduction – Retinal layer segmentation in optical coherence tomography (OCT) images is an important approach for detecting and prognosing disease. Automating segmentation using robust machine learning techniques lead to computationally efficient solutions and significantly reduces the cost of labor-intensive labeling, which is traditionally performed by trained graders at a reading center, sometimes aided by semi-automated algorithms. Although several algorithms have been proposed since the revival of deep learning, eyes with severe pathological conditions continue to challenge fully automated segmentation approaches. There remains an opportunity to leverage the underlying spatial correlations between the retinal surfaces in the segmentation approach. Methods - Some of these proposed traditional methods can be expanded to utilize the three-dimensional spatial context governing the retinal image volumes by replacing the use of 2D filters with 3D filters. Towards this purpose, we propose a spatial-context, continuity and anatomical relationship preserving semantic segmentation algorithm, which utilizes the 3D spatial context from the image volumes with the use of 3D filters. We propose a 3D deep neural network capable of learning the surface positions of the layers in the retinal volumes. Results - We utilize a dataset of OCT images from patients with Age-related Macular Degeneration (AMD) to assess performance of our model and provide both qualitative (including segmentation maps and thickness maps) and quantitative (including error metric comparisons and volumetric comparisons) results, which demonstrate that our proposed method performs favorably even for eyes with pathological changes caused by severe retinal diseases. The Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) for patients with a wide range of AMD severity scores (0–11) were within 0.84±0.41 and 1.33±0.73 pixels, respectively, which are significantly better than some of the other state-of-the-art algorithms. Conclusion – The results demonstrate the utility of extracting features from the entire OCT volume by treating the volume as a correlated entity and show the benefit of utilizing 3D autoencoder based regression networks for smoothing the approximated retinal layers by inducing shape based regularization constraints.     

MF-AV-Net: an open-source deep learning network with multimodal fusion options for artery-vein segmentation in OCT angiography

This study is to demonstrate the effect of multimodal fusion on the performance of deep learning artery-vein (AV) segmentation in optical coherence tomography (OCT) and OCT angiography (OCTA); and to explore OCT/OCTA characteristics used in the deep learning AV segmentation. We quantitatively evaluated multimodal architectures with early and late OCT-OCTA fusions, compared to the unimodal architectures with OCT-only and OCTA-only inputs. The OCTA-only architecture, early OCT-OCTA fusion architecture, and late OCT-OCTA fusion architecture yielded competitive performances. For the 6 mm×6 mm and 3 mm×3 mm datasets, the late fusion architecture achieved an overall accuracy of 96.02% and 94.00%, slightly better than the OCTA-only architecture which achieved an overall accuracy of 95.76% and 93.79%. 6 mm×6 mm OCTA images show AV information at pre-capillary level structure, while 3 mm×3 mm OCTA images reveal AV information at capillary level detail. In order to interpret the deep learning performance, saliency maps were produced to identify OCT/OCTA image characteristics for AV segmentation. Comparative OCT and OCTA saliency maps support the capillary-free zone as one of the possible features for AV segmentation in OCTA. The deep learning network MF-AV-Net used in this study is available on GitHub for open access.     

MetricUNet: Synergistic image- and voxel-level learning for precise prostate segmentation via online sampling

Fully convolutional networks (FCNs), including UNet and VNet, are widely-used network architectures for semantic segmentation in recent studies. However, conventional FCN is typically trained by the cross-entropy or Dice loss, which only calculates the error between predictions and ground-truth labels for pixels individually. This often results in non-smooth neighborhoods in the predicted segmentation. This problem becomes more serious in CT prostate segmentation as CT images are usually of low tissue contrast. To address this problem, we propose a two-stage framework, with the first stage to quickly localize the prostate region, and the second stage to precisely segment the prostate by a multi-task UNet architecture. We introduce a novel online metric learning module through voxel-wise sampling in the multi-task network. Therefore, the proposed network has a dual-branch architecture that tackles two tasks: (1) a segmentation sub-network aiming to generate the prostate segmentation, and (2) a voxel-metric learning sub-network aiming to improve the quality of the learned feature space supervised by a metric loss. Specifically, the voxel-metric learning sub-network samples tuples (including triplets and pairs) in voxel-level through the intermediate feature maps. Unlike conventional deep metric learning methods that generate triplets or pairs in image-level before the training phase, our proposed voxel-wise tuples are sampled in an online manner and operated in an end-to-end fashion via multi-task learning. To evaluate the proposed method, we implement extensive experiments on a real CT image dataset consisting 339 patients. The ablation studies show that our method can effectively learn more representative voxel-level features compared with the conventional learning methods with cross-entropy or Dice loss. And the comparisons show that the proposed method outperforms the state-of-the-art methods by a reasonable margin.     

Weakly supervised histopathology image segmentation with self-attention

Accurate segmentation in histopathology images at pixel-level plays a critical role in the digital pathology workflow. The development of weakly supervised methods for histopathology image segmentation liberates pathologists from time-consuming and labor-intensive works, opening up possibilities of further automated quantitative analysis of whole-slide histopathology images. As an effective subgroup of weakly supervised methods, multiple instance learning (MIL) has achieved great success in histopathology images. In this paper, we specially treat pixels as instances so that the histopathology image segmentation task is transformed into an instance prediction task in MIL. However, the lack of relations between instances in MIL limits the further improvement of segmentation performance. Therefore, we propose a novel weakly supervised method called SA-MIL for pixel-level segmentation in histopathology images. SA-MIL introduces a self-attention mechanism into the MIL framework, which captures global correlation among all instances. In addition, we use deep supervision to make the best use of information from limited annotations in the weakly supervised method. Our approach makes up for the shortcoming that instances are independent of each other in MIL by aggregating global contextual information. We demonstrate state-of-the-art results compared to other weakly supervised methods on two histopathology image datasets. It is evident that our approach has generalization ability for the high performance on both tissue and cell histopathology datasets. There is potential in our approach for various applications in medical images.     

Quantitative characterization of human breast tissue based on deep learning segmentation of 3D optical coherence tomography images

In this study, we performed dual-modality optical coherence tomography (OCT) characterization (volumetric OCT imaging and quantitative optical coherence elastography) on human breast tissue specimens. We trained and validated a U-Net for automatic image segmentation. Our results demonstrated that U-Net segmentation can be used to assist clinical diagnosis for breast cancer, and is a powerful enabling tool to advance our understanding of the characteristics for breast tissue. Based on the results obtained from U-Net segmentation of 3D OCT images, we demonstrated significant morphological heterogeneity in small breast specimens acquired through diagnostic biopsy. We also found that breast specimens affected by different pathologies had different structural characteristics. By correlating U-Net analysis of structural OCT images with mechanical measurement provided by quantitative optical coherence elastography, we showed that the change of mechanical properties in breast tissue is not directly due to the change in the amount of dense or porous tissue.     

Retinal optical coherence tomography image analysis by a restricted Boltzmann machine

Optical coherence tomography (OCT) is an emerging imaging technique for ophthalmic disease diagnosis. Two major problems in OCT image analysis are image enhancement and image segmentation. Deep learning methods have achieved excellent performance in image analysis. However, most of the deep learning-based image analysis models are supervised learning-based approaches and need a high volume of training data (e.g., reference clean images for image enhancement and accurate annotated images for segmentation). Moreover, acquiring reference clean images for OCT image enhancement and accurate annotation of the high volume of OCT images for segmentation is hard. So, it is difficult to extend these deep learning methods to the OCT image analysis. We propose an unsupervised learning-based approach for OCT image enhancement and abnormality segmentation, where the model can be trained without reference images. The image is reconstructed by Restricted Boltzmann Machine (RBM) by defining a target function and minimizing it. For OCT image enhancement, each image is independently learned by the RBM network and is eventually reconstructed. In the reconstruction phase, we use the ReLu function instead of the Sigmoid function. Reconstruction of images given by the RBM network leads to improved image contrast in comparison to other competitive methods in terms of contrast to noise ratio (CNR). For anomaly detection, hyper-reflective foci (HF) as one of the first signs in retinal OCTs of patients with diabetic macular edema (DME) are identified based on image reconstruction by RBM and post-processing by removing the HFs candidates outside the area between the first and the last retinal layers. Our anomaly detection method achieves a high ability to detect abnormalities.     

SSA-Net: Spatial self-attention network for COVID-19 pneumonia infection segmentation with semi-supervised few-shot learning

Coronavirus disease (COVID-19) broke out at the end of 2019, and has resulted in an ongoing global pandemic. Segmentation of pneumonia infections from chest computed tomography (CT) scans of COVID-19 patients is significant for accurate diagnosis and quantitative analysis. Deep learning-based methods can be developed for automatic segmentation and offer a great potential to strengthen timely quarantine and medical treatment. Unfortunately, due to the urgent nature of the COVID-19 pandemic, a systematic collection of CT data sets for deep neural network training is quite difficult, especially high-quality annotations of multi-category infections are limited. In addition, it is still a challenge to segment the infected areas from CT slices because of the irregular shapes and fuzzy boundaries. To solve these issues, we propose a novel COVID-19 pneumonia lesion segmentation network, called Spatial Self-Attention network (SSA-Net), to identify infected regions from chest CT images automatically. In our SSA-Net, a self-attention mechanism is utilized to expand the receptive field and enhance the representation learning by distilling useful contextual information from deeper layers without extra training time, and spatial convolution is introduced to strengthen the network and accelerate the training convergence. Furthermore, to alleviate the insufficiency of labeled multi-class data and the long-tailed distribution of training data, we present a semi-supervised few-shot iterative segmentation framework based on re-weighting the loss and selecting prediction values with high confidence, which can accurately classify different kinds of infections with a small number of labeled image data. Experimental results show that SSA-Net outperforms state-of-the-art medical image segmentation networks and provides clinically interpretable saliency maps, which are useful for COVID-19 diagnosis and patient triage. Meanwhile, our semi-supervised iterative segmentation model can improve the learning ability in small and unbalanced training set and can achieve higher performance.     

Moment-based texture segmentation of luminal contour in intravascular ultrasound images

Purpose A system for luminal contour segmentation in intravascular ultrasound images is proposed. Methods Moment-based texture features are used for clustering of the pixels in the input image. After the clustering, morphological smoothing and a boundary detection process are applied and the final image is obtained. Results The proposed method was applied to 15 images from different patients, and a correlation coefficient of 0.86 was obtained between the areas of lumen automatically and manually defined. Conclusion Moment-based texture features together with the radial feature are powerful tools for identification of the lumen region in intravascular ultrasound images. Morphological filtering was useful for improving the segmentation results.     

Optical coherence tomography in the gastrointestinal tract

Optical coherence tomography (OCT) is a high-resolution, cross-sectional optical imaging technique that allows in situ imaging of tissue by measuring back-reflected light. OCT provides images in real time with a resolution approaching that of conventional histopathology, but without the need for tissue removal. OCT imaging can be performed endoscopically to visualize gastrointestinal tissue using a fiberoptic catheter passed through the instrument channel of a conventional endoscope. The resolution of OCT allows visualization of the different layers of gastrointestinal epithelium and the differentiation of Barrett's epithelium from normal gastric and squamous mucosa. OCT has also been used to image esophageal adenocarcinoma and colonic polyps. Recent developments include Doppler OCT, spectroscopic OCT, and ultrahigh-resolution OCT, which can visualize nuclei within single cells. Although still in its infancy as a clinical tool, OCT currently provides high-resolution images over the same imaging depth as conventional mucosal biopsy, and may prove to be a useful and minimally invasive technique for evaluating gastrointestinal tissue, particularly for early neoplastic changes.     

Deep pyramid local attention neural network for cardiac structure segmentation in two-dimensional echocardiography

Automatic semantic segmentation in 2D echocardiography is vital in clinical practice for assessing various cardiac functions and improving the diagnosis of cardiac diseases. However, two distinct problems have persisted in automatic segmentation in 2D echocardiography, namely the lack of an effective feature enhancement approach for contextual feature capture and lack of label coherence in category prediction for individual pixels. Therefore, in this study, we propose a deep learning model, called deep pyramid local attention neural network (PLANet), to improve the segmentation performance of automatic methods in 2D echocardiography. Specifically, we propose a pyramid local attention module to enhance features by capturing supporting information within compact and sparse neighboring contexts. We also propose a label coherence learning mechanism to promote prediction consistency for pixels and their neighbors by guiding the learning with explicit supervision signals. The proposed PLANet was extensively evaluated on the dataset of cardiac acquisitions for multi-structure ultrasound segmentation (CAMUS) and sub-EchoNet-Dynamic, which are two large-scale and public 2D echocardiography datasets. The experimental results show that PLANet performs better than traditional and deep learning-based segmentation methods on geometrical and clinical metrics. Moreover, PLANet can complete the segmentation of heart structures in 2D echocardiography in real time, indicating a potential to assist cardiologists accurately and efficiently.     

LMISA: A lightweight multi-modality image segmentation network via domain adaptation using gradient magnitude and shape constraint

In medical image segmentation, supervised machine learning models trained using one image modality (e.g. computed tomography (CT)) are often prone to failure when applied to another image modality (e.g. magnetic resonance imaging (MRI)) even for the same organ. This is due to the significant intensity variations of different image modalities. In this paper, we propose a novel end-to-end deep neural network to achieve multi-modality image segmentation, where image labels of only one modality (source domain) are available for model training and the image labels for the other modality (target domain) are not available. In our method, a multi-resolution locally normalized gradient magnitude approach is firstly applied to images of both domains for minimizing the intensity discrepancy. Subsequently, a dual task encoder-decoder network including image segmentation and reconstruction is utilized to effectively adapt a segmentation network to the unlabeled target domain. Additionally, a shape constraint is imposed by leveraging adversarial learning. Finally, images from the target domain are segmented, as the network learns a consistent latent feature representation with shape awareness from both domains. We implement both 2D and 3D versions of our method, in which we evaluate CT and MRI images for kidney and cardiac tissue segmentation. For kidney, a public CT dataset (KiTS19, MICCAI 2019) and a local MRI dataset were utilized. The cardiac dataset was from the Multi-Modality Whole Heart Segmentation (MMWHS) challenge 2017. Experimental results reveal that our proposed method achieves significantly higher performance with a much lower model complexity in comparison with other state-of-the-art methods. More importantly, our method is also capable of producing superior segmentation results than other methods for images of an unseen target domain without model retraining. The code is available at GitHub (https://github.com/MinaJf/LMISA) to encourage method comparison and further research.     

ResGANet: Residual group attention network for medical image classification and segmentation

In recent years, deep learning technology has shown superior performance in different fields of medical image analysis. Some deep learning architectures have been proposed and used for computational pathology classification, segmentation, and detection tasks. Due to their simple, modular structure, most downstream applications still use ResNet and its variants as the backbone network. This paper proposes a modular group attention block that can capture feature dependencies in medical images in two independent dimensions: channel and space. By stacking these group attention blocks in ResNet-style, we obtain a new ResNet variant called ResGANet. The stacked ResGANet architecture has 1.51–3.47 times fewer parameters than the original ResNet and can be directly used for downstream medical image segmentation tasks. Many experiments show that the proposed ResGANet is superior to state-of-the-art backbone models in medical image classification tasks. Applying it to different segmentation networks can improve the baseline model in medical image segmentation tasks without changing the network architecture. We hope that this work provides a promising method for enhancing the feature representation of convolutional neural networks (CNNs) in the future.     

Boundary-aware context neural network for medical image segmentation

Medical image segmentation can provide a reliable basis for further clinical analysis and disease diagnosis. With the development of convolutional neural networks (CNNs), medical image segmentation performance has advanced significantly. However, most existing CNN-based methods often produce unsatisfactory segmentation masks without accurate object boundaries. This problem is caused by the limited context information and inadequate discriminative feature maps after consecutive pooling and convolution operations. Additionally, medical images are characterized by high intra-class variation, inter-class indistinction and noise, extracting powerful context and aggregating discriminative features for fine-grained segmentation remain challenging. In this study, we formulate a boundary-aware context neural network (BA-Net) for 2D medical image segmentation to capture richer context and preserve fine spatial information, which incorporates encoder-decoder architecture. In each stage of the encoder sub-network, a proposed pyramid edge extraction module first obtains multi-granularity edge information. Then a newly designed mini multi-task learning module for jointly learning segments the object masks and detects lesion boundaries, in which a new interactive attention layer is introduced to bridge the two tasks. In this way, information complementarity between different tasks is achieved, which effectively leverages the boundary information to offer strong cues for better segmentation prediction. Finally, a cross feature fusion module acts to selectively aggregate multi-level features from the entire encoder sub-network. By cascading these three modules, richer context and fine-grain features of each stage are encoded and then delivered to the decoder. The results of extensive experiments on five datasets show that the proposed BA-Net outperforms state-of-the-art techniques.     

Automatic ischemic stroke lesion segmentation from computed tomography perfusion images by image synthesis and attention-based deep neural networks

Ischemic stroke lesion segmentation from Computed Tomography Perfusion (CTP) images is important for accurate diagnosis of stroke in acute care units. However, it is challenged by low image contrast and resolution of the perfusion parameter maps, in addition to the complex appearance of the lesion. To deal with this problem, we propose a novel framework based on synthesized pseudo Diffusion-Weighted Imaging (DWI) from perfusion parameter maps to obtain better image quality for more accurate segmentation. Our framework consists of three components based on Convolutional Neural Networks (CNNs) and is trained end-to-end. First, a feature extractor is used to obtain both a low-level and high-level compact representation of the raw spatiotemporal Computed Tomography Angiography (CTA) images. Second, a pseudo DWI generator takes as input the concatenation of CTP perfusion parameter maps and our extracted features to obtain the synthesized pseudo DWI. To achieve better synthesis quality, we propose a hybrid loss function that pays more attention to lesion regions and encourages high-level contextual consistency. Finally, we segment the lesion region from the synthesized pseudo DWI, where the segmentation network is based on switchable normalization and channel calibration for better performance. Experimental results showed that our framework achieved the top performance on ISLES 2018 challenge and: (1) our method using synthesized pseudo DWI outperformed methods segmenting the lesion from perfusion parameter maps directly; (2) the feature extractor exploiting additional spatiotemporal CTA images led to better synthesized pseudo DWI quality and higher segmentation accuracy; and (3) the proposed loss functions and network structure improved the pseudo DWI synthesis and lesion segmentation performance. The proposed framework has a potential for improving diagnosis and treatment of the ischemic stroke where access to real DWI scanning is limited.     

Intra-retinal layer segmentation of 3D optical coherence tomography using coarse grained diffusion map

Optical coherence tomography (OCT) is a powerful and noninvasive method for retinal imaging. In this paper, we introduce a fast segmentation method based on a new variant of spectral graph theory named diffusion maps. The research is performed on spectral domain (SD) OCT images depicting macular and optic nerve head appearance. The presented approach does not require edge-based image information in localizing most of boundaries and relies on regional image texture. Consequently, the proposed method demonstrates robustness in situations of low image contrast or poor layer-to-layer image gradients. Diffusion mapping applied to 2D and 3D OCT datasets is composed of two steps, one for partitioning the data into important and less important sections, and another one for localization of internal layers. In the first step, the pixels/voxels are grouped in rectangular/cubic sets to form a graph node. The weights of the graph are calculated based on geometric distances between pixels/voxels and differences of their mean intensity. The first diffusion map clusters the data into three parts, the second of which is the area of interest. The other two sections are eliminated from the remaining calculations. In the second step, the remaining area is subjected to another diffusion map assessment and the internal layers are localized based on their textural similarities. The proposed method was tested on 23 datasets from two patient groups (glaucoma and normals). The mean unsigned border positioning errors (mean ± SD) was 8.52 ± 3.13 and 7.56 ± 2.95 μm for the 2D and 3D methods, respectively.     

Real-time noise reduction based on ground truth free deep learning for optical coherence tomography

Optical coherence tomography (OCT) is a high-resolution non-invasive 3D imaging modality, which has been widely used for biomedical research and clinical studies. The presence of noise on OCT images is inevitable which will cause problems for post-image processing and diagnosis. The frame-averaging technique that acquires multiple OCT images at the same or adjacent locations can enhance the image quality significantly. Both conventional frame averaging methods and deep learning-based methods using averaged frames as ground truth have been reported. However, conventional averaging methods suffer from the limitation of long image acquisition time, while deep learning-based methods require complicated and tedious ground truth label preparation. In this work, we report a deep learning-based noise reduction method that does not require clean images as ground truth for model training. Three network structures, including Unet, super-resolution residual network (SRResNet), and our modified asymmetric convolution-SRResNet (AC-SRResNet), were trained and evaluated using signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), edge preservation index (EPI) and computation time (CT). The effectiveness of these three trained models on OCT images of different samples and different systems was also investigated and confirmed. The SNR improvement for different sample images for L₂-loss-trained Unet, SRResNet, and AC-SRResNet are 20.83 dB, 24.88 dB, and 22.19 dB, respectively. The SNR improvement for public images from different system for L₁-loss-trained Unet, SRResNet, and AC-SRResNet are 19.36 dB, 20.11 dB, and 22.15 dB, respectively. AC-SRResNet and SRResNet demonstrate better denoising effect than Unet with longer computation time. AC-SRResNet demonstrates better edge preservation capability than SRResNet while Unet is close to AC-SRResNet. Eventually, we incorporated Unet, SRResNet, and AC-SRResNet into our graphic processing unit accelerated OCT imaging system for online noise reduction evaluation. Real-time noise reduction for OCT images with size of 512×512 pixels for Unet, SRResNet, and AC-SRResNet at 64 fps, 19 fps, and 17 fps were achieved respectively.     

MallesNet: A multi-object assistance based network for brachial plexus segmentation in ultrasound images

Ultrasound-guided injection is widely used to help anesthesiologists perform anesthesia in peripheral nerve blockade (PNB). However, it is a daunting task to accurately identify nerve structure in ultrasound images even for the experienced anesthesiologists. In this paper, a Multi-object assistance based Brachial Plexus Segmentation Network, named MallesNet, is proposed to improve the nerve segmentation performance in ultrasound image with the assistance of simultaneously segmenting its surrounding anatomical structures (e.g., muscle, vein, and artery). The MallesNet is designed by following the framework of Mask R-CNN to implement the multi object identification and segmentation. Moreover, a spatial local contrast feature (SLCF) extraction module is proposed to compute contrast features at different scales to effectively obtain useful features for small objects. And the self-attention gate (SAG) is also utilized to capture the spatial relationships in different channels and further re-weight the channels in feature maps by following the design of non-local operation and channel attention. Furthermore, the upsampling mechanism in original Feature Pyramid Network (FPN) is improved by adopting the transpose convolution and skip concatenation to fine-tune the feature maps. The Ultrasound Brachial Plexus Dataset (UBPD) is also proposed to support the research on brachial plexus segmentation, which consists of 1055 ultrasound images with four objects (i.e., nerve, artery, vein and muscle) and their corresponding label masks. Extensive experimental results using UBPD dataset demonstrate that MallesNet can achieve a better segmentation performance on nerves structure and also on surrounding structures in comparison to other competing approaches.     

基于深度学习的甲状腺结节超声图像分割的临床应用

目的探讨深度学习方法在超声甲状腺结节分割中的效果及其临床应用价值。 方法收集2018年8月至2020年10月首都医科大学附属北京天坛医院的166例甲状腺结节患者的1044张超声图像。观察使用改进自注意力机制的Unet深度学习方法和Unet基础方法在测试数据集上的分割效果。以分割结果是否接近有多年临床经验的超声医师的手动标注作为参考标准,将改进自注意力机制的Unet和Unet基础方法对甲状腺结节的分割效果进行比较,以交并比（IoU）、戴斯（Dice）相似性系数及与超声医师对甲状腺结节的手动勾勒接近程度来评价深度学习模型对甲状腺结节分割效果及临床应用价值的性能。 结果改进自注意力机制的Unet深度学习模型对甲状腺结节分割的IoU及Dice系数分别为0.815和0.839,与Unet基础方法结果（IoU为0.788,Dice系数为0.817）相比,具有更高的IoU和Dice系数值。从分割图像可以看出,基于改进自注意力机制的Unet深度学习模型对甲状腺结节整体和边缘细节上的分割效果好于Unet基础方法,更接近于超声医师的手动勾勒结果。 结论基于自注意力机制的Unet深度学习模型在甲状腺结节分割方面有着较高的性能,可提高诊断效率,并且该方法具有一定的临床应用价值。