Automatic Segmentation Results Research Articles

SM-GRSNet: sparse mapping-based graph representation segmentation network for honeycomb lung lesion

Objective. Honeycomb lung is a rare but severe disease characterized by honeycomb-like imaging features and distinct radiological characteristics. Therefore, this study aims to develop a deep-learning model capable of segmenting honeycomb lung lesions from Computed Tomography (CT) scans to address the efficacy issue of honeycomb lung segmentation. Methods. This study proposes a sparse mapping-based graph representation segmentation network (SM-GRSNet). SM-GRSNet integrates an attention affinity mechanism to effectively filter redundant features at a coarse-grained region level. The attention encoder generated by this mechanism specifically focuses on the lesion area. Additionally, we introduce a graph representation module based on sparse links in SM-GRSNet. Subsequently, graph representation operations are performed on the sparse graph, yielding detailed lesion segmentation results. Finally, we construct a pyramid-structured cascaded decoder in SM-GRSNet, which combines features from the sparse link-based graph representation modules and attention encoders to generate the final segmentation mask. Results. Experimental results demonstrate that the proposed SM-GRSNet achieves state-of-the-art performance on a dataset comprising 7170 honeycomb lung CT images. Our model attains the highest IOU (87.62%), Dice(93.41%). Furthermore, our model also achieves the lowest HD95 (6.95) and ASD (2.47). Significance. The SM-GRSNet method proposed in this paper can be used for automatic segmentation of honeycomb lung CT images, which enhances the segmentation performance of Honeycomb lung lesions under small sample datasets. It will help doctors with early screening, accurate diagnosis, and customized treatment. This method maintains a high correlation and consistency between the automatic segmentation results and the expert manual segmentation results. Accurate automatic segmentation of the honeycomb lung lesion area is clinically important.

Diabetic foot ulcers segmentation challenge report: Benchmark and analysis

Monitoring the healing progress of diabetic foot ulcers is a challenging process. Accurate segmentation of foot ulcers can help podiatrists to quantitatively measure the size of wound regions to assist prediction of healing status. The main challenge in this field is the lack of publicly available manual delineation, which can be time consuming and laborious. Recently, methods based on deep learning have shown excellent results in automatic segmentation of medical images, however, they require large-scale datasets for training, and there is limited consensus on which methods perform the best. The 2022 Diabetic Foot Ulcers segmentation challenge was held in conjunction with the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention, which sought to address these issues and stimulate progress in this research domain. A training set of 2000 images exhibiting diabetic foot ulcers was released with corresponding segmentation ground truth masks. Of the 72 (approved) requests from 47 countries, 26 teams used this data to develop fully automated systems to predict the true segmentation masks on a test set of 2000 images, with the corresponding ground truth segmentation masks kept private. Predictions from participating teams were scored and ranked according to their average Dice similarity coefficient of the ground truth masks and prediction masks. The winning team achieved a Dice of 0.7287 for diabetic foot ulcer segmentation. This challenge has now entered a live leaderboard stage where it serves as a challenging benchmark for diabetic foot ulcer segmentation.

Interobserver Agreement in Automatic Segmentation Annotation of Prostate Magnetic Resonance Imaging.

We aimed to compare the performance and interobserver agreement of radiologists manually segmenting images or those assisted by automatic segmentation. We further aimed to reduce interobserver variability and improve the consistency of radiomics features. This retrospective study included 327 patients diagnosed with prostate cancer from September 2016 to June 2018; images from 228 patients were used for automatic segmentation construction, and images from the remaining 99 were used for testing. First, four radiologists with varying experience levels retrospectively segmented 99 axial prostate images manually using T2-weighted fat-suppressed magnetic resonance imaging. Automatic segmentation was performed after 2 weeks. The Pyradiomics software package v3.1.0 was used to extract the texture features. The Dice coefficient and intraclass correlation coefficient (ICC) were used to evaluate segmentation performance and the interobserver consistency of prostate radiomics. The Wilcoxon rank sum test was used to compare the paired samples, with the significance level set at p < 0.05. The Dice coefficient was used to accurately measure the spatial overlap of manually delineated images. In all the 99 prostate segmentation result columns, the manual and automatic segmentation results of the senior group were significantly better than those of the junior group (p < 0.05). Automatic segmentation was more consistent than manual segmentation (p < 0.05), and the average ICC reached >0.85. The automatic segmentation annotation performance of junior radiologists was similar to that of senior radiologists performing manual segmentation. The ICC of radiomics features increased to excellent consistency (0.925 [0.888~0.950]). Automatic segmentation annotation provided better results than manual segmentation by radiologists. Our findings indicate that automatic segmentation annotation helps reduce variability in the perception and interpretation between radiologists with different experience levels and ensures the stability of radiomics features.

Large-scale multi-unit floor plan dataset for architectural plan analysis and recognition

Among automatic floor plan analysis, data-driven methods have become increasingly popular in recent years because of their superior accuracy and generalizability compared to traditional approaches while processing rasterized floor plans. However, the scarcity of public raster datasets with various styles and sufficient quantity hinders the development of new models, as current ones only contain a single apartment or house, limiting the analysis of large-scale plans usually designed in architectural and structural offices. In order to address that issue, this paper presents a multi-unit floor plan dataset comprising 954 high-resolution images of residential buildings with annotated walls and slabs as polygons, enabling large-scale plan analysis. Additionally, this study implements an automatic wall vectorization method that uses a learning discriminative-based semantic segmentation U-Net model to retrieve wall objects, followed by a deep-learning model that predicts the segmented primitives, providing a baseline for future comparison of automatic wall segmentation results.

Deep Learning for Automated Contouring of Primary Gross Tumor Volumes by MRI for Radiation Therapy of Brain Metastasis

Radiotherapy is one of the most effective methods for the treatment of brain metastases (BMs). Traditional manual delineation of primary gross tumor volumes (GTV) of multiple BMs (especially small metastases) in radiotherapy practice is extremely labor intensive and highly dependent on oncologists' experience, achieving the precise and efficient automatic delineation of BMs is of great significance for efficient and homogeneous one-stop adaptive radiotherapy. We retrospectively collected 62 MRI (non-enhanced T1-weighted sequences) sequences of 50 patients with BMs from January 2020 to July 2021. An automatic model (BUC-Net) for automatic delineation BMs was proposed in this work, which was based on deep learning by combining 3D bottler layer module and the cascade architecture to improve the accuracy and efficient of BMs' automatic delineation, especially for small metastases with tiny size and relatively low contrast. The prosed method was compared with the existing 3D U-Net (U-Net) and 3D U-Net Cascade (U-Net Cascade). The performance of our proposed method was evaluated by Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and average surface distance (ASD) with human experts. The automatic segmentation results of BUC-Net evaluated with 310 BMs in 13 test patients was summarized in Table 1. These BMs in each test patient were automatically delineated by two types of contours: as a whole tumor contour (Whole-delineation) and the multiple tumor contours (Multiple-delineation). BUC-Net performed the best mean DSC and HD95, which is significantly outperformed U-Net (Whole-delineation: 0.911 & 0.894 of DSC, Multiple-delineation: 0.794 & 0.754 of DSC, P < 0.05 for both) and U-Net cascade (Whole-delineation: 0.947 & 7.141 of HD95, Multiple-delineation: 0.902 & 1.171 of HD95, P < 0.05 for both); Additionally, BUC-Net achieved the best mean ASD for Whole-delineation and comparable ASD (0.290 & 0.277, P > 0) for Multiple-delineation with U-Net Cascade. Our results showed that the proposed approach is promising for the automatic delineation of BMs in MRI, which can be integrated into a radiotherapy workflow to significantly shorten segmentation time.

Segmentation of measurable images from standard plane of Graf hip ultrasonograms based on Mask Region-Based Convolutional Neural Network.

This study proposed a Mask Region-Based Convolutional Neural Network (R-CNN)-based automatic segmentation to accurately detect the measurable standard plane of Graf hip ultrasonography images via segmentation of the labrum, lower limb of ilium, and the iliac wing. The study examined the hip ultrasonograms of 675 infants (205 males, 470 females; mean age: 7±2.8 weeks; range, 3 to 20 weeks) recorded between January 2011 and January 2018. The standard plane newborn hip ultrasound images were classified according to Graf's method by an experienced ultrasonographer. The hips were grouped as type 1, type 2a, type 2b, and type 2c-D. Two hundred seventy-five ultrasonograms were utilized as training data, 30 were validation data, and 370 were test data. The three anatomical regions were simultaneously segmented by Mask-R CNN in the test data and defective ultrasonograms. Automatic instance-based segmentation results were compared with the manual segmentation results of an experienced orthopedic expert. Success rates were calculated using Dice and mean average precision (mAP) metrics. Of these, 447 Graf type 1, 175 type 2a or 2b, 53 type 2c and D ultrasonograms were utilized. Average success rates with respect to hip types in the whole data were 96.95 and 96.96% according to Dice and mAP methods, respectively. Average success rates with respect to anatomical regions were 97.20 and 97.35% according to Dice and mAP methods, respectively. The highest average success rates were for type 1 hips, with 98.46 and 98.73%, and the iliac wing, with 98.25 and 98.86%, according to Dice and mAP methods, respectively. Mask R-CNN is a robust instance-based method in the segmentation of Graf hip ultrasonograms to delineate the standard plane. The proposed method revealed high success in each type of hip for each anatomic region.

Clinical evaluation on automatic segmentation results of convolutional neural networks in rectal cancer radiotherapy.

Image segmentation can be time-consuming and lacks consistency between different oncologists, which is essential in conformal radiotherapy techniques. We aimed to evaluate automatic delineation results generated by convolutional neural networks (CNNs) from geometry and dosimetry perspectives and explore the reliability of these segmentation tools in rectal cancer. Forty-seven rectal cancer cases treated from February 2018 to April 2019 were randomly collected retrospectively in our cancer center. The oncologists delineated regions of interest (ROIs) on planning CT images as the ground truth, including clinical target volume (CTV), bladder, small intestine, and femoral heads. The corresponding automatic segmentation results were generated by DeepLabv3+ and ResUNet, and we also used Atlas-Based Autosegmentation (ABAS) software for comparison. The geometry evaluation was carried out using the volumetric Dice similarity coefficient (DSC) and surface DSC, and critical dose parameters were assessed based on replanning optimized by clinically approved or automatically generated CTVs and organs at risk (OARs), i.e., the Planref and Plantest. Pearson test was used to explore the correlation between geometric metrics and dose parameters. In geometric evaluation, DeepLabv3+ performed better in DCS metrics for the CTV (volumetric DSC, mean = 0.96, P< 0.01; surface DSC, mean = 0.78, P< 0.01) and small intestine (volumetric DSC, mean = 0.91, P< 0.01; surface DSC, mean = 0.62, P< 0.01), ResUNet had advantages in volumetric DSC of the bladder (mean = 0.97, P< 0.05). For critical dose parameters analysis between Planref and Plantest, there was a significant difference for target volumes (P< 0.01), and no significant difference was found for the ResUNet-generated small intestine (P > 0.05). For the correlation test, a negative correlation was found between DSC metrics (volumetric, surface DSC) and dosimetric parameters (δD95, δD95, HI, CI) for target volumes (P< 0.05), and no significant correlation was found for most tests of OARs (P > 0.05). CNNs show remarkable repeatability and time-saving in automatic segmentation, and their accuracy also has a certain potential in clinical practice. Meanwhile, clinical aspects, such as dose distribution, may need to be considered when comparing the performance of auto-segmentation methods.

Attention-guided multi-scale learning network for automatic prostate and tumor segmentation on MRI

Background and Objective:Image-guided clinical diagnosis can be achieved by automatically and accurately segmenting prostate and prostatic cancer in male pelvic magnetic resonance imaging (MRI) images. For accurate tumor removal, the location, number, and size of prostate cancer are crucial, especially in surgical patients. The morphological differences between the prostate and tumor regions are small, the size of the tumor is uncertain, the boundary between the tumor and surrounding tissue is blurred, and the classification that separates the normal region from the tumor is uneven. Therefore, segmenting prostate and tumor on MRI images is challenging. Methods:This study offers a new prostate and prostatic cancer segmentation network based on double branch attention driven multi-scale learning for MRI. To begin, the dual branch structure provides two input images with different scales for feature coding, as well as a multi-scale attention module that collects details from different scales. The features of the double branch structure are then entered into the built feature fusion module to get more complete context information. Finally, to give a more precise learning representation, each stage is built using a deep supervision mechanism. Results:The results of our proposed network’s prostate and tumor segmentation on a variety of male pelvic MRI data sets show that it outperforms existing techniques. For prostate and prostatic cancer MRI segmentation, the dice similarity coefficient (DSC) values were 91.65% and 84.39%, respectively. Conclusions:Our method maintains high correlation and consistency between automatic segmentation results and expert manual segmentation results. Accurate automatic segmentation of prostate and prostate cancer has important clinical significance.

Interactive Skin Wound Segmentation Based on Feature Augment Networks.

Skin wound segmentation in photographs allows non-invasive analysis of wounds that supports dermatological diagnosis and treatment. In this paper, we propose a novel feature augment network (FANet) to achieve automatic segmentation of skin wounds, and design an interactive feature augment network (IFANet) to provide interactive adjustment on the automatic segmentation results. The FANet contains the edge feature augment (EFA) module and the spatial relationship feature augment (SFA) module, which can make full use of the notable edge information and the spatial relationship information be-tween the wound and the skin. The IFANet, with FANet as the backbone, takes the user interactions and the initial result as inputs, and outputs the refined segmentation result. The pro-posed networks were tested on a dataset composed of miscellaneous skin wound images, and a public foot ulcer segmentation challenge dataset. The results indicate that the FANet gives good segmentation results while the IFANet can effectively improve them based on simple marking. Comprehensive comparative experiments show that our proposed networks outperform some other existing automatic or interactive segmentation methods, respectively.

AN ALGORITHM TO SEGMENT THE MID-BRAIN STRUCTURES USING MULTI- RESOLUTION NON-RIGID REGISTRATION

&#x0D; &#x0D; &#x0D; In present study, a reference based technique has been proposed to segment mid- brain structures in 3D Magnetic Resonance (MR) images using multi-resolution non-rigid registration. The proposed scheme segmented the mid-brain structures in two stages. During first stage, a target image was registered to an already segmented reference image while in second stage, segmentation information was mapped from reference to target medical image. Using this scheme, the aim was to segment nine mid-brain structures including left ventricle, right ventricle, third ventricle, anterior commissure, posterior commissure, left putamen, right putamen, left caudate nucleus and right caudate nucleus. Results of automatic segmentation achieved through reference based non-rigid registration were validated by comparing with the manual segmentation, considered as ground truth. Three metrics namely Dice Coefficient, Sensitivity and Positive Predictive Values were used for assessing the segmentation results. The proposed algorithm showed the satisfactory segmentation of mid-brain structures by achieving a mean sensitivity of 89. 85 % for five target MR images. The results indicated that the proposed scheme performed accurate segmentation of mid-brain structures.&#x0D; &#x0D; &#x0D;

Inter- and intra-operator variations in manual segmentation of hippocampus from MRI

PurposeWe evaluate inter- and intra-operator variations in manual segmentation of hippocampus and present their potential sources. Hippocampal atrophy is common in mesial temporal lobe epilepsy (mTLE). Effective diagnosis and treatment of mTLE depends on accurate and efficient segmentation of hippocampus from magnetic resonance imaging (MRI) data. Manual segmentation by expert radiologists remains the gold standard, although automated segmentation methods exist. MethodsHippocampus was segmented in MRI of 118 unilateral mTLE patients and 25 non-epileptic subjects (65 males, 78 females; mean age 39 years) by three operators (M1, M2, M3) manually and by three software tools (FreeSurfer, LocalInfo, ABSS) automatically. Segmentation results were evaluated using 7 volume-, voxel-, and distance-based performance measures. Inter-operator variation was evaluated by comparing the segmentation results of the three operators. Intra-operator variation was evaluated by comparing manual and automatic segmentation results. Segmentation results were used to lateralize epileptogenicity in mTLE patients. ResultsRanking of performance measures differed when using M3 segmentations as ground truth rather than M1 or M2 segmentations. The standard deviation tended to be higher when using M3 as ground truth and M1 or M2 as test segmentation. Variation in performance measures and increased standard deviation when using M3 as ground truth are indicative of inter-operator variability. Standard deviations were larger when using M2 segmentations as ground truth and automated segmentations as test segmentation, rather than M1 or M3. Large standard deviations between M2 segmentations and automated segmentations are indicative of intra-operator variation. Among automated segmentation methods, ABSS produced segmentations most similar to manual segmentations, but FreeSurfer and LocalInfo lateralized epileptogenicity more accurately. ConclusionsPart of inter-operator variation might be due to temporal separation of M3 segmentations from M1 and M2 segmentations (M3 performed segmentations a few years before operators M1 and M2). Inter-operator variation will likely reduce if all operators segment within the same time frame, reducing discrepancies in training of operators. Intra-operator variation can likely be mitigated with additional oversight by a neuroradiologist. Inter- and intra-operator variability may generate inconsistencies in outcomes. Future automated segmentation techniques may integrate neural-network-based (ABSS) and atlas-based (FreeSurfer and LocalInfo) segmentation techniques for optimal performance.

An Overview of Deep Learning Methods for Left Ventricle Segmentation.

Cardiac health diseases are one of the key causes of death around the globe. The number of heart patients has considerably increased during the pandemic. Therefore, it is crucial to assess and analyze the medical and cardiac images. Deep learning architectures, specifically convolutional neural networks have profoundly become the primary choice for the assessment of cardiac medical images. The left ventricle is a vital part of the cardiovascular system where the boundary and size perform a significant role in the evaluation of cardiac function. Due to automatic segmentation and good promising results, the left ventricle segmentation using deep learning has attracted a lot of attention. This article presents a critical review of deep learning methods used for the left ventricle segmentation from frequently used imaging modalities including magnetic resonance images, ultrasound, and computer tomography. This study also demonstrates the details of the network architecture, software, and hardware used for training along with publicly available cardiac image datasets and self-prepared dataset details incorporated. The summary of the evaluation matrices with results used by different researchers is also presented in this study. Finally, all this information is summarized and comprehended in order to assist the readers to understand the motivation and methodology of various deep learning models, as well as exploring potential solutions to future challenges in LV segmentation.

Multi-Organ Segmentation Using a Low-Resource Architecture

Since their inception, deep-learning architectures have shown promising results for automatic segmentation. However, despite the technical advances introduced by fully convolutional networks, generative adversarial networks or recurrent neural networks, and their usage in hybrid architectures, automatic segmentation in the medical field is still not used at scale. One main reason is related to data scarcity and quality, which in turn generates a lack of annotated data that hinder the generalization of the models. The second main issue refers to challenges in training deep models. This process uses large amounts of GPU memory (that might exceed current hardware limitations) and requires high training times. In this article, we want to prove that despite these issues, good results can be obtained even when using a lower resource architecture, thus opening the way for more researchers to employ and use deep neural networks. In achieving the multi-organ segmentation, we are employing modern pre-processing techniques, a smart model design and fusion between several models trained on the same dataset. Our architecture is compared against state-of-the-art methods employed in a publicly available challenge and the notable results prove the effectiveness of our method.

Study on the accuracy of automatic segmentation of knee CT images based on deep learning

To develop a neural network architecture based on deep learning to assist knee CT images automatic segmentation, and validate its accuracy. A knee CT scans database was established, and the bony structure was manually annotated. A deep learning neural network architecture was developed independently, and the labeled database was used to train and test the neural network. Metrics of Dice coefficient, average surface distance (ASD), and Hausdorff distance (HD) were calculated to evaluate the accuracy of the neural network. The time of automatic segmentation and manual segmentation was compared. Five orthopedic experts were invited to score the automatic and manual segmentation results using Likert scale and the scores of the two methods were compared. The automatic segmentation achieved a high accuracy. The Dice coefficient, ASD, and HD of the femur were 0.953±0.037, (0.076±0.048) mm, and (3.101±0.726) mm, respectively; and those of the tibia were 0.950±0.092, (0.083±0.101) mm, and (2.984±0.740) mm, respectively. The time of automatic segmentation was significantly shorter than that of manual segmentation [(2.46±0.45) minutes vs. (64.73±17.07) minutes; t=36.474, P<0.001). The clinical scores of the femur were 4.3±0.3 in the automatic segmentation group and 4.4±0.2 in the manual segmentation group, and the scores of the tibia were 4.5±0.2 and 4.5±0.3, respectively. There was no significant difference between the two groups ( t=1.753, P=0.085; t=0.318, P=0.752). The automatic segmentation of knee CT images based on deep learning has high accuracy and can achieve rapid segmentation and three-dimensional reconstruction. This method will promote the development of new technology-assisted techniques in total knee arthroplasty.

Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images.

The identification of human activities from videos is important for many applications. For such a task, three-dimensional (3D) depth images or image sequences (videos) can be used, which represent the positioning information of the objects in a 3D scene obtained from depth sensors. This paper presents a framework to create foreground–background masks from depth images for human body segmentation. The framework can be used to speed up the manual depth image annotation process with no semantics known beforehand and can apply segmentation using a performant algorithm while the user only adjusts the parameters, or corrects the automatic segmentation results, or gives it hints by drawing a boundary of the desired object. The approach has been tested using two different datasets with a human in a real-world closed environment. The solution has provided promising results in terms of reducing the manual segmentation time from the perspective of the processing time as well as the human input time.

Correlation of choroidal thickness with age in healthy subjects: automatic detection and segmentation using a deep learning model.

The proposed deep learning model with a mask region-based convolutional neural network (Mask R-CNN) can predict choroidal thickness automatically. Changes in choroidal thickness with age can be detected with manual measurements. In this study, we aimed to investigate choroidal thickness in a comprehensive aspect in healthy eyes by utilizing the Mask R-CNN model. A total of 68 eyes from 57 participants without significant ocular disease were recruited. The participants were allocated to one of three groups according to their age and underwent spectral domain optical coherence tomography (SD-OCT) or enhanced depth imaging OCT (EDI-OCT) centered on the fovea. Each OCT sequence included 25 slices. Physicians labeled the choroidal contours in all the OCT sequences. We applied the Mask R-CNN model for automatic segmentation. Comparisons of choroidal thicknesses were conducted according to age and prediction accuracy. Older age groups had thinner choroids, according to the automatic segmentation results; the mean choroidal thickness was 253.7 ± 41.9μm in the youngest group, 206.8 ± 35.4μm in the middle-aged group, and 152.5 ± 45.7μm in the oldest group (p < 0.01). Measurements obtained using physician sketches demonstrated similar trends. We observed a significant negative correlation between choroidal thickness and age (p < 0.01). The prediction error was lower and less variable in choroids that were thinner than the cutoff point of 280μm. By observing choroid layer continuously and comprehensively. We found that the mean choroidal thickness decreased with age in healthy subjects. The Mask R-CNN model can accurately predict choroidal thickness, especially choroids thinner than 280μm. This model can enable exploring larger and more varied choroid datasets comprehensively, automatically, and conveniently.

Genetic U-Net: Automatically Designed Deep Networks for Retinal Vessel Segmentation Using a Genetic Algorithm

Recently, many methods based on hand-designed convolutional neural networks (CNNs) have achieved promising results in automatic retinal vessel segmentation. However, these CNNs remain constrained in capturing retinal vessels in complex fundus images. To improve their segmentation performance, these CNNs tend to have many parameters, which may lead to overfitting and high computational complexity. Moreover, the manual design of competitive CNNs is time-consuming and requires extensive empirical knowledge. Herein, a novel automated design method, called Genetic U-Net, is proposed to generate a U-shaped CNN that can achieve better retinal vessel segmentation but with fewer architecture-based parameters, thereby addressing the above issues. First, we devised a condensed but flexible search space based on a U-shaped encoder-decoder. Then, we used an improved genetic algorithm to identify better-performing architectures in the search space and investigated the possibility of finding a superior network architecture with fewer parameters. The experimental results show that the architecture obtained using the proposed method offered a superior performance with less than 1% of the number of the original U-Net parameters in particular and with significantly fewer parameters than other state-of-the-art models. Furthermore, through in-depth investigation of the experimental results, several effective operations and patterns of networks to generate superior retinal vessel segmentations were identified. The codes of this work are available at https://github.com/96jhwei/Genetic-U-Net.

NHBS-Net: A Feature Fusion Attention Network for Ultrasound Neonatal Hip Bone Segmentation.

Ultrasound is a widely used technology for diagnosing developmental dysplasia of the hip (DDH) because it does not use radiation. Due to its low cost and convenience, 2-D ultrasound is still the most common examination in DDH diagnosis. In clinical usage, the complexity of both ultrasound image standardization and measurement leads to a high error rate for sonographers. The automatic segmentation results of key structures in the hip joint can be used to develop a standard plane detection method that helps sonographers decrease the error rate. However, current automatic segmentation methods still face challenges in robustness and accuracy. Thus, we propose a neonatal hip bone segmentation network (NHBS-Net) for the first time for the segmentation of seven key structures. We design three improvements, an enhanced dual attention module, a two-class feature fusion module, and a coordinate convolution output head, to help segment different structures. Compared with current state-of-the-art networks, NHBS-Net gains outstanding performance accuracy and generalizability, as shown in the experiments. Additionally, image standardization is a common need in ultrasonography. The ability of segmentation-based standard plane detection is tested on a 50-image standard dataset. The experiments show that our method can help healthcare workers decrease their error rate from 6%-10% to 2%. In addition, the segmentation performance in another ultrasound dataset (fetal heart) demonstrates the ability of our network.

Automatic segmentation of the clinical target volume and organs at risk for rectal cancer radiotherapy using structure-contextual representations based on 3D high-resolution network

Radiotherapy is a cancer treatment that uses high doses of radiation to kill cancer cells. Segmentation of the clinical target volumes (CTVs) and organs at risk (OARs) is an essential step in rectal cancer radiotherapy treatment planning. However, the manual segmentation of CTVs and OARs is labor-intensive and prone to intra- and inter-rater variations. The challenge of this task lies in large shape variations and low-contrast structure boundary for some structures like intestine. The contextual information is very important to handle this challenge. Recently, deep learning has greatly improved the state-of-the-art results in automatic segmentation of anatomical structures including OARs and CTVs. However, existing approaches barely take advantages of relations among anatomical structures as contextual information, which limits the segmentation accuracy. In this study, we propose a novel structure-contextual representations approach based on 3D high-resolution network (3D HRNet-SCR) for segmentation of OARs and CTV of rectal cancer. First, we design a structure-contextual representation module (SCR) which could compute the representation for each structure of interest by aggregating the representations of voxels inside the structure and enhance the feature representation of each voxel with learned structure-contextual representations. Second, we extend the powerful 2D HRNet for semantic segmentation to 3D paradigm to better capture the contextual information across slices of volumetric data. Our propose approach integrates the proposed SCR module on top of the 3D HRNet to form a high-performance segmentation framework. Finally, we collect a large-scale rectal cancer dataset of 536 CT scans (total 64320 slices) for evaluation. Our proposed framework is extensively tested on this self-collected dataset, showing superiority compared with state-of-the-art OARs and CTV segmentation methods for rectal cancer treatment.

Automatic segmentation of foveal avascular zone based on adaptive watershed algorithm in retinal optical coherence tomography angiography images

The size and shape of the foveal avascular zone (FAZ) have a strong positive correlation with several vision-threatening retinovascular diseases. The identification, segmentation and analysis of FAZ are of great significance to clinical diagnosis and treatment. We presented an adaptive watershed algorithm to automatically extract FAZ from retinal optical coherence tomography angiography (OCTA) images. For the traditional watershed algorithm, “over-segmentation” is the most common problem. FAZ is often incorrectly divided into multiple regions by redundant “dams”. This paper analyzed the relationship between the “dams” length and the maximum inscribed circle radius of FAZ, and proposed an adaptive watershed algorithm to solve the problem of “over-segmentation”. Here, 132 healthy retinal images and 50 diabetic retinopathy (DR) images were used to verify the accuracy and stability of the algorithm. Three ophthalmologists were invited to make quantitative and qualitative evaluations on the segmentation results of this algorithm. The quantitative evaluation results show that the correlation coefficients between the automatic and manual segmentation results are 0.945 (in healthy subjects) and 0.927 (in DR patients), respectively. For qualitative evaluation, the percentages of “perfect segmentation” (score of 3) and “good segmentation” (score of 2) are 99.4% (in healthy subjects) and 98.7% (in DR patients), respectively. This work promotes the application of watershed algorithm in FAZ segmentation, making it a useful tool for analyzing and diagnosing eye diseases.