Segmentation Information Research Articles

Digital Information Service to Combat Violence against Women: The Comunica Mulher Project

ABSTRACTThe present study discusses the methods and outcomes of a project conducted at the University of Brasília with the aim of providing information services to the community of the Federal District (Brazil) on COVID‐19 prevention and vaccination, as well as addressing domestic violence. Employing social marketing strategies, such as content marketing and viral marketing, the project sought to disseminate pertinent information and engage the target audience through social media platforms, primarily Instagram. The content marketing approach entailed the creation and distribution of reliable information utilizing authoritative sources and visual resources, such as illustrations, graphs, infographics, and diagrams. Simultaneously, the viral marketing strategy endeavoured to identify emerging subtopics of interest by leveraging the Google Trends tool and relevant commemorative dates. These integrated strategies yielded a remarkable 700% surge in the project's Instagram account reach alongside heightened audience engagement. The study concludes that community information services should prioritize the dissemination of contextually relevant information for various population segments, particularly those that are historically marginalized.

A Cascaded Deep Learning-Based Cardiac Substructures Segmentation Frame and on Non-Gated Non-Enhanced Planning CT Scans in Breast Cancer Patients

To develop a deep learning-based segmentation frame for cardiac substructures especially coronary arteries (CAs) on non-gated non-enhanced planning computed tomography (CT) scans in breast cancer (BC) patients. Non-gated non-enhanced CT scans of 39 BC patients receiving adjuvant radiotherapy (RT) were collected. Cardiac substructures were manually labelled, including four chambers, left main (LM), left anterior descending (LAD), left circumflex (LCX) and right coronary artery (RCA). The training, validation, and test sample is 28, 7 and 4, respectively. A cascaded network, using nnUNet as the backbone, is proposed to use chambers as prior information to constrain the segmentation of CAs. The mean Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95) and average symmetrical surface distance (ASSD) were used as geometric metrics. Dosimetric parameters of cardiac substructures was calculated based on the segmentation frame and manually labeled contouring, respectively. The data of cardiac examination including ultrasonography, electrocardiogram before and during the follow-up after RT were retrospectively collected. The cardiac event was any symptomatic heart disease or new-onset abnormality in the cardiac examination after RT. The mean DSC of heart, atriums and ventricles of the proposed frame was 0.93, 0.90, and 0.93, respectively. As shown in Table 1, compared with direct segmentation (as baseline), the proposed frame had a better performance in terms of HD95, ASSD, and the mean dose (Dmean) absolute error for all CAs. Compared to the dosimetric parameters of the heart collected based on the manual labelled contours, the relative errors of D5, D95, and V15Gy for LAD was 4.3±7.8%, 11.7±5.9%, and 14.6±13.0% collected based on the direct segmentation contours and 2.4±4.4%, 3.9±3.1%, 8.5±6.9% collected based on the auto-segmented contours, respectively. Multivariate analysis showed that increased V15Gy of LAD was an independent cardiac toxicity risk factor ([HR] = 1.07, 95% CI 1-1.15, p = 0.0387). We developed a cascaded network for cardiac substructures segmentation with dosimetric validation on non-enhanced CT scans in breast cancer radiotherapy. This is the first attempt to use chambers as prior information for CAs' segmentation and had a superior stable performance. Accurate segmentation will help radiation oncologists to better evaluate DVHs based on substructures and thus to estimate cardiovascular risk. An optimized cardiac substructure-based dosimetric constrain may be proposed accordingly.

GTV Based Automatic Delineation of Clinical Target Volume for Cervical Cancer

The delineation of gross tumor volume (GTV) and clinical target volume (CTV) are two critical steps in the radiotherapy planning for cervical cancer. GTV defines the primary treatment region for the gross tumor, while CTV is the area surrounding GTV that includes a certain probability (5% to 10%) of subclinical lesions. In contrast to GTV, CTV delineation relies on predefined and judgment-based boundaries, and the high variability among users makes this task particularly challenging. In this study, we evaluated the potential relationship between GTV and CTV and developed an automatic CTV delineation algorithm for cervical cancer based on the fusion of GTV information. We introduced position and shape constraints of GTV to improve the accuracy of CTV delineation. The GTV-Net deep learning method was used to segment the CTV images of cervical cancer. The method aimed to use the delineation results of the GTV region for one-hot coding and add human anatomy experience in the clinical field to guide the CTV segmentation. This retrospective study included 545 cervical cancer patients who received radiation therapy from June 2017 to May 2019, including postoperative and radical treatment groups. The CTV and GTV regions were manually delineated by human experts. Numerous experiments were conducted to evaluate the performance of the network. First, compared with different network architectures, the Dice similarity coefficient (DSC) and 95% Hausdorff distance (95HD) of GTV-Net were both improved. Then, we compared the GTV-Net method with two resident physicians. Our GTV-Net method outperformed both resident physicians. In the postoperative group, our method improved the DSC by 4% compared to 3D-UNet, reaching 76.55%, and increased by about 2.57% compared to V-Net's 73.98%, with an improvement of approximately 1.23% compared to the two resident physicians. In the radical treatment group, compared to 3D-UNet's 78.76%, our method increased the DSC by about 3.25%, reaching 82%, and increased by approximately 2.08% compared to V-Net's 79.92%, with an improvement of about 1.35% compared to the two resident physicians. Compared with 3D-UNet, the average 95HD in the postoperative group decreased from 1.489 to 1.457, and in the radical treatment group, it decreased from 1.454 to 1.433. The results of 95HD also showed some improvement compared to V-Net. This study is the first to introduce GTV information for automatic segmentation of the clinical target area for cervical cancer. In this experiment, we observed a positive gain in CTV target automatic delineation guided by GTV information compared to solely performing CTV segmentation, with an improvement in Dice similarity of more than 4% and Hausdorff distance of more than 6% in the experimental dataset. In addition, GTV-guided CTV automatic delineation has also shown promising results on multicenter data, which will better serve the clinical field.

An Object Detection Method Using Probability Maps for Instance Segmentation to Mask Background

This paper proposes a two-step detector called segmented object detection, whose performance is improved by masking the background region. Previous single-stage object detection methods suffer from the problem of imbalance between foreground and background classes, where the background occupies more regions in the image than the foreground. Thus, the loss from the background is firmly incorporated into the training. RetinaNet addresses this problem with Focal Loss, which focuses on foreground loss. Therefore, we propose a method that generates probability maps using instance segmentation in the first step and feeds back the generated maps as background masks in the second step as prior knowledge to reduce the influence of the background and enhance foreground training. We confirm that the detector can improve the accuracy by adding instance segmentation information to both the input and output rather than only to the output results. On the Cityscapes dataset, our method outperforms the state-of-the-art methods.

Processing of noun plural marking in German-speaking children: an eye-tracking study.

The ability to process plural marking of nouns is acquired early: at a very young age, children are able to understand if a noun represents one item or more than one. However, little is known about how the segmental characteristics of plural marking are used in this process. Using eye-tracking, we aim at understanding how five to twelve-year old children use the phonetic, phonological, and morphological information available to process noun plural marking in German (i.e., a very complex system) compared to adults. We expected differences with stem vowels, stem-final consonants or different suffixes, alone or in combination, reflecting different processing of their segmental information. Our results show that for plural processing: 1) a suffix is the most helpful cue, an umlaut the least helpful, and voicing does not play a role; 2) one cue can be sufficient and 3) school-age children have not reached adult-like processing of plural marking.

Leveraging global binary masks for structure segmentation in medical images

Deep learning (DL) models for medical image segmentation are highly influenced by intensity variations of input images and lack generalization due to primarily utilizing pixels’ intensity information for inference. Acquiring sufficient training data is another challenge limiting models’ applications. Here, we proposed to leverage the consistency of organs’ anatomical position and shape information in medical images. We introduced a framework leveraging recurring anatomical patterns through global binary masks for organ segmentation. Two scenarios were studied: (1) global binary masks were the only input for the U-Net based model, forcing exclusively encoding organs’ position and shape information for rough segmentation or localization. (2) Global binary masks were incorporated as an additional channel providing position/shape clues to mitigate training data scarcity. Two datasets of the brain and heart computed tomography (CT) images with their ground-truth were split into (26:10:10) and (12:3:5) for training, validation, and test respectively. The two scenarios were evaluated using full training split as well as reduced subsets of training data. In scenario (1), training exclusively on global binary masks led to Dice scores of 0.77 ± 0.06 and 0.85 ± 0.04 for the brain and heart structures respectively. Average Euclidian distance of 3.12 ± 1.43 mm and 2.5 ± 0.93 mm were obtained relative to the center of mass of the ground truth for the brain and heart structures respectively. The outcomes indicated encoding a surprising degree of position and shape information through global binary masks. In scenario (2), incorporating global binary masks led to significantly higher accuracy relative to the model trained on only CT images in small subsets of training data; the performance improved by 4.3%–125.3% and 1.3%–48.1% for 1–8 training cases of the brain and heart datasets respectively. The findings imply the advantages of utilizing global binary masks for building models that are robust to image intensity variations as well as an effective approach to boost performance when access to labeled training data is highly limited.

LCW-Net: Low-light-image-based crop and weed segmentation network using attention module in two decoders

Crop segmentation using cameras is commonly used in large agricultural areas, but the time and duration of crop harvesting varies in large farms. Considering this situation, there is a need for low-light image-based segmentation of crop and weed images for late-time harvesting, but no prior research has considered this. As a first study on this topic, we propose a low-light image-based crop and weed segmentation network (LCW-Net) that uses an attention module in two decoders to perform only one step without restoration of low-light images. We also design a loss function to accurately segment regions of objects, crops, and weeds in low-light images to avoid training overfitting and balance the learning task for object, crop, and weed segmentation.There are no existing low-light public databases, and it is difficult to obtain ground truth segmentation information for self-collected database in low-light environments. Therefore, we experimented with converting two public databases, the crop and weed field image dataset (CWFID) and BoniRob dataset, into low-light datasets. The experimental results showed that the mean intersection of unions (mIoUs) of segmentation for crops and weeds were 0.8718 and 0.8693 for the BoniRob dataset, respectively, and 0.8337 and 0.8221 for the CWFID dataset, respectively, indicating that LCW-Net outperforms the state-of-the-art methods.

Hierarchical Edge-Preserving Dense Matching by Exploiting Reliably Matched Line Segments

Image dense matching plays a crucial role in the reconstruction of three-dimensional models of buildings. However, large variations in target heights and serious occlusion lead to obvious mismatches in areas with discontinuous depths, such as building edges. To solve this problem, the present study mines the geometric and semantic information of line segments to produce a constraint for the dense matching process. First, a disparity consistency-based line segment matching method is proposed. This method correctly matches line segments on building structures in discontinuous areas based on the assumption that, within the corresponding local areas formed by two corresponding line pairs, the disparity obtained by the coarse-level matching of the hierarchical dense matching is similar to that derived from the local homography estimated from the corresponding line pairs. Second, an adaptive guide parameter is designed to constrain the cost propagation between pixels in the neighborhood of line segments. This improves the rationality of cost aggregation paths in discontinuous areas, thereby enhancing the matching accuracy near building edges. Experimental results using satellite and aerial images show that the proposed method efficiently obtains reliable line segment matches at building edges with a matching precision exceeding 97%. Under the constraint of the matched line segments, the proposed dense matching method generates building edges that are visually clearer, and achieves higher accuracy around edges, than without the line segment constraint.

ETU-Net: efficient Transformer and convolutional U-style connected attention segmentation network applied to endoscopic image of epistaxis.

Epistaxis is a typical presentation in the otolaryngology and emergency department. When compressive therapy fails, directive nasal cautery is necessary, which strongly recommended operating under the nasal endoscope if it is possible. Limited by the operator's clinical experience, complications such as recurrence, nasal ulcer, and septum perforation may occur due to insufficient or excessive cautery. At present, deep learning technology is widely used in the medical field because of its accurate and efficient recognition ability, but it is still blank in the research of epistaxis. In this work, we first gathered and retrieved the Nasal Bleeding dataset, which was annotated and confirmed by many clinical specialists, filling a void in this sector. Second, we created ETU-Net, a deep learning model that smartly integrated the excellent performance of attention convolution with Transformer, overcoming the traditional model's difficulties in capturing contextual feature information and insufficient sequence modeling skills in picture segmentation. On the Nasal Bleeding dataset, our proposed model outperforms all others models that we tested. The segmentation recognition index, Intersection over Union, and F1-Score were 94.57 and 97.15%. Ultimately, we summarized effective ways of combining artificial intelligence with medical treatment and tested it on multiple general datasets to prove its feasibility. The results show that our method has good domain adaptability and has a cutting-edge reference for future medical technology development.

SaTransformer: Semantic‐aware transformer for breast cancer classification and segmentation

AbstractBreast cancer classification and segmentation play an important role in identifying and detecting benign and malignant breast lesions. However, segmentation and classification still face many challenges: 1) The characteristics of cancer itself, such as fuzzy edges, complex backgrounds, and significant changes in size, shape, and intensity distribution make accurate segment and classification challenges. 2) Existing methods ignore the potential relationship between classification and segmentation tasks, due to the classification and segmentation being treated as two separate tasks. To overcome these challenges, in this paper, a novel Semantic‐aware transformer (SaTransformer) for breast cancer classification and segmentation is proposed. Specifically, the SaTransformer enables doing the two takes simultaneously through one unified framework. Unlike existing well‐known methods, the segmentation and classification information are semantically interactive, reinforcing each other during feature representation learning and improving the ability of feature representation learning while consuming less memory and computational complexity. The SaTransformer is validated on two publicly available breast cancer datasets – BUSI and UDIAT. Experimental results and quantitative evaluations (accuracy: 97.97%, precision: 98.20%, DSC: 86.34%) demonstrate that the SaTransformer outperforms other state‐of‐the‐art methods.

Local labor market and the cross section of stock returns

Local labor market pooling is a crucial benefit in the economics of agglomeration (Marshall, 1890). To capture the pooling function, we employ segment information and occupation statistics to capture average pairwise labor force similarities for each focal firm. We find that firms in thicker local labor markets are underpriced and display significantly positive stock returns afterwards. The return predictability of local labor market measure is concentrated in non-mega cap firms; high-tech firms; younger firms; and firms with more high-skilled labor, less routine tasks, and lower labor intensity. Our results are robust to a battery of control variables and alternative measure specifications.

Does musicianship influence the perceptual integrality of tones and segmental information?

This study investigated the effect of musicianship on the perceptual integrality of tones and segmental information in non-native speech perception. We tested 112 Cantonese musicians, Cantonese non-musicians, English musicians, and English non-musicians with a modified Thai tone AX discrimination task. In the tone discrimination task, the control block only contained tonal variations, whereas the orthogonal block contained both tonal and task-irrelevant segmental variations. Relative to their own performance in the control block, the Cantonese listeners showed decreased sensitivity index (d') and increased response time in the orthogonal block, reflecting integral perception of tones and segmental information. By contrast, the English listeners performed similarly across the two blocks, indicating independent perception. Bayesian analysis revealed that the Cantonese musicians and the Cantonese non-musicians perceived Thai tones and segmental information equally integrally. Moreover, the English musicians and the English non-musicians showed similar degrees of independent perception. Based on the above results, musicianship does not seem to influence tone-segmental perceptual integrality. While musicianship apparently enhances tone sensitivity, not all musical advantages are transferrable to the language domain.

A Multi-Phase Camera-LiDAR Fusion Network for 3D Semantic Segmentation With Weak Supervision

Camera and LiDAR are indispensable perception units in autonomous driving, providing complementary environmental information for 3D semantic segmentation. It is the key point that fuses the information of two modalities to accurate and robust semantic segmentation. However, three major factors will restrict the performance of fusion-based methods, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> ., the reliability of image features, the contribution of different image features, and the trade-off between results of image and point cloud. This paper proposes a novel multi-phase fusion network for 3D semantic segmentation. For the first factor, this paper takes the lead in regarding the problem that image features may be wrong due to the lack of dense annotations in the common datasets as a weak supervision problem and introduces the weakly supervised loss. Second, the proposed attention based feature fusion module can filter and reweight the image features effectively. Third, the results of the two modalities are further fused by self-confidence based late fusion module at pixel-level to complement their advantages. The proposed scheme has been evaluated on nuScenes and SemanticKITTI benchmarks, and the results show the competitiveness with state-of-the-art methods. The ablation studies demonstrate the superiority of the method in sparse classes segmentation. In addition, this paper also evaluates the robustness, and the results of the proposed method can keep relatively accurate even when faults in one of the sensors.

A Study of Chan-Vese Model with the Introduction of Edge Information

In image segmentation, the image edge information and the selection of edge-stopping function have a extremely important influence on the segmentation effect. As a classical geometric active contour model, Chan-Vese model completely utilizes image global information for segmentation, which has the problems of inability to handle grayscale uneven images and slow curve evolution. This paper introduces edge information into the Chan-Vese model, chooses a new edge stopping function and simplifies the driving force term to build a new image segmentation model. The new model can detect the target fast, displaying better detection effect on the targets of images with uneven grayscale and the detection effect of the target in the uneven gray image is better

A Method for Obtaining 3D Point Cloud Data by Combining 2D Image Segmentation and Depth Information of Pigs.

This paper proposes a method for automatic pig detection and segmentation using RGB-D data for precision livestock farming. The proposed method combines the enhanced YOLOv5s model with the Res2Net bottleneck structure, resulting in improved fine-grained feature extraction and ultimately enhancing the precision of pig detection and segmentation in 2D images. Additionally, the method facilitates the acquisition of 3D point cloud data of pigs in a simpler and more efficient way by using the pig mask obtained in 2D detection and segmentation and combining it with depth information. To evaluate the effectiveness of the proposed method, two datasets were constructed. The first dataset consists of 5400 images captured in various pig pens under diverse lighting conditions, while the second dataset was obtained from the UK. The experimental results demonstrated that the improved YOLOv5s_Res2Net achieved a mAP@0.5:0.95 of 89.6% and 84.8% for both pig detection and segmentation tasks on our dataset, while achieving a mAP@0.5:0.95 of 93.4% and 89.4% on the Edinburgh pig behaviour dataset. This approach provides valuable insights for improving pig management, conducting welfare assessments, and estimating weight accurately.

Haar wavelet downsampling: A simple but effective downsampling module for semantic segmentation

Downsampling operations such as max pooling or strided convolution are ubiquitously utilized in Convolutional Neural Networks (CNNs) to aggregate local features, enlarge receptive field, and minimize computational overhead. However, for a semantic segmentation task, pooling features over the local neighbourhood may result in the loss of important spatial information, which is conducive for pixel-wise predictions. To address this issue, we introduce a simple yet effective pooling operation called the Haar Wavelet-based Downsampling (HWD) module. This module can be easily integrated into CNNs to enhance the performance of semantic segmentation models. The core idea of HWD is to apply Haar wavelet transform for reducing the spatial resolution of feature maps while preserving as much information as possible. Furthermore, to investigate the benefits of HWD, we propose a novel metric, named as feature entropy index (FEI), which measures the degree of information uncertainty after downsampling in CNNs. Specifically, the FEI can be used to indicate the ability of downsampling methods to preserve essential information in semantic segmentation. Our comprehensive experiments demonstrate that the proposed HWD module could (1) effectively improve the segmentation performance across different modality image datasets with various CNN architectures, and (2) efficiently reduce information uncertainty compared to the conventional downsampling methods. Our implementation are available at https://github.com/apple1986/HWD.

A method of motion estimation of segmental ventricular wall with tracking of ultrasonic echocardiogram

BackgroundUltrasonic echocardiography is commonly used for monitoring myocardial dysfunction. However, it has limitations such as poor quality of echocardiography images and subjective judgment of doctors.MethodsIn this paper, a calculation model based on optical flow tracking of echocardiogram is proposed for the quantitative estimation motion of the segmental wall. To improve the accuracy of optical flow estimation, a method based on confidence-optimized multiresolution(COM) optical flow model is proposed to reduce the estimation errors caused by the large amplitude of myocardial motion and the presence of “shadows” and other image quality problems. In addition, motion vector decomposition and dynamic tracking of the ventricular region of interest are used to extract information regarding the myocardial segmental motion. The proposed method was validated using simulation images and 50 clinical cases (25 patients and 25 healthy volunteers) for myocardial motion analysis.ResultsThe results demonstrated that the proposed method could track the motion information of myocardial segments well and reduce the estimation errors of optical flow caused due to the use of low-quality echocardiogram images.ConclusionsThe proposed method improves the accuracy of motion estimation for the cardiac ventricular wall.

Joint learning-based feature reconstruction and enhanced network for incomplete multi-modal brain tumor segmentation

Multimodal Magnetic Resonance Imaging (MRI) can provide valuable complementary information and substantially enhance the performance of brain tumor segmentation. However, it is common for certain modalities to be absent or missing during clinical diagnosis, which can significantly impair segmentation techniques that rely on complete modalities. Current advanced methods attempt to address this challenge by developing shared feature representations via modal fusion to handle different missing modality situations. Considering the importance of missing modality information in multimodal segmentation, this paper utilize a feature reconstruction method to recover the missing information, and proposes a joint learning-based feature reconstruction and enhancement method for incomplete modality brain tumor segmentation. The method leverages an information learning mechanism to transfer information from the complete modality to a single modality, enabling it to obtain complete brain tumor information, even without the support of other modalities. Additionally, the method incorporates a module for reconstructing missing modality features, which recovers fused features of the absent modality through utilizing the abundant potential information obtained from the available modalities. Furthermore, the feature enhancement mechanism improves shared feature representation by utilizing the information obtained from the missing modalities that have been reconstructed. These processes enable the method to obtain more comprehensive information regarding brain tumors in various missing modality circumstances, thereby enhancing the model’s robustness. The performance of the proposed model was evaluated on BraTS datasets and compared with other deep learning algorithms using Dice similarity scores. On the BraTS2018 dataset, the proposed algorithm achieved a Dice similarity score of 86.28%, 77.02%, and 59.64% for whole tumors, tumor cores, and enhanced tumors, respectively. These results demonstrate the superiority of our framework over state-of-the-art methods in missing modalities situations.

Neural temporal context reinstatement of event structure during memory recall.

The transformation of experiences into meaningful events and memories is intertwined with the notion of time. Temporal perception can influence, and be influenced by, segmenting continuous experience into meaningful events. Episodic memories formed from these events become associated with temporal information as well. However, it is less clear how temporal perception contributes to structuring events and organizing memory: whether it plays a more active or passive role, and whether this temporal information is encoded initially during perception or influenced by retrieval processes. To address these questions, we examined how event segmentation influences temporal representations during initial perception and memory retrieval, without testing temporal information explicitly. Using a neural measure of temporal context extracted from scalp electroencephalography in human participants (N = 170), we found reduced temporal context similarity between studied items separated by an event boundary when compared to items from the same event. Furthermore, while participants freely recalled list items, neural activity reflected reinstatement of temporal context representations from the study phase, including temporal disruption. A computational model of episodic memory, the context maintenance and retrieval (CMR) model, predicted these results, and made novel predictions regarding the influence of temporal disruption on recall order. These findings implicate the impact of event structure on memory organization via temporal representations, underscoring the role of temporal information in event segmentation and episodic memory. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Brain Tumor Segmentation for Multi-Modal MRI with Missing Information.

Deep convolutional neural networks (DCNNs) have shown promise in brain tumor segmentation from multi-modal MRI sequences, accommodating heterogeneity in tumor shape and appearance. The fusion of multiple MRI sequences allows networks to explore complementary tumor information for segmentation. However, developing a network that maintains clinical relevance in situations where certain MRI sequence(s) might be unavailable or unusual poses a significant challenge. While one solution is to train multiple models with different MRI sequence combinations, it is impractical to train every model from all possible sequence combinations. In this paper, we propose a DCNN-based brain tumor segmentation framework incorporating a novel sequence dropout technique in which networks are trained to be robust to missing MRI sequences while employing all other available sequences. Experiments were performed on the RSNA-ASNR-MICCAI BraTS 2021 Challenge dataset. When all MRI sequences were available, there were no significant differences in performance of the model with and without dropout for enhanced tumor (ET), tumor (TC), and whole tumor (WT) (p-values 1.000, 1.000, 0.799, respectively), demonstrating that the addition of dropout improves robustness without hindering overall performance. When key sequences were unavailable, the network with sequence dropout performed significantly better. For example, when tested on only T1, T2, and FLAIR sequences together, DSC for ET, TC, and WT increased from 0.143 to 0.486, 0.431 to 0.680, and 0.854 to 0.901, respectively. Sequence dropout represents a relatively simple yet effective approach for brain tumor segmentation with missing MRI sequences.