Feature Segmentation Research Articles

Sleep apnea detection from single-lead electrocardiogram signals using effective deep-shallow fusion network

Objective. Explore a network architecture that can efficiently perform single-lead electrocardiogram (ECG) sleep apnea (SA) detection by utilizing the beneficial information of extended ECG segments and reducing the impact of their noisy information. Approach. We propose an effective deep-shallow fusion network (EDSFnet). The deeper residual network is used to extract high-level features with stronger semantics and less noise from the original ECG segments. The shallower convolutional neural network is used to extract lower-level features with higher resolution containing more detailed neighborhood information from the extended ECG segments. These two types of features are then fused using Effective Channel Attention, implementing automatic weight assignment to take advantage of their complementary nature. Main results. The performance of EDSFnet is evaluated on the Apnea-ECG dataset and the FAH-ECG dataset. In the Apnea-ECG dataset with 35 subjects as the training set and 35 subjects as the test set, the accuracy of EDSFnet was 92.6% and 100% for per-segment and per-recording test, respectively. In the FAH-ECG dataset with 348 subjects as the training set and 88 subjects as the test set, the accuracy of EDSFnet was 89.0% and 93.2% for per-segment and per-recording test, respectively. EDSFnet has achieved state-of-the-art results in both experiments using the publicly available Apnea-ECG dataset and subject-independent experiments using the FAH-ECG clinical dataset. Significance. The success of EDSFnet in handling SA detection underlines its robustness and adaptability. By achieving superior results across different datasets, EDSFnet offers promise in advancing the cost-effective and efficient detection of SA through single-lead ECG, reducing the burden on patients and healthcare systems alike.

Automatic feature segmentation in dental panoramic radiographs.

The purpose of the present study was to verify the diagnostic performance of an AI system for the automatic detection of teeth, caries, implants, restorations, and fixed prosthesis on panoramic radiography. This is a cross-sectional study. A dataset comprising 1000 panoramic radiographs collected from 500 adult patients was analyzed by an AI system and compared with annotations provided by two oral and maxillofacial radiologists. A strong correlation (R > 0.5) was observed between AI perception and observers 1 and 2 in carious teeth (0.691-0.878), implants (0.770-0.952), restored teeth (0.773-0.834), teeth with fixed prostheses (0.972-0.980), and missing teeth (0.956-0.988). Panoramic radiographs are commonly used for diagnosis and treatment planning. However, they often suffer from artifacts, distortions, and superimpositions, leading to potential misinterpretations. Thus, an automated detection system is required to tackle these challenges. Artificial intelligence (AI) has revolutionized various fields, including dentistry, by enabling the development of intelligent systems that can assist in complex tasks such as diagnosis and treatment planning. The automatic detection by the AI system was comparable to oral radiologists and may be useful for automatic identifications in panoramic radiographs. These findings signify the potential for AI systems to enhance diagnostic accuracy and efficiency in dental practices, potentially reducing the likelihood of diagnostic errors caused by unexperienced professionals.

Swin-Net: A Swin-Transformer-Based Network Combing with Multi-Scale Features for Segmentation of Breast Tumor Ultrasound Images

Breast cancer is one of the most common cancers in the world, especially among women. Breast tumor segmentation is a key step in the identification and localization of the breast tumor region, which has important clinical significance. Inspired by the swin-transformer model with powerful global modeling ability, we propose a semantic segmentation framework named Swin-Net for breast ultrasound images, which combines Transformer and Convolutional Neural Networks (CNNs) to effectively improve the accuracy of breast ultrasound segmentation. Firstly, our model utilizes a swin-transformer encoder with stronger learning ability, which can extract features of images more precisely. In addition, two new modules are introduced in our method, including the feature refinement and enhancement module (RLM) and the hierarchical multi-scale feature fusion module (HFM), given that the influence of ultrasonic image acquisition methods and the characteristics of tumor lesions is difficult to capture. Among them, the RLM module is used to further refine and enhance the feature map learned by the transformer encoder. The HFM module is used to process multi-scale high-level semantic features and low-level details, so as to achieve effective cross-layer feature fusion, suppress noise, and improve model segmentation performance. Experimental results show that Swin-Net performs significantly better than the most advanced methods on the two public benchmark datasets. In particular, it achieves an absolute improvement of 1.4–1.8% on Dice. Additionally, we provide a new dataset of breast ultrasound images on which we test the effect of our model, further demonstrating the validity of our method. In summary, the proposed Swin-Net framework makes significant advancements in breast ultrasound image segmentation, providing valuable exploration for research and applications in this domain.

Location and segmentation of important railway signs based on improved segmentation

Purpose With the rapid development of railway-intelligent video technology, scene understanding is becoming more and more important. Semantic segmentation is a major part of scene understanding. There is an urgent need for an algorithm with high accuracy and real-time to meet the current railway requirements for railway identification. In response to this demand, this paper aims to explore a variety of models, accurately locate and segment important railway signs based on the improved SegNeXt algorithm, supplement the railway safety protection system and improve the intelligent level of railway safety protection. Design/methodology/approach This paper studies the performance of existing models on RailSem19 and explores the defects of each model through performance so as to further explore an algorithm model dedicated to railway semantic segmentation. In this paper, the authors explore the optimal solution of SegNeXt model for railway scenes and achieve the purpose of this paper by improving the encoder and decoder structure. Findings This paper proposes an improved SegNeXt algorithm: first, it explores the performance of various models on railways, studies the problems of semantic segmentation on railways and then analyzes the specific problems. On the basis of retaining the original excellent MSCAN encoder of SegNeXt, multiscale information fusion is used to further extract detailed features such as multihead attention and mask, solving the problem of inaccurate segmentation of current objects by the original SegNeXt algorithm. The improved algorithm is of great significance for the segmentation and recognition of railway signs. Research limitations/implications The model constructed in this paper has advantages in the feature segmentation of distant small objects, but it still has the problem of segmentation fracture for the railway, which is not completely segmented. In addition, in the throat area, due to the complexity of the railway, the segmentation results are not accurate. Social implications The identification and segmentation of railway signs based on the improved SegNeXt algorithm in this paper is of great significance for the understanding of existing railway scenes, which can greatly improve the classification and recognition ability of railway small object features and can greatly improve the degree of railway security. Originality/value This article introduces an enhanced version of the SegNeXt algorithm, which aims to improve the accuracy of semantic segmentation on railways. The study begins by investigating the performance of different models in railway scenarios and identifying the challenges associated with semantic segmentation on this particular domain. To address these challenges, the proposed approach builds upon the strong foundation of the original SegNeXt algorithm, leveraging techniques such as multi-scale information fusion, multi-head attention, and masking to extract finer details and enhance feature representation. By doing so, the improved algorithm effectively resolves the issue of inaccurate object segmentation encountered in the original SegNeXt algorithm. This advancement holds significant importance for the accurate recognition and segmentation of railway signage.

Automatic evaluation method for vehicle audio warning system using MFCC-polynomial hybrid feature

In the evaluation of vehicle audio warning system, there is no automatic method. Besides, due to the noise interference of in-vehicle environmental, the quantity limitation and only positive training samples, the accuracy of traditional template matching or identification methods for audio is low. To solve the above problems, an efficient, accurate, and automatic evaluation method is proposed for vehicle audio warning system. Firstly, logmmse-spectrum subtraction method is used to filter the dynamic noise and static noise of the evaluation audio acquired in the in-vehicle environment. Secondly, the end point detection based on short-time energy is used to obtain the effective audio segment after noise reduction, and the start time of the audio warning segment can be accurately obtained. Then, the Mel Frequency Cepstrum Coefficient (MFCC) feature and the polynomial fitting feature of each audio segment are extracted. The hybrid features are treated as the input of the Hidden Markov Model-Gaussian Mixture Model (GMM-HMM) based audio matching model. Finally, according to frame shift set by endpoint detection and the audio sampling frequency, the emitted time of matched audio warning can be calculated to support the evaluation of vehicle audio warning system. The experimental result shows that, with dynamic-static noise reduction and MFCC-polynomial hybrid feature, the average matching accuracy of the proposed method reaches 99.6% in the case of only five training samples.

An automated deep learning pipeline for EMVI classification and response prediction of rectal cancer using baseline MRI: a multi-centre study

ABSTRACTThe classification of extramural vascular invasion status using baseline magnetic resonance imaging in rectal cancer has gained significant attention as it is an important prognostic marker. Also, the accurate prediction of patients achieving complete response with primary staging MRI assists clinicians in determining subsequent treatment plans. Most studies utilised radiomics-based methods, requiring manually annotated segmentation and handcrafted features, which tend to generalise poorly. We retrospectively collected 509 patients from 9 centres, and proposed a fully automated pipeline for EMVI status classification and CR prediction with diffusion weighted imaging and T2-weighted imaging. We applied nnUNet, a self-configuring deep learning model, for tumour segmentation and employed learned multiple-level image features to train classification models, named MLNet. This ensures a more comprehensive representation of the tumour features, in terms of both fine-grained detail and global context. On external validation, MLNet, yielding similar AUCs as internal validation, outperformed 3D ResNet10, a deep neural network with ten layers designed for analysing spatiotemporal data, in both CR and EMVI tasks. For CR prediction, MLNet showed better results than the current state-of-the-art model using imaging and clinical features in the same external cohort. Our study demonstrated that incorporating multi-level image representations learned by a deep learning based tumour segmentation model on primary MRI improves the results of EMVI classification and CR prediction with good generalisation to external data. We observed variations in the contributions of individual feature maps to different classification tasks. This pipeline has the potential to be applied in clinical settings, particularly for EMVI classification.

Interpretable feature extraction and dimensionality reduction in ESM2 for protein localization prediction.

As the application of large language models (LLMs) has broadened into the realm of biological predictions, leveraging their capacity for self-supervised learning to create feature representations of amino acid sequences, these models have set a new benchmark in tackling downstream challenges, such as subcellular localization. However, previous studies have primarily focused on either the structural design of models or differing strategies for fine-tuning, largely overlooking investigations into the nature of the features derived from LLMs. In this research, we propose different ESM2 representation extraction strategies, considering both the character type and position within the ESM2 input sequence. Using model dimensionality reduction, predictive analysis and interpretability techniques, we have illuminated potential associations between diverse feature types and specific subcellular localizations. Particularly, the prediction of Mitochondrion and Golgi apparatus prefer segments feature closer to the N-terminal, and phosphorylation site-based features could mirror phosphorylation properties. We also evaluate the prediction performance and interpretability robustness of Random Forest and Deep Neural Networks with varied feature inputs. This work offers novel insights into maximizing LLMs' utility, understanding their mechanisms, and extracting biological domain knowledge. Furthermore, we have made the code, feature extraction API, and all relevant materials available at https://github.com/yujuan-zhang/feature-representation-for-LLMs.

When zero-padding position encoding encounters linear space reduction attention: an efficient semantic segmentation Transformer of remote sensing images

ABSTRACT Semantic segmentation of remote sensing images (RSIs) is of great significance for obtaining geospatial object information. Transformers win promising effect, whereas multi-head self-attention (MSA) is expensive. We propose an efficient semantic segmentation Transformer (ESST) of RSIs that combines zero-padding position encoding with linear space reduction attention (LSRA). First, to capture the coarse-to-fine features of RSI, a zero-padding position encoding is proposed by adding overlapping patch embedding (OPE) layers and convolution feed-forward networks (CFFN) to improve the local continuity of features. Then, we replace LSRA in the attention operation to extract multi-level features to reduce the computational cost of the encoder. Finally, we design a lightweight all multi-layer perceptron (all-MLP) head decoder to easily aggregate multi-level features to generate multi-scale features for semantic segmentation. Experimental results demonstrate that our method produces a trade-off in accuracy and speed for semantic segmentation of RSIs on the Potsdam and Vaihingen datasets, respectively.

Radiomics-Based Machine Learning Classification Strategy for Characterization of Hepatocellular Carcinoma on Contrast-Enhanced Ultrasound in High-Risk Patients with LI-RADS Category M Nodules.

Objective Accurate differentiation within the LI-RADS category M (LR-M) between hepatocellular carcinoma (HCC) and non-HCC malignancies (mainly intrahepatic cholangiocarcinoma [CCA] and combined hepatocellular and cholangiocarcinoma [cHCC-CCA]) is an area of active investigation. We aimed to use radiomics-based machine learning classification strategy for differentiating HCC from CCA and cHCC-CCA on contrast-enhanced ultrasound (CEUS) images in high-risk patients with LR-M nodules. Methods A total of 159 high-risk patients with LR-M nodules (69 HCC and 90 CCA/cHCC-CCA) who underwent CEUS within 1 month before pathologic confirmation from January 2006 to December 2019 were retrospectively included (111 patients for training set and 48 for test set). The training set was used to build models, while the test set was used to compare models. For each observation, six CEUS images captured at predetermined time points (T1, peak enhancement after contrast injection; T2, 30 seconds; T3, 45 seconds; T4, 60 seconds; T5, 1-2 minutes; and T6, 2-3 minutes) were collected for tumor segmentation and selection of radiomics features, which included seven types of features: first-order statistics, shape (2D), gray-level co-occurrence matrix, gray-level size zone matrix, gray-level run length matrix, neighboring gray tone difference matrix, and gray-level dependence matrix. Clinical data and key radiomics features were employed to develop the clinical model, radiomics signature (RS), and combined RS-clinical (RS-C) model. The RS and RS-C model were built using the machine learning framework. The diagnostic performance of these three models was calculated and compared. Results Alpha-fetoprotein (AFP), CA19-9, enhancement pattern, and time of washout were included as independent factors for clinical model (all p < 0.05). Both the RS and RS-C model performed better than the clinical model in the test set (area under the curve [AUC] of 0.698 [0.571-0.812] for clinical model, 0.903 [0.830-0.970] for RS, and 0.912 [0.838-0.977] for the RS-C model; both p < 0.05). Conclusions Radiomics-based machine learning classifiers may be competent for differentiating HCC from CCA and cHCC-CCA in high-risk patients with LR-M nodules.

Phonetics of Early Bilingualism

This article presents an overview of recent research on the phonetics of early bilinguals, individuals who have acquired both of their languages early in life, by either growing up being exposed to two languages since birth (i.e., simultaneous bilinguals) or having initially learned their first language with the second language introduced at a later stage during their childhood (i.e., early sequential or successive/consecutive bilinguals). This review puts forth empirical evidence from methodologically and theoretically diverse studies on the phonetics of early bilingualism and considers explanations for the observed patterns of cross-linguistic influence on the production, perception, and processing of sounds in both of their languages. Throughout, this article discusses the critical significance of early linguistic experience on bilingual speech patterns, how early-onset bilinguals perceive speech sounds in each language, bilinguals’ phonetic abilities when producing language-specific segmental and suprasegmental features, and the dynamic nature of cross-language sound interactions in early bilingual speech.

The relation between perceived non-native features in the L1 speech of English migrants to Austria and their phonetic manifestation in L1 productions

Aims: The purpose of this research was to investigate to what extent the most commonly identified non-native features in the L1 speech of late consecutive bilinguals are reflected in differences in the bilinguals’ productions of these features compared with those of monolingual speakers of the L1. Design: We investigated the L1 accent of English migrants to Austria and monolingual English speakers in the United Kingdom in two inter-related studies. Data: In Study 1, an accent-perception experiment, native English listeners rated the nativeness of the monolinguals’ and bilinguals’ L1 English productions of read sentences, using a 6-point scale, and subsequently commented on the accentual features associated with perceived non-nativeness. In Study 2, the monolinguals’ and bilinguals’ productions of the most commonly identified non-native features from Study 1 were compared acoustically and auditorily. Findings: The accent-perception experiment revealed significantly higher non-nativeness ratings for the bilinguals than the monolinguals. These were associated with a wide range of segmental and prosodic features ( n = 836 feature tokens), with /iː/ and /ɪ/ the most commonly identified for segments, and articulation rate and intonation for prosody. The phonetic analysis of these features in Study 2, in turn, revealed that the bilinguals produced /ɪ/ closer to /iː/ than the monolinguals and had more final rises in questions, with the articulation rate differences between them just failing to reach significance. Originality: This is the first study to document a direct link between the features perceived as non-native in bilinguals’ L1 speech and their measurable manifestation in non-native L1 speech productions. Significance: This research contributes significantly to our understanding of the relationship between the perception and production of attrition in L1 speech, and shows that where listeners are able to provide consistent, detailed descriptions of the features associated with non-nativeness, they truthfully reflect measurable patterns in the speech signal.

Automated MRI liver segmentation for anatomical segmentation, liver volumetry, and the extraction of radiomics.

To develop and evaluate a deep convolutional neural network (DCNN) for automated liver segmentation, volumetry, and radiomic feature extraction on contrast-enhanced portal venous phase magnetic resonance imaging (MRI). This retrospective study included hepatocellular carcinoma patients from an institutional database with portal venous MRI. After manual segmentation, the data was randomly split into independent training, validation, and internal testing sets. From a collaborating institution, de-identified scans were used for external testing. The public LiverHccSeg dataset was used for further external validation. A 3D DCNN was trained to automatically segment the liver. Segmentation accuracy was quantified by theDice similarity coefficient (DSC) with respect to manual segmentation. A Mann-Whitney U test was used to compare the internal and external test sets. Agreement of volumetry and radiomic features was assessed using the intraclass correlation coefficient (ICC). In total, 470 patients met the inclusion criteria (63.9±8.2 years; 376 males) and 20 patients were used for external validation (41±12 years; 13 males). DSC segmentation accuracy of the DCNN was similarly high between the internal (0.97±0.01) and external (0.96±0.03) test sets (p=0.28) and demonstrated robust segmentation performance on public testing (0.93±0.03). Agreement of liver volumetry was satisfactory in the internal (ICC, 0.99), external (ICC, 0.97), and public (ICC, 0.85) test sets. Radiomic features demonstrated excellent agreement in the internal (mean ICC, 0.98±0.04), external (mean ICC, 0.94±0.10), and public (mean ICC, 0.91±0.09) datasets. Automated liver segmentation yields robust and generalizable segmentation performance on MRI data and can be used for volumetry and radiomic feature extraction. Liver volumetry, anatomic localization, and extraction of quantitative imaging biomarkers require accurate segmentation, but manual segmentation is time-consuming. A deep convolutional neural network demonstrates fast and accurate segmentation performance on T1-weighted portal venous MRI. • This deep convolutional neural network yields robust and generalizable liver segmentation performance on internal, external, and public testing data. • Automated liver volumetry demonstrated excellent agreement with manual volumetry. • Automated liver segmentations can be used for robust and reproducible radiomic feature extraction.

Hybrid Topological Data Analysis and Deep Learning for Basal Cell Carcinoma Diagnosis.

A critical clinical indicator for basal cell carcinoma (BCC) is the presence of telangiectasia (narrow, arborizing blood vessels) within the skin lesions. Many skin cancer imaging processes today exploit deep learning (DL) models for diagnosis, segmentation of features, and feature analysis. To extend automated diagnosis, recent computational intelligence research has also explored the field of Topological Data Analysis (TDA), a branch of mathematics that uses topology to extract meaningful information from highly complex data. This study combines TDA and DL with ensemble learning to create a hybrid TDA-DL BCC diagnostic model. Persistence homology (a TDA technique) is implemented to extract topological features from automatically segmented telangiectasia as well as skin lesions, and DL features are generated by fine-tuning a pre-trained EfficientNet-B5 model. The final hybrid TDA-DL model achieves state-of-the-art accuracy of 97.4% and an AUC of 0.995 on a holdout test of 395 skin lesions for BCC diagnosis. This study demonstrates that telangiectasia features improve BCC diagnosis, and TDA techniques hold the potential to improve DL performance.

Deep learning-based semantic segmentation of human features in bath scrubbing robots

With the rise in the aging population, an increase in the number of semidisabled elderly individuals has been noted, leading to notable challenges in medical and healthcare, exacerbated by a shortage of nursing staff. This study aims to enhance the human feature recognition capabilities of bath scrubbing robots operating in a water fog environment. The investigation focuses on semantic segmentation of human features using deep learning methodologies. Initially, 3D point cloud data of human bodies with varying sizes are gathered through light detection and ranging to establish human models. Subsequently, a hybrid filtering algorithm was employed to address the impact of the water fog environment on the modeling and extraction of human regions. Finally, the network is refined by integrating the spatial feature extraction module and the channel attention module based on PointNet. The results indicate that the algorithm adeptly identifies feature information for 3D human models of diverse body sizes, achieving an overall accuracy of 95.7%. This represents a 4.5% improvement compared with the PointNet network and a 2.5% enhancement over mean intersection over union. In conclusion, this study substantially augments the human feature segmentation capabilities, facilitating effective collaboration with bath scrubbing robots for caregiving tasks, thereby possessing significant engineering application value.

Macro-based collagen quantification and segmentation in picrosirius red-stained heart sections using light microscopy.

Picrosirius red staining constitutes an important and broadly used tool to visualize collagen and fibrosis in various tissues. Although multiple qualitative and quantitative analysis methods to evaluate fibrosis are available, many require specialized devices and software or lack objectivity and scalability. Here, we aimed to develop a versatile and powerful "QuantSeg" macro in the FIJI image processing software capable of automated, robust, and quick collagen quantification in cardiac tissue from light micrographs. To examine different patterns of fibrosis, an optional segmentation algorithm was implemented. To ensure the method's validity, we quantified the collagen content in a set of wild-type versus plakoglobin-knockout murine hearts exhibiting extensive fibrosis using both the macro and an established, fluorescence microscopy-based method, and compared results. To demonstrate the capabilities of the segmentation feature, rat hearts were examined post-myocardial infarction. We found the QuantSeg macro to robustly detect the differences in fibrosis between knockout and control hearts. In sections with low collagen content, the macro yielded more consistent results than using the fluorescence microscopy-based technique. With its wide range of output parameters, ease of use, cost effectiveness, and objectivity, the QuantSeg macro has the potential to become an established method for analysis of PSR-stained tissue. The novel segmentation feature allows for automated evaluation of different patterns of cardiac fibrosis for the first time.

CNN-IKOA: convolutional neural network with improved Kepler optimization algorithm for image segmentation: experimental validation and numerical exploration

Chest diseases, especially COVID-19, have quickly spread throughout the world and caused many deaths. Finding a rapid and accurate diagnostic tool was indispensable to combating these diseases. Therefore, scientists have thought of combining chest X-ray (CXR) images with deep learning techniques to rapidly detect people infected with COVID-19 or any other chest disease. Image segmentation as a preprocessing step has an essential role in improving the performance of these deep learning techniques, as it could separate the most relevant features to better train these techniques. Therefore, several approaches were proposed to tackle the image segmentation problem accurately. Among these methods, the multilevel thresholding-based image segmentation methods won significant interest due to their simplicity, accuracy, and relatively low storage requirements. However, with increasing threshold levels, the traditional methods have failed to achieve accurate segmented features in a reasonable amount of time. Therefore, researchers have recently used metaheuristic algorithms to tackle this problem, but the existing algorithms still suffer from slow convergence speed and stagnation into local minima as the number of threshold levels increases. Therefore, this study presents an alternative image segmentation technique based on an enhanced version of the Kepler optimization algorithm (KOA), namely IKOA, to better segment the CXR images at small, medium, and high threshold levels. Ten CXR images are used to assess the performance of IKOA at ten threshold levels (T-5, T-7, T-8, T-10, T-12, T-15, T-18, T-20, T-25, and T-30). To observe its effectiveness, it is compared to several metaheuristic algorithms in terms of several performance indicators. The experimental outcomes disclose the superiority of IKOA over all the compared algorithms. Furthermore, the IKOA-based segmented CXR images at eight different threshold levels are used to train a newly proposed CNN model called CNN-IKOA to find out the effectiveness of the segmentation step. Five performance indicators, namely overall accuracy, precision, recall, F1-score, and specificity, are used to disclose the CNN-IKOA’s effectiveness. CNN-IKOA, according to the experimental outcomes, could achieve outstanding outcomes for the images segmented at T-12, where it could reach 94.88% for overall accuracy, 96.57% for specificity, 95.40% for precision, and 95.40% for recall.

The combination of accent method and phonemic contrast: an innovative strategy to improve speech production on post-stroke dysarthria.

Speech production includes segmental and suprasegmental features, which interact and cooperate with each other. Impaired speech production is common in individuals with post-stroke dysarthria. The commonly used phonemic contrast therapy and Accent Method in clinical practice can improve the segmental and suprasegmental aspects, respectively. This study aimed to explore the feasibility and immediate effectiveness of the combination of specific rhythm patterns of the Accent Method and phonemic contrast on speech production. Fifteen poststroke dysarthria patients (12 males and three females) first received accentuation task of three rhythm patterns (Largo-slow, Andante-medium, Allegro-fast) and later received speech task in appropriate rhythm patterns combined with phonemic contrast materials and non-phonemic contrast materials. Speech parameters were analyzed by considering speech clarity and prosody. The results showed that the number of correct target syllables, sentence clarity, and standard deviation of intensity increased significantly, and the average length of pauses and abnormal pause times decreased significantly in Andante (medium) compared to other rhythms. The number of correct target syllables, sentence clarity, and standard deviation of intensity increased significantly compared with those in the non-phonemic contrast in Andante (medium). The combination of phonemic contrast and Accent Method was verified to have an immediate effect on speech production in Mandarin speakers with post-stroke dysarthria and could be further validated in other diseases with impaired speech production in the clinic in the future.

Audio source recording device recognition based on representation learning of sequential Gaussian mean matrix

Audio source recording device recognition is a critical digital forensic task that involves identifying the source device based on intrinsic audio characteristics. This technology finds widespread application in various digital audio forensic scenarios, including audio source forensics, tamper detection forensics, and copyright protection forensics. However, existing methods often suffer from low accuracy due to limited information utilization. In this study, we propose a novel method for source recording device recognition, grounded in feature representation learning. Our approach aims to overcome the limitations of current methods. We introduce a temporal audio feature called the “Sequential Gaussian Mean Matrix (SGMM),” which is derived from temporal segmented acoustic features. We then design a structured representation learning model that combines Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory Networks (BiLSTM). This model leverages temporal Gaussian representation and convolutional bottleneck representation to effectively condense spatial information and achieve accurate recognition through temporal modeling. Our experimental results demonstrate an impressive recognition accuracy of 98.78%, showcasing the effectiveness of our method in identifying multiple classes of recording devices. Importantly, our approach outperforms state-of-the-art methods in terms of recognition performance. Our implementing code is publicly available at https://github.com/CCNUZFW/SGMM.

CSSNet: Cascaded spatial shift network for multi-organ segmentation

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

YOLOv8-segANDcal: segmentation, extraction, and calculation of soybean radicle features.

The high-throughput and full-time acquisition of images of crop growth processes, and the analysis of the morphological parameters of their features, is the foundation for achieving fast breeding technology, thereby accelerating the exploration of germplasm resources and variety selection by crop breeders. The evolution of embryonic soybean radicle characteristics during germination is an important indicator of soybean seed vitality, which directly affects the subsequent growth process and yield of soybeans. In order to address the time-consuming and labor-intensive manual measurement of embryonic radicle characteristics, as well as the issue of large errors, this paper utilizes continuous time-series crop growth vitality monitoring system to collect full-time sequence images of soybean germination. By introducing the attention mechanism SegNext_Attention, improving the Segment module, and adding the CAL module, a YOLOv8-segANDcal model for the segmentation and extraction of soybean embryonic radicle features and radicle length calculation was constructed. Compared to the YOLOv8-seg model, the model respectively improved the detection and segmentation of embryonic radicles by 2% and 1% in mAP50-95, and calculated the contour features and radicle length of the embryonic radicles, obtaining the morphological evolution of the embryonic radicle contour features over germination time. This model provides a rapid and accurate method for crop breeders and agronomists to select crop varieties.