Head Segmentation Research Articles

Head and neck automatic multi-organ segmentation on Dual-Energy Computed Tomography

Background and purposeDeep-learning-based automatic segmentation is widely used in radiation oncology to delineate organs-at-risk. Dual-energy CT (DECT) allows the reconstruction of enhanced contrast images that could help with manual and auto-delineation. This paper presents a performance evaluation of a commercial auto-segmentation software on image series generated by a DECT. Material and methodsDifferent types of DECT images from seventy four head-and-neck (HN) patients were retrieved, including polyenergetic images at different voltages [80 kV reconstructed with a kernel corresponding to the commercial algorithm DirectDensity™ (PEI80-DD), 80 kV (PEI80), 120 kV-mixed (PEI120)] and a virtual-monoenergetic image at 40 keV (VMI40). Delineations used for treatment planning were considered as ground truth (GT) and were compared with the auto-segmentations performed on the 4 DECT images. A blinded qualitative evaluation of 3 structures (thyroid, left parotid, left nodes level II) was carried out. Performance metrics were calculated for thirteen HN structures to evaluate the auto-contours including dice similarity coefficient (DSC), 95th percentile Hausdorff distance (95HD) and mean surface distance (MSD). ResultsWe observed a high rate of low scores for PEI80-DD and VMI40 auto-segmentations on the thyroid and for GT and VMI40 contours on the nodes level II. All images received excellent scores for the parotid glands. The metrics comparison between GT and auto-segmented contours revealed that PEI80-DD had the highest DSC scores, significantly outperforming other reconstructed images for all organs (p < 0.05). ConclusionsThe results indicate that the auto-contouring system cannot generalize to images derived from DECT acquisition. It is therefore crucial to identify which organs benefit from these acquisitions to adapt the training datasets accordingly.

PSFHS challenge report: Pubic symphysis and fetal head segmentation from intrapartum ultrasound images

Segmentation of the fetal and maternal structures, particularly intrapartum ultrasound imaging as advocated by the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG) for monitoring labor progression, is a crucial first step for quantitative diagnosis and clinical decision-making. This requires specialized analysis by obstetrics professionals, in a task that i) is highly time- and cost-consuming and ii) often yields inconsistent results. The utility of automatic segmentation algorithms for biometry has been proven, though existing results remain suboptimal. To push forward advancements in this area, the Grand Challenge on Pubic Symphysis-Fetal Head Segmentation (PSFHS) was held alongside the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023). This challenge aimed to enhance the development of automatic segmentation algorithms at an international scale, providing the largest dataset to date with 5,101 intrapartum ultrasound images collected from two ultrasound machines across three hospitals from two institutions. The scientific community's enthusiastic participation led to the selection of the top 8 out of 179 entries from 193 registrants in the initial phase to proceed to the competition's second stage. These algorithms have elevated the state-of-the-art in automatic PSFHS from intrapartum ultrasound images. A thorough analysis of the results pinpointed ongoing challenges in the field and outlined recommendations for future work. The top solutions and the complete dataset remain publicly available, fostering further advancements in automatic segmentation and biometry for intrapartum ultrasound imaging.

New evidence for five cephalic appendages in trilobites and implications for segmentation of the trilobite head

AbstractHead segments play a critical role in revealing the relationships within major arthropod groups but the accurate determination of their number and relationship is challenging because of the decoupling of dorsal tergites and ventral appendages. In recent decades, trilobites have been considered to have four pairs of cephalic appendages and, commonly, five dorsal segments, which has served as the basis for understanding euarthropod cephalic evolution. Based on multiple analytical techniques applied to well‐preserved soft‐bodied specimens of the Upper Ordovician olenid Triarthrus eatoni and middle Cambrian corynexochid Olenoides serratus, we argue that an additional pair of cephalic biramous appendages occurred just behind the antennae, indicating that trilobites had five pairs of cephalic appendages and six dorsally expressed segments. We propose that the mismatch between the four dorsal furrows and five ventral appendages in Olenoides may be reconciled by considering the morphology of the hypostome that marks the position of the antenna and the bifurcation of the first glabellar furrow that has two muscle attachment sites fused. The fusion of clustered attachment sites of the cephalic biramous appendages may have aided feeding ability by gathering the limb bases close to the mouth.

Multi-label deep learning for comprehensive optic nerve head segmentation through data of fundus images

Early diagnosis and continuous monitoring of patients with eye diseases are critical in computer-aided detection (CAD) techniques. Semantic segmentation, a key component in computer vision, enables pixel-level classification and provides detailed information about objects within images. In this study, we present three U-Net models designed for multi-class semantic segmentation, leveraging the U-Net architecture with transfer learning. To generate ground truth for the HRF dataset, we combine two U-Net models, namely MSU-Net and BU-Net, to predict probability maps for the optic disc and cup regions. Binary masks are then derived from these probability maps to extract the optic disc and cup regions from retinal images. The dataset used in this study includes pre-existing blood vessels and manually annotated peripapillary atrophy zones (alpha and beta) provided by expert ophthalmologists. This comprehensive dataset, integrating existing blood vessels and expert-marked peripapillary atrophy zones, fulfills the study's objectives. The effectiveness of the proposed approach is validated by training nine pre-trained models on the HRF dataset comprising 45 retinal images, successfully segmenting the optic disc, cup, blood vessels, and peripapillary atrophy zones (alpha and beta). The results demonstrate 87.7 % pixel accuracy, 87 % Intersection over Union (IoU), 86.9 % F1 Score, 85 % mean IoU (mIoU), and 15 % model loss, significantly contributing to the early diagnosis and monitoring of glaucoma and optic nerve disorders.

Deep learning models for separate segmentations of intracerebral and intraventricular hemorrhage on head CT and segmentation quality assessment.

The volume measurement of intracerebral hemorrhage (ICH) and intraventricular hemorrhage (IVH) provides critical information for precise treatment of patients with spontaneous ICH but remains a big challenge, especially for IVH segmentation. However, the previously proposed ICH and IVH segmentation tools lack external validation and segmentation quality assessment. This study aimed to develop a robust deep learning model for the segmentation of ICH and IVH with external validation, and to provide quality assessment for IVH segmentation. In this study, a Residual Encoding Unet (REUnet) for the segmentation of ICH and IVH was developed using a dataset composed of 977 CT images (all contained ICH, and 338 contained IVH; a five-fold cross-validation procedure was adopted for training and internal validation), and externally tested using an independent dataset consisting of 375 CT images (all contained ICH, and 105 contained IVH). The performance of REUnet was compared with six other advanced deep learning models. Subsequently, three approaches, including Prototype Segmentation (ProtoSeg), Test Time Dropout (TTD), and Test Time Augmentation (TTA), were employed to derive segmentation quality scores in the absence of ground truth to provide a way to assess the segmentation quality in real practice. For ICH segmentation, the median (lower-quantile-upper quantile) of Dice scores obtained from REUnet were 0.932 (0.898-0.953) for internal validation and 0.888 (0.859-0.916) for external test, both of which were better than those of other models while comparable to that of nnUnet3D in external test. For IVH segmentation, the Dice scores obtained from REUnet were 0.826 (0.757-0.868) for internal validation and 0.777 (0.693-0.827) for external tests, which were better than those of all other models. The concordance correlation coefficients between the volumes estimated from the REUnet-generated segmentations and those from the manual segmentations for both ICH and IVH ranged from 0.944 to 0.987. For IVH segmentation quality assessment, the segmentation quality score derived from ProtoSeg was correlated with the Dice Score (Spearman r=0.752 for the external test) and performed better than those from TTD (Spearman r=0.718) and TTA (Spearman r=0.260) in the external test. By setting a threshold to the segmentation quality score, we were able to identify low-quality IVH segmentation results by ProtoSeg. The proposed REUnet offers a promising tool for accurate and automated segmentation of ICH and IVH, and for effective IVH segmentation quality assessment, and thus exhibits the potential to facilitate therapeutic decision-making for patients with spontaneous ICH in clinical practice.

Enhancing the reliability of deep learning-based head and neck tumour segmentation using uncertainty estimation with multi-modal images

Objective. Deep learning shows promise in autosegmentation of head and neck cancer (HNC) primary tumours (GTV-T) and nodal metastases (GTV-N). However, errors such as including non-tumour regions or missing nodal metastases still occur. Conventional methods often make overconfident predictions, compromising reliability. Incorporating uncertainty estimation, which provides calibrated confidence intervals can address this issue. Our aim was to investigate the efficacy of various uncertainty estimation methods in improving segmentation reliability. We evaluated their confidence levels in voxel predictions and ability to reveal potential segmentation errors. Approach. We retrospectively collected data from 567 HNC patients with diverse cancer sites and multi-modality images (CT, PET, T1-, and T2-weighted MRI) along with their clinical GTV-T/N delineations. Using the nnUNet 3D segmentation pipeline, we compared seven uncertainty estimation methods, evaluating them based on segmentation accuracy (Dice similarity coefficient, DSC), confidence calibration (Expected Calibration Error, ECE), and their ability to reveal segmentation errors (Uncertainty-Error overlap using DSC, UE-DSC). Main results. Evaluated on the hold-out test dataset (n = 97), the median DSC scores for GTV-T and GTV-N segmentation across all uncertainty estimation methods had a narrow range, from 0.73 to 0.76 and 0.78 to 0.80, respectively. In contrast, the median ECE exhibited a wider range, from 0.30 to 0.12 for GTV-T and 0.25 to 0.09 for GTV-N. Similarly, the median UE-DSC also ranged broadly, from 0.21 to 0.38 for GTV-T and 0.22 to 0.36 for GTV-N. A probabilistic network—PhiSeg method consistently demonstrated the best performance in terms of ECE and UE-DSC. Significance. Our study highlights the importance of uncertainty estimation in enhancing the reliability of deep learning for autosegmentation of HNC GTV. The results show that while segmentation accuracy can be similar across methods, their reliability, measured by calibration error and uncertainty-error overlap, varies significantly. Used with visualisation maps, these methods may effectively pinpoint uncertainties and potential errors at the voxel level.

Methods for three-dimensional characterization of the acetabulum prior to pelvic reorientation osteotomy: a scoping review.

Periacetabular osteotomy is the gold standard treatment for acetabular dysplasia. The great variability of acetabular dysplasia requires a personalized preoperative planning improved by 3D reconstruction and computer-assisted surgery. To plan the displacement of the acetabular fragment by a pelvic osteotomy, it is necessary to define a reference plane and a method to characterize 3D acetabular orientation. A scoping review was performed on PubMed to search for articles with a method to characterize the acetabulum of native hips in a 3D reference frame. Ninety-eight articles out of 3815 reports were included. Three reproducible reference planes were identified: the anterior pelvic plane, the Standardization and Terminology Committee plane used in gait analysis, and the sacral base plane. The different methods for 3D analysis of the acetabulum were divided in four groups: global orientation, triplanar measurements, segmentation, and surface coverage of the femoral head. Two methods were found appropriate for reorientation osteotomies: the global orientation by a vector method and the triplanar method. The global orientation method relies on the creation of a vector from the acetabular rim, from the acetabular surface or from successive planes. Normalization of the global acetabular vector would correct acetabular dysplasia by a single alignment maneuver on an ideal vector. The triplanar method, based on angle measurements at the center of the femoral head, would involve correction of anomalies by considering axial, frontal, and sagittal planes. Although not directly fit for reorientation, the two others would help to candidate patients and verify both planning and postoperative result.

Fetal Head and Pubic Symphysis Segmentation in Intrapartum Ultrasound Image Using a Dual-Path Boundary-Guided Residual Network.

Accurate segmentation of the fetal head and pubic symphysis in intrapartum ultrasound images and measurement of fetal angle of progression (AoP) are critical to both outcome prediction and complication prevention in delivery. However, due to poor quality of perinatal ultrasound imaging with blurred target boundaries and the relatively small target of the public symphysis, fully automated and accurate segmentation remains challenging. In this paper, we propse a dual-path boundary-guided residual network (DBRN), which is a novel approach to tackle these challenges. The model contains a multi-scale weighted module (MWM) to gather global context information, and enhance the feature response within the target region by weighting the feature map. The model also incorporates an enhanced boundary module (EBM) to obtain more precise boundary information. Furthermore, the model introduces a boundary-guided dual-attention residual module (BDRM) for residual learning. BDRM leverages boundary information as prior knowledge and employs spatial attention to simultaneously focus on background and foreground information, in order to capture concealed details and improve segmentation accuracy. Extensive comparative experiments have been conducted on three datasets. The proposed method achieves average Dice score of 0.908 ±0.05 and average Hausdorff distance of 3.396 ±0.66 mm. Compared with state-of-the-art competitors, the proposed DBRN achieves better results. In addition, the average difference between the automatic measurement of AoPs based on this model and the manual measurement results is 6.157 °, which has good consistency and has broad application prospects in clinical practice.

Single annotator versus multi-annotator: Challenge of segmenting two neighboring hippocampus head and body with high precision

Background and objectiveThis work investigates multi-annotator segmentation framework for semantic image segmentation using deep learning approaches. MethodsThe framework consists of various deep learning models which perform independently, and then their decisions are fused by a combiner network. The underlying idea of the multi-annotator (ensemble) segmentation framework is to take advantage of the synergistic effect created by the complementary information provided by the different annotators to reach a peak performance superior to each of the annotators when performing alone. The performance of the multi-annotator framework was assessed for the challenging task of the hippocampus head and body segmentation from MR images. Atlas-based segmentation method, deep learning-based multi-view segmentation approach, as well as different decision fusion algorithms, such as STAPLE and shape-based averaging, were assessed versus the proposed multi-annotator segmentation framework. ResultsAmong the different deep learning architectures and loss functions, ResNet model with cross-entropy loss function (ResNet-CE) exhibited the best performance (best performing single model) with a Dice of 88.6 ± 1.8 % and 88.6 ± 1.8 % for the hippocampus head and body, respectively. However, the multi-annotator segmentation framework (which also involved Resnet-CE as one of the annotators) exhibited superior performance with Dice of 91.1 ± 1.3 % (head) and 91.0 ± 1.3 % (body) compared to the atlas-based method with Dice of 88.5 ± 1.5 % (head) and 88.4 ± 1.5 % (body) and multi-view approach with Dice of 89.0 ± 1.4 % (head) and 88.9 ± 1.5 % (body). ConclusionThe multi-annotator segmentation framework exhibits superior performance over each annotator alone which could be employed almost for all machine learning-related problems to enhance the overall effectiveness of the deep/machine learning algorithms.

Head and neck tumor segmentation from [18F]F-FDG PET/CT images based on 3D diffusion model

Objective. Head and neck (H&N) cancers are among the most prevalent types of cancer worldwide, and [18F]F-FDG PET/CT is widely used for H&N cancer management. Recently, the diffusion model has demonstrated remarkable performance in various image-generation tasks. In this work, we proposed a 3D diffusion model to accurately perform H&N tumor segmentation from 3D PET and CT volumes. Approach. The 3D diffusion model was developed considering the 3D nature of PET and CT images acquired. During the reverse process, the model utilized a 3D UNet structure and took the concatenation of 3D PET, CT, and Gaussian noise volumes as the network input to generate the tumor mask. Experiments based on the HECKTOR challenge dataset were conducted to evaluate the effectiveness of the proposed diffusion model. Several state-of-the-art techniques based on U-Net and Transformer structures were adopted as the reference methods. Benefits of employing both PET and CT as the network input, as well as further extending the diffusion model from 2D to 3D, were investigated based on various quantitative metrics and qualitative results. Main results. Results showed that the proposed 3D diffusion model could generate more accurate segmentation results compared with other methods (mean Dice of 0.739 compared to less than 0.726 for other methods). Compared to the diffusion model in 2D form, the proposed 3D model yielded superior results (mean Dice of 0.739 compared to 0.669). Our experiments also highlighted the advantage of utilizing dual-modality PET and CT data over only single-modality data for H&N tumor segmentation (with mean Dice less than 0.570). Significance. This work demonstrated the effectiveness of the proposed 3D diffusion model in generating more accurate H&N tumor segmentation masks compared to the other reference methods.

Geometric validation of a pediatric upper airways model made using a mainstream desktop 3D printer

BackgroundThree-dimensional (3D) printing has become increasingly affordable. Several research projects used 3D printing to create in vitro upper airways model. However, studies using a mainstream desktop 3D printer never performed geometric validation of their model. The aim of this study was to perform geometric validation of a pediatric upper airways model printed with a mainstream desktop 3D printer. MethodsHead computerized tomography (CT) scan of a 10-month-old female underwent segmentation between airways and surrounding anatomical structures. Airways segmentation allowed their measurement for further comparison with printed model. Head segmentation enabled the creation of a 3D printable volume file. To proceed to the geometric validation of the head model, the latter underwent a CT scan. Similar segmentation work was performed on the printed model for comparison. Overlap proportion between the original infant volume and the printed model as well as an average Hausdorff distance were calculated after manual alignment between the original and printed model. ResultsVolumes were 12.31 cm3 and 12.32 cm3 for the pediatric and the printed model upper airways, respectively (0.08% difference). Dice coefficient of original and printed model was 0.92. The average Hausdorff distance was 0.21 mm. ConclusionDesktop mainstream 3D printers can generate pediatric upper airway model with a high dimensional accuracy, as evidenced by our comprehensive geometrical validation.

The End-to-End Fetal Head Circumference Detection and Estimation in Ultrasound Images.

In prenatal examinations, the fetal head circumference (HC) measurement is essential for assessing fetal weight and health conditions. The sonographers obtain the fetal HC manually by fitting peripheral skull ellipse in clinical practice, which is highly subjective, time-consuming, and experience-dependent. Recently, many fetal HC automatic measurement algorithms have been proposed to improve workflow efficiency in prenatal examination. But most automatic measurement algorithms focus on using fetal head segmentation as an intermediate processing step, and HC estimation relies heavily on segmentation results, which causes the accumulation of errors in the above two stages. Independent of the segmentation method, we design a regression network to generate the oriented bounding box to detect the head contour, and directly obtain the fetal head parameters with a pixel-based ellipse regression (PER) loss. Moreover, an effective 3D attention mechanism is integrated into the network to estimate HC more precisely without adding parameters in complex ultrasound images. The extensive experimental results on the public HC18 and our clinical dataset show that the proposed network provides a feasible scheme for end-to-end estimating fetal HC, and avoids the mistake brought by the intermediary processes.

Efficient Wheat Head Segmentation with Minimal Annotation: A Generative Approach.

Deep learning models have been used for a variety of image processing tasks. However, most of these models are developed through supervised learning approaches, which rely heavily on the availability of large-scale annotated datasets. Developing such datasets is tedious and expensive. In the absence of an annotated dataset, synthetic data can be used for model development; however, due to the substantial differences between simulated and real data, a phenomenon referred to as domain gap, the resulting models often underperform when applied to real data. In this research, we aim to address this challenge by first computationally simulating a large-scale annotated dataset and then using a generative adversarial network (GAN) to fill the gap between simulated and real images. This approach results in a synthetic dataset that can be effectively utilized to train a deep-learning model. Using this approach, we developed a realistic annotated synthetic dataset for wheat head segmentation. This dataset was then used to develop a deep-learning model for semantic segmentation. The resulting model achieved a Dice score of 83.4% on an internal dataset and Dice scores of 79.6% and 83.6% on two external datasets from the Global Wheat Head Detection datasets. While we proposed this approach in the context of wheat head segmentation, it can be generalized to other crop types or, more broadly, to images with dense, repeated patterns such as those found in cellular imagery.

Semi-Self-Supervised Domain Adaptation: Developing Deep Learning Models with Limited Annotated Data for Wheat Head Segmentation

Precision agriculture involves the application of advanced technologies to improve agricultural productivity, efficiency, and profitability while minimizing waste and environmental impacts. Deep learning approaches enable automated decision-making for many visual tasks. However, in the agricultural domain, variability in growth stages and environmental conditions, such as weather and lighting, presents significant challenges to developing deep-learning-based techniques that generalize across different conditions. The resource-intensive nature of creating extensive annotated datasets that capture these variabilities further hinders the widespread adoption of these approaches. To tackle these issues, we introduce a semi-self-supervised domain adaptation technique based on deep convolutional neural networks with a probabilistic diffusion process, requiring minimal manual data annotation. Using only three manually annotated images and a selection of video clips from wheat fields, we generated a large-scale computationally annotated dataset of image–mask pairs and a large dataset of unannotated images extracted from video frames. We developed a two-branch convolutional encoder–decoder model architecture that uses both synthesized image–mask pairs and unannotated images, enabling effective adaptation to real images. The proposed model achieved a Dice score of 80.7% on an internal test dataset and a Dice score of 64.8% on an external test set composed of images from five countries and spanning 18 domains, indicating its potential to develop generalizable solutions that could encourage the wider adoption of advanced technologies in agriculture.

Probability maps for deep learning-based head and neck tumor segmentation: Graphical User Interface design and test

BackgroundThe different tumor appearance of head and neck cancer across imaging modalities, scanners, and acquisition parameters accounts for the highly subjective nature of the manual tumor segmentation task. The variability of the manual contours is one of the causes of the lack of generalizability and the suboptimal performance of deep learning (DL) based tumor auto-segmentation models. Therefore, a DL-based method was developed that outputs predicted tumor probabilities for each PET-CT voxel in the form of a probability map instead of one fixed contour. The aim of this study was to show that DL-generated probability maps for tumor segmentation are clinically relevant, intuitive, and a more suitable solution to assist radiation oncologists in gross tumor volume segmentation on PET-CT images of head and neck cancer patients. MethodA graphical user interface (GUI) was designed, and a prototype was developed to allow the user to interact with tumor probability maps. Furthermore, a user study was conducted where nine experts in tumor delineation interacted with the interface prototype and its functionality. The participants’ experience was assessed qualitatively and quantitatively. ResultsThe interviews with radiation oncologists revealed their preference for using a rainbow colormap to visualize tumor probability maps during contouring, which they found intuitive. They also appreciated the slider feature, which facilitated interaction by allowing the selection of threshold values to create single contours for editing and use as a starting point. Feedback on the prototype highlighted its excellent usability and positive integration into clinical workflows. ConclusionsThis study shows that DL-generated tumor probability maps are explainable, transparent, intuitive and a better alternative to the single output of tumor segmentation models.

Accuracy of dipole source reconstruction in the 3-layer BEM model against the 5-layer BEM-FMM model.

To compare cortical dipole fitting spatial accuracy between the widely used yet highly simplified 3-layer and modern more realistic 5-layer BEM-FMM models with and without adaptive mesh refinement (AMR) methods. We generate simulated noiseless 256-channel EEG data from 5-layer (7-compartment) meshes of 15 subjects from the Connectome Young Adult dataset. For each subject, we test four dipole positions, three sets of conductivity values, and two types of head segmentation. We use the boundary element method (BEM) with fast multipole method (FMM) acceleration, with or without (AMR), for forward modeling. Dipole fitting is carried out with the FieldTrip MATLAB toolbox. The average position error (across all tested dipoles, subjects, and models) is ~4 mm, with a standard deviation of ~2 mm. The orientation error is ~20° on average, with a standard deviation of ~15°. Without AMR, the numerical inaccuracies produce a larger disagreement between the 3- and 5-layer models, with an average position error of ~8 mm (6 mm standard deviation), and an orientation error of 28° (28° standard deviation). The low-resolution 3-layer models provide excellent accuracy in dipole localization. On the other hand, dipole orientation is retrieved less accurately. Therefore, certain applications may require more realistic models for practical source reconstruction. AMR is a critical component for improving the accuracy of forward EEG computations using a high-resolution 5-layer volume conduction model. Improving EEG source reconstruction accuracy is important for several clinical applications, including epilepsy and other seizure-inducing conditions.

PSFHS: Intrapartum ultrasound image dataset for AI-based segmentation of pubic symphysis and fetal head

During the process of labor, the intrapartum transperineal ultrasound examination serves as a valuable tool, allowing direct observation of the relative positional relationship between the pubic symphysis and fetal head (PSFH). Accurate assessment of fetal head descent and the prediction of the most suitable mode of delivery heavily rely on this relationship. However, achieving an objective and quantitative interpretation of the ultrasound images necessitates precise PSFH segmentation (PSFHS), a task that is both time-consuming and demanding. Integrating the potential of artificial intelligence (AI) in the field of medical ultrasound image segmentation, the development and evaluation of AI-based models rely significantly on access to comprehensive and meticulously annotated datasets. Unfortunately, publicly accessible datasets tailored for PSFHS are notably scarce. Bridging this critical gap, we introduce a PSFHS dataset comprising 1358 images, meticulously annotated at the pixel level. The annotation process adhered to standardized protocols and involved collaboration among medical experts. Remarkably, this dataset stands as the most expansive and comprehensive resource for PSFHS to date.

RTSeg-net: A lightweight network for real-time segmentation of fetal head and pubic symphysis from intrapartum ultrasound images

The segmentation of the fetal head (FH) and pubic symphysis (PS) from intrapartum ultrasound images plays a pivotal role in monitoring labor progression and informing crucial clinical decisions. Achieving real-time segmentation with high accuracy on systems with limited hardware capabilities presents significant challenges. To address these challenges, we propose the real-time segmentation network (RTSeg-Net), a groundbreaking lightweight deep learning model that incorporates innovative distribution shifting convolutional blocks, tokenized multilayer perceptron blocks, and efficient feature fusion blocks. Designed for optimal computational efficiency, RTSeg-Net minimizes resource demand while significantly enhancing segmentation performance. Our comprehensive evaluation on two distinct intrapartum ultrasound image datasets reveals that RTSeg-Net achieves segmentation accuracy on par with more complex state-of-the-art networks, utilizing merely 1.86 M parameters—just 6 % of their hyperparameters—and operating seven times faster, achieving a remarkable rate of 31.13 frames per second on a Jetson Nano, a device known for its limited computing capacity. These achievements underscore RTSeg-Net's potential to provide accurate, real-time segmentation on low-power devices, broadening the scope for its application across various stages of labor. By facilitating real-time, accurate ultrasound image analysis on portable, low-cost devices, RTSeg-Net promises to revolutionize intrapartum monitoring, making sophisticated diagnostic tools accessible to a wider range of healthcare settings.

Study on visual localization and evaluation of automatic freshwater fish cutting system based on deep learning framework

ABSTRACT Pre-treatment processing technology plays a crucial role in the overall freshwater fish processing procedure, and automatic head and tail cutting stands out as a significant pre-treatment technique within the industry. The system for removing the head and tail of freshwater fish comprised a Cartesian coordinate manipulator, a fish transfer device, a control system, and an image acquisition device. In the vision system, five image segmentation methods were utilized for fish head and tail image segmentation comparison tests. These methods include U-Net (U-shaped Deep Neural Network), DeeplabV3, PSPNet (Pyramid Scene Parsing Network), FastSCNN (Fast Semantic Segmentation Network), and ICNet (Image Cascade Network), all of which were employed to evaluate their performance. Among the tested segmentation methods, the ICNet demonstrated the most excellent segmentation capability. The experimental results indicated a segmentation accuracy of 99.01%, a mean intersection over union (MIoU) of 82.50%, and an image processing time of 15.25 ms. The results showed that the fish head and tail were successfully cut off using this model for recognition with a circular knife. Consequently, the segmentation model employed in the machine vision system within this study has demonstrated successful applicability in automatically cutting the heads and tails of freshwater fish of various sizes.

Laboratory Dangerous Operation Behavior Detection System Based on Deep Learning Algorithm

Aiming at the problem that dangerous operation behaviors in the laboratory is difficult to identify by monitoring the video. An algorithm of dangerous operation behavior detection in multi-task laboratory based on improved YOLOv5 structure is proposed. Firstly, the algorithm enhances, adaptively scales, and adaptively anchors box computing on the input of YOLO network. Then convolution operation is carried out to strengthen the ability of network feature fusion. Finally, the GIoU_Loss function is used at the output to optimize the network parameters and accelerate the convergence of the model. The experimental results show that the algorithm performs well in real-time head localization, head segmentation, and population regression, with significant innovation and superiority. Compared with traditional methods, this algorithm has better accuracy and real-time performance and can more effectively achieve human operation behaviors detection in laboratory application environments.