Segmentation Of Structures Research Articles

Demography with drones: detecting growth and survival of shrubs with unoccupied aerial systems

Large‐scale disturbances, such as megafires, motivate restoration at equally large extents. Measuring the survival and growth of individual plants plays a key role in current efforts to monitor restoration success. However, the scale of modern restoration (e.g., >10,000 ha) challenges measurements of demographic rates with field data. In this study, we demonstrate how unoccupied aerial system (UAS) flights can provide an efficient solution to the tradeoff of precision and spatial extent in detecting demographic rates from the air. We flew two, sequential UAS flights at two sagebrush (Artemisia tridentata) common gardens to measure the survival and growth of individual plants. The accuracy of Bayesian‐optimized segmentation of individual shrub canopies was high (73–95%, depending on the year and site), and remotely sensed survival estimates were within 10% of ground‐truthed survival censuses. Stand age structure affected remotely sensed estimates of growth; growth was overestimated relative to field‐based estimates by 57% in the first garden with older stands, but agreement was high in the second garden with younger stands. Further, younger stands (similar to those just after disturbance) with shorter, smaller plants were sometimes confused with other shrub species and bunchgrasses, demonstrating a need for integrating spectral classification approaches that are increasingly available on affordable UAS platforms. The older stand had several merged canopies, which led to an underestimation of abundance but did not bias remotely sensed survival estimates. Advances in segmentation and UAS structure from motion photogrammetry will enable demographic rate measurements at management‐relevant extents.

Multi-network approach for image segmentation in non-contrast enhanced cardiac 3D MRI of arrhythmic patients

Left atrial appendage (LAA) is the source of thrombi formation in more than 90% of strokes in patients with nonvalvular atrial fibrillation. Catheter-based LAA occlusion is being increasingly applied as a treatment strategy to prevent stroke. Anatomical complexity of LAA makes percutaneous occlusion commonly performed under transesophageal echocardiography (TEE) and X-ray (XR) guidance especially challenging. Image fusion techniques integrating 3D anatomical models derived from pre-procedural imaging into the live XR fluoroscopy can be applied to guide each step of the LAA closure. Cardiac magnetic resonance (CMR) imaging gains in importance for radiation-free evaluation of cardiac morphology as alternative to gold-standard TEE or computed tomography angiography (CTA). Manual delineation of cardiac structures from non-contrast enhanced CMR is, however, labor-intensive, tedious, and challenging due to the rather low contrast. Additionally, arrhythmia often impairs the image quality in ECG synchronized acquisitions causing blurring and motion artifacts. Thus, for cardiac segmentation in arrhythmic patients, there is a strong need for an automated image segmentation method. Deep learning-based methods have shown great promise in medical image analysis achieving superior performance in various imaging modalities and different clinical applications. Fully-convolutional neural networks (CNNs), especially U-Net, have become the method of choice for cardiac segmentation. In this paper, we propose an approach for automatic segmentation of cardiac structures from non-contrast enhanced CMR images of arrhythmic patients based on CNNs implemented in a multi-stage pipeline. Two-stage implementation allows subdividing the task into localization of the relevant cardiac structures and segmentation of these structures from the cropped sub-regions obtained from previous step leading to efficient and effective way of automated cardiac segmentation.

Attention-Enhanced Co-Interactive Fusion Network (AECIF-Net) for automated structural condition assessment in visual inspection

Efficiently monitoring the condition of civil infrastructure requires automating the structural condition assessment in visual inspection. This paper proposes an Attention-Enhanced Co-Interactive Fusion Network (AECIF-Net) for automatic structural condition assessment in visual bridge inspection. AECIF-Net can simultaneously parse structural elements and segment surface defects on the elements in inspection images. It integrates two task-specific relearning subnets to extract task-specific features from an overall feature embedding. A co-interactive feature fusion module further captures the spatial correlation and facilitates information sharing between tasks. Experimental results demonstrate that the proposed AECIF-Net outperforms the current state-of-the-art approaches, achieving promising performance with 92.11% mIoU for element segmentation and 87.16% mIoU for corrosion segmentation on the test set of the new benchmark dataset Steel Bridge Condition Inspection Visual (SBCIV). An ablation study verifies the merits of the designs for AECIF-Net, and a case study demonstrates its capability to automate structural condition assessment.

Classifications of anterior segment structure of congenital corneal opacity in infants and toddlers by ultrasound biomicroscopy and slit-lamp microscopic photographs: an observational study

BackgroundThe structural features have an impact on the surgical prognosis for congenital corneal opacity (CCO). The structural classification system of CCO, however, is lacking. Based on data from ultrasound biomicroscopy (UBM) findings in infants and toddlers with CCO, this research proposed a classification system for the anterior segment structure severity.MethodsMedical records, preoperative UBM images and slit-lamp photographs of infants and toddlers diagnosed with CCO at University Third Hospital between December 2018 and June 2022 were reviewed. According to the anterior segment structural features observed in UBM images, eyes were classified as follows: U1, opaque cornea only; U2, central anterior synechia; U3, peripheral anterior synechia combined with angle closure; and U4, aniridia or lens anomaly. The opacity appearance and corneal vascularization density observed in slit-lamp photographs were assigned grades according to previous studies. The extent of vascularization was also recorded. The corresponding intraocular anomaly classifications and ocular surface lesion severity were analysed.ResultsAmong 81 eyes (65 patients), 41 (50.6%) were right eyes, and 40 (49.4%) were left eyes. The median age at examination was 6.91 months (n = 81, 1.00, 34.00). Two (2.5%) of the 81 eyes were classified as U1, 20 (24.7%) as U2, 22 (27.2%) as U3a, 11 (13.6%) as U3b and 26 (32.1%) as U4. Bilateral CCO eyes had more severe UBM classifications (P = 0.019), more severe dysgenesis (P = 0.012) and a larger angle closure (P = 0.009). Eyes with more severe UBM classifications had higher opacity grades (P = 0.003) and vascularization grades (P = 0.014) and a larger vascularization extent (P = 0.001). Eyes with dysgenesis had higher haze grades (P = 0.012) and more severe vascularization (P = 0.003 for density; P = 0.008 for extent), while the angle closure range was related to haze grade (P = 0.013) and vascularization extent (P = 0.003).ConclusionsThis classification method based on UBM and slit-lamp photography findings in the eyes of CCO infants and toddlers can truly reflect the degree of abnormality of the ocular surface and anterior segment and is correlated with the severity of ocular surface anomalies. This method might provide meaningful guidance for surgical procedure design and prognostic determinations for keratoplasty in CCO eyes.

Advancements in cardiac structures segmentation: a comprehensive systematic review of deep learning in CT imaging.

Segmentation of cardiac structures is an important step in evaluation of the heart on imaging. There has been growing interest in how artificial intelligence (AI) methods-particularly deep learning (DL)-can be used to automate this process. Existing AI approaches to cardiac segmentation have mostly focused on cardiac MRI. This systematic review aimed to appraise the performance and quality of supervised DL tools for the segmentation of cardiac structures on CT. Embase and Medline databases were searched to identify related studies from January 1, 2013 to December 4, 2023. Original research studies published in peer-reviewed journals after January 1, 2013 were eligible for inclusion if they presented supervised DL-based tools for the segmentation of cardiac structures and non-coronary great vessels on CT. The data extracted from eligible studies included information about cardiac structure(s) being segmented, study location, DL architectures and reported performance metrics such as the Dice similarity coefficient (DSC). The quality of the included studies was assessed using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). 18 studies published after 2020 were included. The DSC scores median achieved for the most commonly segmented structures were left atrium (0.88, IQR 0.83-0.91), left ventricle (0.91, IQR 0.89-0.94), left ventricle myocardium (0.83, IQR 0.82-0.92), right atrium (0.88, IQR 0.83-0.90), right ventricle (0.91, IQR 0.85-0.92), and pulmonary artery (0.92, IQR 0.87-0.93). Compliance of studies with CLAIM was variable. In particular, only 58% of studies showed compliance with dataset description criteria and most of the studies did not test or validate their models on external data (81%). Supervised DL has been applied to the segmentation of various cardiac structures on CT. Most showed similar performance as measured by DSC values. Existing studies have been limited by the size and nature of the training datasets, inconsistent descriptions of ground truth annotations and lack of testing in external data or clinical settings. [www.crd.york.ac.uk/prospero/], PROSPERO [CRD42023431113].

Seismic performance of soft rock tunnel under composite support conditions

In order to effectively improve the seismic and impact resistance performance of soft rock tunnels, a composite support method was proposed and validated in the paper. The UDEC (Universal Distinct Element Code) model of soft rock layers was established, and the movement and subsidence characteristics of the roof and floor of the rock layers under impact loads was simulated and calculated. As a result, a composite support scheme with good cushioning performance was proposed. The top and sides of the tunnel were supported by a combination of anchor rods of different lengths and metal mesh, reinforced by steel beams and vibration absorbing filler around. The anchor rod was designed as a segmented loading structure, and can be set to different preloading forces based on the internal deformation of the rock layer. The dynamic response testing scheme was designed, and the results indicate that the segmented loading anchor rod has a significant buffering effect on the response to impact load, and can provide reasonable tension feedback at different stages. Research has found that when the water cement ratio is 0.5-1.5, the curing efficiency and strength are both higher. In order to compare the seismic performance of composite support and traditional constant resistance anchor rod support, local blasting experiments were conducted. Based on a blasting vibration tester, a data detection and transmission system were designed to obtain the vibration speed of the tunnel roof during the vibration process. The research results show that composite support can reduce the maximum vibration by more than 40 %, stabilize the fragmentation coefficient at 1.38, and have a very significant vibration reduction effect.

From work unit segmentation to occupational segmentation: non-smooth structural changes in China’s labor market from 1994 to 2018

China’s labor market has changed dramatically since the beginning of reform and opening up. Previous studies have pointed out that marketization changed the segmentation structure of China’s labor market. However, there was a lack of theoretical derivation of the mechanism, and empirical analysis was relatively rough due to methodological limitations. In this study, a pseudo-employer mobility temporal network was constructed for China’s labor market from 1994 to 2018. Based on the temporal network analysis, this study finds the following: first, China’s labor market is now structurally more open and flexible than it was before market-oriented reforms; second, the labor market in China has seen a shift from work unit segmentation to occupational segmentation; third, non-smoothness manifests itself in the structural changes in China’s labor market. China’s labor market quickly disintegrated after the launch of market-oriented reforms in the 1990s and then ushered in a turbulent period of drastic changes. It was after this turbulent period had ended that the present labor market structure took shape.

The Impact of Colonialism on Surgical Training Structures In Africa Part 2: Surveying Current and Past Trainees

As a result of gradual independence from colonial rule over the course of the past century, Africa has developed and evolved 3 primary surgical training structures: an extracontinental colonial model, an intracontinental college-based model, and several smaller national or local models. There is consistent evidence of international brain drain of surgical trainees and an unequal continental distribution of surgeons; however there has not, to date, been an evaluation of the impact colonialism on the evolution of surgical training on the continent. This study aims to identify the etiologies and consequences of this segmentation of surgical training in Africa. This is a cross-sectional survey of the experience and perspectives of surgical training by current African trainees and graduates. A surgeon's region of residence was found to have a statistically significant positive association with that of a surgeon's training structure (P <0.001). A surgeon's professional college or structure of residency has a significantly positive association with desire to complete subspecialty training (P= 0.008). College and structure of residency also are statistically significantly associated with successful completion of subspecialty training (P<0.001). These findings provide evidence to support the concept that the segmentation of surgical training structures in Africa, which is the direct result of prior colonization, has affected the distribution of trainees and specialists across the continent and the globe. This maldistribution of African surgical trainees directly impacts patient care, as the surgeon-patient ratios in many African countries are insufficient. These inequities should be acknowledged addressed and rectified to ensure that patients in Africa receive timely and appropriate surgical care.

FAFS-UNet: Redesigning skip connections in UNet with feature aggregation and feature selection

In recent years, the encoder–decoder U-shaped network architecture has become a mainstream structure for medical image segmentation. Its biggest advantage lies in the incorporation of shallow features into deeper layers of the network through skip connections. However, according to our research, there are still some limitations in the skip connection part of the network: (1) The information from the encoder stage is not completely and effectively supplemented to the decoder stage; (2) The decoder receives the supplemented feature information from the encoder indiscriminately, which sometimes leads to the poor performance of the model. Therefore, to effectively address these limitations, we have redesigned the skip connections in UNet using a feature aggregation and feature selection approach. We firstly design the FA module to aggregate all encoder features and perform local multi-scale information extraction to obtain the complete multi-scale aggregated features. Further, we design the FS module to actively perform specific selection of these aggregated features through the decoder, thus effectively guiding the semantic recovery of the decoder. Finally, we conduct experiments on several medical image datasets, and the results show that our method has higher segmentation accuracy compared with other methods.

The effect of enhanced structure in the posterior segment of clear aligners during anterior retraction: a three-dimensional finite element and experimental model analysis

BackgroundMesial tipping of posterior teeth occurs frequently during space closure with clear aligners (CAs). In this study, we proposed a new modification of CA by localized thickening of the aligner to form the enhanced structure and investigate its biomechanical effect during anterior retraction.MethodsTwo methods were employed in this study. First, a finite element (FE) model was constructed, which included alveolar bone, the first premolars extracted maxillary dentition, periodontal ligaments (PDL), attachments and aligners. The second method involved an experimental model—a measuring device using multi-axis transducers and vacuum thermoforming aligners. Two groups were formed: (1) The control group used common CAs and (2) the enhanced structure group used partially thickened CAs.ResultsFE model revealed that the enhanced structure improved the biomechanics during anterior retraction. Specifically, the second premolar, which had a smaller PDL area, experienced a smaller protraction force and moment, making it less likely to tip mesially. In the same vein, the molars could resist movement due to their larger PDL area even though they were applied larger forces. The resultant force of the posterior tooth was closer to the center of resistance, reducing the tipping moment. The canine was applied a larger retraction force and moment, resulting in sufficient retraction of anterior teeth. The experimental model demonstrated a similar trend in force variation as the FE model.ConclusionsEnhanced structure allowed force distribution more in accordance with optimal principles of biomechanics during the extraction space closure while permitting less mesial tipping and anchorage loss of posterior teeth and better retraction of anterior teeth. Thus, enhanced structure alleviated the roller coaster effect associated with extraction cases and offered a new possibility for anchorage reinforcement in clear aligner therapy.

Full-scale experimental and structural characterization study of shield tunnel reinforcement under ground stacking loads

To investigate the internal force response characteristics and reinforcement effects of the shield tunnel segment structure in the presence of ground load disturbances in the Hangzhou Metro, full-scale tests were conducted on three-ring misaligned assembled segments using a self-developed "Shield Tunnel Segment Hydraulic Loading System." The study examined the structural characteristics of tunnel segments under the influence of different ground resistance coefficients (λ) and eccentric loads (P), and explored the reinforcement effects of the internal tension ring method from multiple perspectives. The research results indicate that under different ground resistance coefficients (λ), the sensitivity of internal force response is concentrated in the waist concrete, with a maximum bending moment reduction of 88.8%. The effective rate of bending stiffness tends to flatten, joint bending moment transfer effects strengthen, and the bearing capacity of the segments significantly increases after reinforcement, leading to a more uniform overall structural response. Under different eccentric loads (P), the bending moment of the segments after reinforcement approximates central symmetry with a reduced distribution range. The rate of change of the effective bending stiffness (η) shifts from "rapid" to "slow," and the variation of joint bending moment transfer coefficient (ζ) stabilizes. The reinforcement with steel rings significantly enhances the overall stiffness of the segments and reinforces the joint bending moment transfer effect. The reinforcement effect of the segments can be evaluated through the bending moment transfer coefficient and effective bending stiffness. After reinforcement, the bearing capacity of the segments is noticeably enhanced, and significant forces are observed at two locations in the right waist joint, where the combination of steel plates and segments exhibits optimal performance.

Two new species of Monstrilla (Copepoda: Monstrilloida: Monstrillidae) from a protected reef system of the Mexican Caribbean

Several adult female monstrilloid copepods, collected in March 2022 from the protected reef area of Xcalak, on the southern part of the Mexican Caribbean coast, proved to belong to two undescribed species of Monstrilla Dana, 1849. They are described here as M. xcalakensis sp. nov. and M. annulata sp. nov., partly by use of scanning electron microscopy. Females of the two species are generally similar but differ in: (1) antennular segmental structure, (2) antennular armature and ornamentation, (3) structure and setation of the fifth leg, (4) number and modifications of the caudal setae, and (5) integumental ornamentation. Comparison with congeneric species revealed distinctive features for both species that support their status as new. These two species are interesting additions to the reef-dwelling monstrilloid copepod fauna of the Mexican Caribbean and confirm Monstrilla as the most diverse genus of monstrilloids in this area, now represented by nine species.

Ultrasound biomicroscopy in the management of complex cataract and intraocular lens: A review.

Ultrasound biomicroscopy (UBM) is an invaluable investigation for imaging anterior segment structures. Although it is operator-dependent and time consuming, unlike optical-based imaging techniques, it is able to image structures posterior to the iris, such as the zonules, ciliary body and part of the pars plana. It is especially useful in advanced cataracts, traumatic cataracts, subluxed lenses, posterior polar cataracts, and congenital and developmental anomalies affecting the anterior segment. It provides diagnostic information in eyes with complex cataracts or intraocular lens (IOL)-related pathology, and aids in surgical planning in order to minimise complications. In this review, we describe the UBM features of various lenticular pathologies and demonstrate its application in the diagnosis and surgical management of lens and IOL-related pathologies.

Segmentation of pelvic structures in T2 MRI via MR-to-CT synthesis

Segmentation of multiple pelvic structures in MRI volumes is a prerequisite for many clinical applications, such as sarcopenia assessment, bone density measurement, and muscle-to-fat volume ratio estimation. While many CT-specific datasets and automated CT-based multi-structure pelvis segmentation methods exist, there are few MRI-specific multi-structure segmentation methods in literature. In this pilot work, we propose a lightweight and annotation-free pipeline to synthetically translate T2 MRI volumes of the pelvis to CT, and subsequently leverage an existing CT-only tool called TotalSegmentator to segment 8 pelvic structures in the generated CT volumes. The predicted masks were then mapped back to the original MR volumes as segmentation masks. We compared the predicted masks against the expert annotations of the public TCGA-UCEC dataset and an internal dataset. Experiments demonstrated that the proposed pipeline achieved Dice measures ≥65% for 8 pelvic structures in T2 MRI. The proposed pipeline is an alternative method to obtain multi-organ and structure segmentations without being encumbered by time-consuming manual annotations. By exploiting the significant research progress in CTs, it is possible to extend the proposed pipeline to other MRI sequences in principle. Our research bridges the chasm between the current CT-based multi-structure segmentation and MRI-based segmentation. The manually segmented structures in the TCGA-UCEC dataset are publicly available.

CMF defects database: A craniomaxillofacial defects dataset and a data-driven repair method

Due to the large number of medical images generated each year, data-driven machine learning methods hold great promise in the field of medical image diagnosis and analysis. In recent years, the application of deep neural networks in oral and cranio-maxillofacial surgery has gradually increased, helping surgeons to obtain more comprehensive information and develop more accurate treatment planning, including segmentation and recognition of anatomical structures, disease diagnosis, and automatic surgical planning. This paper presents a new dataset of maxillofacial defect images, containing computed tomography (CT) data of 125 normal human cranial skeletal 3D reconstructions and 2625 corresponding craniomaxillofacial bone defects. The data are classified according to seven different types of defects which are anterior skull and forehead, zygomatic arch, zygomatic bone, Naso-orbital-ethmoidal (NOE), wall of the maxillary sinus, mandibular body, mandibular ramus, and condylar respectively. Each kind of defect is further divided into three categories according to the different locations, including left side, right side, and bilateral sides (or defect passes through the midline of the face). There are three main contributions: first, a dataset is publicly available to assist researchers in the development of data-based methods for generating missing portions of the skull; second, a repair method is proposed to evaluate the dataset; third, a review of various related datasets. The release of this dataset aims to advance artificial intelligence methods in the field of oral and cranio-maxillofacial surgery and plastic surgery helping physicians to reduce the difficulty and time consumption while improving the efficiency and accuracy of prosthesis design.

Comparison of Intestinal Microbiota of Blue Fox before and after Weaning.

Intestinal flora plays an important role in maintaining the internal stability and health of the intestine. Currently, intestinal microbes are considered an important "organ" but are mostly ignored by people. This study evaluated the flora structure of each intestinal segment of blue foxes pre-weaning and explored the differences between the fecal flora and intestinal flora structure of each segment after weaning. Samples of intestinal contents from three blue foxes at 45 days of age (before weaning) and intestinal contents and feces samples from at 80 days (after weaning) were collected for 16s rRNA flora analysis. The species and distribution characteristics of microorganisms in different intestinal segments of blue foxes before and after weaning were different. Except for the rectum, the dominant flora of each intestinal segment of blue fox changed significantly after experiencing weaning, and the fecal flora structure of young fox at the weaning stage did not represent the whole intestinal flora structure but was highly similar to that of the colon and rectum. To sum up, the intestinal flora of blue foxes changed systematically before and after weaning. When performing non-invasive experiments, the microflora structure of the colon and rectum of blue foxes can be predicted by collecting fecal samples.

Failure-distribution-dependent leader-following fault-tolerant consensus for multiagent system with cyberattacks

This article concentrates on a failure-distribution-dependent leader-following fault-tolerant consensus control for multiagent systems with cyberattacks. First, considering the characteristic of failures, a failure distribution model which is more in line with the actual situation is established. To reduce the influence of zero initial conditions, an [Formula: see text] performance index suitable for leader-following multiagent systems is constructed. After this, it is difficult to obtain the augmented form of the closed-loop system due to the coupling of parameters caused by cyberattacks. Thus, based on the provided failure model and performance index, a new fault-tolerant controller is designed by using topological structure segmentation to satisfy the leader-following multiagent system fault-tolerant consensus. Finally, a numerical example is shown to prove the feasibility of this algorithm.

Clinical Applications of Anterior Segment Optical Coherence Tomography: An Updated Review.

Since its introduction, optical coherence tomography (OCT) has revolutionized the field of ophthalmology and has now become an indispensable, noninvasive tool in daily practice. Most ophthalmologists are familiar with its use in the assessment and monitoring of retinal and optic nerve diseases. However, it also has important applications in the assessment of anterior segment structures, including the cornea, conjunctiva, sclera, anterior chamber, and iris, and has the potential to transform the clinical examination of these structures. In this review, we aim to provide a comprehensive overview of the potential clinical utility of anterior segment OCT (AS-OCT) for a wide range of anterior segment pathologies, such as conjunctival neoplasia, pterygium, scleritis, keratoconus, corneal dystrophies, and infectious/noninfectious keratitis. In addition, the clinical applications of AS-OCT (including epithelial mapping) in preoperative planning and postoperative monitoring for corneal and refractive surgeries are discussed.

Host genetic regulation of human gut microbial structural variation

Although the impact of host genetics on gut microbial diversity and the abundance of specific taxa is well established1–6, little is known about how host genetics regulates the genetic diversity of gut microorganisms. Here we conducted a meta-analysis of associations between human genetic variation and gut microbial structural variation in 9,015 individuals from four Dutch cohorts. Strikingly, the presence rate of a structural variation segment in Faecalibacterium prausnitzii that harbours an N-acetylgalactosamine (GalNAc) utilization gene cluster is higher in individuals who secrete the type A oligosaccharide antigen terminating in GalNAc, a feature that is jointly determined by human ABO and FUT2 genotypes, and we could replicate this association in a Tanzanian cohort. In vitro experiments demonstrated that GalNAc can be used as the sole carbohydrate source for F. prausnitzii strains that carry the GalNAc-metabolizing pathway. Further in silico and in vitro studies demonstrated that other ABO-associated species can also utilize GalNAc, particularly Collinsella aerofaciens. The GalNAc utilization genes are also associated with the host’s cardiometabolic health, particularly in individuals with mucosal A-antigen. Together, the findings of our study demonstrate that genetic associations across the human genome and bacterial metagenome can provide functional insights into the reciprocal host–microbiome relationship.

Randomness-restricted Diffusion Model for Ocular Surface Structure Segmentation.

Ocular surface diseases affect a significant portion of the population worldwide. Accurate segmentation and quantification of different ocular surface structures are crucial for the understanding of these diseases and clinical decision-making. However, the automated segmentation of the ocular surface structure is relatively unexplored and faces several challenges. Ocular surface structure boundaries are often inconspicuous and obscured by glare from reflections. In addition, the segmentation of different ocular structures always requires training of multiple individual models. Thus, developing a one-model-fits-all segmentation approach is desirable. In this paper, we introduce a randomness-restricted diffusion model for multiple ocular surface structure segmentation. First, a time-controlled fusion-attention module (TFM) is proposed to dynamically adjust the information flow within the diffusion model, based on the temporal relationships between the network's input and time. TFM enables the network to effectively utilize image features to constrain the randomness of the generation process. We further propose a low-frequency consistency filter and a new loss to alleviate model uncertainty and error accumulation caused by the multi-step denoising process. Extensive experiments have shown that our approach can segment seven different ocular surface structures. Our method performs better than both dedicated ocular surface segmentation methods and general medical image segmentation methods. We further validated the proposed method over two clinical datasets, and the results demonstrated that it is beneficial to clinical applications, such as the meibomian gland dysfunction grading and aqueous deficient dry eye diagnosis.