HLAIImaster: a deep learning method with adaptive domain knowledge predicts HLA II neoepitope immunogenic responses.

While significant strides have been made in predicting neoepitopes that trigger autologous CD4+ T cell responses, accurately identifying the antigen presentation by human leukocyte antigen (HLA) class II molecules remains a challenge. This identification is critical for developing vaccines and cancer immunotherapies. Current prediction methods are limited, primarily due to a lack of high-quality training epitope datasets and algorithmic constraints. To predict the exogenous HLA class II-restricted peptides across most of the human population, we utilized the mass spectrometry data to profile >223 000 eluted ligands over HLA-DR, -DQ, and -DP alleles. Here, by integrating these data with peptide processing and gene expression, we introduce HLAIImaster, an attention-based deep learning framework with adaptive domain knowledge for predicting neoepitope immunogenicity. Leveraging diverse biological characteristics and our enhanced deep learning framework, HLAIImaster is significantly improved against existing tools in terms of positive predictive value across various neoantigen studies. Robust domain knowledge learning accurately identifies neoepitope immunogenicity, bridging the gap between neoantigen biology and the clinical setting and paving the way for future neoantigen-based therapies to provide greater clinical benefit. In summary, we present a comprehensive exploitation of the immunogenic neoepitope repertoire of cancers, facilitating the effective development of "just-in-time" personalized vaccines.

DrugMGR: a deep bioactive molecule binding method to identify compounds targeting proteins.

MOTIVATION: Understanding the intermolecular interactions of ligand-target pairs is key to guiding the optimization of drug research on cancers, which can greatly mitigate overburden workloads for wet labs. Several improved computational methods have been introduced and exhibit promising performance for these identification tasks, but some pitfalls restrict their practical applications: (i) first, existing methods do not sufficiently consider how multigranular molecule representations influence interaction patterns between proteins and compounds; and (ii) second, existing methods seldom explicitly model the binding sites when an interaction occurs to enable better prediction and interpretation, which may lead to unexpected obstacles to biological researchers. RESULTS: To address these issues, we here present DrugMGR, a deep multigranular drug representation model capable of predicting binding affinities and regions for each ligand-target pair. We conduct consistent experiments on three benchmark datasets using existing methods and introduce a new specific dataset to better validate the prediction of binding sites. For practical application, target-specific compound identification tasks are also carried out to validate the capability of real-world compound screen. Moreover, the visualization of some practical interaction scenarios provides interpretable insights from the results of the predictions. The proposed DrugMGR achieves excellent overall performance in these datasets, exhibiting its advantages and merits against state-of-the-art methods. Thus, the downstream task of DrugMGR can be fine-tuned for identifying the potential compounds that target proteins for clinical treatment. AVAILABILITY AND IMPLEMENTATION: https://github.com/lixiaokun2020/DrugMGR.

A simulation study on the antiarrhythmic mechanisms of established agents in myocardial ischemia and infarction.

Patients with myocardial ischemia and infarction are at increased risk of arrhythmias, which in turn, can exacerbate the overall risk of mortality. Despite the observed reduction in recurrent arrhythmias through antiarrhythmic drug therapy, the precise mechanisms underlying their effectiveness in treating ischemic heart disease remain unclear. Moreover, there is a lack of specialized drugs designed explicitly for the treatment of myocardial ischemic arrhythmia. This study employs an electrophysiological simulation approach to investigate the potential antiarrhythmic effects and underlying mechanisms of various pharmacological agents in the context of ischemia and myocardial infarction (MI). Based on physiological experimental data, computational models are developed to simulate the effects of a series of pharmacological agents (amiodarone, telmisartan, E-4031, chromanol 293B, and glibenclamide) on cellular electrophysiology and utilized to further evaluate their antiarrhythmic effectiveness during ischemia. On 2D and 3D tissues with multiple pathological conditions, the simulation results indicate that the antiarrhythmic effect of glibenclamide is primarily attributed to the suppression of efflux of potassium ion to facilitate the restitution of [K+]o, as opposed to recovery of IKATP during myocardial ischemia. This discovery implies that, during acute cardiac ischemia, pro-arrhythmogenic alterations in cardiac tissue's excitability and conduction properties are more significantly influenced by electrophysiological changes in the depolarization rate, as opposed to variations in the action potential duration (APD). These findings offer specific insights into potentially effective targets for investigating ischemic arrhythmias, providing significant guidance for clinical interventions in acute coronary syndrome.

Mechanisms of ventricular arrhythmias elicited by coexistence of multiple electrophysiological remodeling in ischemia: A simulation study.

Myocardial ischemia, injury and infarction (MI) are the three stages of acute coronary syndrome (ACS). In the past two decades, a great number of studies focused on myocardial ischemia and MI individually, and showed that the occurrence of reentrant arrhythmias is often associated with myocardial ischemia or MI. However, arrhythmogenic mechanisms in the tissue with various degrees of remodeling in the ischemic heart have not been fully understood. In this study, biophysical detailed single-cell models of ischemia 1a, 1b, and MI were developed to mimic the electrophysiological remodeling at different stages of ACS. 2D tissue models with different distributions of ischemia and MI areas were constructed to investigate the mechanisms of the initiation of reentrant waves during the progression of ischemia. Simulation results in 2D tissues showed that the vulnerable windows (VWs) in simultaneous presence of multiple ischemic conditions were associated with the dynamics of wave propagation in the tissues with each single pathological condition. In the tissue with multiple pathological conditions, reentrant waves were mainly induced by two different mechanisms: one is the heterogeneity along the excitation wavefront, especially the abrupt variation in conduction velocity (CV) across the border of ischemia 1b and MI, and the other is the decreased safe factor (SF) for conduction at the edge of the tissue in MI region which is attributed to the increased excitation threshold of MI region. Finally, the reentrant wave was observed in a 3D model with a scar reconstructed from MRI images of a MI patient. These comprehensive findings provide novel insights for understanding the arrhythmic risk during the progression of myocardial ischemia and highlight the importance of the multiple pathological stages in designing medical therapies for arrhythmias in ischemia.

Reciprocal interaction between IK1 and If in biological pacemakers: A simulation study.

Pacemaking dysfunction (PD) may result in heart rhythm disorders, syncope or even death. Current treatment of PD using implanted electronic pacemakers has some limitations, such as finite battery life and the risk of repeated surgery. As such, the biological pacemaker has been proposed as a potential alternative to the electronic pacemaker for PD treatment. Experimentally and computationally, it has been shown that bio-engineered pacemaker cells can be generated from non-rhythmic ventricular myocytes (VMs) by knocking out genes related to the inward rectifier potassium channel current (IK1) or by overexpressing hyperpolarization-activated cyclic nucleotide gated channel genes responsible for the "funny" current (If). However, it is unclear if a bio-engineered pacemaker based on the modification of IK1- and If-related channels simultaneously would enhance the ability and stability of bio-engineered pacemaking action potentials. In this study, the possible mechanism(s) responsible for VMs to generate spontaneous pacemaking activity by regulating IK1 and If density were investigated by a computational approach. Our results showed that there was a reciprocal interaction between IK1 and If in ventricular pacemaker model. The effect of IK1 depression on generating ventricular pacemaker was mono-phasic while that of If augmentation was bi-phasic. A moderate increase of If promoted pacemaking activity but excessive increase of If resulted in a slowdown in the pacemaking rate and even an unstable pacemaking state. The dedicated interplay between IK1 and If in generating stable pacemaking and dysrhythmias was evaluated. Finally, a theoretical analysis in the IK1/If parameter space for generating pacemaking action potentials in different states was provided. In conclusion, to the best of our knowledge, this study provides a wide theoretical insight into understandings for generating stable and robust pacemaker cells from non-pacemaking VMs by the interplay of IK1 and If, which may be helpful in designing engineered biological pacemakers for application purposes.

Performance of novel deep learning network with the incorporation of the automatic segmentation network for diagnosis of breast cancer in automated breast ultrasound.

OBJECTIVE: To develop novel deep learning network (DLN) with the incorporation of the automatic segmentation network (ASN) for morphological analysis and determined the performance for diagnosis breast cancer in automated breast ultrasound (ABUS). METHODS: A total of 769 breast tumors were enrolled in this study and were randomly divided into training set and test set at 600 vs. 169. The novel DLNs (Resent v2, ResNet50 v2, ResNet101 v2) added a new ASN to the traditional ResNet networks and extracted morphological information of breast tumors. The accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic (ROC) curve (AUC), and average precision (AP) were calculated. The diagnostic performances of novel DLNs were compared with those of two radiologists with different experience. RESULTS: The ResNet34 v2 model had higher specificity (76.81%) and PPV (82.22%) than the other two, the ResNet50 v2 model had higher accuracy (78.11%) and NPV (72.86%), and the ResNet101 v2 model had higher sensitivity (85.00%). According to the AUCs and APs, the novel ResNet101 v2 model produced the best result (AUC 0.85 and AP 0.90) compared with the remaining five DLNs. Compared with the novice radiologist, the novel DLNs performed better. The F1 score was increased from 0.77 to 0.78, 0.81, and 0.82 by three novel DLNs. However, their diagnostic performance was worse than that of the experienced radiologist. CONCLUSIONS: The novel DLNs performed better than traditional DLNs and may be helpful for novice radiologists to improve their diagnostic performance of breast cancer in ABUS. KEY POINTS: • A novel automatic segmentation network to extract morphological information was successfully developed and implemented with ResNet deep learning networks. • The novel deep learning networks in our research performed better than the traditional deep learning networks in the diagnosis of breast cancer using ABUS images. • The novel deep learning networks in our research may be useful for novice radiologists to improve diagnostic performance.

Heart failure-induced atrial remodelling promotes electrical and conduction alternans.

Heart failure (HF) is associated with an increased propensity for atrial fibrillation (AF), causing higher mortality than AF or HF alone. It is hypothesized that HF-induced remodelling of atrial cellular and tissue properties promotes the genesis of atrial action potential (AP) alternans and conduction alternans that perpetuate AF. However, the mechanism underlying the increased susceptibility to atrial alternans in HF remains incompletely elucidated. In this study, we investigated the effects of how HF-induced atrial cellular electrophysiological (with prolonged AP duration) and tissue structural (reduced cell-to-cell coupling caused by atrial fibrosis) remodelling can have an effect on the generation of atrial AP alternans and their conduction at the cellular and one-dimensional (1D) tissue levels. Simulation results showed that HF-induced atrial electrical remodelling prolonged AP duration, which was accompanied by an increased sarcoplasmic reticulum (SR) Ca2+ content and Ca2+ transient amplitude. Further analysis demonstrated that HF-induced atrial electrical remodelling increased susceptibility to atrial alternans mainly due to the increased sarcoplasmic reticulum Ca2+-ATPase (SERCA) Ca2+ reuptake, modulated by increased phospholamban (PLB) phosphorylation, and the decreased transient outward K+ current (Ito). The underlying mechanism has been suggested that the increased SR Ca2+ content and prolonged AP did not fully recover to their previous levels at the end of diastole, resulting in a smaller SR Ca2+ release and AP in the next beat. These produced Ca2+ transient alternans and AP alternans, and further caused AP alternans and Ca2+ transient alternans through Ca2+→AP coupling and AP→Ca2+ coupling, respectively. Simulation of a 1D tissue model showed that the combined action of HF-induced ion channel remodelling and a decrease in cell-to-cell coupling due to fibrosis increased the heart tissue's susceptibility to the formation of spatially discordant alternans, resulting in an increased functional AP propagation dispersion, which is pro-arrhythmic. These findings provide insights into how HF promotes atrial arrhythmia in association with atrial alternans.

Effects of amiodarone on short QT syndrome variant 3 in human ventricles: a simulation study.

BACKGROUND: Short QT syndrome (SQTS) is a newly identified clinical disorder associated with atrial and/or ventricular arrhythmias and increased risk of sudden cardiac death (SCD). The SQTS variant 3 is linked to D172N mutation to the KCNJ2 gene that causes a gain-of-function to the inward rectifier potassium channel current (I K1), which shortens the ventricular action potential duration (APD) and effective refractory period (ERP). Pro-arrhythmogenic effects of SQTS have been characterized, but less is known about the possible pharmacological treatment of SQTS. Therefore, in this study, we used computational modeling to assess the effects of amiodarone, class III anti-arrhythmic agent, on human ventricular electrophysiology in SQT3. METHODS: The ten Tusscher et al. model for the human ventricular action potentials (APs) was modified to incorporate I K1 formulations based on experimental data of Kir2.1 channels (including WT, WT-D172N and D172N conditions). The modified cell model was then implemented to construct one-dimensional (1D) and 2D tissue models. The blocking effects of amiodarone on ionic currents were modeled using IC50 and Hill coefficient values from literatures. Effects of amiodarone on APD, ERP and pseudo-ECG traces were computed. Effects of the drug on the temporal and spatial vulnerability of ventricular tissue to genesis and maintenance of re-entry were measured, as well as on the dynamic behavior of re-entry. RESULTS: Amiodarone prolonged the ventricular cell APD and decreased the maximal voltage heterogeneity (δV) among three difference cells types across transmural ventricular wall, leading to a decreased transmural heterogeneity of APD along a 1D model of ventricular transmural strand. Amiodarone increased cellular ERP, prolonged QT interval and decreased the T-wave amplitude. It reduced tissue's temporal susceptibility to the initiation of re-entry and increased the minimum substrate size necessary to sustain re-entry in the 2D tissue. CONCLUSIONS: At the therapeutic-relevant concentration of amiodarone, the APD and ERP at the single cell level were increased significantly. The QT interval in pseudo-ECG was prolonged and the re-entry in tissue was prevented. This study provides further evidence that amiodarone may be a potential pharmacological agent for preventing arrhythmogenesis for SQT3 patients.

A composite visualization method for electrophysiology-morphous merging of human heart.

BACKGROUND: Electrophysiological behavior is of great importance for analyzing the cardiac functional mechanism under cardiac physiological and pathological condition. Due to the complexity of cardiac structure and biophysiological function, visualization of a cardiac electrophysiological model compositively is still a challenge. The lack of either modality of the whole organ structure or cardiac electrophysiological behaviors makes analysis of the intricate mechanisms of cardiac dynamic function a difficult task. This study aims at exploring 3D conduction of stimulus and electrical excitation reactivity on the level of organ with the authentic fine cardiac anatomy structure. METHODS: In this paper, a cardiac electrical excitation propagation model is established based on the human cardiac cross-sectional data to explore detailed cardiac electrical activities. A novel biophysical merging visualization method is then presented for biophysical integration of cardiac anatomy and electrophysiological properties in the form of the merging optical model, which provides the corresponding position, spatial relationship and the whole process in 3D space with the context of anatomical structure for representing the biophysical detailed electrophysiological activity. RESULTS: The visualization result present the action potential propagation of the left ventricle within the excitation cycle with the authentic fine cardiac organ anatomy. In the visualized images, all vital organs are identified and distinguished without ambiguity. The three dimensional spatial position, relation and the process of cardiac excitation conduction and re-entry propagation in the anatomical structure during the phase of depolarization and repolarization is also shown in the result images, which exhibits the performance of a more detailed biophysical understanding of the electrophysiological kinetics of human heart in vivo. CONCLUSIONS: Results suggest that the proposed merging optical model can merge cardiac electrophysiological activity with the anatomy structure. By specifying the respective opacity for the cardiac anatomy structure and the electrophysiological model in the merging attenuation function, the visualized images can provide an in-depth insight into the biophysical detailed cardiac functioning phenomena and the corresponding electrophysiological behavior mechanism, which is helpful for further speculating cardiac physiological and pathological responses and is fundamental to the cardiac research and clinical diagnoses.

Mechanism underlying impaired cardiac pacemaking rhythm during ischemia: A simulation study.

Ischemia in the heart impairs function of the cardiac pacemaker, the sinoatrial node (SAN). However, the ionic mechanisms underlying the ischemia-induced dysfunction of the SAN remain elusive. In order to investigate the ionic mechanisms by which ischemia causes SAN dysfunction, action potential models of rabbit SAN and atrial cells were modified to incorporate extant experimental data of ischemia-induced changes to membrane ion channels and intracellular ion homeostasis. The cell models were incorporated into an anatomically detailed 2D model of the intact SAN-atrium. Using the multi-scale models, the functional impact of ischemia-induced electrical alterations on cardiac pacemaking action potentials (APs) and their conduction was investigated. The effects of vagal tone activity on the regulation of cardiac pacemaker activity in control and ischemic conditions were also investigated. The simulation results showed that at the cellular level ischemia slowed the SAN pacemaking rate, which was mainly attributable to the altered Na+-Ca2+ exchange current and the ATP-sensitive potassium current. In the 2D SAN-atrium tissue model, ischemia slowed down both the pacemaking rate and the conduction velocity of APs into the surrounding atrial tissue. Simulated vagal nerve activity, including the actions of acetylcholine in the model, amplified the effects of ischemia, leading to possible SAN arrest and/or conduction exit block, which are major features of the sick sinus syndrome. In conclusion, this study provides novel insights into understanding the mechanisms by which ischemia alters SAN function, identifying specific conductances as contributors to bradycardia and conduction block.

A robust statistics driven volume-scalable active contour for segmenting anatomical structures in volumetric medical images with complex conditions.

BACKGROUND: Accurate segmentation of anatomical structures in medical images is a critical step in the development of computer assisted intervention systems. However, complex image conditions, such as intensity inhomogeneity, noise and weak object boundary, often cause considerable difficulties in medical image segmentation. To cope with these difficulties, we propose a novel robust statistics driven volume-scalable active contour framework, to extract desired object boundary from magnetic resonance (MR) and computed tomography (CT) imagery in 3D. METHODS: We define an energy functional in terms of the initial seeded labels and two fitting functions that are derived from object local robust statistics features. This energy is then incorporated into a level set scheme which drives the active contour evolving and converging at the desired position of the object boundary. Due to the local robust statistics and the volume scaling function in the energy fitting term, the object features in local volumes are learned adaptively to guide the motion of the contours, which thereby guarantees the capability of our method to cope with intensity inhomogeneity, noise and weak boundary. In addition, the initialization of active contour is simplified by select several seeds in the object and/or background to eliminate the sensitivity to initialization. RESULTS: The proposed method was applied to extensive public available volumetric medical images with challenging image conditions. The segmentation results of various anatomical structures, such as white matter (WM), atrium, caudate nucleus and brain tumor, were evaluated quantitatively by comparing with the corresponding ground truths. It was found that the proposed method achieves consistent and coherent segmentation accuracy of 0.9246 ± 0.0068 for WM, 0.9043 ± 0.0131 for liver tumors, 0.8725 ± 0.0374 for caudate nucleus, 0.8802 ± 0.0595 for brain tumors, etc., measured by Dice similarity coefficients value for the overlap between the algorithm one and the ground truth. Further comparative experimental results showed desirable performances of the proposed method over several well-known segmentation methods in terms of accuracy and robustness. CONCLUSION: We proposed an approach to accurate segment volumetric medical images with complex conditions. The accuracy of segmentation, robustness to noise and contour initialization were validated on the basis of extensive MR and CT volumes.

A Visualization System for Interactive Exploration of the Cardiac Anatomy.

Because of the complex and fine structure, visualization of the heart still remains a challenging task, which makes it an active research topic. In this paper, we present a visualization system for medical data, which takes advantage of the recent graphics processing unit (GPU) and can provide real-time cardiac visualization. This work focuses on investigating the anatomical structure visualization of the human heart, which is fundamental to the cardiac visualization, medical training and diagnosis assistance. Several state-of-the-art cardiac visualization methods are integrated into the proposed system and a task specified visualization method is proposed. In addition, auxiliary tools are provided to generate user specified visualization results. The contributions of our work lie in two-fold: for doctors and medical staff, the system can provide task specified visualization with interactive visualization tools; for researchers, the proposed platform can serve as a baseline for comparing different rendering methods and can easily incorporate new rendering methods. Experimental results show that the proposed system can provide favorable cardiac visualization results in terms of both effectiveness and efficiency.

Neuron anatomy structure reconstruction based on a sliding filter.

BACKGROUND: Reconstruction of neuron anatomy structure is a challenging and important task in neuroscience. However, few algorithms can automatically reconstruct the full structure well without manual assistance, making it essential to develop new methods for this task. METHODS: This paper introduces a new pipeline for reconstructing neuron anatomy structure from 3-D microscopy image stacks. This pipeline is initialized with a set of seeds that were detected by our proposed Sliding Volume Filter (SVF), given a non-circular cross-section of a neuron cell. Then, an improved open curve snake model combined with a SVF external force is applied to trace the full skeleton of the neuron cell. A radius estimation method based on a 2D sliding band filter is developed to fit the real edge of the cross-section of the neuron cell. Finally, a surface reconstruction method based on non-parallel curve networks is used to generate the neuron cell surface to finish this pipeline. RESULTS: The proposed pipeline has been evaluated using publicly available datasets. The results show that the proposed method achieves promising results in some datasets from the DIgital reconstruction of Axonal and DEndritic Morphology (DIADEM) challenge and new BigNeuron project. CONCLUSION: The new pipeline works well in neuron tracing and reconstruction. It can achieve higher efficiency, stability and robustness in neuron skeleton tracing. Furthermore, the proposed radius estimation method and applied surface reconstruction method can obtain more accurate neuron anatomy structures.

Multiview stereo and silhouette fusion via minimizing generalized reprojection error.

Accurate reconstruction of 3D geometrical shape from a set of calibrated 2D multiview images is an active yet challenging task in computer vision. The existing multiview stereo methods usually perform poorly in recovering deeply concave and thinly protruding structures, and suffer from several common problems like slow convergence, sensitivity to initial conditions, and high memory requirements. To address these issues, we propose a two-phase optimization method for generalized reprojection error minimization (TwGREM), where a generalized framework of reprojection error is proposed to integrate stereo and silhouette cues into a unified energy function. For the minimization of the function, we first introduce a convex relaxation on 3D volumetric grids which can be efficiently solved using variable splitting and Chambolle projection. Then, the resulting surface is parameterized as a triangle mesh and refined using surface evolution to obtain a high-quality 3D reconstruction. Our comparative experiments with several state-of-the-art methods show that the performance of TwGREM based 3D reconstruction is among the highest with respect to accuracy and efficiency, especially for data with smooth texture and sparsely sampled viewpoints.

Bright field microscopic cells counting method for BEVS using nonlinear convergence index sliding band filter.

BACKGROUND: The Baculovirus Expression Vector System (BEVS) is a very popular expression vector system in gene engineering. An effective host cell line cultivation protocol can facilitate the baculovirus preparation and following experiments. However, the counting of the number of host cells in the protocol is usually performed by manual observation with microscopy, which is time consuming and labor intensive work, and prone to errors for one person or between different individuals. This study aims at giving a bright field insect cells counting protocol to help improve the efficient of BEVS. METHOD: To develop a reliable and accurate counting method for the host cells in the bright field, such as Sf9 insect cells, a novel method based on a nonlinear Transformed Sliding Band Filter (TSBF) was proposed. And 3 collaborators counted cells at the same time to produce the ground truth for evaluation. The performance of TSBF method was evaluated with the image datasets of Sf9 insect cells according to the different periods of cell cultivation on the cell density, error rate and growth curve. RESULTS: The average error rate of our TSBF method is 2.21% on average, ranging from 0.89% to 3.97%, which exhibited an excellent performance with its high accuracy in lower error rate compared with traditional methods and manual counting. And the growth curve was much the manual method well. CONCLUSION: Results suggest the proposed TSBF method can detect insect cells with low error rate, and it is suitable for the counting task in BEVS to take the place of manual counting by humans. Growth curve results can reflect the cells' growth manner, which was generated by our proposed TSBF method in this paper can reflected the similar manner with it's from the manual method. All of these proven that the proposed insect cell counting method can clearly improve the efficiency of BEVS.

TTN: Topological Transformer Network for Automated Coronary Artery Branch Labeling in Cardiac CT Angiography.

OBJECTIVE: Existing methods for automated coronary artery branch labeling in cardiac CT angiography face two limitations: 1) inability to model overall correlation of branches, since differences between branches cannot be captured directly. 2) a serious class imbalance between main and side branches. METHODS AND PROCEDURES: Inspired by the application of Transformer in sequence data, we propose a topological Transformer network (TTN), which solves the vessel branch labeling from a novel perspective of sequence labeling learning. TTN detects differences between branches by establishing their overall correlation. A topological encoding that represents the positions of vessel segments in the artery tree, is proposed to assist the model in classifying branches. Also, a segment-depth loss is introduced to solve the class imbalance between main and side branches. RESULTS: On a dataset with 325 CCTA, our method obtains the best overall result on all branches, the best result on side branches, and a competitive result on main branches. CONCLUSION: TTN solves two limitations in existing methods perfectly, thus achieving the best result in coronary artery branch labeling task. It is the first Transformer based vessel branch labeling method and is notably different from previous methods. CLINICAL IMPACT: This Pre-Clinical Research can be integrated into a computer-aided diagnosis system to generate cardiovascular disease diagnosis report, assisting clinicians in locating the atherosclerotic plaques.

Boosting knowledge diversity, accuracy, and stability via tri-enhanced distillation for domain continual medical image segmentation.

Domain continual medical image segmentation plays a crucial role in clinical settings. This approach enables segmentation models to continually learn from a sequential data stream across multiple domains. However, it faces the challenge of catastrophic forgetting. Existing methods based on knowledge distillation show potential to address this challenge via a three-stage process: distillation, transfer, and fusion. Yet, each stage presents its unique issues that, collectively, amplify the problem of catastrophic forgetting. To address these issues at each stage, we propose a tri-enhanced distillation framework. (1) Stochastic Knowledge Augmentation reduces redundancy in knowledge, thereby increasing both the diversity and volume of knowledge derived from the old network. (2) Adaptive Knowledge Transfer selectively captures critical information from the old knowledge, facilitating a more accurate knowledge transfer. (3) Global Uncertainty-Guided Fusion introduces a global uncertainty view of the dataset to fuse the old and new knowledge with reduced bias, promoting a more stable knowledge fusion. Our experimental results not only validate the feasibility of our approach, but also demonstrate its superior performance compared to state-of-the-art methods. We suggest that our innovative tri-enhanced distillation framework may establish a robust benchmark for domain continual medical image segmentation.

Curriculum label distribution learning for imbalanced medical image segmentation.

Label distribution learning (LDL) has the potential to resolve boundary ambiguity in semantic segmentation tasks. However, existing LDL-based segmentation methods suffer from severe label distribution imbalance: the ambiguous label distributions contain a small fraction of the data, while the unambiguous label distributions occupy the majority of the data. The imbalanced label distributions induce model-biased distribution learning and make it challenging to accurately predict ambiguous pixels. In this paper, we propose a curriculum label distribution learning (CLDL) framework to address the above data imbalance problem by performing a novel task-oriented curriculum learning strategy. Firstly, the region label distribution learning (R-LDL) is proposed to construct more balanced label distributions and improves the imbalanced model learning. Secondly, a novel learning curriculum (TCL) is proposed to enable easy-to-hard learning in LDL-based segmentation by decomposing the segmentation task into multiple label distribution estimation tasks. Thirdly, the prior perceiving module (PPM) is proposed to effectively connect easy and hard learning stages based on the priors generated from easier stages. Benefiting from the balanced label distribution construction and prior perception, the proposed CLDL effectively conducts a curriculum learning-based LDL and significantly improves the imbalanced learning. We evaluated the proposed CLDL using the publicly available BRATS2018 and MM-WHS2017 datasets. The experimental results demonstrate that our method significantly improves different segmentation metrics compared to many state-of-the-art methods. The code will be available.1.

Ambiguity-aware breast tumor cellularity estimation via self-ensemble label distribution learning.

In this work, we address the task of tumor cellularity (TC) estimation with a novel framework based on the label distribution learning (LDL) paradigm. We propose a self-ensemble label distribution learning framework (SLDL) to resolve the challenges of existing LDL-based methods, including difficulties for inter-rater ambiguity exploitation, proper and flexible label distribution generation, and accurate TC value recovery. The proposed SLDL makes four main contributions which have been demonstrated to be quite effective in numerous experiments. First, we propose an expertness-aware conditional VAE for diversified single-rater modeling and an attention-based multi-rater fusion strategy that enables effective inter-rater ambiguity exploitation. Second, we propose a template-based label distribution generation method that is tailored for the TC estimation task and constructs label distributions based on the annotation priors. Third, we propose a novel restricted distribution loss, significantly improving the TC value estimation by effectively regularizing the learning with unimodal loss and regression loss. Fourth, to the best of our knowledge, we are the first to simultaneously leverage inter-rater and intra-rater variability to address the label ambiguity issue in the breast tumor cellularity estimation tasks. The experimental results on the public BreastPathQ dataset demonstrate that the SLDL outperforms the existing methods by a large margin and achieves new state-of-the-art results in the TC estimation task. The code will be available from https://github.com/PerceptionComputingLab/ULTRA.

ColonNet: A novel polyp segmentation framework based on LK-RFB and GPPD.

Colorectal cancer (CRC) holds the distinction of being the most prevalent malignant tumor affecting the digestive system. It is a formidable global health challenge, as it ranks as the fourth leading cause of cancer-related fatalities around the world. Despite considerable advancements in comprehending and addressing colorectal cancer (CRC), the likelihood of recurring tumors and metastasis remains a major cause of high morbidity and mortality rates during treatment. Currently, colonoscopy is the predominant method for CRC screening. Artificial intelligence has emerged as a promising tool in aiding the diagnosis of polyps, which have demonstrated significant potential. Unfortunately, most segmentation methods face challenges in terms of limited accuracy and generalization to different datasets, especially the slow processing and analysis speed has become a major obstacle. In this study, we propose a fast and efficient polyp segmentation framework based on the Large-Kernel Receptive Field Block (LK-RFB) and Global Parallel Partial Decoder(GPPD). Our proposed ColonNet has been extensively tested and proven effective, achieving a DICE coefficient of over 0.910 and an FPS of over 102 on the CVC-300 dataset. In comparison to the state-of-the-art (SOTA) methods, ColonNet outperforms or achieves comparable performance on five publicly available datasets, establishing a new SOTA. Compared to state-of-the-art methods, ColonNet achieves the highest FPS (over 102 FPS) while maintaining excellent segmentation results, achieving the best or comparable performance on the five public datasets. The code will be released at: https://github.com/SPECTRELWF/ColonNet.