An unrolled neural network for accelerated dynamic MRI based on second-order half-quadratic splitting model.

The reconstruction of dynamic magnetic resonance images from incomplete k-space data has sparked significant research interest due to its potential to reduce scan time. However, traditional iterative optimization algorithms fail to faithfully reconstruct images at higher acceleration factors and incur long reconstruction time. Furthermore, end-to-end deep learning-based reconstruction algorithms suffer from large model parameters and lack robustness in the reconstruction results. Recently, unrolled deep learning models, have shown immense potential in algorithm stability and applicability flexibility. In this paper, we propose an unrolled deep learning network based on a second-order Half-Quadratic Splitting(HQS) algorithm, where the forward propagation process of this framework strictly follows the computational flow of the HQS algorithm. In particular, we propose a degradation-aware module by associating random sampling patterns with intermediate variables to guide the iterative process. We introduce the Information Fusion Transformer(IFT) to extract both local and non-local prior information from image sequences, thereby removing aliasing artifacts resulting from random undersampling. Finally, we impose low-rank constraints within the HQS algorithm to further enhance the reconstruction results. The experiments demonstrate that each component module of our proposed model contributes to the improvement of the reconstruction task. Our proposed method achieves comparably satisfying performance to the state-of-the-art methods and it exhibits excellent generalization capabilities across different sampling masks. At the low acceleration factor, there is a 0.7% enhancement in the PSNR. Furthermore, when the acceleration factor reached 8 and 12, the PSNR achieves an improvement of 3.4% and 5.8% respectively.

Macroscopic brain dynamics beyond contralateral primary motor cortex for movement prediction.

This study investigates the complex relationship between upper limb movement direction and macroscopic neural signals in the brain, which is critical for understanding brain-computer interfaces (BCI). Conventional BCI research has primarily focused on a local area, such as the contralateral primary motor cortex (M1), relying on the population-based decoding method with microelectrode arrays. In contrast, macroscopic approaches such as electroencephalography (EEG) and magnetoencephalography (MEG) utilize numerous electrodes to cover broader brain regions. This study probes the potential differences in the mechanisms of microscopic and macroscopic methods. It is important to determine which neural activities effectively predict movements. To investigate this, we analyzed MEG data from nine right-handed participants while performing arm-reaching tasks. We employed dynamic statistical parametric mapping (dSPM) to estimate source activity and built a decoding model composed of long short-term memory (LSTM) and a multilayer perceptron to predict movement trajectories. This model achieved a high correlation coefficient of 0.79 between actual and predicted trajectories. Subsequently, we identified brain regions sensitive to predicting movement direction using the integrated gradients (IG) method, which assesses the predictive contribution of each source activity. The resulting salience map demonstrated a distribution without significant differences across motor-related regions, including M1. Predictions based solely on M1 activity yielded a correlation coefficient of 0.42, nearly half as effective as predictions incorporating all source activities. This suggests that upper limb movements are influenced by various factors such as movement coordination, planning, body and target position recognition, and control, beyond simple muscle activity. All of the activities are needed in the decoding model using macroscopic signals. Our findings also revealed that contralateral and ipsilateral hemispheres contribute equally to movement prediction, implying that BCIs could potentially benefit patients with brain damage in the contralateral hemisphere by utilizing brain signals from the ipsilateral hemisphere. In conclusion, this study demonstrates that macroscopic activity from large brain regions significantly contributes to predicting upper limb movement. Non-invasive BCI systems would require a comprehensive collection of neural signals from multiple brain regions.

Self-Trained Convolutional Neural Network (CNN) for Tuberculosis Diagnosis in Medical Imaging.

Background Tuberculosis (TB) is a serious infectious disease that primarily affects the lungs. Despite advancements in the medical industry, TB remains a significant global health challenge. Early and accurate detection of TB is crucial for effective treatment and reducing transmission. This article presents a deep learning approach using convolutional neural networks (CNNs) to improve TB detection in chest X-ray images. Methods For the dataset, we collected 7000 images from Kaggle.com, of which 3500 exhibit tuberculosis evidence and the remaining 3500 are normal. Preprocessing techniques such as wavelet transformation, contrast-limited adaptive histogram equalisation (CLAHE), and gamma correction were applied to enhance the image quality. Random flipping, random rotation, random resizing, and random rescaling were among the techniques employed to increase dataset variability and model robustness. Convolutional, max-pooling, flatten, and dense layers comprised the CNN model architecture. For binary classification, sigmoid activation was utilised in the output layer and rectified linear unit (ReLU) activation in the input and hidden layers. Results The CNN model achieved an accuracy of ~96.57% in detecting TB from chest X-ray images, demonstrating the effectiveness of deep learning, particularly CNNs, in this application. Self-trained CNNs have optimised the results as compared to the transfer learning of various pre-trained models. Conclusion This study shows how well deep learning-in particular, CNNs-performs in the identification of tuberculosis. Subsequent efforts have to give precedence to optimising the model by obtaining more extensive datasets from the local hospitals and localities, which are vulnerable to TB, and stress the possibility of augmenting diagnostic knowledge in medical imaging via machine learning methodologies.

Advancing critical care recovery: The pivotal role of machine learning in early detection of intensive care unit-acquired weakness.

This editorial explores the significant challenge of intensive care unit-acquired weakness (ICU-AW), a prevalent condition affecting critically ill patients, characterized by profound muscle weakness and complicating patient recovery. Highlighting the paradox of modern medical advances, it emphasizes the urgent need for early identification and intervention to mitigate ICU-AW's impact. Innovatively, the study by Wang et al is showcased for employing a multilayer perceptron neural network model, achieving high accuracy in predicting ICU-AW risk. This advancement underscores the potential of neural network models in enhancing patient care but also calls for continued research to address limitations and improve model applicability. The editorial advocates for the development and validation of sophisticated predictive tools, aiming for personalized care strategies to reduce ICU-AW incidence and severity, ultimately improving patient outcomes in critical care settings.

Prediction equations for detecting COVID-19 infection using basic laboratory parameters.

Objectives: Coronavirus disease 2019 (COVID-19) emerged as a global pandemic during 2019 to 2022. The gold standard method of detecting this disease is reverse transcription-polymerase chain reaction (RT-PCR). However, RT-PCR has a number of shortcomings. Hence, the objective is to propose a cheap and effective method of detecting COVID-19 infection by using machine learning (ML) techniques, which encompasses five basic parameters as an alternative to the costly RT-PCR. Materials and Methods: Two machine learning-based predictive models, namely, Artificial Neural Network (ANN) and Multivariate Adaptive Regression Splines (MARS), are designed for predicting COVID-19 infection as a cheaper and simpler alternative to RT-PCR utilizing five basic parameters [i.e., age, total leucocyte count, red blood cell count, platelet count, C-reactive protein (CRP)]. Each of these parameters was studied, and correlation is drawn with COVID-19 diagnosis and progression. These laboratory parameters were evaluated in 171 patients who presented with symptoms suspicious of COVID-19 in a hospital at Kharagpur, India, from April to August 2022. Out of a total of 171 patients, 88 and 83 were found to be COVID-19-negative and COVID-19-positive, respectively. Results: The accuracies of the predicted class are found to be 97.06% and 91.18% for ANN and MARS, respectively. CRP is found to be the most significant input parameter. Finally, two predictive mathematical equations for each ML model are provided, which can be quite useful to detect the COVID-19 infection easily. Conclusion: It is expected that the present study will be useful to the medical practitioners for predicting the COVID-19 infection in patients based on only five very basic parameters.

Optimization of transfer learning based on source sample selection in Euclidean space for P300-based brain-computer interfaces.

Introduction: Event-related potentials (ERPs), such as P300, are widely utilized for non-invasive monitoring of brain activity in brain-computer interfaces (BCIs) via electroencephalogram (EEG). However, the non-stationary nature of EEG signals and different data distributions among subjects create significant challenges for implementing real-time P300-based BCIs. This requires time-consuming calibration and a large number of training samples. Methods: To address these challenges, this study proposes a transfer learning-based approach that uses a convolutional neural network for high-level feature extraction, followed by Euclidean space data alignment to ensure similar distributions of extracted features. Furthermore, a source selection technique based on the Euclidean distance metric was applied to measure the distance between each source feature sample and a reference point from the target domain. The samples with the lowest distance were then chosen to increase the similarity between source and target datasets. Finally, the transferred features are applied to a discriminative restricted Boltzmann machine classifier for P300 detection. Results: The proposed method was evaluated on the state-of-the-art BCI Competition III dataset II and rapid serial visual presentation dataset. The results demonstrate that the proposed technique achieves an average accuracy of 97% for both online and offline after 15 repetitions, which is comparable to the state-of-the-art methods. Notably, the proposed approach requires <½ of the training samples needed by previous studies. Discussion: Therefore, this technique offers an efficient solution for developing ERP-based BCIs with robust performance against reduced a number of training data.

Hazard evaluation of goaf based on DBO algorithm coupled with BP neural network.

China is rich in mineral resources, and problems of goaf formed in the process of resource exploitation are serious obstacle to the development of China's economic, so it is of great significance for the assessment and management of goafs. This paper introduces emerging dung beetle optimizer (DBO) algorithm and establishes DBO-BP (back-propagation) model, at the same time, it is compared with a series of heuristic algorithms coupled with BP neural network models: PSO (particle swarm optimization) - BP model, WOA (whale optimization algorithm) - BP model, and SSA (sparrow search algorithm) - BP model. Then they are applied to evaluate the hazard of goafs, the result shows that the DBO-BP model gets the highest train set accuracy, which is at least 2.7 % higher than other models, while the DBO-BP model obtains the highest test set accuracy, meanwhile its effectiveness and stability have also been proven. Finally we apply the established DBO-BP model to evaluate the hazard of the tungsten mine goaf of Yaogangshan in Hunan Province, and its excellent practicability was confirmed. This paper may provide a reference for the solution of nonlinear engineering problems.

Machine learning-based model to predict severe acute kidney injury after total aortic arch replacement for acute type A aortic dissection.

Background: Severe acute kidney injury (AKI) after total aortic arch replacement (TAAR) is related to adverse outcomes in patients with acute type A aortic dissection (ATAAD). However, the early prediction of severe AKI remains a challenge. This study aimed to develop a novel model to predict severe AKI after TAAR in ATAAD patients using machine learning algorithms. Methods: A total of 572 ATAAD patients undergoing TAAR were enrolled in this retrospective study, and randomly divided into a training set (70 %) and a validation set (30 %). Lasso regression, support vector machine-recursive feature elimination and random forest algorithms were used to screen indicators for severe AKI (defined as AKI stage III) in the training set, respectively. Then the intersection indicators were selected to construct models through artificial neural network (ANN) and logistic regression. The AUC-ROC curve was employed to ascertain the prediction efficacy of the ANN and logistic regression models. Results: The incidence of severe AKI after TAAR was 22.9 % among ATAAD patients. The intersection predictors identified by different machine learning algorithms were baseline serum creatinine and ICU admission variables, including serum cystatin C, procalcitonin, aspartate transaminase, platelet, lactic dehydrogenase, urine N-acetyl-ß-d-glucosidase and Acute Physiology and Chronic Health Evaluation II score. The ANN model showed a higher AUC-ROC than logistic regression (0.938 vs 0.908, p < 0.05). Furthermore, the ANN model could predict 89.1 % of severe AKI cases beforehand. In the validation set, the superior performance of the ANN model was further confirmed in terms of discrimination ability (AUC = 0.916), calibration curve analysis and decision curve analysis. Conclusion: This study developed a novel and reliable clinical prediction model for severe AKI after TAAR in ATAAD patients using machine learning algorithms. Importantly, the ANN model showed a higher predictive ability for severe AKI than logistic regression.

Optimization of teacher evaluation indicator system based on fuzzy-DEMATEL-BP.

The establishment of a reasonable teacher evaluation indicator system has always been a research hotspot in teacher evaluation. Simplifying and essential indicators are the foundation for maintaining the speed and accuracy of teacher evaluation. Therefore, optimizing indicators in a convincing and interpretable manner becomes highly important. Due to the complex causal relationships and fuzzy uncertainties among teacher evaluation indicators, this paper proposes a method that combines the Triangular Fuzzy Decision-making Trial and Evaluation Laboratory Model (Fuzzy-DEMATEL) with Backpropagation Neural Network (BP) to optimize the complexity of assessment systems and identify key indicators, thereby establishing a precise and rational teacher evaluation index system. DEMATEL allows us to simplify and analyze the complex causal relationships among assessment indicators, mapping them into a causal relationship diagram. Fuzzy logic effectively handles the fuzzy and uncertain relationships among the indicators, converting fuzzy information into computable forms. The BP neural network is a data training model that, from an objective data perspective, compensates for subjective errors, thereby optimizing our indicator results. In addition, we conducted empirical and comparative research using relevant data from the TIMSS 2019 dataset, and found that this method can reduce the original indicator quantity by approximately 28 %-30 %, compared to methods such as Multi-Criteria Decision Making (MCDM), the results are superior and the indicators are more accurate.

Improved STNNet, A benchmark for detection, tracking, and counting crowds using Drones.

In computer vision, navigating multi-object tracking in crowded scenes poses a fundamental challenge with broad applications ranging from surveillance systems to autonomous vehicles. Traditional tracking methods encounter difficulties associating noisy object detections and maintaining consistent labels across frames, particularly in scenarios like video surveillance for crowd control and public safety. This paper introduces 'Improved Space-Time Neighbor-Aware Network (STNNet),' an advanced framework for online Multi-Object Tracking (MOT) designed to address these challenges. Expanding upon the foundational STNNet architecture, our enhanced model incorporates deep reinforcement learning techniques to refine decision-making. By framing the online MOT problem as a Markov Decision Process (MDP), Improved STNNet learns a sophisticated policy for data association, adeptly handling complexities such as object birth/death and appearance/disappearance as state transitions within the MDP. Through extensive experimentation on benchmark datasets, including the MOT Challenge, our proposed Improved STNNet demonstrates superior performance, surpassing existing methods in demanding, crowded scenarios. This study showcases the effectiveness of our approach and lays the groundwork for advancing real-time video analysis applications, particularly in dynamic, crowded environments. Additionally, we utilize the dataset provided by STNNET for density map estimation, forming the basis for our research.•Develop an advanced framework for online Multi-Object Tracking (MOT) to address crowded scene challenges, particularly improving object association and label consistency across frames.•Explore integrating Deep Reinforcement learning techniques into the MOT framework, framing the problem as an MDP to refine decision-making and handle complexities such as object birth or death and appearance or disappearance transitions.

Compositional transferability of deep learning potentials: a case study for LiCl-KCl melt.

CONTEXT: One of the crucial issues related to machine learning potentials is the formation of representative dataset. For multicomponent systems, it is a general methodology to scan the composition range with a certain step. However, there is a lack of information on the compositional transferability of machine learning potentials. In this paper, we extend the knowledge in this area by studying the transferability of deep learning potential over the range of compositions of LiCl-KCl molten mixtures. The training dataset was formed using only the near-eutectic composition of 60% LiCl-40% KCl. Then, we tested the ability of the model to predict physicochemical properties of the melts far from the reference composition. It was found that for the composition range from 0 to 100% of LiCl, the calculated properties concur closely with those of other studies and ab initio calculations. Therefore, the model shows prominent non-intuitive compositional transferability. Moreover, the solid states and solid-liquid coexistence were reproduced. The calculated melting temperatures of LiCl and KCl show the errors of 6.6% and 0.4%, respectively. We argue that such good transferability stems from the local structure configurations that are typical both for pure LiCl and for pure KCl which are implicitly presented in the training dataset because of local fluctuations in composition. METHODS: To collect the data for the initial dataset, density functional theory was employed. Then, the DeePMD package was used to train a neural network potential. To calculate the properties of the melts, standard equilibrium and non-equilibrium molecular dynamic approaches were utilized.

Prediction of leukemia peptides using convolutional neural network and protein compositions.

Leukemia is a type of blood cell cancer that is in the bone marrow's blood-forming cells. Two types of Leukemia are acute and chronic; acute enhances fast and chronic growth gradually which are further classified into lymphocytic and myeloid leukemias. This work evaluates a unique deep convolutional neural network (CNN) classifier that improves identification precision by carefully examining concatenated peptide patterns. The study uses leukemia protein expression for experiments supporting two different techniques including independence and applied cross-validation. In addition to CNN, multilayer perceptron (MLP), gated recurrent unit (GRU), and recurrent neural network (RNN) are applied. The experimental results show that the CNN model surpasses competitors with its outstanding predictability in independent and cross-validation testing applied on different features extracted from protein expressions such as amino acid composition (AAC) with a group of AAC (GAAC), tripeptide composition (TPC) with a group of TPC (GTPC), and dipeptide composition (DPC) for calculating its accuracies with their receiver operating characteristic (ROC) curve. In independence testing, a feature expression of AAC and a group of GAAC are applied using MLP and CNN modules, and ROC curves are achieved with overall 100% accuracy for the detection of protein patterns. In cross-validation testing, a feature expression on a group of AAC and GAAC patterns achieved 98.33% accuracy which is the highest for the CNN module. Furthermore, ROC curves show a 0.965% extraordinary result for the GRU module. The findings show that the CNN model is excellent at figuring out leukemia illnesses from protein expressions with higher accuracy.

Identification of Calculous Pyonephrosis by CT-Based Radiomics and Deep Learning.

Urgent detection of calculous pyonephrosis is crucial for surgical planning and preventing severe outcomes. This study aims to evaluate the performance of computed tomography (CT)-based radiomics and a three-dimensional convolutional neural network (3D-CNN) model, integrated with independent clinical factors, to identify patients with calculous pyonephrosis. We recruited 182 patients receiving either percutaneous nephrostomy tube placement or percutaneous nephrolithotomy for calculous hydronephrosis or pyonephrosis. The regions of interest were manually delineated on plain CT images and the CT attenuation value (HU) was measured. Radiomics analysis was performed using least absolute shrinkage and selection operator (LASSO). A 3D-CNN model was also developed. The better-performing machine-learning model was combined with independent clinical factors to build a comprehensive clinical machine-learning model. The performance of these models was assessed using receiver operating characteristic analysis and decision curve analysis. Fever, blood neutrophils, and urine leukocytes were independent risk factors for pyonephrosis. The radiomics model showed higher area under the curve (AUC) than the 3D-CNN model and HU (0.876 vs. 0.599, 0.578; p = 0.003, 0.002) in the testing cohort. The clinical machine-learning model surpassed the clinical model in both the training (0.975 vs. 0.904, p = 0.019) and testing (0.967 vs. 0.889, p = 0.045) cohorts.

Leverage Effective Deep Learning Searching Method for Forensic Age Estimation.

Dental age estimation is extensively employed in forensic medicine practice. However, the accuracy of conventional methods fails to satisfy the need for precision, particularly when estimating the age of adults. Herein, we propose an approach for age estimation utilizing orthopantomograms (OPGs). We propose a new dental dataset comprising OPGs of 27,957 individuals (16,383 females and 11,574 males), covering an age range from newborn to 93 years. The age annotations were meticulously verified using ID card details. Considering the distinct nature of dental data, we analyzed various neural network components to accurately estimate age, such as optimal network depth, convolution kernel size, multi-branch architecture, and early layer feature reuse. Building upon the exploration of distinctive characteristics, we further employed the widely recognized method to identify models for dental age prediction. Consequently, we discovered two sets of models: one exhibiting superior performance, and the other being lightweight. The proposed approaches, namely AGENet and AGE-SPOS, demonstrated remarkable superiority and effectiveness in our experimental results. The proposed models, AGENet and AGE-SPOS, showed exceptional effectiveness in our experiments. AGENet outperformed other CNN models significantly by achieving outstanding results. Compared to Inception-v4, with the mean absolute error (MAE) of 1.70 and 20.46 B FLOPs, our AGENet reduced the FLOPs by 2.7×. The lightweight model, AGE-SPOS, achieved an MAE of 1.80 years with only 0.95 B FLOPs, surpassing MobileNetV2 by 0.18 years while utilizing fewer computational operations. In summary, we employed an effective DNN searching method for forensic age estimation, and our methodology and findings hold significant implications for age estimation with oral imaging.

Integrating Convolutional Neural Networks with Attention Mechanisms for Magnetic Resonance Imaging-Based Classification of Brain Tumors.

The application of magnetic resonance imaging (MRI) in the classification of brain tumors is constrained by the complex and time-consuming characteristics of traditional diagnostics procedures, mainly because of the need for a thorough assessment across several regions. Nevertheless, advancements in deep learning (DL) have facilitated the development of an automated system that improves the identification and assessment of medical images, effectively addressing these difficulties. Convolutional neural networks (CNNs) have emerged as steadfast tools for image classification and visual perception. This study introduces an innovative approach that combines CNNs with a hybrid attention mechanism to classify primary brain tumors, including glioma, meningioma, pituitary, and no-tumor cases. The proposed algorithm was rigorously tested with benchmark data from well-documented sources in the literature. It was evaluated alongside established pre-trained models such as Xception, ResNet50V2, Densenet201, ResNet101V2, and DenseNet169. The performance metrics of the proposed method were remarkable, demonstrating classification accuracy of 98.33%, precision and recall of 98.30%, and F1-score of 98.20%. The experimental finding highlights the superior performance of the new approach in identifying the most frequent types of brain tumors. Furthermore, the method shows excellent generalization capabilities, making it an invaluable tool for healthcare in diagnosing brain conditions accurately and efficiently.

Two-Stream Convolutional Neural Networks for Breathing Pattern Classification: Real-Time Monitoring of Respiratory Disease Patients.

A two-stream convolutional neural network (TCNN) for breathing pattern classification has been devised for the continuous monitoring of patients with infectious respiratory diseases. The TCNN consists of a convolutional neural network (CNN)-based autoencoder and classifier. The encoder of the autoencoder generates deep compressed feature maps, which contain the most important information constituting data. These maps are concatenated with feature maps generated by the classifier to classify breathing patterns. The TCNN, single-stream CNN (SCNN), and state-of-the-art classification models were applied to classify four breathing patterns: normal, slow, rapid, and breath holding. The input data consisted of chest tissue hemodynamic responses measured using a wearable near-infrared spectroscopy device on 14 healthy adult participants. Among the classification models evaluated, random forest had the lowest classification accuracy at 88.49%, while the TCNN achieved the highest classification accuracy at 94.63%. In addition, the proposed TCNN performed 2.6% better in terms of classification accuracy than an SCNN (without an autoencoder). Moreover, the TCNN mitigates the issue of declining learning performance with increasing network depth, as observed in the SCNN model. These results prove the robustness of the TCNN in classifying breathing patterns despite using a significantly smaller number of parameters and computations compared to state-of-the-art classification models.

MuCoCP: A priori chemical knowledge-based multimodal contrastive learning pre-trained neural network for the prediction of cyclic peptide membrane penetration ability.

MOTIVATION: There has been a burgeoning interest in cyclic peptide therapeutics due to their various outstanding advantages and strong potential for drug formation. However, it is undoubtedly costly and inefficient to use traditional wet lab methods to clarify their biological activities. Using Artificial Intelligence instead is a more energy-efficient and faster approach. MuCoCP aims to build a complete pre-trained model for extracting potential features of cyclic peptides, which can be fine-tuned to accurately predict cyclic peptide bioactivity on various downstream tasks. To maximize its effectiveness, we use a novel data augmentation method based on a priori chemical knowledge and multiple unsupervised training objective functions to greatly improve the information-grabbing ability of the model. RESULTS: To assay the efficacy of the model, we conducted validation on the membrane-permeability of cyclic peptides which achieved an accuracy of 0.87 and R-squared of 0.503 on CycPeptMPDB using semi-supervised training and obtained an accuracy of 0.84 and R-squared of 0.384 using a model with frozen parameters on an external dataset. This result has achieved state-of-the-art (SOTA), which substantiates the stability and generalization capability of MuCoCP. It means that MuCoCP can fully explore the high-dimensional information of cyclic peptides and make accurate predictions on downstream bioactivity tasks, which will serve as a guide for the future de novo design of cyclic peptide drugs and promote the development of cyclic peptide drugs. AVAILABILITY: All code used in our proposed method can be found at https://github.com/lennonyu11234/MuCoCP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics.

PIDiff: Physics informed diffusion model for protein pocket-specific 3D molecular generation.

Designing drugs capable of binding to the structure of target proteins for treating diseases is essential in drug development. Recent remarkable advancements in geometric deep learning have led to unprecedented progress in three-dimensional (3D) generation of ligands that can bind to the protein pocket. However, most existing methods primarily focus on modeling the geometric information of ligands in 3D space. Consequently, these methods fail to consider that the binding of proteins and ligands is a phenomenon driven by intrinsic physicochemical principles. Motivated by this understanding, we propose PIDiff, a model for generating molecules by accounting in the physicochemical principles of protein-ligand binding. Our model learns not only the structural information of proteins and ligands but also to minimize the binding free energy between them. To evaluate the proposed model, we introduce an experimental framework that surpasses traditional assessment methods by encompassing various essential aspects for the practical application of generative models to actual drug development. The results confirm that our model outperforms baseline models on the CrossDocked2020 benchmark dataset, demonstrating its superiority. Through diverse experiments, we have illustrated the promising potential of the proposed model in practical drug development.

Model-based federated learning for accurate MR image reconstruction from undersampled k-space data.

Deep learning-based methods have achieved encouraging performances in the field of Magnetic Resonance (MR) image reconstruction. Nevertheless, building powerful and robust deep learning models requires collecting large and diverse datasets from multiple centers. This raises concerns about ethics and data privacy. Recently, federated learning has emerged as a promising solution, enabling the utilization of multi-center data without the need for data transfer between institutions. Despite its potential, existing federated learning methods face challenges due to the high heterogeneity of data from different centers. Aggregation methods based on simple averaging, which are commonly used to combine the client's information, have shown limited reconstruction and generalization capabilities. In this paper, we propose a Model-based Federated learning framework (ModFed) to address these challenges. ModFed has three major contributions: (1) Different from existing data-driven federated learning methods, ModFed designs attention-assisted model-based neural networks that can alleviate the need for large amounts of data on each client; (2) To address the data heterogeneity issue, ModFed proposes an adaptive dynamic aggregation scheme, which can improve the generalization capability and robustness of the trained neural network models; (3) ModFed incorporates a spatial Laplacian attention mechanism and a personalized client-side loss regularization to capture the detailed information for accurate image reconstruction. The effectiveness of the proposed ModFed is evaluated on three in-vivo datasets. Experimental results show that when compared to six existing state-of-the-art federated learning approaches, ModFed achieves better MR image reconstruction performance with increased generalization capability. Codes will be made available at https://github.com/ternencewu123/ModFed.

Efficient multi-stage feedback attention for diverse lesion in cancer image segmentation.

In the domain of Computer-Aided Diagnosis (CAD) systems, the accurate identification of cancer lesions is paramount, given the life-threatening nature of cancer and the complexities inherent in its manifestation. This task is particularly arduous due to the often vague boundaries of cancerous regions, compounded by the presence of noise and the heterogeneity in the appearance of lesions, making precise segmentation a critical yet challenging endeavor. This study introduces an innovative, an iterative feedback mechanism tailored for the nuanced detection of cancer lesions in a variety of medical imaging modalities, offering a refining phase to adjust detection results. The core of our approach is the elimination of the need for an initial segmentation mask, a common limitation in iterative-based segmentation methods. Instead, we utilize a novel system where the feedback for refining segmentation is derived directly from the encoder-decoder architecture of our neural network model. This shift allows for more dynamic and accurate lesion identification. To further enhance the accuracy of our CAD system, we employ a multi-scale feedback attention mechanism to guide and refine predicted mask subsequent iterations. In parallel, we introduce a sophisticated weighted feedback loss function. This function synergistically combines global and iteration-specific loss considerations, thereby refining parameter estimation and improving the overall precision of the segmentation. We conducted comprehensive experiments across three distinct categories of medical imaging: colonoscopy, ultrasonography, and dermoscopic images. The experimental results demonstrate that our method not only competes favorably with but also surpasses current state-of-the-art methods in various scenarios, including both standard and challenging out-of-domain tasks. This evidences the robustness and versatility of our approach in accurately identifying cancer lesions across a spectrum of medical imaging contexts. Our source code can be found at https://github.com/dewamsa/EfficientFeedbackNetwork.