Independent Set Research Articles

Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets.

Purpose To determine whether the unsupervised domain adaptation (UDA) method with generated images improves the performance of a supervised learning (SL) model for prostate cancer (PCa) detection using multisite biparametric (bp) MRI datasets. Materials and Methods This retrospective study included data from 5150 patients (14 191 samples) collected across nine different imaging centers. A novel UDA method using a unified generative model was developed for PCa detection using multisite bpMRI datasets. This method translates diffusion-weighted imaging (DWI) acquisitions, including apparent diffusion coefficient (ADC) and individual diffusion-weighted (DW) images acquired using various b values, to align with the style of images acquired using b values recommended by Prostate Imaging Reporting and Data System (PI-RADS) guidelines. The generated ADC and DW images replace the original images for PCa detection. An independent set of 1692 test cases (2393 samples) was used for evaluation. The area under the receiver operating characteristic curve (AUC) was used as the primary metric, and statistical analysis was performed via bootstrapping. Results For all test cases, the AUC values for baseline SL and UDA methods were 0.73 and 0.79 (P < .001), respectively, for PCa lesions with PI-RADS score of 3 or greater and 0.77 and 0.80 (P < .001) for lesions with PI-RADS scores of 4 or greater. In the 361 test cases under the most unfavorable image acquisition setting, the AUC values for baseline SL and UDA were 0.49 and 0.76 (P < .001) for lesions with PI-RADS scores of 3 or greater and 0.50 and 0.77 (P < .001) for lesions with PI-RADS scores of 4 or greater. Conclusion UDA with generated images improved the performance of SL methods in PCa lesion detection across multisite datasets with various b values, especially for images acquired with significant deviations from the PI-RADS-recommended DWI protocol (eg, with an extremely high b value). Keywords: Prostate Cancer Detection, Multisite, Unsupervised Domain Adaptation, Diffusion-weighted Imaging, b Value Supplemental material is available for this article. © RSNA, 2024.

Staying Ahead of the Curve: The Case for Recovery Curves in Total Knee Arthroplasty

BackgroundSensor technology embedded within the total knee arthroplasty (TKA) implant has the potential to record data that can track recovery and provide diagnostic information. In this study, we introduce the concept of physical function recovery curve analytics, which are created from daily spatial-temporal gait metrics and step counts from a large cohort of TKA patients. MethodsIn our study population, 258 patients underwent a primary TKA with a smart implanted tibial extension between October 4, 2021, and July 15, 2022, by 33 surgeons. The average age was 63 years, with 138 (54%) women. All kinematic data was collected on a Health Insurance Portability and Accountability Act (HIPAA)-compliant cloud data management platform. ResultsSummaries of the gait parameters at 6 weeks are suggestive of differences between people over and under 65 years, with the older patients walking more slowly and having shorter stride lengths. The 6-week percentiles demonstrated a strong, linear correlation to the 12-week percentiles for each gait parameter, with correlation coefficients ranging from 0.87 to 0.92. ConclusionsA novel screening gait test at 6 weeks shows promising results for predicting patients who will likely have poor recovery based on at least 1 gait parameter recovery curve at 12 weeks with high sensitivity and specificity. A future study is needed to validate the screening tool with an independent set of patients.

Imaging of I Zw 18 by JWST

Context. The blue compact dwarf (BCD) galaxy I Zw 18 is one of the most metal-poor (Z ∼ 3% Z⊙) star-forming galaxies known in the local Universe. Since its discovery, the evolutionary status of this system has been at the center of numerous debates within the astronomical community. Aims. We aim to probe and resolve the stellar populations of I Zw 18 in the near-IR using JWST/NIRCam’s unprecedented imaging spatial resolution and sensitivity. Additionally, our goal is to derive the spatially resolved star formation history (SFH) of the galaxy within the last 1 Gyr, and to provide constraints for older epochs. Methods. We used the point spread function fitting photometry package DOLPHOT to measure positions and fluxes of point sources in the F115W and F200W filters’ images of I Zw 18, acquired as part of the JWST GTO ID 1233 (PI: Meixner). Furthermore, to derive I Zw 18’s SFH, we applied a state-of-the-art color-magnitude diagram (CMD) fitting technique (SFERA 2.0), using two independent sets of stellar models: PARSEC-COLIBRI and MIST. Results. Our analysis of I Zw 18’s CMD reveal three main stellar populations: one younger than ∼30 Myr, mainly associated with the northwest star-forming (SF) region; an intermediate-age population (∼100 − 800 Myr), associated with the southeast SF region; and a red and faint population, linked to the underlying halo of the galaxy, older than 1 Gyr and possibly as old as 13.8 Gyr. The main body of the galaxy shows a very low star formation rate (SFR) of ~10-4M⊙ yr−1 between 1 and 13.8 Gyr ago. In the last billion years, I Zw 18 shows an increasing trend, culminating in two strong bursts of SF around ∼10 and ∼100 Myr ago. Notably, I Zw 18 Component C mimics the evolution of the main body, but with lower SFRs on average. Conclusions. Our results confirm that I Zw 18 is populated by stars of all ages, without any major gaps. Thus, I Zw 18 is not a truly young galaxy, but rather a system characterized by an old underlying stellar halo, in agreement with what has been found in other BCDs by similar studies. The low SF activity exhibited at epochs older than 1 Gyr is in agreement with the “slow cooking" dwarf scenario proposed in the literature, and could have contributed to its low metal content. The galaxy is now experiencing its strongest episode of star formation (∼ 0.6 M⊙ yr−1) mainly located in the northwest region. A recent gravitational interaction between the main body and Component C is the most likely explanation for this starburst.

Automatic Transcranial Sonography-Based Classification of Parkinson's Disease Using a Novel Dual-Channel CNXV2-DANet.

Transcranial sonography (TCS) has been introduced to assess hyper-echogenicity in the substantia nigra of the midbrain for Parkinson's disease (PD); however, its subjective and resource-demanding nature has impeded its widespread application. An AI-empowered TCS-based PD classification tool is greatly demanding, yet relevant research is severely scarce. Therefore, we proposed a novel dual-channel CNXV2-DANet for TCS-based PD classification using a large cohort. A total of 1176 TCS images from 588 subjects were retrospectively enrolled from Beijing Tiantan Hospital, encompassing both the left and right side of the midbrain for each subject. The entire dataset was divided into a training/validation/testing set at a ratio of 70%/15%/15%. Development of the proposed CNXV2-DANet was performed on the training set with comparisons between the single-channel and dual-channel input settings; model evaluation was conducted on the independent testing set. The proposed dual-channel CNXV2-DANet was compared against three state-of-the-art networks (ConvNeXtV2, ConvNeXt, Swin Transformer). The results demonstrated that both CNXV2-DANet and ConvNeXt V2 performed more superiorly under dual-channel inputs than the single-channel input. The dual-channel CNXV2-DANet outperformed the single-channel, achieving superior average metrics for accuracy (0.839 ± 0.028), precision (0.849 ± 0.014), recall (0.845 ± 0.043), F1-score (0.820 ± 0.038), and AUC (0.906 ± 0.013) compared with the single channel metrics for accuracy (0.784 ± 0.037), precision (0.817 ± 0.090), recall (0.748 ± 0.093), F1-score (0.773 ± 0.037), and AUC (0.861 ± 0.047). Furthermore, the dual-channel CNXV2-DANet outperformed all other networks (all p-values < 0.001). These findings suggest that the proposed dual-channel CNXV2-DANet may provide the community with an AI-empowered TCS-based tool for PD assessment.

Achromatic colorings of polarity graphs

A complete partition of a graph G is a partition of the vertex set such that there is at least one edge between any two parts. The largest r such that G has a complete partition into r parts, each of which is an independent set, is the achromatic number of G. We determine the achromatic number of polarity graphs of biaffine planes coming from generalized polygons. Our colorings of a family of unitary polarity graphs are used to solve a problem of Axenovich and Martin on complete partitions of C4-free graphs. Furthermore, these colorings prove that there are sequences of graphs which are optimally complete and have unbounded degree, a problem that had been studied for the sequence of hypercubes independently by Roichman, and Ahlswede, Bezrukov, Blokhuis, Metsch, and Moorhouse.

Hindcasting Estuarine Bottom Salinity Using Observing Systems Data and Nonlinear Regression, as Applied to Oysters in Delaware Bay

Salinity is a major environmental factor that influences the population dynamics of fish and shellfish along coasts and estuaries, yet empirical methods for hindcasting salinity at specific sampling stations are not widely available. The specific aim of this research was to predict the salinity experienced by juvenile and adult oysters (Crassostrea virginica) collected at sampling stations in Delaware Bay. To do so, empirical relationships were created to predict salinity at five oyster bed stations using observing systems data. These relationships were then applied to construct indices of salinity exposure over an oyster’s lifetime. Three independent salinity data sources were used in conjunction with observing systems data to construct and validate the predictive relationships. The root mean square error (RMSE) of the models ranged from 0.5 to 1.6 psu when model predictions were compared with the three independent data sets. Results demonstrated that data from an observing system near the head of Delaware Bay could be used to predict salinity within ± 2 psu at oyster bed stations as far down-estuary as 39 km. When these models were applied to estimate low salinity exposure of 2-year-old oysters via the metric of consecutive days below 5 psu, the indices suggested that there could be as much as a 42-day difference in low salinity exposure for oysters at stations just 31 km apart. The approach of using observing systems data to hindcast salinity could be applied to advance understanding of salt distribution and the effect of low salinity exposure on organisms in other estuaries, especially bottom-associated species.

Multitask Learning on Graph Convolutional Residual Neural Networks for Screening of Multitarget Anticancer Compounds.

Recently, various modern experimental screening pipelines and assays have been developed to find promising anticancer drug candidates. However, it is time-consuming and almost infeasible to screen an immense number of compounds for anticancer activity via experimental approaches. To partially address this issue, several computational advances have been proposed. In this study, we present iACP-GCR, a model based on multitask learning on graph convolutional residual neural networks with two types of shortcut connections, to identify multitarget anticancer compounds. In our architecture, the graph convolutional residual neural networks are shared by all the prediction tasks before being separately customized. The NCI-60 data set, one of the most reliable and well-known sources of experimentally verified compounds, was used to develop our model. From that data set, we collected and refined data about compounds screened across nine cancer types (panels), including breast, central nervous system, colon, leukemia, nonsmall cell lung, melanoma, ovarian, prostate, and renal, for model training and evaluation. The model performance evaluated on an independent test set shows that iACP-GCR surpasses the three advanced computational methods for multitask learning. The integration of two shortcut connection types in the shared networks also improves the prediction efficiency. We also deployed the model as a public web server to assist the research community in screening potential anticancer compounds.

Cliques, Chromatic Number, and Independent Sets in the Semi-random Process

Cliques, Chromatic Number, and Independent Sets in the Semi-random Process

A Point Cloud Graph Neural Network for Protein-Ligand Binding Site Prediction.

Predicting protein-ligand binding sites is an integral part of structural biology and drug design. A comprehensive understanding of these binding sites is essential for advancing drug innovation, elucidating mechanisms of biological function, and exploring the nature of disease. However, accurately identifying protein-ligand binding sites remains a challenging task. To address this, we propose PGpocket, a geometric deep learning-based framework to improve protein-ligand binding site prediction. Initially, the protein surface is converted into a point cloud, and then the geometric and chemical properties of each point are calculated. Subsequently, the point cloud graph is constructed based on the inter-point distances, and the point cloud graph neural network (GNN) is applied to extract and analyze the protein surface information to predict potential binding sites. PGpocket is trained on the scPDB dataset, and its performance is verified on two independent test sets, Coach420 and HOLO4K. The results show that PGpocket achieves a 58% success rate on the Coach420 dataset and a 56% success rate on the HOLO4K dataset. These results surpass competing algorithms, demonstrating PGpocket's advancement and practicality for protein-ligand binding site prediction.

Deep learning model for intravascular ultrasound image segmentation with temporal consistency.

This study was conducted to develop and validate a deep learning model for delineating intravascular ultrasound (IVUS) images of coronary arteries.Using a total of 1240 40-MHz IVUS pullbacks with 191,407 frames, the model for lumen and external elastic membrane (EEM) segmentation was developed. Both frame- and vessel-level performances and clinical impact of the model on 3-year cardiovascular events were evaluated in the independent data sets. In the test set, the Dice similarity coefficients (DSC) were 0.966 ± 0.025 and 0.982 ± 0.017 for the lumen and EEM, respectively. Even at sites of extensive attenuation, the frame-level performance was excellent (DSCs > 0.96 for the lumen and EEM). The model (vs. the expert) showed a better temporal consistency for contouring the EEM. The agreement between the model- vs. the expert-derived cross-sectional and volumetric measurements was excellent in the independent retrospective cohort (all, intra-class coefficients > 0.94). The model-derived percent atheroma volume > 52.5% (area under curve 0.70, sensitivity 71% and specificity 67%) and plaque burden at the minimal lumen area site (area under curve 0.72, sensitivity 72% and specificity 66%) best predicted 3-year cardiac death and nonculprit-related target vessel revascularization, respectively. In the stented segment, the DSCs > 0.96 for contouring lumen and EEM were achieved. Applied to the 60-MHz IVUS images, the DSCs were > 0.97. In the external cohort with 45-MHz IVUS, the DSCs were > 0.96. The deep learning model accurately delineated vascular geometry, which may be cost-saving and support clinical decision-making.

Generation of quantum phases of matter and finding a maximum-weight independent set of unit-disk graphs using Rydberg atoms

Generation of quantum phases of matter and finding a maximum-weight independent set of unit-disk graphs using Rydberg atoms

Automated peripheral nerve segmentation for MR-neurography

BackgroundMagnetic resonance neurography (MRN) is increasingly used as a diagnostic tool for peripheral neuropathies. Quantitative measures enhance MRN interpretation but require nerve segmentation which is time-consuming and error-prone and has not become clinical routine. In this study, we applied neural networks for the automated segmentation of peripheral nerves.MethodsA neural segmentation network was trained to segment the sciatic nerve and its proximal branches on the MRN scans of the right and left upper leg of 35 healthy individuals, resulting in 70 training examples, via 5-fold cross-validation (CV). The model performance was evaluated on an independent test set of one-sided MRN scans of 60 healthy individuals.ResultsMean Dice similarity coefficient (DSC) in CV was 0.892 (95% confidence interval [CI]: 0.888–0.897) with a mean Jaccard index (JI) of 0.806 (95% CI: 0.799–0.814) and mean Hausdorff distance (HD) of 2.146 (95% CI: 2.184–2.208). For the independent test set, DSC and JI were lower while HD was higher, with a mean DSC of 0.789 (95% CI: 0.760–0.815), mean JI of 0.672 (95% CI: 0.642–0.699), and mean HD of 2.118 (95% CI: 2.047–2.190).ConclusionThe deep learning-based segmentation model showed a good performance for the task of nerve segmentation. Future work will focus on extending training data and including individuals with peripheral neuropathies in training to enable advanced peripheral nerve disease characterization.Relevance statementThe results will serve as a baseline to build upon while developing an automated quantitative MRN feature analysis framework for application in routine reading of MRN examinations.Key PointsQuantitative measures enhance MRN interpretation, requiring complex and challenging nerve segmentation.We present a deep learning-based segmentation model with good performance.Our results may serve as a baseline for clinical automated quantitative MRN segmentation.Graphical

New Ramsey Multiplicity Bounds and Search Heuristics

AbstractWe study two related problems concerning the number of homogeneous subsets of given size in graphs that go back to questions of Erdős. Most notably, we improve the upper bounds on the Ramsey multiplicity of $$K_4$$ K 4 and $$K_5$$ K 5 and settle the minimum number of independent sets of size 4 in graphs with clique number at most 4. Motivated by the elusiveness of the symmetric Ramsey multiplicity problem, we also introduce an off-diagonal variant and obtain tight results when counting monochromatic $$K_4$$ K 4 or $$K_5$$ K 5 in only one of the colors and triangles in the other. The extremal constructions for each problem turn out to be blow-ups of a graph of constant size and were found through search heuristics. They are complemented by lower bounds established using flag algebras, resulting in a fully computer-assisted approach. For some of our theorems we can also derive that the extremal construction is stable in a very strong sense. More broadly, these problems lead us to the study of the region of possible pairs of clique and independent set densities that can be realized as the limit of some sequence of graphs.

Expert-Level Detection of Referable Glaucoma from Fundus Photographs in a Safety Net Population: The AI and Teleophthalmology in Los Angeles Initiative.

To develop and test a deep learning (DL) algorithm for detecting referable glaucoma in the Los Angeles County (LAC) Department of Health Services (DHS) teleretinal screening program. Fundus photographs and patient-level labels of referable glaucoma (defined as cup-to-disc ratio [CDR] ≥ 0.6) provided by 21 trained optometrist graders were obtained from the LAC DHS teleretinal screening program. A DL algorithm based on the VGG-19 architecture was trained using patient-level labels generalized to images from both eyes. Area under the receiver operating curve (AUC), sensitivity, and specificity were calculated to assess algorithm performance using an independent test set that was also graded by 13 clinicians with one to 15 years of experience. Algorithm performance was tested using reference labels provided by either LAC DHS optometrists or an expert panel of 3 glaucoma specialists. 12,098 images from 5,616 patients (2,086 referable glaucoma, 3,530 non-glaucoma) were used to train the DL algorithm. In this dataset, mean age was 56.8 ± 10.5 years with 54.8% females and 68.2% Latinos, 8.9% Blacks, 2.7% Caucasians, and 6.0% Asians. 1,000 images from 500 patients (250 referable glaucoma, 250 non-glaucoma) with similar demographics (p ≥ 0.57) were used to test the DL algorithm. Algorithm performance matched or exceeded that of all independent clinician graders in detecting patient-level referable glaucoma based on LAC DHS optometrist (AUC = 0.92) or expert panel (AUC = 0.93) reference labels. Clinician grader sensitivity (range: 0.33-0.99) and specificity (range: 0.68-0.98) ranged widely and did not correlate with years of experience (p ≥ 0.49). Algorithm performance (AUC = 0.93) also matched or exceeded the sensitivity (range: 0.78-1.00) and specificity (range: 0.32-0.87) of 6 LAC DHS optometrists in the subsets of the test dataset they graded based on expert panel reference labels. A DL algorithm for detecting referable glaucoma developed using patient-level data provided by trained LAC DHS optometrists approximates or exceeds performance by ophthalmologists and optometrists, who exhibit variable sensitivity and specificity unrelated to experience level. Implementation of this algorithm in screening workflows could help reallocate eye care resources and provide more reproducible and timely glaucoma care.

DRpred: A Novel Deep Learning-Based Predictor for Multi-Label mRNA Subcellular Localization Prediction by Incorporating Bayesian Inferred Prior Label Relationships.

The subcellular localization of messenger RNA (mRNA) not only helps us to understand the localization regulation of gene expression but also helps to understand the relationship between RNA localization pattern and human disease mechanism, which has profound biological and medical significance. Several predictors have been proposed for predicting the subcellular localization of mRNA. However, there is still considerable room for improvement in their predictive performance, especially regarding multi-label prediction. This study proposes a novel multi-label predictor, DRpred, for mRNA subcellular localization prediction. This predictor first utilizes Bayesian networks to capture the dependencies among labels. Subsequently, it combines these dependencies with features extracted from mRNA sequences using Word2vec, forming the input for the predictor. Finally, it employs a neural network combining BiLSTM and an attention mechanism to capture the internal relationships of the input features for mRNA subcellular localization. The experimental validation on an independent test set demonstrated that DRpred obtained a competitive predictive performance in multi-label prediction and outperformed state-of-the-art predictors in predicting single subcellular localizations, obtaining accuracies of 82.14%, 93.02%, 80.37%, 94.00%, 90.58%, 84.53%, 82.01%, 79.71%, and 85.67% for the chromatin, cytoplasm, cytosol, exosome, membrane, nucleolus, nucleoplasm, nucleus, and ribosome, respectively. It is anticipated to offer profound insights for biological and medical research.

Enhanced machine learning approaches for OSA patient screening: model development and validation study

Age, gender, body mass index (BMI), and mean heart rate during sleep were found to be risk factors for obstructive sleep apnea (OSA), and a variety of methods have been applied to predict the occurrence of OSA. This study aimed to develop and evaluate OSA prediction models using simple and accessible parameters, combined with multiple machine learning algorithms, and integrate them into a cloud-based mobile sleep medicine management platform for clinical use. The study data were obtained from the clinical records of 610 patients who underwent polysomnography (PSG) at the Sleep Medicine Center of the Second Affiliated Hospital of Fujian Medical University between January 2021 and December 2022. The participants were randomly divided into a training-test group (80%) and an independent validation group (20%). The logistic regression, artificial neural network, naïve Bayes, support vector machine, random forest, and decision tree algorithms were used with age, gender, BMI, and mean heart rate during sleep as predictors to build a risk prediction model for moderate-to-severe OSA. To evaluate the performance of the models, we calculated the area under the receiver operating curve (AUROC), accuracy, recall, specificity, precision, and F1-score for the independent validation set. In addition, the calibration curve, decision curve, and clinical impact curve were generated to determine clinical usefulness. Age, gender, BMI, and mean heart rate during sleep were significantly associated with OSA. The artificial neural network model had the best efficacy compared with the other prediction algorithms. The AUROC, accuracy, recall, specificity, precision, F1-score, and Brier score were 80.4% (95% CI 76.7–84.1%), 69.9% (95% CI 69.8–69.9%), 86.5% (95% CI 81.6–91.3%), 61.5% (95% CI 56.6–66.4%), 53.2% (95% CI 47.7–58.7%), 65.9% (95% CI 60.2–71.5%), and 0.165, respectively, for the artificial neural network model. The AUROCs for the LR, NB, SVM, RF, and DT models were 80.2%, 79.7%, 79.2%, 78.4%, and 70.4%, respectively. The six models based on four simple and easily accessible parameters effectively predicted moderate-to-severe OSA in patients with PSG screening, with the artificial neural network model having the best performance. These models can provide a reliable tool for early OSA diagnosis, and their integration into a cloud-based mobile sleep medicine management platform could improve clinical decision making.

In vivo dosimetry with an inorganic scintillation detector during multi-channel vaginal cylinder pulsed dose-rate brachytherapy: Dosimetry for pulsed dose-rate brachytherapy

Background and purposeIn vivo dosimetry is not standard in brachytherapy and some errors go undetected. The aim of this study was to evaluate the accuracy of multi-channel vaginal cylinder pulsed dose-rate brachytherapy using in vivo dosimetry. Materials and methodsIn vivo dosimetry data was collected during the years 2019–2022 for 22 patients (32 fractions) receiving multi-channel cylinder pulsed dose-rate brachytherapy. An inorganic scintillation detector was inserted in a cylinder channel. Each fraction was analysed as independent data sets. In vivo dosimetry-based source-tracking was used to determine the relative source-to-detector position. Measured dose was compared to planned and re-calculated source-tracking based doses. Assuming no change in organ and applicator geometry throughout treatment, the planned and source-tracking based dose distributions were compared in select volumes via γ-index analysis and dose-volume-histograms. ResultsThe mean ± SD planned vs. measured dose deviations in the first pulse were 0.8 ± 5.9 %. In 31/32 fractions the deviation was within the combined in vivo dosimetry uncertainty (averaging 9.7 %, k = 2) and planning dose calculation uncertainty (1.6 %, k = 2). The dwell-position offsets were < 2 mm for 88 % of channels, with the largest being 5.1 mm (4.0 mm uncertainty, k = 2). 3 %/2 mm γ pass-rates averaged 97.0 % (clinical target volume (CTV)), 100.0 % (rectum), 99.9 % (bladder). The mean ± SD deviation was −1.1 ± 2.9 % for CTV D98, and −0.2 ± 0.9 % and −1.2 ± 2.5 %, for bladder and rectum D2cm3 respectively, indicating good agreement between intended and delivered dose. ConclusionsIn vivo dosimetry verified accurate and stable dose delivery in multi-channel vaginal cylinder based pulsed dose-rate brachytherapy.

NeuroPpred-SHE: An interpretable neuropeptides prediction model based on selected features from hand-crafted features and embeddings of T5 model

Neuropeptides are the most ubiquitous neurotransmitters in the immune system, regulating various biological processes. Neuropeptides play a significant role for the discovery of new drugs and targets for nervous system disorders. Traditional experimental methods for identifying neuropeptides are time-consuming and costly. Although several computational methods have been developed to predict the neuropeptides, the accuracy is still not satisfactory due to the representability of the extracted features. In this work, we propose an efficient and interpretable model, NeuroPpred-SHE, for predicting neuropeptides by selecting the optimal feature subset from both hand-crafted features and embeddings of a protein language model. Specially, we first employed a pre-trained T5 protein language model to extract embedding features and twelve other encoding methods to extract hand-crafted features from peptide sequences, respectively. Secondly, we fused both embedding features and hand-crafted features to enhance the feature representability. Thirdly, we utilized random forest (RF), Max-Relevance and Min-Redundancy (mRMR) and eXtreme Gradient Boosting (XGBoost) methods to select the optimal feature subset from the fused features. Finally, we employed five machine learning methods (GBDT, XGBoost, SVM, MLP, and LightGBM) to build the models. Our results show that the model based on GBDT achieves the best performance. Furthermore, our final model was compared with other state-of-the-art methods on an independent test set, the results indicate that our model achieves an AUROC of 97.8 % which is higher than all the other state-of-the-art predictors. Our model is available at: https://github.com/wenjean/NeuroPpred-SHE.

On finding short reconfiguration sequences between independent sets

Token Sliding Optimization asks whether there exists a sequence of at most ℓ steps that transforms independent set S into T, where at each step a token slides to an unoccupied neighboring vertex (while maintaining independence). In Token Jumping Optimization, we are instead allowed to jump from a vertex to any unoccupied vertex. Both problems are known to be FPT when parameterized by ℓ on nowhere dense graphs. In this work, we show that both problems are FPT for parameter k+ℓ+d on d-degenerate graphs as well as for parameter |M|+ℓ+Δ on graphs having a modulator M to maximum degree Δ. We complement these results by showing that for parameter ℓ both problems become hard already on 2-degenerate graphs. Finally, we show that using such families one can obtain a unified algorithm for the standard Token Jumping problem parameterized by k on degenerate and nowhere dense graphs.

Preoperative Ultrasound Radomics to Predict Posthepatectomy Liver Failure in Patients With Hepatocellular Carcinoma.

Posthepatectomy liver failure (PHLF) is a major cause of postoperative mortality in hepatocellular carcinoma (HCC) patients. The study aimed to develop a method based on the two-dimensional shear wave elastography and clinical data to evaluate the risk of PHLF in HCC patients with chronic hepatitis B. This multicenter study proposed a deep learning model (PHLF-Net) incorporating dual-modal ultrasound features and clinical indicators to predict the PHLF risk. The datasets were divided into a training cohort, an internal validation cohort, an internal independent testing cohort, and three external independent testing cohorts. Based on ResNet50 pretrained on ImageNet, PHLF-Net used a progressive training strategy with images of varying granularity and incorporated conventional B-mode and elastography images and clinical indicators related to liver reserve function. In total, 532 HCC patients who underwent hepatectomy at five hospitals were enrolled. PHLF occurred in 147 patients (27.6%, 147/532). The PHLF-Net combining dual-modal ultrasound and clinical indicators demonstrated high effectiveness for predicting PHLF, with AUCs of 0.957 and 0.923 in the internal validation and testing sets, and AUCs of 0.950, 0.860, and 1.000 in the other three independent external testing sets. The performance of PHLF-Net outperformed models of single- and dual-modal US. Preoperative ultrasound imaging combining clinical indicators can effectively predict the PHLF probability in patients with HCC. In the internal and external validation sets, PHLF-Net demonstrated its usefulness in predicting PHLF.