Drug Database
SH

SH-U-454

✓ Approved

Bayer AG · Small Molecule · Small Molecule

What is SH-U-454?

SH-U-454 is a small molecule developed by Bayer AG. It is approved for therapeutic indications via injectable (others) or intravenous (iv).

Drug Profile

CompanyBayer AG
Drug ClassSmall Molecule, Imaging Agents
RouteInjectable (Others), Intravenous (IV)
StatusApproved
Sources: ClinicalTrials.gov, Bayer AG

Therapeutic Indications

SH-U-454 is developed for 1 unique indication across 1 therapeutic area.

Therapeutic AreaConditionPhase
Cardiac disordersArteriosclerosis coronary artery✓ Approved

Related Research Articles

PubMedFrontiers in medicine2026-09-16

Differential diagnosis model for tuberculous and malignant pleural effusion combining U-Net automatic segmentation and deep learning.

Song Chang C, Zhao Chun-Yan CY, Song Shu-Lin SL, Huang Xue-Wen XW et al.

We aimed to construct and validate an intelligent differential diagnosis model that integrates U-Net-based automatic segmentation with a deep learning classification model, and to evaluate its diagnostic performance and clinical value for distinguishing tuberculous pleural effusion (TPE) from malignant pleural effusion (MPE). A total of 281 patients with pleural effusion confirmed by etiological or pathological evidence between January 2018 and August 2025 were included, comprising 143 patients with TPE and 138 with MPE. First, a U-Net model was employed to automatically segment pleural lesion regions on chest computed tomography (CT) images and extract regions of interest (ROIs). Subsequently, based on the segmentation results, a radiomics model, a two-dimensional deep learning (DL2D) model, and a comprehensive model integrating clinical features were constructed. Multiple machine learning algorithms, including support vector machines (SVMs), random forests (RFs), and extremely randomized trees (ERTs), were utilized for model construction and comparison. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, calibration curves, decision curve analysis (DCA), and the integrated discrimination improvement (IDI) and net reclassification improvement (NRI) indices. The U-Net segmentation model achieved Dice coefficients of 0.873 and 0.862 in the training and test sets, respectively, indicating good segmentation performance. In the test set, the comprehensive model demonstrated the best performance, with an AUC of 0.934 (95% CI 0.8733-0.9955), sensitivity of 0.875, and specificity of 0.900. Its performance was superior to that of the clinical model (AUC = 0.767), the radiomics model (AUC = 0.841), and the DL2D model (AUC = 0.776). DCA confirmed that the comprehensive model provided a higher net clinical benefit across a wide range of threshold probabilities. Furthermore, IDI and NRI analyses indicated that the comprehensive model significantly improved predictive performance relative to the individual models (p < 0.05). The model combining U-Net-based automatic segmentation with a deep learning classification model exhibited excellent and balanced diagnostic performance for differentiating TPE from MPE. It has the potential to provide an objective, stable, and scalable intelligent decision-support tool for clinical practice.

PMID 42746091
Read full article →
PubMedJournal of imaging informatics in medicine2026-09-16

Multi-Scale Residual Gated Attention U-Net for Liver Tumor Segmentation.

Huang Hu H, Chen Ying Y, Peng Kun K, Guo Shili S et al.

Accurate early diagnosis and treatment planning of liver cancer relies on precise liver and tumor segmentation in medical images. However, liver tumor segmentation faces complex anatomical structures, large lesion scale differences, and fuzzy lesion boundaries. Vanilla U-Net has three inherent structural drawbacks: inadequate cross-scale feature interaction in the encoder, semantic mismatch in skip connections, and insufficient multi-scale feature aggregation in the decoder. Therefore, this paper proposes a Multi-scale Residual Gated Attention U-Net (MRGA-UNet) for liver tumor segmentation. The Multi-Residual Coordinate Enhancement (MRCE), Cascaded Residual Gating (CRG) and Multi-Scale Feature Fusion (MFF) form an end-to-end feature pipeline tailored for liver CT segmentation. Coordinated feature propagation across the three modules adapts to the imaging traits of liver CT. This systematic matching across modules forms the overall novelty relative to mainstream residual and attention-based U-Net variants. The MRCE module is embedded in the encoder and combines multi-residual branches with coordinate attention to extract abundant multi-scale tumor features, tackling insufficient cross-scale interaction. The CRG module is arranged on skip connections; guided by high-level semantics, it optimizes features bottom-up to eliminate semantic mismatch between layers. The MFF module is deployed in the decoder to achieve sufficient multi-scale aggregation and reinforce tumor feature representation. Tested on the LiTS and 3DIRCADb datasets, the proposed model achieves a Dice Similarity Coefficient (DSC) of 83.3% and 81.8%, respectively. Compared with MedNeXt, the proposed model increases DSC by 5.3 percentage points and reduces VOE by 0.069 on the LiTS dataset. On the 3DIRCADb dataset, the proposed method achieves a 7.0 percentage points improvement in DSC and reduces VOE by 0.080. The proposed model achieves superior segmentation performance primarily in DSC and VOE, while maintaining competitive performance on other metrics. Ablation studies confirm that each proposed module contributes positively to the overall segmentation performance.

PMID 42745113
Read full article →
PubMedBiomolecules & biomedicine2026-09-16

Stroke-associated pneumonia risk prediction: Development and internal validation of a preliminary nomogram.

Wang Baichen B

Stroke-associated pneumonia (SAP) is a common complication of acute stroke, highlighting the need for early risk identification. This study aimed to develop and internally validate a preliminary SAP nomogram using routinely available clinical and hematological parameters. This single-center retrospective study included 650 patients randomly divided into training (n = 454) and internal validation (n = 196) cohorts. Baseline blood samples were obtained within 24 hours of admission and before SAP onset; the outcome was SAP within 7 days of stroke onset. Least absolute shrinkage and selection operator (LASSO) regression followed by multivariable logistic regression was used to select predictors and construct the nomogram. SAP occurred in 190 patients (29.2%). Older age, atrial fibrillation, higher white blood cell count, lower lymphocyte percentage, and lower hemoglobin were independently associated with SAP. The area under the receiver operating characteristic curve (AUC) was 0.772 in the training cohort and 0.738 in the internal validation cohort, with respective 95% confidence intervals of 0.723-0.820 and 0.662-0.815. The optimism-corrected training AUC was 0.762. The validation Brier score was 0.181, and decision curve analysis suggested potential clinical net benefit. This preliminary nomogram may support early SAP risk stratification. However, the single-center retrospective design and omission of key neurological predictors, including stroke severity and dysphagia, necessitate prospective multicenter validation before clinical implementation.

PMID 42745697
Read full article →
PubMedJournal of imaging informatics in medicine2026-09-16

SOTS: Leveraging Self-supervised Pretraining for Label-Efficient Ovarian Tumor Segmentation in Ultrasound Images.

Bui Hoang-Son HS, Dao Thanh-Phuc TP, Le Thi-Lan TL

Ovarian cancer is one of the most serious diseases globally, and ultrasound imaging is a widely used modality for its diagnosis and monitoring. Accurate segmentation of ovarian tumors is critical for reliable morphological assessment and clinical decision-making, yet supervised models are often limited in performance when annotated data are scarce due to the high cost and expertise required for labeling. To address this challenge, we propose a Self-supervised Ovarian Tumor Segmentation (SOTS) framework that leverages unlabeled ultrasound images to learn robust feature representations. In the proposed framework, for the supervised stage, a new architecture named SovaSegNet-U is proposed. The encoder is pretrained using the Barlow Twins objective to learn invariant and non-redundant embeddings, while an uncertainty-based augmentation strategy further strengthens representation robustness by prioritizing challenging transformations during pretraining on unlabeled data. The pretrained encoder is subsequently fine-tuned under varying labeled data ratios, consistently outperforming purely supervised models in low-label scenarios. Notably, SOTS achieves segmentation accuracy comparable to fully supervised U-Net variants while requiring substantially fewer annotations. These results demonstrate that the proposed approach provides an annotation-efficient solution for ovarian tumor segmentation and holds strong potential for supporting clinical decision-making. Source code is available at https://github.com/SonBH0410/SOTS .

PMID 42745118
Read full article →
PubMedCureus2026-09-16

Non-suppurative Destructive Cholangitis After Avacopan Therapy in Myeloperoxidase-Antineutrophil Cytoplasmic Antibody (MPO-ANCA)-Associated Glomerulonephritis: A Case Report and Review of the Literature.

Terakawa Kensuke K, Wada Yukihiro Y, Toyoda Yuki Y, Nakamura Keiya K et al.

Avacopan, a selective complement C5a receptor antagonist, is utilized to manage microscopic polyangiitis (MPA). Recently, attention has grown regarding severe liver injury, particularly vanishing bile duct syndrome (VBDS), as a potential adverse event during avacopan therapy. However, its clinicopathological features and underlying mechanisms remain poorly understood. Herein, we report a case of non-suppurative destructive cholangitis (NSDC), considered a pre-conditional state of VBDS, after avacopan therapy for MPA. A 55-year-old obese female with myeloperoxidase-antineutrophil cytoplasmic antibody (MPO-ANCA)-associated crescentic glomerulonephritis achieved remission via steroid pulse therapy, oral prednisolone (PSL), and rituximab. Seven weeks before admission, avacopan and ursodeoxycholic acid (UDCA) were initiated. Despite stable renal function, MPO-ANCA seroconversion to negative, and successful PSL tapering, she presented with acute liver injury. Laboratory tests revealed marked elevations in transaminases and biliary enzymes (aspartate aminotransferase (AST): 313 U/L, alanine aminotransferase (ALT): 488 U/L, gamma-glutamyl transferase (γ-GTP): 364 U/L) with normal direct bilirubin (D-bil). Avacopan was discontinued, and PSL was increased. A liver biopsy showed lymphocytic (non-suppurative) destructive cholangitis with a florid duct lesion and frequent spotty necrosis in lobuli, without central necrosis. Immunohistochemical staining revealed focal decreased CK19 immunointensity in the bile ducts and predominant infiltration of CD4-positive T cells and CD68-positive macrophages around interlobular bile ducts. Although D-bil transiently peaked at 4.0 mg/dL on day 7, intensive treatment with high-dose UDCA and intravenous glycyrrhizin restored D-bil to the normal range by day 34, with significant transaminase improvement.　 Pathological findings revealed biliary epithelial damage with predominant T-cell and macrophage infiltration, distinct from typical drug-induced liver injury. The onset during PSL tapering and responsiveness to temporary PSL intensification strongly support a cell-mediated immune mechanism driving VBDS. To the best of our knowledge, this is the first report describing a comprehensive immunohistochemical evaluation of the periportal microenvironment in avacopan-induced biliary injury. This case highlights that severe cholangitis can occur regardless of baseline risk profiles or disease activity, underscoring the need for vigilant, long-term monitoring of liver enzymes and bilirubin levels during avacopan therapy.

PMID 42746016
Read full article →
PubMedFrontiers in psychology2026-09-16

The role of home-based math activities in developing mathematical reasoning skills in preschool children: a pilot randomized controlled trial.

Deleş Bayram B, Aral Neriman N

Early mathematical reasoning skills are important predictors of later academic achievement. Although home-based learning environments contribute to early mathematics development, structured home-based intervention programs specifically targeting mathematical reasoning skills remain limited. The study employed a pilot randomized pretest-posttest control group design to evaluate the HBMR program. The study sample consisted of 20 preschool children (10 in the experimental group and 10 in the control group) selected using a stratified random sampling procedure. Following pre-test assessments, participants were randomly assigned to either the experimental or control group. The HBMR program was implemented over 5 weeks through ten structured home sessions, including reasoning-based activities such as matching, classifying, comparing, sequencing, and basic number operations. As the data did not meet normality assumptions, non-parametric analyses (Mann-Whitney U and Wilcoxon signed-rank tests) were conducted. Effect sizes were calculated using the formula r = Z/√N. Wilcoxon signed-rank test results revealed significant improvements in the experimental group in measurement (Z = -2.684, p = 0.007), data analysis (Z = -2.831, p = 0.005), and overall mathematical reasoning scores (Z = -2.812, p = 0.005), with large effect sizes (r = 0.85-0.90). No statistically significant improvements were observed in the control group. Mann-Whitney U test results indicated that the experimental group's post-test scores were significantly higher than those of the control group (p < 0.05). The findings indicate that children who participated in the HBMR program showed greater improvements in mathematical reasoning skills than children in the control group.

PMID 42746067
Read full article →

+9996 more articles available with a free account

Sign up free to view all articles →

Ask about SH-U-454