Front Immunol. 2025 Feb 17;16:1488851. doi: 10.3389/fimmu.2025.1488851. eCollection 2025.

ABSTRACT

We describe the establishment and current content of the ImmuneCODE™ database, which includes hundreds of millions of T-cell Receptor (TCR) sequences from over 1,400 subjects exposed to or infected with the SARS-CoV-2 virus, as well as over 160,000 high-confidence SARS-CoV-2-associated TCRs. This database is made freely available, and the data contained in it can be used to assist with global efforts to understand the immune response to the SARS-CoV-2 virus and develop new interventions.

PMID:40034696 | PMC:PMC11873104 | DOI:10.3389/fimmu.2025.1488851

Bioinform Biol Insights. 2025 Mar 2;19:11779322241271565. doi: 10.1177/11779322241271565. eCollection 2025.

ABSTRACT

Breast cancer is a highly heterogeneous disorder characterized by dysregulated expression of number of genes and their cascades. It is one of the most common types of cancer in women posing serious health concerns globally. Recent developments and discovery of specific prognostic biomarkers have enabled its application toward developing personalized therapies. The basic premise of this study was to investigate key signature genes and signaling pathways involved in triple-negative breast cancer using bioinformatics approach. Microarray data set GSE65194 from the National Center for Biotechnology Information (NCBI) Gene Expression Omnibus was used for identification of differentially expressed genes (DEGs) using R software. Gene ontology and Kyoto Encyclopedia of Genes and Genome (KEGG) pathway enrichment analyses were carried out using the ClueGO plugin in Cytoscape software. The up-regulated DEGs were primarily engaged in the regulation of cell cycle, overexpression of spindle assembly checkpoint, and so on, whereas down-regulated DEGs were employed in alteration to major signaling pathways and metabolic reprogramming. The hub genes were identified using cytoHubba from protein-protein interaction (PPI) network for top up-regulated and down-regulated DEG's plugin in Cytoscape software. The hub genes were validated as potential signature biomarkers by evaluating the overall survival percentage in breast cancer patients.

PMID:40034579 | PMC:PMC11873876 | DOI:10.1177/11779322241271565

Synth Syst Biotechnol. 2025 Feb 8;10(2):511-522. doi: 10.1016/j.synbio.2025.02.002. eCollection 2025 Jun.

ABSTRACT

Corynebacterium glutamicum is a versatile industrial microorganism for producing various amino acids. However, there have been no reports of well-defined C. glutamicum strains capable of hyperproducing l-tryptophan. This study presents a comprehensive metabolic engineering approach to establish robust C. glutamicum strains for l-tryptophan biosynthesis, including: (1) identification of potential targets by enzyme-constrained genome-scale modeling; (2) enhancement of the l-tryptophan biosynthetic pathway; (3) reconfiguration of central metabolic pathways; (4) identification of metabolic bottlenecks through comparative metabolome analysis; (5) engineering of the transport system, shikimate pathway, and precursor supply; and (6) repression of competing pathways and iterative optimization of key targets. The resulting C. glutamicum strain achieved a remarkable l-tryptophan titer of 50.5 g/L in 48h with a yield of 0.17 g/g glucose in fed-batch fermentation. This study highlights the efficacy of integrating computational modeling with systems metabolic engineering for significantly enhancing the production capabilities of industrial microorganisms.

PMID:40034180 | PMC:PMC11872490 | DOI:10.1016/j.synbio.2025.02.002

ArXiv [Preprint]. 2025 Feb 21:arXiv:2502.15597v1.

ABSTRACT

Guidelines for managing scientific data have been established under the FAIR principles requiring that data be Findable, Accessible, Interoperable, and Reusable. In many scientific disciplines, especially computational biology, both data and models are key to progress. For this reason, and recognizing that such models are a very special type of 'data', we argue that computational models, especially mechanistic models prevalent in medicine, physiology and systems biology, deserve a complementary set of guidelines. We propose the CURE principles, emphasizing that models should be Credible, Understandable, Reproducible, and Extensible. We delve into each principle, discussing verification, validation, and uncertainty quantification for model credibility; the clarity of model descriptions and annotations for understandability; adherence to standards and open science practices for reproducibility; and the use of open standards and modular code for extensibility and reuse. We outline recommended and baseline requirements for each aspect of CURE, aiming to enhance the impact and trustworthiness of computational models, particularly in biomedical applications where credibility is paramount. Our perspective underscores the need for a more disciplined approach to modeling, aligning with emerging trends such as Digital Twins and emphasizing the importance of data and modeling standards for interoperability and reuse. Finally, we emphasize that given the non-trivial effort required to implement the guidelines, the community moves to automate as many of the guidelines as possible.

PMID:40034129 | PMC:PMC11875277

New Phytol. 2025 Mar 3. doi: 10.1111/nph.20446. Online ahead of print.

ABSTRACT

Drought stress imposes severe challenges on agriculture by impacting crop performance. Understanding drought responses in plants at a cellular level is a crucial first step toward engineering improved drought resilience. However, the molecular responses to drought are complex as they depend on multiple factors, including the severity of drought, the profiled organ, its developmental stage or even the cell types therein. Thus, deciphering the transcriptional responses to drought is especially challenging. In this study, we investigated tissue-specific responses to mild drought (MD) in young Arabidopsis thaliana (Arabidopsis) leaves using single-cell RNA sequencing (scRNA-seq). To preserve transcriptional integrity during cell isolation, we inhibited RNA synthesis using the transcription inhibitor actinomycin D, and demonstrated the benefits of transcriptome fixation for studying mild stress responses at a single-cell level. We present a curated and validated single-cell atlas, comprising 50 797 high-quality cells from almost all known cell types present in the leaf. All cell type annotations were validated with a new library of reporter lines. The curated data are available to the broad community in an intuitive tool and a browsable single-cell atlas (http://www.single-cell.be/plant/leaf-drought). We show that the mesophyll contains two spatially separated cell populations with distinct responses to drought: one enriched in canonical abscisic acid-related drought-responsive genes, and another one enriched in genes involved in iron starvation responses. Our study thus reveals a dual adaptive mechanism of the leaf mesophyll in response to MD and provides a valuable resource for future research on stress responses.

PMID:40033544 | DOI:10.1111/nph.20446

World J Mens Health. 2025 Feb 27. doi: 10.5534/wjmh.240295. Online ahead of print.

ABSTRACT

PURPOSE: Pentosan polysulfate sodium (PPS) is the only pharmacological intervention approved by the US Food and Drug Administration for treating interstitial cystitis (IC) to date. However, PPS may induce an adverse event, maculopathy, which can be a significant challenge. To determine the risk of PPS-induced maculopathy in patients with IC.

MATERIALS AND METHODS: PubMed and Embase were systematically searched through July 2024. Two authors also independently and manually searched all relevant studies. We included national level cohort studies using healthcare claim big data or real-world data with the following criteria: (1) patients diagnosed with IC; (2) interventions included PPS as an active treatment; (3) comparisons were specified as non-PPS interventions; and (4) the primary outcome of interest was the risk of maculopathy. The pairwise meta-analysis was performed to compare the PPS treatment group with control used in IC. The primary outcome measure was the hazard ratio (HR), odds ratio (OR), and proportional report ratio (PRR) of maculopathy after receiving the PPS treatment, as compared to non-PPS interventions.

RESULTS: A comprehensive literature search was conducted, and identified 6 studies with 411,098 patients. The pooled risk for maculopathy due to PPS in patients with IC was significant (HR, 1.678; 95% confidence interval [95% CI], 1.066-2.642]). The heterogeneity test produced a Higgins' I-squared statistic, which was 83.6%. In the subgroup analysis of follow-up period of less than 5 years (HR, 1.285; 95% CI, 1.139-1.449) and more (HR, 1.341; 95% CI, 1.307-1.375) were statistically significant, indicating that the patients with IC who had a long-term PPS treatment were more likely to have maculopathy than the control groups.

CONCLUSIONS: This is the first study to investigate the relationship between PPS and its association with the risk of maculopathy in patients with IC through a systematic review and meta-analysis.

PMID:40034025 | DOI:10.5534/wjmh.240295

IEEE J Biomed Health Inform. 2025 Mar;29(3):2161-2171. doi: 10.1109/JBHI.2024.3500094. Epub 2025 Mar 6.

ABSTRACT

The automated diagnosis of rare skin diseases using dermoscopy images, known as a few-shot learning (FSL) problem, remains challenging, since traditional FSL research tends to disregard the intrinsic hierarchical nature of rare diseases and data uncertainty. To address these issues, we propose to conduct rare skin disease diagnosis in hyperbolic space, which facilitates implicit class hierarchical structures and precise uncertainty measurement due to pivotal geometrical properties. We propose a Hyperbolic Geometry-driven Robustness Enhancement (HGRE) framework specifically tailored for diagnosing rare skin diseases. The HGRE framework uses implicit hierarchical relation in the hyperbolic space to better represent the features of rare diseases. Moreover, the framework incorporates an Adversarial Proxy Construction (APC) module to address the problem of data uncertainty. Specifically, the APC module uses the distance to the hyperbolic space origin as an indicator of uncertainty to filter and construct adversarial proxies for each uncertain prototype to achieve adversarial robust training. Leveraging the two unique geometrical properties, our HGRE framework effectively addresses the limitations of insufficient hierarchical relation utilization and data uncertainty in FSL-based rare skin disease diagnosis. This enhancement of the model's robustness in training has been corroborated by extensive empirical validation on two skin lesion datasets, where HGRE's performance notably surpassed existing state-of-the-art FSL methods.

PMID:40030401 | DOI:10.1109/JBHI.2024.3500094

IEEE J Biomed Health Inform. 2025 Mar;29(3):1759-1770. doi: 10.1109/JBHI.2024.3510297. Epub 2025 Mar 6.

ABSTRACT

Investigating the inhibitory effects of compounds on cardiac ion channels is essential for assessing cardiac drug safety. Consequently, researchers have developed computational models to evaluate combined cardiotoxicity (CCT) on cardiac ion channels. However, limitations in experimental data often cause issues like uneven data distribution and scarcity. Additionally, existing models primarily emphasize atomic information flow within graph neural networks (GNNs) while overlooking chemical bonds, leading to inadequate recognition of key structures. Therefore, this study integrates optimal transport (OT), structure remapping (SR), and Kolmogorov-Arnold networks (KANs) into a GNN-based CCT prediction model, CardiOT. First, the proposed CardiOT model employs OT pooling to optimize sample-feature joint distribution using expectation maximization, identifying "important" sample-feature pairs. Additionally, SR technology is used to emphasize the role of chemical bond information in message propagation. KAN technology is integrated to greatly enhance model interpretability. In summary, the model mitigates challenges related to uneven data distribution and scarcity. Multiple experiments on public datasets confirm the model's robust performance. We anticipate that this model will provide deeper insights into compound inhibition mechanisms on cardiac ion channels and reduce toxicity risks.

PMID:40030556 | DOI:10.1109/JBHI.2024.3510297

Malar J. 2025 Mar 3;24(1):71. doi: 10.1186/s12936-025-05295-9.

ABSTRACT

BACKGROUND: Active surveillance involves systematically monitoring patients to seek detailed information about the occurrence of adverse events (AEs) following drug administration. The Seta technology was developed to improve active surveillance of AEs or pregnancy in low- and middle-income countries and geographically challenging areas. Seta actively solicits responses from participants via WhatsApp messages. The study aimed to determine whether Seta facilitated reporting of AEs and pregnancies to the Brazilian National Health Surveillance Agency (ANVISA).

METHODS: Malaria patients participating in the Tafenoquine Roll-out STudy (TRuST) in Brazil's Amazon region were invited to participate in this observational pilot study evaluating Seta. The study was conducted at two sites from 27 July 2022 to 28 October 2022. Seta sent messages to all participants on Day 7 and in Week 8 asking if they had experienced an AE or if they had become pregnant during the time since they took the malaria medication. If a participant responded "yes", a pharmacovigilance coordinator (PVC) called them to collect further details, which the PVC was then encouraged to report to ANVISA.

RESULTS: This pilot study included 149 participants, 50 from Manaus and 99 from Porto Velho. On Day 7, 117 (79%) of 149 participants responded to WhatsApp messages generated by Seta asking whether they had experienced an AE or become pregnant; 45 participants responded "yes". At Week 8, 64 (55%) of the Day 7 responders also responded, 10 of whom indicated that they had experienced an AE or become pregnant. A total of 55 follow-up calls were therefore attempted by PVCs, of which, 25 (45%) were answered and allowed for reporting of AEs and pregnancies, as appropriate, to ANVISA.

CONCLUSIONS: This observational pilot study provides insights into how digital reporting tools such as Seta can enhance pharmacovigilance in remote areas and build upon existing signal detection methodologies. Twenty-five AEs or pregnancies were reported to ANVISA that were unlikely to have been reported otherwise.

PMID:40033382 | DOI:10.1186/s12936-025-05295-9

J Transl Med. 2025 Mar 3;23(1):258. doi: 10.1186/s12967-025-06293-w.

ABSTRACT

Pentamidine (PTM) is an aromatic diamidine administered for infectious diseases, e.g. sleeping sickness, malaria, and Pneumocystis jirovecii pneumonia. Due to similarities of cellular mechanisms between human cells and such infections, PTM has also been proposed for repurposing in non-infectious diseases such as cancer. Indeed, by modulating different signaling pathways such as PI3K/AKT, MAPK/ERK, p53, PD-1/PD-L1, etc., PTM has been shown to inhibit different properties of cancer, including proliferation, invasion, migration, hypoxia, and angiogenesis, while inducing anti-tumor immune responses and apoptosis. Given the promising implications of PTM for cancer treatment, however, the clinical translation of PTM in cancer is not without certain challenges. In fact, clinical trials have shown that systemic administration of PTM can be concurrent with serious adverse effects, e.g. hypoglycemia. Therefore, to reduce the administered doses of PTM, lower the risk of adverse effects, and prevent any potential drug resistance, while maintaining the anti-tumor efficacy, two main strategies have been suggested. One is combination therapy that employs PTM in conjunction with other anti-cancer modalities, such as chemotherapy and radiotherapy, and attacks tumor cells with significant additive or synergistic anti-tumor effects. The other is developing PTM-loaded nanocarrier drug delivery systems e.g. pegylated liposomes, chitosan-coated niosomes, squalene-based nanoparticles, hyaluronated lipid-polymer hybrid nanoparticles, etc., that offer enhanced pharmacokinetic characteristics, including increased bioavailability, sit-targeting, and controlled/sustained drug release. This review highlights the anti-tumor properties of PTM that favor its repurposing for cancer treatment, as well as, PTM-based combination therapies and nanocarrier delivery systems which can enhance therapeutic efficacy and simultaneously reduce toxicity.

PMID:40033361 | DOI:10.1186/s12967-025-06293-w

Comput Biol Med. 2025 Mar 2:109919. doi: 10.1016/j.compbiomed.2025.109919. Online ahead of print.

NO ABSTRACT

PMID:40032537 | DOI:10.1016/j.compbiomed.2025.109919

Pulm Pharmacol Ther. 2025 Mar 1:102348. doi: 10.1016/j.pupt.2025.102348. Online ahead of print.

NO ABSTRACT

PMID:40032240 | DOI:10.1016/j.pupt.2025.102348

J Gen Intern Med. 2025 Mar 3. doi: 10.1007/s11606-025-09449-y. Online ahead of print.

ABSTRACT

BACKGROUND: Despite guideline recommendations to offer continuous glucose monitoring (CGM) to all patients with diabetes using insulin, prescription rates for CGM remain low in primary care.

OBJECTIVE: This quality improvement project aimed to improve access to CGM in primary care for patients with type 2 diabetes on insulin.

DESIGN: This was a quality improvement project conducted by a joint endocrinology/primary care team at a single primary care community health clinic. After defining the problem through process mapping, driver diagrams, and Pareto charts, several interventions were trialed through Plan-Do-Study-Act (PDSA) cycles.

PARTICIPANTS: The study team consisted of four endocrinologists, two primary care providers (MD/NP), the lead primary care nurse, and the primary care population health specialist.

INTERVENTIONS: Interventions included a directory for durable medical equipment (DME) suppliers, nursing education with device company representatives, a new electronic ordering system for DME, and a nursing outreach program to patients eligible for CGM.

MAIN MEASURES: The primary outcome was percentage of eligible patients using CGM. Process measures included the number of CGM orders started weekly. Nursing comfort with CGM, knowledge of CGM, and perceptions of communication with DME suppliers were also measured.

KEY RESULTS: The percentage of eligible patients using CGM increased from 28 to 42%, and the percentage of patients using CGM started in primary care increased from 8 to 14%. Weekly orders increased from 0.3 per week to 2.3 per week. Nursing reported feeling more comfortable and knowledgeable about CGM after the interventions and reported improved communication with DME suppliers.

CONCLUSIONS: CGM is known to improve outcomes for patients with diabetes but is an underutilized tool in primary care. Collaborative quality improvement projects between endocrinology and primary care can rapidly build capacity within primary care to prescribe CGM and expand access for patients with diabetes who do not have endocrinologists.

PMID:40032724 | DOI:10.1007/s11606-025-09449-y

Oral Dis. 2025 Mar 3. doi: 10.1111/odi.15300. Online ahead of print.

ABSTRACT

OBJECTIVES: Temporomandibular disorders (TMDs) refer to a group of disorders related to the temporomandibular joint (TMJ), the diagnosis of which is important in dental practice but remains challenging for nonspecialists. With the development of machine learning (ML) methods, ML-based TMDs diagnostic models have shown great potential. The purpose of this review is to summarize the application of ML in TMDs diagnosis, as well as future directions and possible challenges.

METHODS: PubMed, Google Scholar, and Web of Science databases were searched for electronic literature published up to October 2024, in order to describe the current application of ML in the classification and diagnosis of TMDs.

RESULTS: We summarized the application of various ML methods in the diagnosis and classification of different subtypes of TMDs and described the role of different imaging modalities in constructing diagnostic models. Ultimately, we discussed future directions and challenges that ML methods may confront in the application of TMDs diagnosis.

CONCLUSIONS: The screening and diagnosis models of TMDs based on ML methods hold significant potential for clinical application, but still need to be further verified by a large number of multicenter data and longitudinal studies.

PMID:40033467 | DOI:10.1111/odi.15300

World J Emerg Surg. 2025 Mar 3;20(1):17. doi: 10.1186/s13017-025-00594-7.

ABSTRACT

BACKGROUND: Mild acute biliary pancreatitis (MABP) presents significant clinical and economic challenges due to its potential for relapse. Current guidelines advocate for early cholecystectomy (EC) during the same hospital admission to prevent recurrent acute pancreatitis (RAP). Despite these recommendations, implementation in clinical practice varies, highlighting the need for reliable and accessible predictive tools. The MINERVA study aims to develop and validate a machine learning (ML) model to predict the risk of RAP (at 30, 60, 90 days, and at 1-year) in MABP patients, enhancing decision-making processes.

METHODS: The MINERVA study will be conducted across multiple academic and community hospitals in Italy. Adult patients with a clinical diagnosis of MABP, in accordance with the revised Atlanta Criteria, who have not undergone EC during index admission will be included. Exclusion criteria encompass non-biliary aetiology, severe pancreatitis, and the inability to provide informed consent. The study involves both retrospective data from the MANCTRA-1 study and prospective data collection. Data will be captured using REDCap. The ML model will utilise convolutional neural networks (CNN) for feature extraction and risk prediction. The model includes the following steps: the spatial transformation of variables using kernel Principal Component Analysis (kPCA), the creation of 2D images from transformed data, the application of convolutional filters, max-pooling, flattening, and final risk prediction via a fully connected layer. Performance metrics such as accuracy, precision, recall, and area under the ROC curve (AUC) will be used to evaluate the model.

DISCUSSION: The MINERVA study aims to address the specific gap in predicting RAP risk in MABP patients by leveraging advanced ML techniques. By incorporating a wide range of clinical and demographic variables, the MINERVA score aims to provide a reliable, cost-effective, and accessible tool for healthcare professionals. The project emphasises the practical application of AI in clinical settings, potentially reducing the incidence of RAP and associated healthcare costs.

TRIAL REGISTRATION: ClinicalTrials.gov ID: NCT06124989.

PMID:40033414 | DOI:10.1186/s13017-025-00594-7

BMC Med Imaging. 2025 Mar 3;25(1):67. doi: 10.1186/s12880-025-01582-8.

ABSTRACT

PURPOSES: To develop a predictive model for recurrent intussusception based on abdominal ultrasound (US) images and abdominal radiographs.

METHODS: A total of 3665 cases of intussusception were retrospectively collected from January 2017 to December 2022. The cohort was randomly assigned to training and validation sets at a 6:4 ratio. Two types of images were processed: abdominal grayscale US images and abdominal radiographs. These images served as inputs for the deep learning algorithm and were individually processed by five detection models for training, with each model predicting its respective categories and probabilities. The optimal models were selected individually for decision fusion to obtain the final predicted categories and their probabilities.

RESULTS: With US, the VGG11 model showed the best performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.669 (95% CI: 0.635-0.702). In contrast, with radiographs, the ResNet18 model excelled with an AUC of 0.809 (95% CI: 0.776-0.841). We then employed two fusion methods. In the averaging fusion method, the two models were combined to reach a diagnostic decision. Specifically, a soft voting scheme was used to average the probabilities predicted by each model, resulting in an AUC of 0.877 (95% CI: 0.846-0.908). In the stacking fusion method, a meta-model was built based on the predictions of the two optimal models. This approach notably enhanced the overall predictive performance, with LightGBM emerging as the top performer, achieving an AUC of 0.897 (95% CI: 0.869-0.925). Both fusion methods demonstrated excellent performance.

CONCLUSIONS: Deep learning algorithms developed using multimodal medical imaging may help predict recurrent intussusception.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:40033220 | DOI:10.1186/s12880-025-01582-8

BMC Plant Biol. 2025 Mar 4;25(1):282. doi: 10.1186/s12870-025-06289-0.

ABSTRACT

OBJECTIVE: The objective is to develop a reliable deep learning (DL) based model that can accurately diagnose diseases. It seeks to address the challenges posed by the traditional approach of manually diagnosing diseases to enhance the control of disease and sugarcane production.

METHODS: In order to identify the diseases in sugarcane leaves, this study used EfficientNet architectures along with other well-known convolutional neural network (ConvNet) models such as DenseNet201, ResNetV2, InceptionV4, MobileNetV3 and RegNetX. The models were trained and tested on the Sugarcane Leaf Dataset (SLD) which consists of 6748 images of healthy and diseased leaves, across 11 disease classes. To provide a valid evaluation for the proposed models, the dataset was additionally split into subsets for training (70%), validation (15%) and testing (15%). The models provided were also assessed inclusively in terms of accuracy, further evaluation also took into account level of model's complexity and its depth.

RESULTS: EfficientNet-B7 and DenseNet201 achieved the highest classification accuracy rates of 99.79% and 99.50%, respectively, among 14 models tested. To ensure a robust evaluation and reduce potential biases, 5-fold cross-validation was used, further validating the consistency and reliability of the models across different dataset partitions. Analysis revealed no direct correlation between model complexity, depth, and accuracy for the 11-class sugarcane dataset, emphasizing that optimal performance is not solely dependent on the model's architecture or depth but also on its adaptability to the dataset.

DISCUSSION: The study demonstrates the effectiveness of DL models, particularly EfficientNet-B7 and DenseNet201, for fast, accurate, and automatic disease detection in sugarcane leaves. These systems offer a significant improvement over traditional manual methods, enabling farmers and agricultural managers to make timely and informed decisions, ultimately reducing crop loss and enhancing overall sugarcane yield. This work highlights the transformative potential of DL in agriculture.

PMID:40033192 | DOI:10.1186/s12870-025-06289-0

Respirology. 2025 Mar 3. doi: 10.1111/resp.70010. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Echo features of lymph nodes (LNs) influence target selection during endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA). This study evaluates deep learning's diagnostic capabilities on EBUS images for detecting mediastinal LN metastasis in lung cancer, emphasising the added value of integrating a region of interest (ROI), LN size on CT, and PET-CT findings.

METHODS: We analysed 2901 EBUS images from 2055 mediastinal LN stations in 1454 lung cancer patients. ResNet18-based deep learning models were developed to classify images of true positive malignant and true negative benign LNs diagnosed by EBUS-TBNA using different inputs: original images, ROI images, and CT size and PET-CT data. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC) and other diagnostic metrics.

RESULTS: The model using only original EBUS images showed the lowest AUROC (0.870) and accuracy (80.7%) in classifying LN images. Adding ROI information slightly increased the AUROC (0.896) without a significant difference (p = 0.110). Further adding CT size resulted in a minimal change in AUROC (0.897), while adding PET-CT (original + ROI + PET-CT) showed a significant improvement (0.912, p = 0.008 vs. original; p = 0.002 vs. original + ROI + CT size). The model combining original and ROI EBUS images with CT size and PET-CT findings achieved the highest AUROC (0.914, p = 0.005 vs. original; p = 0.018 vs. original + ROI + PET-CT) and accuracy (82.3%).

CONCLUSION: Integrating an ROI, LN size on CT, and PET-CT findings into the deep learning analysis of EBUS images significantly enhances the diagnostic capability of models for detecting mediastinal LN metastasis in lung cancer, with the integration of PET-CT data having a substantial impact.

PMID:40033122 | DOI:10.1111/resp.70010

BJC Rep. 2025 Mar 3;3(1):12. doi: 10.1038/s44276-025-00123-8.

ABSTRACT

BACKGROUND: Within the colorectal cancer (CRC) tumour microenvironment, tumour infiltrating lymphocytes (TILs) and tumour cell density (TCD) are recognised prognostic markers. Measurement of TILs and TCD using deep-learning (DL) on haematoxylin and eosin (HE) whole slide images (WSIs) could aid management.

METHODS: HE WSIs from the primary tumours of 127 CRC patients were included. DL was used to quantify TILs across different regions of the tumour and TCD at the luminal surface. The relationship between TILs, TCD, and cancer-specific survival was analysed.

RESULTS: Median TIL density was higher at the invasive margin than the luminal surface (963 vs 795 TILs/mm2, P = 0.010). TILs and TCD were independently prognostic in multivariate analyses (HR 4.28, 95% CI 1.87-11.71, P = 0.004; HR 2.72, 95% CI 1.19-6.17, P = 0.017, respectively). Patients with both low TCD and low TILs had the poorest survival (HR 10.0, 95% CI 2.51-39.78, P = 0.001), when compared to those with a high TCD and TILs score.

CONCLUSIONS: DL derived TIL and TCD score were independently prognostic in CRC. Patients with low TILs and TCD are at the highest risk of cancer-specific death. DL quantification of TILs and TCD could be used in combination alongside other validated prognostic biomarkers in routine clinical practice.

PMID:40033106 | DOI:10.1038/s44276-025-00123-8

Sci Rep. 2025 Mar 3;15(1):7425. doi: 10.1038/s41598-025-92293-1.

ABSTRACT

Skin cancer is the most dominant and critical method of cancer, which arises all over the world. Its damaging effects can range from disfigurement to major medical expenditures and even death if not analyzed and preserved timely. Conventional models of skin cancer recognition require a complete physical examination by a specialist, which is time-wasting in a few cases. Computer-aided medicinal analytical methods have gained massive popularity due to their efficiency and effectiveness. This model can assist dermatologists in the initial recognition of skin cancer, which is significant for early diagnosis. An automatic classification model utilizing deep learning (DL) can help doctors perceive the kind of skin lesion and improve the patient's health. The classification of skin cancer is one of the hot topics in the research field, along with the development of DL structure. This manuscript designs and develops a Detection of Skin Cancer Using an Ensemble Deep Learning Model and Gray Wolf Optimization (DSC-EDLMGWO) method. The proposed DSC-EDLMGWO model relies on the recognition and classification of skin cancer in biomedical imaging. The presented DSC-EDLMGWO model initially involves the image preprocessing stage at two levels: contract enhancement using the CLAHE method and noise removal using the wiener filter (WF) model. Furthermore, the proposed DSC-EDLMGWO model utilizes the SE-DenseNet method, which is the fusion of the squeeze-and-excitation (SE) module and DenseNet to extract features. For the classification process, the ensemble of DL models, namely the long short-term memory (LSTM) technique, extreme learning machine (ELM) model, and stacked sparse denoising autoencoder (SSDA) method, is employed. Finally, the gray wolf optimization (GWO) method optimally adjusts the ensemble DL models' hyperparameter values, resulting in more excellent classification performance. The effectiveness of the DSC-EDLMGWO approach is evaluated using a benchmark image database, with outcomes measured across various performance metrics. The experimental validation of the DSC-EDLMGWO approach portrayed a superior accuracy value of 98.38% and 98.17% under HAM10000 and ISIC datasets across other techniques.

PMID:40033075 | DOI:10.1038/s41598-025-92293-1