IEEE Trans Pattern Anal Mach Intell. 2025 Apr 3;PP. doi: 10.1109/TPAMI.2025.3557498. Online ahead of print.

ABSTRACT

Deep learning has significantly propelled the development of photometric stereo by handling the challenges posed by unknown reflectance and global illumination effects. However, how supervised learning-based photometric stereo networks resolve these challenges remains to be elucidated. In this paper, we aim to reveal how existing methods address these challenges by revisiting their deep features, deep feature encoding strategies, and network architectures. Based on the insights gained from our analysis, we propose ESSENCE-Net, which effectively encodes deep shading features with an easy-first-encoding strategy, enhances shading features with shading supervision, and accurately decodes normal with spatial context-aware attention. The experimental results verify that the proposed method outperforms state-of-the-art methods on three benchmark datasets, whether with dense or sparse inputs. The code is available at https://github.com/wxy-zju/ESSENCE-Net.

PMID:40178960 | DOI:10.1109/TPAMI.2025.3557498

IEEE Trans Med Imaging. 2025 Apr 3;PP. doi: 10.1109/TMI.2025.3557430. Online ahead of print.

ABSTRACT

Cephalometric landmark detection is essential for orthodontic diagnostics and treatment planning. Nevertheless, the scarcity of samples in data collection and the extensive effort required for manual annotation have significantly impeded the availability of diverse datasets. This limitation has restricted the effectiveness of deep learning-based detection methods, particularly those based on large-scale vision models. To address these challenges, we have developed an innovative data generation method capable of producing diverse cephalometric X-ray images along with corresponding annotations without human intervention. To achieve this, our approach initiates by constructing new cephalometric landmark annotations using anatomical priors. Then, we employ a diffusion-based generator to create realistic X-ray images that correspond closely with these annotations. To achieve precise control in producing samples with different attributes, we introduce a novel prompt cephalometric X-ray image dataset. This dataset includes real cephalometric X-ray images and detailed medical text prompts describing the images. By leveraging these detailed prompts, our method improves the generation process to control different styles and attributes. Facilitated by the large, diverse generated data, we introduce large-scale vision detection models into the cephalometric landmark detection task to improve accuracy. Experimental results demonstrate that training with the generated data substantially enhances the performance. Compared to methods without using the generated data, our approach improves the Success Detection Rate (SDR) by 6.5%, attaining a notable 82.2%. All code and data are available at: https://um-lab.github.io/cepha-generation/.

PMID:40178956 | DOI:10.1109/TMI.2025.3557430

Respir Care. 2025 Apr 3. doi: 10.1089/respcare.12540. Online ahead of print.

ABSTRACT

Patient-ventilator asynchrony (PVA) is a challenge to invasive mechanical ventilation characterized by misalignment of ventilatory support and patient respiratory effort. PVA is highly prevalent and associated with adverse clinical outcomes, including increased work of breathing, oxygen consumption, and risk of barotrauma. Artificial intelligence (AI) is a potentially transformative solution offering capabilities for automated detection of PVA. This narrative review characterizes the landscape of AI models designed for PVA detection and quantification. A comprehensive literature search identified 13 studies, spanning diverse settings and patient populations. Machine learning (ML) techniques, derivation datasets, types of asynchronies detected, and performance metrics were assessed to provide a contemporary view of AI in this domain. We reviewed 166 articles published between 1989 and April 2024, of which 13 were included, encompassing 332 participants and analyzing >5.8 million breaths. Patient counts ranged between 8 and 107 and breath data ranged between 1,375 and 4.2 M. The reason for invasive mechanical ventilation use was given as ARDS in three articles, whereas the remainder had different invasive mechanical ventilation indications. Various ML methods as well as newer deep learning techniques were used to address PVA types. Sensitivity and specificity of 10 of the 13 models were >0.9, and 8 models reported accuracy of >0.9. AI models have significant potential to address PVA in invasive mechanical ventilation, displaying high accuracy across various populations and asynchrony types. This showcases their potential to accurately detect and quantify PVA. Future work should focus on model validation in diverse clinical settings and patient populations.

PMID:40178919 | DOI:10.1089/respcare.12540

J Clin Invest. 2025 Apr 3:e180570. doi: 10.1172/JCI180570. Online ahead of print.

ABSTRACT

Hyaluronan (HA) in the extracellular matrix promotes epithelial-to-mesenchymal transition (EMT) and metastasis; however, the mechanism by which the HA network constructed by cancer cells regulates cancer progression and metastasis in the tumor microenvironment (TME) remains largely unknown. In this study, inter-alpha-trypsin inhibitor heavy chain 2 (ITIH2), an HA-binding protein, was confirmed to be secreted from mesenchymal-like lung cancer cells when co-cultured with cancer-associated fibroblasts. ITIH2 expression is transcriptionally upregulated by the EMT-inducing transcription factor ZEB1, along with HA synthase 2 (HAS2), which positively correlates with ZEB1 expression. Depletion of ITIH2 and HAS2 reduced HA matrix formation and the migration and invasion of lung cancer cells. Furthermore, ZEB1 facilitates alternative splicing and isoform expression of CD44, an HA receptor, and CD44 knockdown suppresses the motility and invasiveness of lung cancer cells. Using a deep learning-based drug-target interaction algorithm, we identified an ITIH2 inhibitor (sincalide) that inhibited HA matrix formation and migration of lung cancer cells, preventing metastatic colonization of lung cancer cells in mouse models. These findings suggest that ZEB1 remodels the HA network in the TME through the regulation of ITIH2, HAS2, and CD44, presenting a strategy for targeting this network to suppress lung cancer progression.

PMID:40178908 | DOI:10.1172/JCI180570

STAR Protoc. 2025 Apr 1;6(2):103721. doi: 10.1016/j.xpro.2025.103721. Online ahead of print.

ABSTRACT

Autotaxin (ATX), a secreted lysophospholipase D responsible for the extracellular production of the bioactive phospholipid lysophosphatidic acid (LPA), is a therapeutic target in idiopathic pulmonary fibrosis and pancreatic cancer, among other disorders, promoting the synthesis of novel ATX inhibitors. Here, we present a protocol for detecting and characterizing ATX inhibitors using a fluorometry-based microplate assay. We describe steps for a first screening of compounds, half-maximal inhibitory concentration (IC50) quantification of initial hits, screening for false positives, and identification of the hits' mode of inhibition. For complete details on the use and execution of this protocol, please refer to Stylianaki et al.1.

PMID:40178971 | DOI:10.1016/j.xpro.2025.103721

J Am Soc Mass Spectrom. 2025 Apr 3. doi: 10.1021/jasms.4c00467. Online ahead of print.

ABSTRACT

Targeted quantification metabolomics provides dynamic insights across various domains within the life sciences. Nevertheless, maintaining high-quality data obtained through liquid chromatography-mass spectrometry presents ongoing challenges. It is essential to develop normalization methods to correct for unwanted variations in metabolomic profiling such as batch effects and analytical drift. In this study, we assessed the normalization efficacy of Norm ISWSVR in targeted quantification metabolomics by comparing it with IS normalization and SERRF normalization. Consequently, Norm ISWSVR demonstrated exceptional efficacy in mitigating batch effects and reducing the relative standard deviation of quality control samples, in addition to correcting signal drift. Following normalization with Norm ISWSVR, the number of metabolites suitable for quantification increased with high precision. Collectively, Norm ISWSVR proves to be a robust and reliable method for enhancing data quality in targeted metabolomics, establishing itself as a promising approach for metabolomics research.

PMID:40179246 | DOI:10.1021/jasms.4c00467

Science. 2025 Apr 4;388(6742):52-59. doi: 10.1126/science.ads7951. Epub 2025 Apr 3.

ABSTRACT

Most phenotype-associated genetic variants map to noncoding regulatory regions of the human genome, but their mechanisms remain elusive in most cases. We developed a highly efficient strategy, Perturb-multiome, to simultaneously profile chromatin accessibility and gene expression in single cells with CRISPR-mediated perturbation of master transcription factors (TFs). We examined the connection between TFs, accessible regions, and gene expression across the genome throughout hematopoietic differentiation. We discovered that variants within TF-sensitive accessible chromatin regions in erythroid differentiation, although representing <0.3% of the genome, show a ~100-fold enrichment for blood cell phenotype heritability, which is substantially higher than that for other accessible chromatin regions. Our approach facilitates large-scale mechanistic understanding of phenotype-associated genetic variants by connecting key cis-regulatory elements and their target genes within gene regulatory networks.

PMID:40179192 | DOI:10.1126/science.ads7951

J Agric Food Chem. 2025 Apr 3. doi: 10.1021/acs.jafc.5c00568. Online ahead of print.

ABSTRACT

Natural acylsucrose, often found in the glandular trichomes of Solanaceae plants, has potential applications in many industries, including food, cosmetics, and pharmaceuticals. In this study, we engineered an Escherichia coli strain to complete the biosynthesis of acylsucroses through whole-cell transformation. Using acylsucrose acyltransferases and CoA ligases, acylsucroses, including monoacylsucrose S1:5 ("S" represents an acylsucrose backbone, the number before the colon indicates the number of acyl chains, and the number after the colon indicates the sum of carbons in all acyl chains), diacylsucrose S2:10, triacylsucrose S3:14, and triacylsucrose S3:15 were synthesized from the substrate sucrose and short branched-chain fatty acids by the engineered E. coli EcoSE07, of which S3:15 was the primary product. Several strategies were applied to improve acylsucrose production, including codon optimization, constitutive promoter replacement, and serial resting cell assays. The use of fed-batch fermentation with an engineered E. coli strain of EcoSE22 containing a constitutive promoter further improved the production of acylsucroses. Serial resting cell assays with an optical density of 50 at 600 nm significantly increased the production of acylsucroses S3:15 and S2:10. These findings will facilitate the synthesis of natural acylsucroses through whole-cell transformations and provide the potential for future industrial applications.

PMID:40179051 | DOI:10.1021/acs.jafc.5c00568

Rev Med Suisse. 2025 Apr 2;21(912):660-663. doi: 10.53738/REVMED.2025.21.912.660.

ABSTRACT

In everyday practice, many patients experience reactions to substances from different drug families. Multiple Drug Hypersensitivity Syndrome (MDHS) and Multiple Drug Intolerance Syndrome (MDIS) both involve reactions to several unrelated drugs but differ in pathophysiology and clinical presentation. Rare and immune-mediated, MDHS involves T lymphocytes and presents with severe delayed exanthems, eosinophilia, and moderate hepatic cytolysis triggered by at least two chemically distinct drugs. In contrast, MDIS is a diagnosis of exclusion, characterized by adverse reactions-often pseudoallergic and immediate-to three or more unrelated drugs, occurring upon separate exposures with negative allergy tests.

PMID:40176614 | DOI:10.53738/REVMED.2025.21.912.660

Interdiscip Sci. 2025 Apr 3. doi: 10.1007/s12539-025-00698-3. Online ahead of print.

ABSTRACT

Identification of drug-target interactions (DTIs) is critical for drug discovery and drug repositioning. However, most DTI methods that extract features from drug molecules and protein entities neglect specific substructure information of pharmacological responses, which leads to poor predictive performance. Moreover, most existing methods are based on molecular graphs or molecular descriptors to obtain abstract representations of molecules, but combining the two feature learning methods for DTI prediction remains unexplored. Therefore, a new ASCS-DTI framework for DTI prediction is proposed, which utilizes a substructure attention mechanism to flexibly capture substructures of compounds at different grain sizes, allowing the important substructure information of each molecule to be learned. Additionally, the framework combines three different molecular fingerprinting information to comprehensively characterize molecular representations. A stacked convolutional coding module processes the sequence information of target proteins in a multi-scale and multi-level view. Finally, multi-modal fusion of molecular graph features and molecular fingerprint features, along with multi-modal information encoding of DTIs, is performed by the feature fusion module. The method outperforms six advanced baseline models on different benchmark datasets: Biosnap, BindingDB, and Human, with a significant improvement in performance, particularly in maintaining strong results across different experimental settings.

PMID:40178777 | DOI:10.1007/s12539-025-00698-3

Neurogenetics. 2025 Apr 3;26(1):41. doi: 10.1007/s10048-025-00822-x.

ABSTRACT

Neurodevelopmental, jaw, eye, and digital syndrome (NEDJED) is a rare autosomal dominant condition that has demonstrated diverse phenotypes. This is the second case report published on this condition, covering the disease history of an 8 year old patient with a severe manifestation of the disease. The patient was born with hydrocephalus, and demonstrated major developmental delay as he aged. Whole-genome sequencing of the patient and his parents was conducted, detecting a de novo variant, NM_001378974.1:c.1220 A > T [p.Lys407Ile], located in the conserved WD4 region of the WD40 domain of FBXW11, which is consistent with all previously reported patients. The phenotype of the patient is presented with a focus on MRI and EEG features, including images and detailed description for both. While the patient's phenotype is overall consistent with previous findings, there are a number of major factors we believe are caused by the FBXW11 variant that have not been previously described, such as the patient's complete inability to walk.

PMID:40178747 | DOI:10.1007/s10048-025-00822-x

J Insect Sci. 2025 Mar 14;25(2):8. doi: 10.1093/jisesa/ieaf019.

ABSTRACT

Taxonomy provides a general foundation for research on insects. Using stored product pest (SPP) arthropods as a model group, this article overviews the historical impacts of taxonomy on applied entomology. The article surveys the dynamics of historical descriptions of new species in various SPP taxa; the majority of all species (90%) were described prior to 1925, while the key pests were described prior to 1866. The review shows that process of describing new SPP species is not random but is influenced by following factors: (i) larger species tend to be described earlier than smaller and SPP moths and beetles are described earlier than psocids and mites; (ii) key economic pests are on average described earlier than less significant ones. Considering a species name as a "password" to unique information resources, this review also assesses the historical number of synonymous or duplicate names of SPP species. Pests belonging to some higher taxa Lepidoptera and Coleoptera has accumulated more scientific synonyms than those others belonging to Psocoptera and Acari. Number of synonyms positively correlated with the economic importance of SPP species. The review summarized semantic origin of SPP names showing minor proportion of names (17.6%) are toponyms (geography) or eponyms (people), while the majority (82.4%) fall into other categories (descriptive, etc.). It is concluded that awareness of taxonomic advances, including changes to species and higher taxa names, should be effectively communicated to pest control practitioners and applied entomology students, and specifically addressed in relevant textbooks, web media, and databases.

PMID:40178352 | DOI:10.1093/jisesa/ieaf019

Angew Chem Int Ed Engl. 2025 Apr 3:e202505714. doi: 10.1002/anie.202505714. Online ahead of print.

ABSTRACT

Antibiotic-resistant bacteria of the genus Pandoraea, frequently acquired from the environment, are an emerging cause of opportunistic respiratory infections, especially in cystic fibrosis (CF) patients. However, their specialized metabolites, including niche and virulence factors, remained unknown. Through genome mining of environmental and clinical isolates of diverse Pandoraea species, we identified a highly conserved biosynthesis gene cluster (pan) that codes for a non-ribosomal peptide synthetase (NRPS) assembling a new siderophore. Using bioinformatics-guided metabolic profiling of wild type and a targeted null mutant, we discovered the corresponding metabolites, pandorabactin A and B. Their structures and chelate (gallium) complexes were elucidated by a combination of chemical degradation, derivatization, NMR, and MS analysis. Metagenomics and bioinformatics of sputum samples of CF patients indicated that the presence of the pan gene locus correlates with the prevalence of specific bacteria in the lung microbiome. Bioassays and mass spectrometry imaging showed that pandorabactins have antibacterial activities against various lung pathogens (Pseudomonas, Mycobacterium, and Stenotrophomonas) through depleting iron in the competitors. Taken together, these findings offer first insight into niche factors of Pandoraea and indicate that pandorabactins shape the diseased lung microbiota through the competition for iron.

PMID:40178319 | DOI:10.1002/anie.202505714

Abdom Radiol (NY). 2025 Apr 3. doi: 10.1007/s00261-025-04921-z. Online ahead of print.

ABSTRACT

BACKGROUND: This study aimed to preoperatively predict Ki-67 proliferation levels in patients with pancreatic solid pseudopapillary neoplasm (pSPN) using radiomics features extracted from arterial phase helical CT images.

METHODS: We retrospectively analyzed 92 patients (Ningbo Medical Center Lihuili Hospital: n = 64, Taizhou Central Hospital: n = 28) with pathologically confirmed pSPN from June 2015 to June 2023. Ki-67 positivity > 3% was considered high. Radiomics features were extracted using PyRadiomics, with patients from training cohort (n = 64) and validation cohort (n = 28). A radiomics signature was constructed, and a CT radiomics score (CTscore) was calculated. Deep learning models were employed for prediction, with early stopping to prevent overfitting.

RESULTS: Seven key radiomics features were selected via LASSO regression with cross-validation. The deep learning model demonstrated improved accuracy with demographics and CTscore, with key features such as Morphology and CTscore contributing significantly to predictive accuracy. The best-performing models, including GBM and deep learning algorithms, achieved high predictive performance with an AUC of up to 0.946 in the training cohort.

CONCLUSIONS: We developed a robust deep learning-based radiomics model using arterial phase CT images to predict Ki-67 levels in pSPN patients, identifying CTscore and Morphology as key predictors. This non-invasive approach has potential utility in guiding personalized preoperative treatment strategies.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:40178588 | DOI:10.1007/s00261-025-04921-z

Radiol Cardiothorac Imaging. 2025 Apr;7(2):e240272. doi: 10.1148/ryct.240272.

ABSTRACT

Purpose To develop and evaluate a free-breathing, highly accelerated, multisection, single-beat cine sequence for cardiac MRI. Materials and Methods This prospective study, conducted from July 2022 to December 2023, included participants with various cardiac conditions as well as healthy participants who were imaged using a 3-T MRI system. A single-beat sequence was implemented, collecting data for each section in one heartbeat. Images were acquired with an in-plane spatiotemporal resolution of 1.9 × 1.9 mm2 and 37 msec and reconstructed using resolution enhancement generative adversarial inline neural network (REGAIN), a deep learning model. Multibreath-hold k-space-segmented (4.2-fold acceleration) and free-breathing single-beat (14.8-fold acceleration) cine images were collected, both reconstructed with REGAIN. Left ventricular (LV) and right ventricular (RV) parameters between the two methods were evaluated with linear regression, Bland-Altman analysis, and Pearson correlation. Three expert cardiologists independently scored diagnostic and image quality. Scan and rescan reproducibility was evaluated in a subset of participants 1 year apart using the intraclass correlation coefficient (ICC). Results This study included 136 participants (mean age [SD], 54 years ± 15; 69 female, 67 male), 40 healthy and 96 with cardiac conditions. k-Space-segmented and single-beat scan times were 2.6 minutes ± 0.8 and 0.5 minute ± 0.1, respectively. Strong correlations (P < .001) were observed between k-space-segmented and single-beat cine parameters in both LV (r = 0.97-0.99) and RV (r = 0.89-0.98). Scan and rescan reproducibility of single-beat cine was excellent (ICC, 0.97-1.0). Agreement among readers was high, with 125 of 136 (92%) images consistently assessed as diagnostic and 133 of 136 (98%) consistently rated as having good image quality by all readers. Conclusion Free-breathing 30-second single-beat cardiac cine MRI yielded accurate biventricular measurements, reduced scan time, and maintained high diagnostic and image quality compared with conventional multibreath-hold k-space-segmented cine images. Keywords: MR-Imaging, Cardiac, Heart, Imaging Sequences, Comparative Studies, Technology Assessment Supplemental material is available for this article. © RSNA, 2025.

PMID:40178397 | DOI:10.1148/ryct.240272

Brief Bioinform. 2025 Mar 4;26(2):bbaf126. doi: 10.1093/bib/bbaf126.

ABSTRACT

With the rapid advances in single-cell sequencing technology, it is now feasible to conduct in-depth genetic analysis in individual cells. Study on the dynamics of single cells in response to perturbations is of great significance for understanding the functions and behaviors of living organisms. However, the acquisition of post-perturbation cellular states via biological experiments is frequently cost-prohibitive. Predicting the single-cell perturbation responses poses a critical challenge in the field of computational biology. In this work, we propose a novel deep learning method called coupled variational autoencoders (CoupleVAE), devised to predict the postperturbation single-cell RNA-Seq data. CoupleVAE is composed of two coupled VAEs connected by a coupler, initially extracting latent features for controlled and perturbed cells via two encoders, subsequently engaging in mutual translation within the latent space through two nonlinear mappings via a coupler, and ultimately generating controlled and perturbed data by two separate decoders to process the encoded and translated features. CoupleVAE facilitates a more intricate state transformation of single cells within the latent space. Experiments in three real datasets on infection, stimulation and cross-species prediction show that CoupleVAE surpasses the existing comparative models in effectively predicting single-cell RNA-seq data for perturbed cells, achieving superior accuracy.

PMID:40178283 | DOI:10.1093/bib/bbaf126

Brief Bioinform. 2025 Mar 4;26(2):bbaf134. doi: 10.1093/bib/bbaf134.

ABSTRACT

Drug response prediction (DRP) methods tackle the complex task of associating the effectiveness of small molecules with the specific genetic makeup of the patient. Anti-cancer DRP is a particularly challenging task requiring costly experiments as underlying pathogenic mechanisms are broad and associated with multiple genomic pathways. The scientific community has exerted significant efforts to generate public drug screening datasets, giving a path to various machine learning models that attempt to reason over complex data space of small compounds and biological characteristics of tumors. However, the data depth is still lacking compared to application domains like computer vision or natural language processing domains, limiting current learning capabilities. To combat this issue and improves the generalizability of the DRP models, we are exploring strategies that explicitly address the imbalance in the DRP datasets. We reframe the problem as a multi-objective optimization across multiple drugs to maximize deep learning model performance. We implement this approach by constructing Multi-Objective Optimization Regularized by Loss Entropy loss function and plugging it into a Deep Learning model. We demonstrate the utility of proposed drug discovery methods and make suggestions for further potential application of the work to achieve desirable outcomes in the healthcare field.

PMID:40178282 | DOI:10.1093/bib/bbaf134

Brief Bioinform. 2025 Mar 4;26(2):bbaf115. doi: 10.1093/bib/bbaf115.

ABSTRACT

The rapid advancement of next-generation sequencing (NGS) technology and the expanding availability of NGS datasets have led to a significant surge in biomedical research. To better understand the molecular processes, underlying cancer and to support its development, diagnosis, prediction, and therapy; NGS data analysis is crucial. However, the NGS multi-layer omics high-dimensional dataset is highly complex. In recent times, some computational methods have been developed for cancer omics data interpretation. However, various existing methods face challenges in accounting for diverse types of cancer omics data and struggle to effectively extract informative features for the integrated identification of core units. To address these challenges, we proposed a hybrid feature selection (HFS) technique to detect optimal features from multi-layer omics datasets. Subsequently, this study proposes a novel hybrid deep recurrent neural network-based model DOMSCNet to classify stomach cancer. The proposed model was made generic for all four multi-layer omics datasets. To observe the robustness of the DOMSCNet model, the proposed model was validated with eight external datasets. Experimental results showed that the SelectKBest-maximum relevancy minimum redundancy-Boruta (SMB), HFS technique outperformed all other HFS techniques. Across four multi-layer omics datasets and validated datasets, the proposed DOMSCNet model outdid existing classifiers along with other proposed classifiers.

PMID:40178281 | DOI:10.1093/bib/bbaf115

J Chem Inf Model. 2025 Apr 3. doi: 10.1021/acs.jcim.4c02293. Online ahead of print.

ABSTRACT

This study investigates the application of a deep learning (DL) model, specifically a message-passing neural network (MPNN) implemented through Chemprop, to predict the persistence, bioaccumulation, and toxicity (PBT) characteristics of compounds, with a focus on pharmaceuticals. We employed a clustering strategy to provide a fair assessment of the model performances. By applying the generated model to a set of pharmaceutically relevant molecules, we aim to highlight potential PBT chemicals and extract PBT-relevant substructures. These substructures can serve as structural flags, alerting drug designers to potential environmental issues from the earliest stages of the drug discovery process. Incorporating these findings into pharmaceutical development workflows is expected to drive significant advancements in creating more environmentally friendly drug candidates while preserving their therapeutic efficacy.

PMID:40178174 | DOI:10.1021/acs.jcim.4c02293

Cancer Invest. 2025 Apr 3:1-19. doi: 10.1080/07357907.2025.2483302. Online ahead of print.

ABSTRACT

Colon Cancer (CC) arises from abnormal cell growth in the colon, which severely impacts a person's health and quality of life. Detecting CC through histopathological images for early diagnosis offers substantial benefits in medical diagnostics. This study proposes NalexNet, a hybrid deep-learning classifier, to enhance classification accuracy and computational efficiency. The research methodology involves Vahadane stain normalization for preprocessing and Watershed segmentation for accurate tissue separation. The Teamwork Optimization Algorithm (TOA) is employed for optimal feature selection to reduce redundancy and improve classification performance. Furthermore, the NalexNet model is structured with convolutional layers and normal and reduction cells, ensuring efficient feature representation and high classification accuracy. Experimental results demonstrate that the proposed model achieves a precision of 99.9% and an accuracy of 99.5%, significantly outperforming existing models. This study contributes to the development of an automated and computationally efficient CC classification system, which has the potential for real-world clinical implementation, aiding pathologists in early and accurate diagnosis.

PMID:40178023 | DOI:10.1080/07357907.2025.2483302