Development and validation of an individualized nomogram for gastric cancer patients treated with perioperative chemotherapy followed by radical surgery.

Background: Prognostic factors are complicated and changeable for locally advanced gastric cancer (GC) patients. This study aimed to perform a novel prognostic model on survival for locally advanced GC patients who have received neoadjuvant chemotherapy and radical surgery. Methods: The locally advanced GC patients with neoadjuvant chemotherapy were included in this study from Zhongshan Hospital, Fudan University. A nomogram was developed based on independent prognostic factors identified through a multivariable Cox regression model. Model performance was evaluated in training and independent external cohorts in terms of calibration, discrimination, and clinical usefulness. Results: A total of 273 patients received radical resections. The median progression-free survival (PFS) and overall survival (OS) for all patients were 43.8 and 61.2 months, respectively. Nomogram showed that Lauren type made the greatest contribution to prognosis, followed by ypN. The prognostic nomogram had excellent discriminative ability, with a C-index of 0.689 [95% confidence interval (CI): 0.661-0.716], and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.778, 0.746, and 0.725 for 3-, 5- and 10-year OS, respectively. Similar results were obtained in the external validation cohort. Based on the nomogram, the whole cohort was divided into high-risk and low-risk groups. And risk group classification was significantly associated with clinical characteristics, and produced an AUC value of 0.781, 0.748, and 0.727 for 3-, 5- and 10-year OS, respectively. Furthermore, compared with the tumor-node-metastasis (TNM) staging system (8th edition), Japanese criteria, and German criteria, the decision curve analysis (DCA) graphically demonstrated that the new model had more optimal net benefits in predicting the 3-, 5-, and 10-year OS for GC patients. Both C-index and time-dependent ROC curve demonstrated that the nomogram had a stronger capability for accurately predicting prognosis compared with the other staging system. Conclusions: The nomogram model is an effective support tool to predict OS in GC patients undergoing perioperative chemotherapy followed by radical surgery.

Emerald Ash Borer Infestation-Induced Elevated Negative Correlations and Core Genera Shift in the Endophyte Community of Fraxinus bungeana.

Endophytes, prevalent in plants, mediate plant-insect interactions. Nevertheless, our understanding of the key members of endophyte communities involved in inhibiting or assisting EAB infestation remains limited. Employing ITS and 16S rRNA high-throughput sequencing, along with network analysis techniques, we conducted a comprehensive investigation into the reaction of endophytic fungi and bacteria within F. bungeana phloem by comparing EAB-infested and uninfected samples. Our findings reveal that EAB infestation significantly impacts the endophytic communities, altering both their diversity and overall structure. Interestingly, both endophytic fungi and bacteria exhibited distinct patterns in response to the infestation. For instance, in the EAB-infested phloem, the fungi abundance remained unchanged, but diversity decreased significantly. Conversely, bacterial abundance increased, without significant diversity changes. The fungi community structure altered significantly, which was not observed in bacteria. The bacterial composition in the infested phloem underwent significant changes, characterized by a substantial decrease in beneficial species abundance, whereas the fungal composition remained largely unaffected. In network analysis, the endophytes in infested phloem exhibited a modular topology, demonstrating greater complexity due to an augmented number of network nodes, elevated negative correlations, and a core genera shift compared to those observed in healthy phloem. Our findings increase understanding of plant-insect-microorganism relationships, crucial for pest control, considering endophytic roles in plant defense.

Charge self-regulation over in-plane two-dimensional/two-dimensional hetero-cocatalyst for robust photocatalytic hydrogen generation.

The rationally designing and constructing atomic-level heterointerface of two-dimensional (2D) chalcogenides is highly desirable to overcome the sluggish H2O-activation process toward efficient solar-driven hydrogen evolution. Herein, a novel in-plane 2D/2D molybdenum disulfide-rhenium disulfide (ReS2-MoS2) heterostructure is well-designed to induce the charge self-regulation of active site by forming electron-enriched Re(4-δ)+ and electron-deficient S(2-δ)- sites, thus collectively facilitating the activation of adsorbed H2O molecules and its subsequent H2 evolution. Furthermore, the obtained in-plane heterogenous ReS2-MoS2 nanosheet can powerfully transfer photoexcited electrons to inhibit photocarrier recombination as observed by advanced Kelvin probe measurement (KPFM), in-situ X-ray photoelectron spectroscopy (XPS) and femtosecond transient absorption spectroscopy (fs-TAS). As expected, the obtained ReS2-MoS2/TiO2 photocatalyst achieves an outperformed H2-generation rate of 6878.3 µmol h-1 g-1 with visualizing H2 bubbles in alkaline/neutral conditions. This work about in-plane 2D/2D heterostructure with strong free-electron interaction provides a promising strategy for designing novel and efficient catalysts for various applications.

Radiomics-based analysis of dynamic contrast-enhanced magnetic resonance image: A prediction nomogram for lymphovascular invasion in breast cancer.

OBJECTIVE: To develop and validate a nomogram for quantitively predicting lymphovascular invasion (LVI) of breast cancer (BC) based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics and morphological features. METHODS: We retrospectively divided 238 patients with BC into training and validation cohorts. Radiomic features from DCE-MRI were subdivided into A1 and A2, representing the first and second post-contrast images respectively. We utilized the minimal redundancy maximal relevance filter to extract radiomic features, then we employed the least absolute shrinkage and selection operator regression to screen these features and calculate individualized radiomics score (Rad score). Through the application of multivariate logistic regression, we built a prediction nomogram that integrated DCE-MRI radiomics and MR morphological features (MR-MF). The diagnostic capabilities were evaluated by comparing C-indices and calibration curves. RESULTS: The diagnostic efficiency of the A1/A2 radiomics model surpassed that of the A1 and A2 alone. Furthermore, we incorporated the MR-MF (diffusion-weighted imaging rim sign, peritumoral edema) and optimized Radiomics into a hybrid nomogram. The C-indices for the training and validation cohorts were 0.868 (95% CI: 0.839-0.898) and 0.847 (95% CI: 0.787-0.907), respectively, indicating a good level of discrimination. Moreover, the calibration plots demonstrated excellent agreement in the training and validation cohorts, confirming the effectiveness of the calibration. CONCLUSION: This nomogram combined MR-MF and A1/A2 Radiomics has the potential to preoperatively predict LVI in patients with BC.

Microclimate diversity drives grape quality difference at high-altitude: Observation using PCA analysis and structural equation modeling (SEM).

With the increasing threat of global warming, the cultivation of wine grapes in high-altitude with cool-temperature climates has become a viable option. However, the precise mechanism of environmental factors regulating grape quality remains unclear. Therefore, principal component analysis (PCA) was utilized to evaluate the quality of wine grape (Cabernet Sauvignon) in six high-altitude wine regions (1987, 2076, 2181, 2300, 2430, 2540 m). Structural equation modeling (SEM) was applied for the first time to identify the environmental contribution to grape quality. The wine grape quality existed spatial variation in basic physical attributes (BP), basic chemical compositions (BC), phenolic compounds (PC) and individual phenols. The PCA models (variance > 85 %) well separate wine grapes from the six altitudes into three groups according to scores. The score of grapes at 2300 m was significantly high (3.83), and the grapes of 2540 m showed a significantly low score (1.46). Subsequently, the malic acid, total tannin, total phenol, titratable acid, total anthocyanin, and skin thickness were the main differing indexes. SEM model characterized the relational network of differing indexes and microclimatic factors, which showed that temperature and extreme air temperature had a greater direct effect on differing indexes than light, with great contributions from soil temperature (0.98**), day-night temperature difference (0.825*), and day air temperature (0.789**). Our findings provided a theoretical basis for grape cultivation management in high-altitude regions and demonstrated that the SEM model is a useful tool for exploring the relationship between climate and fruit quality.

Efficacy of acupuncture in refractory irritable bowel syndrome patients: a randomized controlled trial.

Previous studies have confirmed that acupuncture for irritable bowel syndrome (IBS) provided an additional benefit over usual care alone. Therefore, we performed a multicenter, randomized, sham-controlled trial to assess the efficacy and safety of acupuncture versus sham acupuncture for refractory IBS in patients in the context of conventional treatments. Patients in the acupuncture and sham acupuncture groups received real or sham acupuncture treatment in 3 sessions per week for a total of 12 sessions. The primary outcome was a change in the IBS-Symptom Severity Scale (IBS-SSS) score from baseline to week 4. A total of 521 participants were screened, and 170 patients (85 patients per group) were enrolled and included in the intention-to-treat analysis. Baseline characteristics were comparable across the two groups. From baseline to 4 weeks, the IBS-SSS total score decreased by 140.0 (95% CI: 126.0 to 153.9) in the acupuncture group and 64.4 (95% CI: 50.4 to 78.3) in the sham acupuncture group. The between-group difference was 75.6 (95% CI: 55.8 to 95.4). Acupuncture efficacy was maintained during the 4-week follow-up period. There were no serious adverse events. In conclusion, acupuncture provided benefits when combined with treatment as usual, providing more options for the treatment of refractory IBS.

Artificial intelligence assisted ultrasound for the non-invasive prediction of axillary lymph node metastasis in breast cancer.

PURPOSE: A practical noninvasive method is needed to identify lymph node (LN) status in breast cancer patients diagnosed with a suspicious axillary lymph node (ALN) at ultrasound but a negative clinical physical examination. To predict ALN metastasis effectively and noninvasively, we developed an artificial intelligence-assisted ultrasound system and validated it in a retrospective study. METHODS: A total of 266 patients treated with sentinel LN biopsy and ALN dissection at Peking Union Medical College & Hospital(PUMCH) between the year 2017 and 2019 were assigned to training, validation and test sets (8:1:1). A deep learning model architecture named DeepLabV3 + was used together with ResNet-101 as the backbone network to create an ultrasound image segmentation diagnosis model. Subsequently, the segmented images are classified by a Convolutional Neural Network to predict ALN metastasis. RESULTS: The area under the receiver operating characteristic curve of the model for identifying metastasis was 0.799 (95% CI: 0.514-1.000), with good end-to-end classification accuracy of 0.889 (95% CI: 0.741-1.000). Moreover, the specificity and positive predictive value of this model was 100%, providing high accuracy for clinical diagnosis. CONCLUSION: This model can be a direct and reliable tool for the evaluation of individual LN status. Our study focuses on predicting ALN metastasis by radiomic analysis, which can be used to guide further treatment planning in breast cancer.

Pea protein-inulin conjugate prepared by atmospheric pressure plasma jet combined with glycosylation: structure and emulsifying properties.

Pea protein is one of plant proteins with high nutritional value, but its lower solubility and poor emulsifying properties limit its application in food industry. Based on wet-heating glycosylation of pea protein and inulin, effects of discharge power of atmospheric pressure plasma jet (APPJ) on structure, solubility, and emulsifying ability of pea protein-inulin glycosylation conjugate were explored. Results indicated that the APPJ discharge power did not affect the primary structure of pea protein. However, changes in secondary and spatial structure of pea protein were observed. When APPJ discharge power was 600 W, the solubility of glycosylation conjugate was 75.0% and the emulsifying stability index was 98.9 min, which increased by 14.85 and 21.95% than that of only glycosylation sample, respectively. These findings could provide technical support for APPJ treatment combination with glycosylation to enhance the physicochemical properties of plant-based proteins.

Computer-aided molecular design and optimization of potent inhibitors disrupting APC‒Asef interaction.

Colorectal cancer (CRC) is the second leading cause of cancer mortality worldwide. At initial diagnosis, approximately 20% of patients are diagnosed with metastatic CRC (mCRC). Although the APC‒Asef interaction is a well-established target for mCRC therapy, the discovery and development of effective and safe drugs for mCRC patients remains an urgent and challenging endeavor. In this study, we identified a novel structural scaffold based on MAI inhibitors, the first-in-class APC‒Asef inhibitors we reported previously. ONIOM model-driven optimizations of the N-terminal cap and experimental evaluations of inhibitory activity were performed, and 24-fold greater potency was obtained with the best inhibitor compared to the parental compound. In addition, the cocrystal structure validated that the two-layer π‒π stacking interactions were essential for inhibitor stabilization in the bound state. Furthermore, in vitro and in vivo studies have demonstrated that novel inhibitors suppressed lung metastasis in CRC by disrupting the APC‒Asef interaction. These results provide an intrinsic structural basis to further explore drug-like molecules for APC‒Asef-mediated CRC therapy.

Automated classification of cellular expression in multiplexed imaging data with Nimbus.

Multiplexed imaging offers a powerful approach to characterize the spatial topography of tissues in both health and disease. To analyze such data, the specific combination of markers that are present in each cell must be enumerated to enable accurate phenotyping, a process that often relies on unsupervised clustering. We constructed the Pan-Multiplex (Pan-M) dataset containing 197 million distinct annotations of marker expression across 15 different cell types. We used Pan-M to create Nimbus, a deep learning model to predict marker positivity from multiplexed image data. Nimbus is a pre-trained model that uses the underlying images to classify marker expression across distinct cell types, from different tissues, acquired using different microscope platforms, without requiring any retraining. We demonstrate that Nimbus predictions capture the underlying staining patterns of the full diversity of markers present in Pan-M. We then show how Nimbus predictions can be integrated with downstream clustering algorithms to robustly identify cell subtypes in image data. We have open-sourced Nimbus and Pan-M to enable community use at https://github.com/angelolab/Nimbus-Inference.

Animal models of studying the pathogenesis of multi-organ tissue damage in lupus.

Moderate-to-severe systemic lupus erythematosus (SLE) is characterized by extensive autoantibody deposition and persistent autoinflammation. As the existing animal models are limited in accurately reproducing the pathological characteristics of human SLE, we introduced a novel animal model simulating multi-organ autoinflammation through intra-organ injections. The model closely mimicked key features of SLE, including IgG deposition, inflammation, and tissue damage. The model could be used to assess the roles of IgG, immune cells, cytokines, and Fc gamma receptor (FcγR) in the pathogenesis of autoinflammation. The results obtained from this model could be confirmed by lupus MRL/lpr mice. The review suggested that the diagnostic criteria should be reconsidered to incorporate IgG deposition in tissues and highlighted the limitations of current T-cell and B-cell-focused treatments. To summarize, the IgG deposition model can be used to investigate the pathogenesis and treatment of multi-organ tissue damage associated with SLE.

Accurate single-molecule spot detection for image-based spatial transcriptomics with weakly supervised deep learning.

Image-based spatial transcriptomics methods enable transcriptome-scale gene expression measurements with spatial information but require complex, manually tuned analysis pipelines. We present Polaris, an analysis pipeline for image-based spatial transcriptomics that combines deep-learning models for cell segmentation and spot detection with a probabilistic gene decoder to quantify single-cell gene expression accurately. Polaris offers a unifying, turnkey solution for analyzing spatial transcriptomics data from multiplexed error-robust FISH (MERFISH), sequential fluorescence in situ hybridization (seqFISH), or in situ RNA sequencing (ISS) experiments. Polaris is available through the DeepCell software library (https://github.com/vanvalenlab/deepcell-spots) and https://www.deepcell.org.

Identification of Microorganism in Infected Wounds by Positively Charged Selective Sensor Array and Deep Learning Algorithm.

Microorganism are ubiquitous and intimately connected with human health and disease management. The accurate and fast identification of pathogenic microorganisms is especially important for diagnosing infections. Herein, three tetraphenylethylene derivatives (S-TDs: TBN, TPN, and TPI) featuring different cationic groups, charge numbers, emission wavelengths, and hydrophobicities were successfully synthesized. Benefiting from distinct cell wall binding properties, S-TDs were collectively utilized to create a sensor array capable of imaging various microorganisms through their characteristic fluorescent signatures. Furthermore, the interaction mechanism between S-TDs and different microorganisms was explored by calculating the binding energy between S-TDs and cell membrane/wall constituents, including phospholipid bilayer and peptidoglycan. Using a combination of the fluorescence sensor array and a deep learning model of residual network (ResNet), readily differentiation of Gram-negative bacteria (G-), Gram-positive bacteria (G+), fungi, and their mixtures was achieved. Specifically, by extensive training of two ResNet models with large quantities of images data from 14 kinds of microorganism stained with S-TDs, identification of microorganism was achieved at high-level accuracy: over 92.8% for both Gram species and antibiotic-resistant species, with 90.35% accuracy for the detection of mixed microorganism in infected wound. This novel method provides a rapid and accurate method for microbial classification, potentially aiding in the diagnosis and treatment of infectious diseases.

VvERF117 positively regulates grape cold tolerance through direct regulation of the antioxidative gene BAS1.

Cold stress significantly threatens grape quality, yield, and geographical distribution. Although ethylene-responsive factors (ERFs) are recognized for their pivotal roles in cold stress, the regulatory mechanisms of many ERFs contributing to tolerance remain unclear. In this study, we identified the cold-responsive gene VvERF117 and elucidated its positive regulatory function in cold tolerance. VvERF117 exhibits transcriptional activity and localizes to the nucleus. VvERF117 overexpression improved cold tolerance in transgenic Arabidopsis, grape calli, and grape leaves, whereas VvERF117 silencing increased cold sensitivity in grape calli and leaves. Furthermore, VvERF117 overexpression remarkably upregulated the expression of several stress-related genes. Importantly, BAS1, encoding a 2-Cys peroxidase (POD), was confirmed as a direct target gene of VvERF117. Meanwhile, compared to the wild-type, POD activity and H2O2 content were remarkably increased and decreased in VvERF117-overexpressing grape calli and leaves, respectively. Conversely, VvERF117 silencing displayed the opposite trend in grape calli and leaves under cold stress. These findings indicate that VvERF117 plays a positive role in cold resistance by, at least in part, enhancing antioxidant capacity through regulating the POD-encoding gene VvBAS1, leading to effective mitigation of reactive oxygen species.

Does Serum Uric Acid to Creatinine Ratio Predict Mortality Risk in Patients With Heart Failure?

BACKGROUND: Previous studies have established a positive correlation between serum uric acid to creatinine (SUA/Cr) ratio and cardiovascular disease, but the relationship between SUA/Cr ratio and the prognosis of heart failure (HF) remains unknown. This study investigated the potential of SUA/Cr ratio as a prognostic predictor for patients with HF. METHODS: This single-center prospective cohort study enrolled 2,122 patients with HF between March 2013 and June 2017. All patients were divided into 3 groups according to SUA/Cr ratio tertiles and were followed up with until December 31, 2022. The association between SUA/Cr ratio and the prognosis of HF was assessed using the Cox proportional hazards model. RESULTS: The mean (SD) age and mean (SD) SUA/Cr ratio of the study cohort (66% male) were 59.3 (14.7) years and 4.71 (2.09), respectively. During a median follow-up period of 15 months (range, 11-26 months), 390 end-point events were observed. Prognosis analysis revealed that a high SUA/Cr ratio was associated with an increased mortality risk of HF (hazard ratio, 1.62 [95% CI, 1.26-2.09]; P < .001) compared with the SUA/Cr ratio in the lowest tertile. After adjusting for covariates, the hazard ratio for mortality risk of HF was 1.71 (95% CI, 1.23-2.37; P = .001). Subgroup analysis showed that mortality risk increased in direct proportion with the SUA/Cr ratio in female patients, patients with a history of hypertension and ß-blocker use, and patients with UA levels below 428 µmol/L and creatinine levels less than 97 mg/dL. Stratification by age; by history of diabetes, hyperlipidemia, and smoking; and by level of fasting plasma glucose, however, had no obvious effect on the association between SUA/Cr ratio and HF prognosis. Patients with higher SUA/Cr ratios had reduced left ventricular ejection fraction and increased left ventricular end-diastolic diameter. CONCLUSION: A high SUA/Cr ratio was an independent risk factor for the mortality risk of HF.

Polyhedral Oligomeric Sesquioxane Cross-Linked Chitosan-Based Multi-Effective Aerogel Preparation and Its Water-Driven Recovery Mechanism.

The use of environmentally friendly and non-toxic biomass-based interfacial solar water evaporators has been widely reported as a method for water purification in recent years. However, the poor stability of the water transport layer made from biomass materials and its susceptibility to deformation when exposed to harsh environments limit its practical application. To address this issue, water-driven recovery aerogel (PCS) was prepared by cross-linking epoxy-based polyhedral oligomeric silsesquioxane (EP-POSS) epoxy groups with chitosan (CS) amino groups. The results demonstrate that PCS exhibits excellent water-driven recovery performance, regaining its original volume within a very short time (1.9 s) after strong compression (ε > 80%). Moreover, PCS has a water absorption rate of 2.67 mm s-1 and exhibits an excellent water absorption capacity of 22.09 g g-1 even after ten cycles of absorption-removal. Furthermore, a photothermal evaporator (PCH) was prepared by loading the top layer with hydrothermally reacted tannins (HAs) and Zn2+ complexes. The results indicate that PCH achieves an impressive evaporation rate of 1.89 kg m-2 h-1 under one sun illumination. Additionally, due to the antimicrobial properties of Zn2+, PCH shows inhibitory effects against Staphylococcus aureus and Escherichia coli, thereby extending the application of solar water evaporators to include antimicrobial purification in natural waters.

Progress in single-cell multimodal sequencing and multi-omics data integration.

With the rapid advance of single-cell sequencing technology, cell heterogeneity in various biological processes was dissected at different omics levels. However, single-cell mono-omics results in fragmentation of information and could not provide complete cell states. In the past several years, a variety of single-cell multimodal omics technologies have been developed to jointly profile multiple molecular modalities, including genome, transcriptome, epigenome, and proteome, from the same single cell. With the availability of single-cell multimodal omics data, we can simultaneously investigate the effects of genomic mutation or epigenetic modification on transcription and translation, and reveal the potential mechanisms underlying disease pathogenesis. Driven by the massive single-cell omics data, the integration method of single-cell multi-omics data has rapidly developed. Integration of the massive multi-omics single-cell data in public databases in the future will make it possible to construct a cell atlas of multi-omics, enabling us to comprehensively understand cell state and gene regulation at single-cell resolution. In this review, we summarized the experimental methods for single-cell multimodal omics data and computational methods for multi-omics data integration. We also discussed the future development of this field.

Single cell analyses of cancer cells identified two regulatorily and functionally distinct categories in differentially expressed genes among tumor subclones.

To explore the feature of cancer cells and tumor subclones, we analyzed 101,065 single-cell transcriptomes from 12 colorectal cancer (CRC) patients and 92 single cell genomes from one of these patients. We found cancer cells, endothelial cells and stromal cells in tumor tissue expressed much more genes and had stronger cell-cell interactions than their counterparts in normal tissue. We identified copy number variations (CNVs) in each cancer cell and found correlation between gene copy number and expression level in cancer cells at single cell resolution. Analysis of tumor subclones inferred by CNVs showed accumulation of mutations in each tumor subclone along lineage trajectories. We found differentially expressed genes (DEGs) between tumor subclones had two populations: DEGCNV and DEGreg. DEGCNV, showing high CNV-expression correlation and whose expression differences depend on the differences of CNV level, enriched in housekeeping genes and cell adhesion associated genes. DEGreg, showing low CNV-expression correlation and mainly in low CNV variation regions and regions without CNVs, enriched in cytokine signaling genes. Furthermore, cell-cell communication analyses showed that DEGCNV tends to involve in cell-cell contact while DEGreg tends to involve in secreted signaling, which further support that DEGCNV and DEGreg are two regulatorily and functionally distinct categories.

Deep learning on tertiary lymphoid structures in hematoxylin-eosin predicts cancer prognosis and immunotherapy response.

Tertiary lymphoid structures (TLSs) have been associated with favorable immunotherapy responses and prognosis in various cancers. Despite their significance, their quantification using multiplex immunohistochemistry (mIHC) staining of T and B lymphocytes remains labor-intensive, limiting its clinical utility. To address this challenge, we curated a dataset from matched mIHC and H&E whole-slide images (WSIs) and developed a deep learning model for automated segmentation of TLSs. The model achieved Dice coefficients of 0.91 on the internal test set and 0.866 on the external validation set, along with intersection over union (IoU) scores of 0.819 and 0.787, respectively. The TLS ratio, defined as the segmented TLS area over the total tissue area, correlated with B lymphocyte levels and the expression of CXCL13, a chemokine associated with TLS formation, in 6140 patients spanning 16 tumor types from The Cancer Genome Atlas (TCGA). The prognostic models for overall survival indicated that the inclusion of the TLS ratio with TNM staging significantly enhanced the models' discriminative ability, outperforming the traditional models that solely incorporated TNM staging, in 10 out of 15 TCGA tumor types. Furthermore, when applied to biopsied treatment-naïve tumor samples, higher TLS ratios predicted a positive immunotherapy response across multiple cohorts, including specific therapies for esophageal squamous cell carcinoma, non-small cell lung cancer, and stomach adenocarcinoma. In conclusion, our deep learning-based approach offers an automated and reproducible method for TLS segmentation and quantification, highlighting its potential in predicting immunotherapy response and informing cancer prognosis.