Search Results (379)

This paper presents a novel data-driven framework for real-time State of Charge (SOC) estimation in lithium-ion battery systems using a data-driven Prognostics and Health Management (PHM) approach. The method leverages an optimized bidirectional Long Short-Term Memory (Bi-LSTM) network, trained with enhanced datasets filtered via exponentially weighted moving averages (EWMAs) and refined through SHAP-based feature attribution. Compared against a Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) across ten diverse drive cycles, the proposed model consistently achieved superior performance, with mean absolute errors (MAEs) as low as 0.40%, outperforming EKF (0.66%) and UKF (1.36%). The Bi-LSTM model also demonstrated higher R² values (up to 0.9999) and narrower 95% confidence intervals, confirming its precision and robustness. Real-time implementation on embedded platforms yielded inference times of 1.3–2.2 s, validating its deployability for edge applications. The framework’s model-free nature makes it adaptable to other nonlinear, time-dependent systems beyond battery SOC estimation. Full article

Purpose: Predicting colorectal cancer liver metastasis (CRLM) is essential for prognostic assessment. This study aims to develop and validate an interpretable multimodal machine learning framework based on multiparametric MRI for predicting CRLM, and to enhance the clinical interpretability of the model through SHapley Additive exPlanations (SHAP) analysis and deep learning visualization. Methods: This multicenter retrospective study included 463 patients with pathologically confirmed colorectal cancer from two institutions, divided into training (n = 256), internal testing (n = 111), and external validation (n = 96) sets. Radiomics features were extracted from manually segmented regions on axial T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI). Deep learning features were obtained from a pretrained ResNet101 network using the same MRI inputs. A least absolute shrinkage and selection operator (LASSO) logistic regression classifier was developed for clinical, radiomics, deep learning, and combined models. Model performance was evaluated by AUC, sensitivity, specificity, and F1-score. SHAP was used to assess feature contributions, and Grad-CAM was applied to visualize deep feature attention. Results: The combined model integrating features across the three modalities achieved the highest performance across all datasets, with AUCs of 0.889 (training), 0.838 (internal test), and 0.822 (external validation), outperforming single-modality models. Decision curve analysis (DCA) revealed enhanced clinical net benefit from the integrated model, while calibration curves confirmed its good predictive consistency. SHAP analysis revealed that radiomic features related to T2WI texture (e.g., LargeDependenceLowGrayLevelEmphasis) and clinical biomarkers (e.g., CA19-9) were among the most predictive for CRLM. Grad-CAM visualizations confirmed that the deep learning model focused on tumor regions consistent with radiological interpretation. Conclusions: This study presents a robust and interpretable multiparametric MRI-based model for noninvasively predicting liver metastasis in colorectal cancer patients. By integrating handcrafted radiomics and deep learning features, and enhancing transparency through SHAP and Grad-CAM, the model provides both high predictive performance and clinically meaningful explanations. These findings highlight its potential value as a decision-support tool for individualized risk assessment and treatment planning in the management of colorectal cancer. Full article

Prognostic markers such as overall survival (OS) and tertiary lymphoid structure (TLS) ratios, alongside diagnostic signatures like primary cancer-type classification, provide critical information for treatment selection, risk stratification, and longitudinal care planning across the oncology continuum. However, extracting these signals solely from sparse, high-dimensional multi-omics data remains a major challenge due to heterogeneity and frequent missingness in patient profiles. To address this challenge, we present SeNMo, a self-normalizing deep neural network trained on five heterogeneous omics layers—gene expression, DNA methylation, miRNA abundance, somatic mutations, and protein expression—along with the clinical variables, that learns a unified representation robust to missing modalities. Trained on more than 10,000 patient profiles across 32 tumor types from The Cancer Genome Atlas (TCGA), SeNMo provides a baseline that can be readily fine-tuned for diverse downstream tasks. On a held-out TCGA test set, the model achieved a concordance index of 0.758 for OS prediction, while external evaluation yielded 0.73 on the CPTAC lung squamous cell carcinoma cohort and 0.66 on an independent 108-patient Moffitt Cancer Center cohort. Furthermore, on Moffitt’s cohort, baseline SeNMo fine-tuned for TLS ratio prediction aligned with expert annotations (p < 0.05) and sharply separated high- versus low-TLS groups, reflecting distinct survival outcomes. Without altering the backbone, a single linear head classified primary cancer type with 99.8% accuracy across the 33 classes. By unifying diagnostic and prognostic predictions in a modality-robust architecture, SeNMo demonstrated strong performance across multiple clinically relevant tasks, including survival estimation, cancer classification, and TLS ratio prediction, highlighting its translational potential for multi-omics oncology applications. Full article

Large-scale battery datasets often contain anomalous data due to sensor noise, communication errors, and operational inconsistencies, which degrade the accuracy of data-driven prognostics. However, many existing studies overlook the impact of such anomalies or apply filtering heuristically without rigorous benchmarking, which can potentially introduce biases into training and evaluation pipelines. This study presents a deep learning framework that integrates autoencoder-based anomaly detection with a residual neural network (ResNet) to achieve state-of-the-art prediction of remaining useful life at the cycle level using only a single-cycle input. The framework systematically filters out anomalous samples using multiple variants of convolutional and sequence-to-sequence autoencoders, thereby enhancing data integrity before optimizing and training the ResNet-based models. Benchmarking against existing deep learning approaches demonstrates a significant performance improvement, with the best model achieving a mean absolute percentage error of 2.85% and a root mean square error of 40.87 cycles, surpassing prior studies. These results indicate that autoencoder-based anomaly filtering significantly enhances prediction accuracy, reinforcing the importance of systematic anomaly detection in battery prognostics. The proposed method provides a scalable and interpretable solution for intelligent battery management in electric vehicles and energy storage systems. Full article

Background: Extremely premature neonates are at increased risk for respiratory complications, often resulting in recurrent hospitalizations during early childhood. Early identification of preterm infants at highest risk of respiratory hospitalizations could enable targeted preventive interventions. While clinical and demographic factors offer some prognostic value, integrating transcriptomic data may improve predictive accuracy. Objective: To determine whether early-life gene expression profiles can predict respiratory-related hospitalizations within the first four years of life in extremely preterm neonates. Methods: We conducted a retrospective cohort study of 58 neonates born at <32 weeks’ gestational age, using publicly available transcriptomic data from peripheral blood samples collected on days 5, 14, and 28 of life. Random forest models were trained to predict unplanned respiratory readmissions. Model performance was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC). Results: All three models, built using transcriptomic data from days 5, 14, and 28, demonstrated strong predictive performance (AUC = 0.90), though confidence intervals were wide due to small sample size. We identified 31 genes and eight biological pathways that were differentially expressed between preterm neonates with and without subsequent respiratory readmissions. Conclusions: Transcriptomic data from the neonatal period, combined with machine learning, accurately predicted respiratory-related rehospitalizations in extremely preterm neonates. The identified gene signatures offer insight into early biological disruptions that may predispose preterm neonates to chronic respiratory morbidity. Validation in larger, diverse cohorts is needed to support clinical translation. Full article

Background/Objectives: Peripheral artery disease (PAD) impacts more than 200 million individuals globally and leads to mortality and morbidity secondary to progressive limb dysfunction and amputation. However, clinical management of PAD remains suboptimal, in part because of the lack of standardized biomarkers to predict patient outcomes. Growth differentiation factor 15 (GDF15) is a stress-responsive cytokine that has been studied extensively in cardiovascular disease, but its investigation in PAD remains limited. This study aimed to use explainable statistical and machine learning methods to assess the prognostic value of GDF15 for limb outcomes in patients with PAD. Methods: This prognostic investigation was carried out using a prospectively enrolled cohort comprising 454 patients diagnosed with PAD. At baseline, plasma GDF15 levels were measured using a validated multiplex immunoassay. Participants were monitored over a two-year period to assess the occurrence of major adverse limb events (MALE), a composite outcome encompassing major lower extremity amputation, need for open/endovascular revascularization, or acute limb ischemia. An Extreme Gradient Boosting (XGBoost) model was trained to predict 2-year MALE using 10-fold cross-validation, incorporating GDF15 levels along with baseline variables. Model performance was primarily evaluated using the area under the receiver operating characteristic curve (AUROC). Secondary model evaluation metrics were accuracy, sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). Prediction histogram plots were generated to assess the ability of the model to discriminate between patients who develop vs. do not develop 2-year MALE. For model interpretability, SHapley Additive exPlanations (SHAP) analysis was performed to evaluate the relative contribution of each predictor to model outputs. Results: The mean age of the cohort was 71 (SD 10) years, with 31% (n = 139) being female. Over the two-year follow-up period, 157 patients (34.6%) experienced MALE. The XGBoost model incorporating plasma GDF15 levels and demographic/clinical features achieved excellent performance for predicting 2-year MALE in PAD patients: AUROC 0.84, accuracy 83.5%, sensitivity 83.6%, specificity 83.7%, PPV 87.3%, and NPV 86.2%. The prediction probability histogram for the XGBoost model demonstrated clear separation for patients who developed vs. did not develop 2-year MALE, indicating strong discrimination ability. SHAP analysis showed that GDF15 was the strongest predictive feature for 2-year MALE, followed by age, smoking status, and other cardiovascular comorbidities, highlighting its clinical relevance. Conclusions: Using explainable statistical and machine learning methods, we demonstrated that plasma GDF15 levels have important prognostic value for 2-year MALE in patients with PAD. By integrating clinical variables with GDF15 levels, our machine learning model can support early identification of PAD patients at elevated risk for adverse limb events, facilitating timely referral to vascular specialists and aiding in decisions regarding the aggressiveness of medical/surgical treatment. This precision medicine approach based on a biomarker-guided prognostication algorithm offers a promising strategy for improving limb outcomes in individuals with PAD. Full article

Background: Glioblastoma (GBM) is one of the most challenging malignancies in all of neoplasms. These malignancies are associated with unfavorable clinical outcomes and significantly compromised patient wellbeing. The immunological landscape within the tumor microenvironment (TME) plays a critical role in determining GBM prognosis. By mining data from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases and correlating them with immune responses in the TME, genes associated with the immune microenvironment with potential prognostic value were obtained. Method: We selected GSE16011 as the training set. Gene expression profiles were substrates scored by both ESTIMATE and xCell, and immune cell subpopulations in GBM were analyzed by CIBERSORT. Gene expression profiles associated with low immune scores were performed by lasso regression, Cox analysis and random forest (RF) to identify a prognostic model for the multiple genes associated with immune infiltration in GBM. Then we constructed a nomogram to optimize the prognostic model using GSE7696 and TCGA-GBM as validation sets and evaluated these data for gene mutation and gene enrichment analysis. Result: The prognostic correlation between the six genes (MEOX2, PHYHIP, RBBP8, ST18, TCF12, and THRB) and GBM was finally found by lasso regression, Cox regression, and RF, and the online database obtained that all six genes were differentially expressed in GBM. Therefore, a prognostic correlation model was constructed based on the six genes. Kaplan–Meier (KM) survival analysis showed that this prognostic model had excellent prognostic ability. Conclusions: Prognostic models based on tumor microenvironment and immune score stratification and the construction of related genes have potential applications for prognostic analysis of GBM patients. Full article

Background: Pathological complete response (pCR) serves as a prognostic surrogate endpoint for long-term clinical outcomes in breast cancer patients receiving neoadjuvant systemic therapy (NAST). This study aims to develop and evaluate machine learning-based biomarkers for predicting pCR and recurrence-free survival (RFS). Methods: This retrospective monocentric study included 235 women (mean age 46 ± 11 years) with non-metastatic breast cancer treated with NAST. We developed various machine learning models using clinical features (age, genetic mutations, TNM stage, hormonal receptor expression, HER2 status, and histological grade), along with morphological features (size, T2 signal, and surrounding edema) and radiomics data extracted from pre-treatment MRI. Patients were divided into training and test groups with different MRI models. A customized machine learning pipeline was implemented to handle these diverse data types, consisting of feature selection and classification components. Results: The models demonstrated superior prediction ability using radiomics features, with the best model achieving an AUC of 0.72. Subgroup analysis revealed optimal performance in triple-negative breast cancer (AUC of 0.80) and HER2-positive subgroups (AUC of 0.65). Conclusion: Machine learning models incorporating clinical, qualitative, and radiomics data from pre-treatment MRI can effectively predict pCR in breast cancer patients receiving NAST, particularly among triple-negative and HER2-positive breast cancer subgroups. Full article

Background: The prognosis management of thyroid cancer remains a significant challenge. This study highlights the critical role of T cells in the tumor microenvironment and aims to improve prognostic precision by integrating bulk RNA-seq and single-cell RNA-seq (scRNA-seq) data, providing a more comprehensive view of tumor biology at the single-cell level. Method: 15 thyroid cancer scRNA-seq samples were analyzed from GEO and 489 patients from TCGA. A multi-level attention graph neural network (MLA-GNN) model was applied to integrate T-cell-related differentially expressed genes (DEGs) for predicting disease-free survival (DFS). Patients were divided into training and validation cohorts in an 8:2 ratio. Result: We systematically characterized the immune microenvironment of metastatic thyroid cancer by using single-cell transcriptomics and identified the important role of T-cell subtypes in the development of thyroid cancer. T-cell-based DEGS between tumor tissues and normal tissues were also identified. Subsequently, T-cell-based risk signatures were selected for establishing a risk model using MLA-GNN. Finally, our MLA-GNN-based model demonstrated an excellent ability to predict the DFS of thyroid cancer patients (1-year AUC: 0.965, 3-years AUC: 0.979, and 5-years AUC: 0.949 in training groups, and 1-year AUC: 0.879, 3-years AUC: 0.804, and 5-years AUC: 0.804 in validation groups). Conclusions: Risk features based on T-cell genes have demonstrated the effectiveness in predicting the prognosis of thyroid cancer. By conducting a comprehensive characterization of T-cell features, we aim to enhance our understanding of the tumor’s response to immunotherapy and uncover new strategies for the treatment of cancer. Full article

Regulatory T cells (Tregs) have multiple roles in the tumor microenvironment (TME), which maintain a balance between autoimmunity and immunosuppression. This research aimed to investigate the interaction between cancer stemness and Regulatory T cells (Tregs) in the breast cancer tumor immune microenvironment. Breast cancer stemness was calculated using one-class logistic regression. Twelve main cell clusters were identified, and the subsequent three subsets of Regulatory T cells with different differentiation states were identified as being closely related to immune regulation and metabolic pathways. A prognostic risk model including MEA1, MTFP1, PASK, PSENEN, PSME2, RCC2, and SH2D2A was generated through the intersection between Regulatory T cell differentiation-related genes and stemness-related genes using LASSO and univariate Cox regression. The patient’s total survival times were predicted and validated with AUC of 0.96 and 0.831 in both training and validation sets, respectively; the immunotherapeutic predication efficacy of prognostic signature was confirmed in four ICI RNA-Seq cohorts. Seven drugs, including Ethinyl Estradiol, Epigallocatechin gallate, Cyclosporine, Gentamicin, Doxorubicin, Ivermectin, and Dronabinol for prognostic signature, were screened through molecular docking and found a synergistic effect among drugs with deep learning. Our prognostic signature potentially paves the way for overcoming immune resistance, and blocking the interaction between cancer stemness and Tregs may be a new approach in the treatment of breast cancer. Full article

Objective: Tumor progression is regulated by systemic immune status, nutritional metabolism, and the inflammatory microenvironment. This study aims to investigate inflammatory–nutritional biomarkers associated with metachronous liver metastasis (MLM) in colorectal cancer (CRC) and develop a machine learning model for accurate prediction. Methods: This study enrolled 680 patients with CRC who underwent curative resection, randomly allocated into a training set (n = 477) and a validation set (n = 203) in a 7:3 ratio. Feature selection was performed using Boruta and Lasso algorithms, identifying nine core prognostic factors through variable intersection. Seven machine learning (ML) models were constructed using the training set, with the optimal predictive model selected based on comprehensive evaluation metrics. An interactive visualization tool was developed to interpret the dynamic impact of key features on individual predictions. The partial dependence plots (PDPs) revealed a potential dose–response relationship between inflammatory–nutritional markers and MLM risk. Results: Among 680 patients with CRC, the cumulative incidence of MLM at 6 months postoperatively was 39.1%. Multimodal feature selection identified nine key predictors, including the N stage, vascular invasion, carcinoembryonic antigen (CEA), systemic immune–inflammation index (SII), albumin–bilirubin index (ALBI), differentiation grade, prognostic nutritional index (PNI), fatty liver, and T stage. The gradient boosting machine (GBM) demonstrated the best overall performance (AUROC: 0.916, sensitivity: 0.772, specificity: 0.871). The generalized additive model (GAM)-fitted SHAP analysis established, for the first time, risk thresholds for four continuous variables (CEA > 8.14 μg/L, PNI < 44.46, SII > 856.36, ALBI > −2.67), confirming their significant association with MLM development. Conclusions: This study developed a GBM model incorporating inflammatory-nutritional biomarkers and clinical features to accurately predict MLM in colorectal cancer. Integrated with dynamic visualization tools, the model enables real-time risk stratification via a freely accessible web calculator, guiding individualized surveillance planning and optimizing clinical decision-making for precision postoperative care. Full article

Peripheral artery disease (PAD) is associated with an elevated risk of major adverse cardiovascular events (MACE). Despite this, few reliable biomarkers exist to identify patients at heightened risk of MACE. Growth differentiation factor 15 (GDF15), a stress-responsive cytokine implicated in inflammation, atherosclerosis, and thrombosis, has been broadly studied in cardiovascular disease but remains underexplored in PAD. This study aimed to evaluate the prognostic utility of GDF15 for predicting 2-year MACE in PAD patients using explainable statistical and machine learning approaches. We conducted a prospective analysis of 1192 individuals (454 with PAD and 738 without PAD). At study entry, patient plasma GDF15 concentrations were measured using a validated multiplex immunoassay. The cohort was followed for two years to monitor the occurrence of MACE, defined as stroke, myocardial infarction, or death. Baseline GDF15 levels were compared between PAD and non-PAD participants using the Mann–Whitney U test. A machine learning model based on extreme gradient boosting (XGBoost) was trained to predict 2-year MACE using 10-fold cross-validation, incorporating GDF15 and clinical variables including age, sex, comorbidities (hypertension, diabetes, dyslipidemia, congestive heart failure, coronary artery disease, and previous stroke or transient ischemic attack), smoking history, and cardioprotective medication use. The model’s primary evaluation metric was the F1 score, a validated measurement of the harmonic mean of the precision and recall values of the prediction model. Secondary model performance metrics included precision, recall, positive likelihood ratio (LR+), and negative likelihood ratio (LR-). A prediction probability histogram and Shapley additive explanations (SHAP) analysis were used to assess model discrimination and interpretability. The mean participant age was 70 ± SD 11 years, with 32% (n = 386) female representation. Median plasma GDF15 levels were significantly higher in PAD patients compared to the levels in non-PAD patients (1.29 [IQR 0.77–2.22] vs. 0.99 [IQR 0.61–1.63] pg/mL; p < 0.001). During the 2-year follow-up period, 219 individuals (18.4%) experienced MACE. The XGBoost model demonstrated strong predictive performance for 2-year MACE (F1 score = 0.83; precision = 82.0%; recall = 83.7%; LR+ = 1.88; LR− = 0.83). The prediction histogram revealed distinct stratification between those who did vs. did not experience 2-year MACE. SHAP analysis identified GDF15 as the most influential predictive feature, surpassing traditional clinical predictors such as age, cardiovascular history, and smoking status. This study highlights GDF15 as a strong prognostic biomarker for 2-year MACE in patients with PAD. When combined with clinical variables in an interpretable machine learning model, GDF15 supports the early identification of patients at high risk for systemic cardiovascular events, facilitating personalized treatment strategies including multidisciplinary specialist referrals and aggressive cardiovascular risk reduction therapy. This biomarker-guided approach offers a promising pathway for improving cardiovascular outcomes in the PAD population through precision risk stratification. Full article

Background/Objective: The approach to the clinical management of metastatic melanoma patients is undergoing a significant transformation. The availability of a large amount of data from medical images has made Artificial Intelligence (AI) applications an innovative and cutting-edge solution that could revolutionize the surveillance and management of these patients. In this study, we develop and validate a machine-learning model based on radiomic data extracted from a computed tomography (CT) analysis of patients with metastatic melanoma (MM). This approach was designed to accurately predict prognosis and identify the potential key factors associated with prognosis. Methods: To achieve this goal, we used radiomic pipelines to extract the quantitative features related to lesion texture, morphology, and intensity from high-quality CT images. We retrospectively collected a cohort of 58 patients with metastatic melanoma, from which a total of 60 CT series were used for model training, and 70 independent CT series were employed for external testing. Model performance was evaluated using metrics such as sensitivity, specificity, and AUC (area under the curve), demonstrating particularly favorable results compared to traditional methods. Results: The model used in this study presented a ROC-AUC curve of 82% in the internal test and, in combination with AI, presented a good predictive ability regarding lesion outcome. Conclusions: Although the cohort size was limited and the data were collected retrospectively from a single institution, the findings provide a promising basis for further validation in larger and more diverse patient populations. This approach could directly support clinical decision-making by providing accurate and personalized prognostic information. Full article

Background: Parkinson’s disease (PD) is the second most common neurodegenerative disorder after Alzheimer’s disease, affecting countless individuals worldwide. PD is characterized by the onset of a marked motor symptomatology in association with several non-motor manifestations. The clinical phase of the disease is usually preceded by a long prodromal phase, devoid of overt motor symptomatology but often showing some conditions such as sleep disturbance, constipation, anosmia, and phonatory changes. To date, speech analysis appears to be a promising digital biomarker to anticipate even 10 years before the onset of clinical PD, as well serving as a useful prognostic tool for patient follow-up. That is why, the voice can be nominated as the non-invasive method to detect PD from healthy subjects (HS). Methods: Our study was based on cross-sectional study to analysis voice impairment. A dataset comprising 81 voice samples (41 from healthy individuals and 40 from PD patients) was utilized to train and evaluate common machine learning (ML) models using various types of features, including long-term (jitter, shimmer, and cepstral peak prominence (CPP)), short-term features (Mel-frequency cepstral coefficient (MFCC)), and non-standard measurements (pitch period entropy (PPE) and recurrence period density entropy (RPDE)). The study adopted multiple machine learning (ML) algorithms, including random forest (RF), K-nearest neighbors (KNN), decision tree (DT), naïve Bayes (NB), support vector machines (SVM), and logistic regression (LR). Cross-validation technique was applied to ensure the reliability of performance metrics on train and test subsets. These metrics (accuracy, recall, and precision), help determine the most effective models for distinguishing PD from healthy subjects. Result: Among all the algorithms used in this research, random forest (RF) was the best-performing model, achieving an accuracy of 82.72% with a ROC-AUC score of 89.65%. Although other models, such as support vector machine (SVM), could be considered with an accuracy of 75.29% and a ROC-AUC score of 82.63%, RF was by far the best one when evaluated across all metrics. The K-nearest neighbor (KNN) and decision tree (DT) performed the worst. Notably, by combining a comprehensive set of long-term, short-term, and non-standard acoustic features, unlike previous studies that typically focused on only a subset, our study achieved higher predictive performance, offering a more robust model for early PD detection. Conclusions: This study highlights the potential of combining advanced acoustic analysis with ML algorithms to develop non-invasive and reliable tools for early PD detection, offering substantial benefits for the healthcare sector. Full article

Background/Objectives: Circulating tumor cells (CTCs) are important biomarkers for predicting prognosis and evaluating treatment efficacy in cancer. We developed the “CTC-Chip” system based on microfluidics, enabling highly sensitive CTC detection and prognostic assessment in lung cancer and malignant pleural mesothelioma. However, the final identification and enumeration of CTCs require manual intervention, which is time-consuming, prone to human error, and necessitates the involvement of experienced medical professionals. Medical image recognition using machine learning can reduce workload and improve automation. However, CTCs are rare in clinical samples, limiting the training data available to construct a robust CTC image recognition system. In this study, we established a highly accurate artificial intelligence-based CTC recognition system by pre-training convolutional neural networks using images from lung cancer cell lines. Methods: We performed transfer learning of convolutional neural networks. Initially, the models were pre-trained using images obtained from lung cancer cell lines. The model’s accuracy was improved by training with a limited number of clinical CTC images. Results: Transfer learning significantly improved the CTC classification accuracy to an average of 99.51%, compared to 96.96% for a model trained solely on pre-trained cell lines (p < 0.05). This approach showed notable efficacy when clinical training images were limited, achieving statistically significant accuracy improvements with as few as 17 clinical CTC images (p < 0.05). Conclusions: Overall, our findings demonstrate that pre-training with cancer cell lines enables rapid and highly accurate automated CTC recognition even with limited clinical data, significantly enhancing clinical applicability and potential utility across diverse cancer diagnostic workflows. Full article