BME frontiersPub Date : 2026-08-31eCollection Date: 2026-01-01DOI: 10.34133/bmef.0296
Suyan Duan, Mengchu Tang, Ningning Wang, Tingyu Xu, Mengyun He, Shihui Xu, Juan Zhang, Zhongze Gu, Zaozao Chen, Yun Liu
{"title":"New Dimensions in Diabetic Kidney Disease Research: Advanced Organoids and Organs-on-a-Chip.","authors":"Suyan Duan, Mengchu Tang, Ningning Wang, Tingyu Xu, Mengyun He, Shihui Xu, Juan Zhang, Zhongze Gu, Zaozao Chen, Yun Liu","doi":"10.34133/bmef.0296","DOIUrl":"10.34133/bmef.0296","url":null,"abstract":"<p><p>Diabetic kidney disease has increasingly emerged as a global public health concern, yet substantial challenges persist in its mechanistic research and drug development. Traditional 2-dimensional cell cultures and animal models frequently lack the capacity to faithfully recapitulate human pathophysiological conditions, and the use of animal models is increasingly limited by ethical and policy-related hurdles. In vitro models such as organoids and organs-on-a-chip have demonstrated remarkable advantages, enabling more faithful simulation of the in vivo microenvironment. The advancement of 3-dimensional bioprinting, microfluidic, and vascularization technologies has further propelled the maturation and progress of in vitro kidney models. This review summarizes and discusses in vitro kidney models and their advances, including kidney cell lines, spheroids, kidney organoids, and kidneys-on-a-chip. It also elaborates on the establishment of diabetic kidney disease models based on these in vitro platforms, which provides robust support for both basic and clinical research.</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":"7 ","pages":"0296"},"PeriodicalIF":9.1,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13527213/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148868134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A General-Purpose Framework for Microvascular Reconstruction and Quantitative Analysis in Ultrasound Localization Microscopy.","authors":"Peinan Liu, Jie Guo, Xuedi Han, Yuan Zong, Ting Zhang, Ligang Cui, Xuejun Qian","doi":"10.34133/bmef.0295","DOIUrl":"10.34133/bmef.0295","url":null,"abstract":"<p><p><b>Objective:</b> Microvascular alterations are early biomarkers of many diseases, but clinical translation is hindered by the lack of noninvasive deep-tissue imaging tools with capillary resolution and standardized analysis approaches. <b>Impact Statement:</b> ULM-based Vascular Biomarker Automated Analysis (U-VBA) provides a standardized framework that bridges microvascular imaging reconstruction and automated biomarker analysis, with feasibility demonstration in animals models in vivo and clinical patient data. <b>Introduction:</b> Ultrasound localization microscopy (ULM) can overcome the diffraction limit but lacks generalizable imaging reconstruction and biomarker quantification pipelines. <b>Methods:</b> We developed U-VBA, integrating motion correction, cascaded denoising (singular value decomposition, high-pass filtering, and background subtraction), and a panel of 6 vascular biomarkers (density, intervessel distance, diameter, velocity, perfusion, and tortuosity). Performance was validated in various settings, including flow phantoms, chicken chorioallantoic membranes (<i>n</i> = 5), rabbit optic nerve injury models (<i>n</i> = 4), and a clinical patient cohort with cervical lymph node tumors (<i>n</i> = 39). <b>Results:</b> U-VBA achieved robust performance in flow phantoms and resolved the finest capillaries down to 16.2 μm in chorioallantoic membrane models. In rabbit eye models, it precisely captures the dynamic vascular changes and establishes the vascular biomarkers during elevated intraocular pressure and recovery. In the clinical cohort, we demonstrated the potential value of U-VBA, which leverages 4 biomarkers (intervessel distance, diameter, perfusion, and tortuosity) to differentiate 3 lymph node conditions, with 85% accuracy in 5-fold cross-validation. <b>Conclusion:</b> U-VBA standardizes ULM-based microvascular phenotyping and integrates into routine ultrasound workflows, offering a noninvasive tool for preclinical and clinical vascular biomarker analysis.</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":"7 ","pages":"0295"},"PeriodicalIF":9.1,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13429912/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148671379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
BME frontiersPub Date : 2026-07-23eCollection Date: 2026-01-01DOI: 10.34133/bmef.0292
Ying Fan, Ting Feng, Yangkun Liu, Abdula Aji, Libo Jiang, Dean Ta
{"title":"Edge-Aware Short-Chain Diffusion Enables High-Fidelity Sparse-Sampling Optoacoustic Tomography.","authors":"Ying Fan, Ting Feng, Yangkun Liu, Abdula Aji, Libo Jiang, Dean Ta","doi":"10.34133/bmef.0292","DOIUrl":"10.34133/bmef.0292","url":null,"abstract":"<p><p><b>Objective:</b> To improve image quality in multispectral optoacoustic tomography (MSOT) under conditions of strong noise and extreme sparse sampling. <b>Impact Statement:</b> This work provides a practical solution to enhance MSOT image quality while reducing hardware requirements, which may help expand its use in preclinical and clinical imaging. <b>Introduction:</b> MSOT provides useful biochemical and molecular contrast in tissues. However, image quality is often limited by system noise and sparse sampling. <b>Methods:</b> We propose the optoacoustic universal denoising network (OA-UDNet), a hybrid diffusion-based framework for sparse MSOT data. The model is trained on more than 250,000 in vivo images. It performs joint denoising and high-fidelity image restoration by combining an edge-aware module with diffusion-based generation to preserve structural boundaries. <b>Results:</b> With data from only 32 detectors, the method improves image quality and increases peak signal-to-noise ratio (PSNR) by nearly 14 dB. Evaluated against the standard 256-detector reference, the framework consistently preserves structural fidelity under extreme undersampling. Validation on whole-body mouse imaging, tumor models, and human samples shows reduced artifacts and improved recovery of anatomical and functional features. <b>Conclusion:</b> OA-UDNet improves MSOT image quality under sparse conditions. It offers a simple and effective way to accelerate imaging while reducing hardware complexity.</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":"7 ","pages":"0292"},"PeriodicalIF":9.1,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13392286/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148581194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Taste Bud Organoid-Based Biosensor with a 3-Dimensional Microelectrode Array for Evaluating Caffeine's Impacts on Taste Sensing.","authors":"Shuge Liu, Yuqi Chen, Zhiyao Wang, Miaomiao Wang, Yating Chen, Yulan Tian, Xinyi Liu, Jingyi Li, Jingxi Li, Liping Du, Xiaojun Li, Chunsheng Wu","doi":"10.34133/bmef.0286","DOIUrl":"10.34133/bmef.0286","url":null,"abstract":"<p><p><b>Objective:</b> The impact of caffeine on the gustatory system is still not fully understood. Therefore, it is highly essential to investigate caffeine's impacts on taste sensing. <b>Impact Statement:</b> The present study develops a taste bud organoid-based biosensor using a 3-dimensional microelectrode array to systematically investigate the modulatory effects of caffeine on various taste perceptions. <b>Introduction:</b> The integration of taste bud organoids with a 3-dimensional microelectrode array introduces a novel class of biomimetic taste sensors. This study utilizes this sophisticated sensor technology to systematically assess the responses of caffeine-treated taste bud organoids to a range of flavor stimuli. <b>Methods:</b> Biosensor functionality was assessed through metrics such as the proportion of responsive electrodes and signal-to-noise ratio. The electrophysiological characterization of the firing patterns was analyzed including firing rate and amplitude, in response to diverse flavor stimuli and caffeine exposure. Principal component analysis was employed to determine the sensor's efficacy in identifying and differentiating distinct flavor profiles. <b>Results:</b> The results indicate that the electrode response rate of the fabricated chip ranges between 45% and 56%, with signal-to-noise ratio values ranging from 20.71 to 23.62. Taste bud organoids exhibit distinct electrophysiological responses contingent upon the taste stimulus: sweet stimuli elicit the strongest response, followed by sour stimuli, whereas responses to bitter, salty, and umami stimuli approximate baseline levels observed prior to stimulation. <b>Conclusion:</b> This investigation enhances the understanding of caffeine's interaction with taste bud organoids, thereby contributing to the field of sensory biology and facilitating the advancement of sophisticated flavor sensing technologies.</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":"7 ","pages":"0286"},"PeriodicalIF":9.1,"publicationDate":"2026-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13323712/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148378299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
BME frontiersPub Date : 2026-07-02eCollection Date: 2026-01-01DOI: 10.34133/bmef.0283
Hui Xie, Yan Wang, Xin Li, Zengyong Li, Lin Wang, Gongcheng Xu, Daifa Wang, Yinghu Peng, Zulin Dou, Qitao Tan, Ming Zhang
{"title":"A Repetitive Transcranial Magnetic Stimulation-Functional Near-Infrared Spectroscopy System: Achieving Dynamic Monitoring of Neuroplasticity in Clinical Rehabilitation.","authors":"Hui Xie, Yan Wang, Xin Li, Zengyong Li, Lin Wang, Gongcheng Xu, Daifa Wang, Yinghu Peng, Zulin Dou, Qitao Tan, Ming Zhang","doi":"10.34133/bmef.0283","DOIUrl":"10.34133/bmef.0283","url":null,"abstract":"<p><p><b>Objective:</b> This study aimed to integrate repetitive transcranial magnetic stimulation (rTMS) with functional near-infrared spectroscopy (fNIRS) to achieve concurrent monitoring of neural activity during neuromodulation and to evaluate its feasibility in stroke rehabilitation. <b>Impact Statement:</b> This work addresses the long-standing lack of concurrent feedback in stroke neuromodulation and provides an important pathway for developing adaptive, closed-loop neurorehabilitation technologies. <b>Introduction:</b> The application and optimization of rTMS in stroke rehabilitation are constrained by the absence of concurrent physiological feedback, which limits timely evaluation of stimulation efficacy and adjustment of treatment parameters. Existing techniques combining neuromodulation with neuroimaging often lack validation, hindering their clinical translation and widespread application. <b>Methods:</b> This study employed improved fNIRS probes to construct an rTMS-fNIRS system capable of proximal detection under routine clinical rTMS conditions. Magnetic interference testing and simulation analyses were performed to evaluate system artifacts, field penetration, and focality. A 14-d clinical trial was conducted to verify the system's feasibility and effectiveness. A total of 80 patients with stroke were enrolled, and wavelet amplitude and laterality index were used to quantify neuroplasticity changes while clinical scales were applied to assess behavioral improvements. <b>Results:</b> Engineering validation demonstrated that the system stably recorded cortical hemodynamic responses under high-intensity stimulation. Concurrent clinical monitoring revealed that excitatory rTMS induced dynamic enhancement of cortical activation and interhemispheric rebalancing, and these neurophysiological changes were significantly correlated with improvements in upper-limb motor recovery. <b>Conclusion:</b> The proposed rTMS-fNIRS system not only provides stable neuromodulatory intervention but also enables concurrent monitoring of stimulation-induced neuroplastic changes under clinical conditions.</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":"7 ","pages":"0283"},"PeriodicalIF":9.1,"publicationDate":"2026-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13323713/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148378287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
BME frontiersPub Date : 2026-06-16eCollection Date: 2026-01-01DOI: 10.34133/bmef.0278
Che-Yung Shen, Xilin Yang, Yuzhu Li, Leon Lenk, Zixiang Ji, Aydogan Ozcan
{"title":"Automated HER2 Scoring with Uncertainty Quantification Using Lensfree Holography and Deep Learning.","authors":"Che-Yung Shen, Xilin Yang, Yuzhu Li, Leon Lenk, Zixiang Ji, Aydogan Ozcan","doi":"10.34133/bmef.0278","DOIUrl":"10.34133/bmef.0278","url":null,"abstract":"<p><p><b>Objective:</b> To develop an automated human epidermal growth factor receptor 2 (HER2) scoring system using lensfree holography. <b>Impact Statement:</b> We created a compact and cost-effective lensfree holography device integrated with deep learning for rapid, automated HER2 scoring of immunohistochemically stained breast tissue sections. <b>Introduction:</b> Accurate assessment of HER2 expression is critical for breast cancer diagnosis, prognosis, and therapy selection; yet, most existing digital HER2 scoring methods rely on bulky and expensive optical systems. <b>Results:</b> The system captures lensfree diffraction patterns of stained HER2 tissue sections under RGB laser illumination and captures complex field information over a sample area of ~1,250 mm<sup>2</sup> at an effective throughput of ~84 mm<sup>2</sup> per minute. To enhance diagnostic reliability, we incorporated an uncertainty quantification strategy based on Bayesian Monte Carlo dropout, which provides autonomous uncertainty estimates for each prediction and supports reliable, robust HER2 scoring. Using a blinded test set of 412 unique tissue samples, our approach achieved a testing accuracy of 84.9% for 4-class (0, 1+, 2+, 3+) HER2 classification and 94.8% for binary (0/1+ versus 2+/3+) HER2 scoring with uncertainty quantification. <b>Conclusion:</b> This lensfree holography approach provides a practical pathway toward high-throughput, cost-effective HER2 scoring, particularly suited for resource-limited settings where traditional digital pathology infrastructure is unavailable.</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":"7 ","pages":"0278"},"PeriodicalIF":9.1,"publicationDate":"2026-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13269775/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148273980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
BME frontiersPub Date : 2026-05-18eCollection Date: 2026-01-01DOI: 10.34133/bmef.0271
Yushun Zeng, Qifa Zhou
{"title":"Prospect of Wearable Ultrasound.","authors":"Yushun Zeng, Qifa Zhou","doi":"10.34133/bmef.0271","DOIUrl":"10.34133/bmef.0271","url":null,"abstract":"<p><p>Wearable ultrasound presents a promising technological solution for continuous, noninvasive monitoring of deep-tissue structures and physiological functions, addressing the key limitation of traditional wearable sensors that are largely confined to superficial signal detection. In recent years, wearable ultrasound transducers have advanced from early flexible and stretchable array designs to high-performance platforms that combine rigid functional components with flexible architectures. This hybrid design enables more stable coupling with the body surface and supports multimodal imaging capabilities. These developments highlight the strong potential of wearable ultrasound for long-term physiological monitoring and personalized medicine. However, several critical challenges remain before fully continuous and practical applications can be realized. This perspective reviews recent progress in wearable ultrasound technology and discusses future directions, such as the development of compact wireless systems, the incorporation of artificial intelligence, the expansion to 2-dimensional array configurations, and the creation of multimodal functional platforms.</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":"7 ","pages":"0271"},"PeriodicalIF":9.1,"publicationDate":"2026-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13181164/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147977440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
BME frontiersPub Date : 2026-04-21eCollection Date: 2026-01-01DOI: 10.34133/bmef.0240
Basit Ali Shah, Hongguo Zhu, Asma Sardar, Yuan Gu, Syed Taj Ud Din, Kashif Naseem, Xinyan Wu, Bin Yuan, Bin Yang
{"title":"Erratum to \"Synergistic Antibacterial Activity of Fe<sub>3</sub>O<sub>4</sub>@mPEG-Ag Nanoparticles with Molecular Docking Analyses\".","authors":"Basit Ali Shah, Hongguo Zhu, Asma Sardar, Yuan Gu, Syed Taj Ud Din, Kashif Naseem, Xinyan Wu, Bin Yuan, Bin Yang","doi":"10.34133/bmef.0240","DOIUrl":"10.34133/bmef.0240","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.34133/bmef.0214.].</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":"7 ","pages":"0240"},"PeriodicalIF":9.1,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13098286/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147790591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
BME frontiersPub Date : 2026-03-30eCollection Date: 2026-01-01DOI: 10.34133/bmef.0241
Xingfang Qiao, Yiwen Hao, Yinglan Yu, Zhe Qiang, Xingjian Wen, Yanlei Guo, Zhen Wu, Hao Shao, Lei Luo
{"title":"A Hemoglobin-Based Nanoparticle Delivery System Enhances the Pharmacokinetics and Efficacy of Tigecycline in <i>Klebsiella pneumoniae</i> Infections.","authors":"Xingfang Qiao, Yiwen Hao, Yinglan Yu, Zhe Qiang, Xingjian Wen, Yanlei Guo, Zhen Wu, Hao Shao, Lei Luo","doi":"10.34133/bmef.0241","DOIUrl":"10.34133/bmef.0241","url":null,"abstract":"<p><p><b>Objective:</b> This study aims to engineer a tigecycline-hemoglobin nanoparticle (TIG-HBNP) system to enhance the targeting effect of tigecycline (TIG) on <i>Klebsiella pneumoniae</i>, thereby improving its antibacterial efficacy. <b>Impact Statement:</b> This study represents the first report of loading TIG onto hemoglobin (HB) nanoparticles. This system utilizes the iron dependence of <i>K. pneumoniae</i> to enhance the targeting ability of TIG and increase the drug concentration at the infection site, thereby enhancing the antibacterial activity and providing a promising strategy for combating drug-resistant gram-negative bacterial pneumonia. <b>Introduction:</b> <i>K. pneumoniae</i> is a gram-negative bacillus that causes severe primary pneumonia with high pathogenicity and increasing drug resistance. TIG is a key therapeutic option, but its clinical effectiveness is limited by extensive systemic distribution and insufficient drug concentration at infectious foci. HB serves as a promising protein nanocarrier and provides iron, an essential nutrient for <i>K. pneumoniae</i> growth, suggesting great potential for targeted antibiotic delivery. <b>Methods:</b> Molecular docking was performed to analyze the binding affinity and interaction between HB and TIG. TIG-HBNP was fabricated via a drug-protein self-assembly approach. The nanoparticles were characterized in terms of particle size, zeta potential, drug-loading efficiency, morphology using transmission electron microscopy and atomic force microscopy, stability, and biocompatibility. Targeting capability was evaluated. Pharmacokinetic profiles and antibacterial activity were further assessed. <b>Results:</b> Molecular docking verified stable binding between TIG and HB. TIG-HBNP exhibited a uniform spherical morphology, a particle size of approximately 200 nm, a negative surface charge, and a drug-loading efficiency exceeding 20%. The nanoparticles showed favorable stability and safety. Enhanced targeting to <i>K. pneumoniae</i> was confirmed in both in vitro and in vivo models. Improved pharmacokinetic behavior and enhanced antibacterial activity against <i>K. pneumoniae</i> were also observed. <b>Conclusion:</b> TIG-HBNP enhances TIG's therapeutic efficacy against <i>K. pneumoniae</i> infections. Furthermore, HB holds promise as a versatile carrier for diverse antibiotics, offering a scalable platform to combat multidrug-resistant pathogens.</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":"7 ","pages":"0241"},"PeriodicalIF":9.1,"publicationDate":"2026-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13033835/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147596319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Machine Learning-Powered fNIRS Detection of Idiopathic Central Precocious Puberty via Prefrontal Cortex Activation.","authors":"Zeying Li, Lifang Jia, Yingxue Zou, Mengyu Jia, Limin Zhang, Dongyuan Liu, Feng Gao","doi":"10.34133/bmef.0223","DOIUrl":"10.34133/bmef.0223","url":null,"abstract":"<p><p><b>Objective and Impact Statement:</b> This study examines prefrontal cortex (PFC) hemodynamic responses in children with idiopathic central precocious puberty (ICPP) versus normals and constructs a noninvasive diagnostic model using functional near-infrared spectroscopy (fNIRS) augmented by machine learning. <b>Introduction:</b> Current ICPP diagnosis relies on invasive and time-consuming gonadotropin-releasing hormone stimulation tests. While fNIRS offers a noninvasive alternative, the neural mechanisms underlying ICPP remain unclear, and reliable automated diagnostic tools distinguishing patients from healthy peers are lacking. <b>Methods:</b> fNIRS data were acquired from 167 participants (82 ICPP and 85 normal) during a mental arithmetic (MA) task. General linear models and statistical tests were employed to analyze group and gender-specific activation patterns. Multidimensional features were extracted from hemodynamic signals, and a conditional denoising diffusion probabilistic model (C-DDPM) was introduced for data augmentation. <b>Results:</b> Analysis revealed gender-specific disparities, with the normal group exhibiting more extensive PFC activation than the ICPP group. In classification, a decision tree model using features from key negatively correlated channels achieved 86.57% accuracy. Notably, integrating C-DDPM-generated synthetic data further improved classifier performance metrics. <b>Conclusion:</b> The study elucidates the mechanisms of PFC activation in both normative and ICPP-affected cohorts during MA tasks and validates the effectiveness of machine learning in distinguishing between normal and ICPP children. This study provides a scientific basis for the development of automated, noninvasive rapid diagnostic tools for ICPP.</p>","PeriodicalId":72430,"journal":{"name":"BME frontiers","volume":"7 ","pages":"0223"},"PeriodicalIF":9.1,"publicationDate":"2026-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13014019/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147522870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}