Chronic pain is a complex condition shaped by long-standing alterations in both physiological and psychological processes. Rather than representing a simple continuation of acute nociceptive signaling, chronic pain is increasingly understood as the outcome of progressive dysregulation within distributed neural systems that govern sensation, affect, motivation, and cognitive control. Neuroimaging and electrophysiological studies indicate that this state is accompanied by extensive plastic changes in deep brain structures and large-scale networks. Beyond well-described central sensitization processes, chronic pain is characterized by disrupted oscillatory rhythms and altered connectivity within large-scale brain networks, including thalamo-cortical circuits and prefrontal-limbic-reward networks. These findings support a conceptual shift from viewing chronic pain as a focal, lesion-driven phenomenon toward recognizing it as a disorder of distributed network pathology. Pharmacological treatments remain central to clinical practice, yet their long-term efficacy is often limited and frequently accompanied by substantial side effects. The ongoing concerns about opioid-related risks and the inadequate therapeutic response in a subset of patients highlight the need for safe, non-pharmacological approaches that can address not only pain but also comorbid disturbances in mood, sleep, and social functioning. Neuromodulation provides a promising path toward mechanism-based and non-pharmacological management of chronic pain by employing physical or chemical stimulation to alter the excitability and synchrony of specific neural populations within central, peripheral, and autonomic systems. While invasive deep brain stimulation demonstrates that targeting deep brain structures can be effective, its clinical application is restricted by surgical risks and cost, highlighting the importance of non-invasive techniques capable of reaching deep targets. Current non-invasive approaches, such as transcranial electric stimulation, are constrained by limited penetration depth and insufficient spatial precision. These limitations hinder reliable engagement of deep regions implicated in pain, including the thalamus and nucleus accumbens, and tend to produce broad, non-specific modulation of cross-network oscillatory activity. Temporal interference (TI) stimulation has emerged as a means of overcoming these obstacles. By delivering interacting high-frequency currents that generate a low-frequency envelope within the head, TI enables focal stimulation of deep targets while minimizing superficial current delivery. Recent multiscale modeling and animal studies indicate that TI exploits the nonlinear rectification properties of neuronal membranes in response to high-frequency carriers, as well as their phase-locked responses to low-frequency envelopes, to generate “peak-focused” electric fields in deep regions under relatively low superficial current loads. Moreover, TI appears to exhibit potential advantages in terms of cell-type selectivity and rhythm-specific engagement, including differential responses across neuronal subtypes and distinct coupling to θ-, β-, and γ-band oscillations. These features suggest a promising avenue for correcting abnormal rhythms and network dynamics that contribute to chronic pain. This review summarizes current knowledge of the neural mechanisms underlying chronic pain and recent advances in TI research. It examines functional disturbances across key pain-related regions and networks, outlines the principles and technical characteristics of TI, and discusses potential deep-brain targets and stimulation strategies relevant to chronic pain. Evidence to date indicates that TI, with its non-invasiveness, tolerability, and capacity for precise deep brain modulation, holds great promise for the management of treatment-resistant chronic pain and may evolve into a new generation of precise and efficient non-pharmacological analgesic strategies.

Chronic pain is a complex condition shaped by long-standing alterations in both physiological and psychological processes. Rather than representing a simple continuation of acute nociceptive signaling, chronic pain is increasingly understood as the outcome of progressive dysregulation within distributed neural systems that govern sensation, affect, motivation, and cognitive control. Neuroimaging and electrophysiological studies indicate that this state is accompanied by extensive plastic changes in deep brain structures and large-scale networks. Beyond well-described central sensitization processes, chronic pain is characterized by disrupted oscillatory rhythms and altered connectivity within large-scale brain networks, including thalamo-cortical circuits and prefrontal-limbic-reward networks. These findings support a conceptual shift from viewing chronic pain as a focal, lesion-driven phenomenon toward recognizing it as a disorder of distributed network pathology. Pharmacological treatments remain central to clinical practice, yet their long-term efficacy is often limited and frequently accompanied by substantial side effects. The ongoing concerns about opioid-related risks and the inadequate therapeutic response in a subset of patients highlight the need for safe, non-pharmacological approaches that can address not only pain but also comorbid disturbances in mood, sleep, and social functioning. Neuromodulation provides a promising path toward mechanism-based and non-pharmacological management of chronic pain by employing physical or chemical stimulation to alter the excitability and synchrony of specific neural populations within central, peripheral, and autonomic systems. While invasive deep brain stimulation demonstrates that targeting deep brain structures can be effective, its clinical application is restricted by surgical risks and cost, highlighting the importance of non-invasive techniques capable of reaching deep targets. Current non-invasive approaches, such as transcranial electric stimulation, are constrained by limited penetration depth and insufficient spatial precision. These limitations hinder reliable engagement of deep regions implicated in pain, including the thalamus and nucleus accumbens, and tend to produce broad, non-specific modulation of cross-network oscillatory activity. Temporal interference (TI) stimulation has emerged as a means of overcoming these obstacles. By delivering interacting high-frequency currents that generate a low-frequency envelope within the head, TI enables focal stimulation of deep targets while minimizing superficial current delivery. Recent multiscale modeling and animal studies indicate that TI exploits the nonlinear rectification properties of neuronal membranes in response to high-frequency carriers, as well as their phase-locked responses to low-frequency envelopes, to generate “peak-focused” electric fields in deep regions under relatively low superficial current loads. Moreover, TI appears to exhibit potential advantages in terms of cell-type selectivity and rhythm-specific engagement, including differential responses across neuronal subtypes and distinct coupling to θ-, β-, and γ-band oscillations. These features suggest a promising avenue for correcting abnormal rhythms and network dynamics that contribute to chronic pain. This review summarizes current knowledge of the neural mechanisms underlying chronic pain and recent advances in TI research. It examines functional disturbances across key pain-related regions and networks, outlines the principles and technical characteristics of TI, and discusses potential deep-brain targets and stimulation strategies relevant to chronic pain. Evidence to date indicates that TI, with its non-invasiveness, tolerability, and capacity for precise deep brain modulation, holds great promise for the management of treatment-resistant chronic pain and may evolve into a new generation of precise and efficient non-pharmacological analgesic strategies.

ObjectiveThe widespread adoption of portable fundus cameras for primary care and community screening is hindered by limitations in current autofocus(AF) technologies. Image-based methods relying on sharpness evaluation require iterative searches, resulting in slow convergence, while projection-based techniques are susceptible to optical artifacts and calibration errors. To address these challenges, this study introduces a novel AF system based on direct wavefront sensing, designed to deliver simultaneous high speed, high precision, and operational robustness within the compact form factor essential for portable ophthalmic devices. MethodsOur approach fundamentally reimagines the AF process by directly measuring the ocular wavefront aberration. We developed a custom portable fundus camera integrating a miniaturized Shack-Hartmann wavefront sensor (SHWS) into the optical path. An 850 nm laser diode projects a point source onto the retina via oblique illumination to minimize corneal reflections. Light scattered from this spot carries the eye’s refractive error through the imaging optics and is directed to the SHWS, positioned at a plane optically conjugate to the primary color CMOS imaging sensor. A microlens array within the SHWS samples the incident wavefront, generating a pattern of focal spots on a CCD. Real-time centroid analysis of these spots provides a map of local wavefront slopes. These measurements are processed through a singular value decomposition (SVD) algorithm to fit a Zernike polynomial basis set, enabling real-time reconstruction of the wavefront phase. The defocus component (S) is extracted from the second-order Zernike coefficients, providing a direct, quantitative measure of the refractive error in diopters. This value serves as a precise error signal in a closed-loop control system, which commands a voice-coil actuated focusing lens to its null position in a single, deterministic step, eliminating the need for iterative search algorithms. ResultsComprehensive evaluation demonstrated the system’s high performance. Testing on a calibrated model eye (OEMI-7) established a highly linear relationship between the computed defocus S and the focusing lens position across a ±20 Diopter (D) compensation range, achievable within a 5 mm mechanical travel. The system achieved a focusing precision of 0.08 D, corresponding to an 18-fold improvement over a conventional projection spot-size method tested under identical conditions. The total focus acquisition time, encompassing wavefront measurement, computation, and lens actuation, averaged under 0.5 s. Clinical validation with 25 human volunteers (50 eyes, refractive range -15 D to +10 D) confirmed practical efficacy. The wavefront-sensing AF succeeded in 92% of attempts with a mean time of 0.5 s, substantially outperforming a projection-based benchmark which achieved only a 32% success rate with an average time of 4.25 s. The system provided instantaneous directional guidance and maintained stability during minor ocular movements. Objective assessment of image quality, via amplitude contrast of retinal vasculature, showed consistent and significant enhancement following AF correction across the entire tested diopter range. ConclusionThis work successfully implements and validates a direct wavefront-sensing autofocus paradigm for portable fundus cameras. By directly quantifying and compensating for the optical defocus aberration, this method bypasses the fundamental limitations of image-processing and projection-based techniques, enabling rapid, precise, and deterministic diopter compensation. The developed system delivers an exceptional combination of a wide operational range (±20 D), high accuracy (0.08 D), fast convergence (0.5 s), and a compact physical footprint. This technology provides a practical and high-performance focusing solution capable of enhancing the reliability, throughput, and diagnostic utility of portable retinal imaging in large-scale screening applications. Future efforts will be directed towards system cost optimization and performance adaptation for diverse ocular conditions.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

Objective: To develop and validate a clinically actionable prediction model for postoperative pulmonary complications (PPCs) in cardiac surgery patients, focusing on modifiable preoperative risk factors amenable to targeted optimization. Methods: In this prospective observational cohort study, 492 adults undergoing open-chest cardiac surgery between August 15, 2023 and December 31, 2023 were analyzed. Prespecified predictors included gas exchange variables, pulmonary function, inspiratory muscle strength, and physical performance. Univariable and multivariable logistic regression analyses were used to develop the prediction model. Discrimination was assessed by the area under the receiver operating characteristic curve (AUC). Results: A total of 90 patients (14.1%) developed PPCs after surgery. Five independent predictors were identified: elevated arterial PaCO2 (odds ratio [OR] 1.12, 95% confidence interval [CI] 1.00–1.26), oxygen desaturation (SpO2<93%) (OR 12.47, 95% CI 3.51–48.13), reduced gait speed (OR 0.17, 95% CI 0.04–0.71), lower FEV1/FVC ratio (OR 0.96, 95% CI 0.92–1.00), and diminished inspiratory muscle strength (MIP % predicted) (OR 0.96, 95% CI 0.92–0.99). The model demonstrated good discriminative ability with an AUC of 0.86 (95% CI 0.80–0.93) in the training cohort and 0.87 (95% CI 0.74–0.93) in the validation cohort. Conclusion This parsimonious model achieved high predictive accuracy using five modifiable physiological variables. By targeting abnormalities in gas exchange, pulmonary mechanics, muscle strength, and functional reserve, the model offers a practical tool to guide individualized prehabilitation strategies for reducing PPC risk in cardiac surgery patients.

Objective This study aims to assess the impact of four-dimensional cone-beam computed tomography (4D-CBCT) image guidance on setup error correction and target dose distribution optimization in patients receiving stereotactic body radiotherapy for lung cancer. Methods A total of 82 lung cancer patients treated with SBRT in our hospital between February 2023 and February 2025 were randomly selected as study subjects. Using a random number table, they were divided into two groups. The conventional group underwent positioning verification using traditional three-dimensional cone-beam CT, while the study group underwent verification using 4D-CBCT. Setup errors, target dose-volume parameters, organ at risk dose-volume parameters, and adverse reactions were compared between the two groups. Results The setup errors in the X, Y, and Z axes in the study group were 0.21, 0.19, and 0.23 mm, respectively, which were significantly lower than 0.58, 0.62, and 0.59 mm in the conventional group (P<0.05). The three-dimensional vector error was 0.34 (0.21, 0.48) mm in the study group, which was significantly lower than 0.98 (0.65, 1.32) mm in the conventional group (P<0.05). The rotational errors in left-right, anteroposterior, and superior-inferior directions in the study group were (0.25±0.12)°, (0.21±0.10)°, and (0.23±0.11)°, respectively; these values were significantly lower than (0.48±0.18)°, (0.42±0.15)°, and (0.45±0.16)° in the conventional group (P<0.05). The minimum dose received by 95% of the target volume [(59.45±0.85) Gy] and the percentage of the target volume receiving at least 100% of the prescription dose [(95.82±2.65)%] in the study group were higher than those in the conventional group [(58.90±1.20) Gy and (93.65±3.85)%]. The homogeneity index and conformity index in the study group were 1.07±0.03 and 1.15±0.05, respectively, which were lower than 1.12±0.05 and 1.23±0.08 in the conventional group (P<0.05). No significant differences were observed between the two groups in the volume of the lung receiving 5 Gy [(28.11±5.52)% vs. (28.85±6.24)%], the volume of the lung receiving 20 Gy [(12.84±3.56)% vs. (13.45±3.90)%], mean lung dose [(8.65±2.11) Gy vs. (8.95±2.34) Gy], maximum spinal cord dose [(18.54±3.62) Gy vs. (19.13±4.25) Gy], or mean heart dose[(14.85±4.22) Gy vs. (16.27±4.83) Gy](P>0.05). The incidence rates of radiation pneumonitis, radiation esophagitis, and skin reactions in the study group were 12.20%, 7.32%, and 4.88%, respectively, which were not significantly different from 17.07%, 9.76%, and 7.32% in the conventional group (P>0.05). Conclusion The 4D-CBCT can reduce setup errors, improve target dose accuracy and conformity in lung cancer patients undergoing SBRT, and minimize radiation exposure to normal tissues, making it worthy of clinical promotion.

Objective This study aims to assess the impact of four-dimensional cone-beam computed tomography (4D-CBCT) image guidance on setup error correction and target dose distribution optimization in patients receiving stereotactic body radiotherapy for lung cancer. Methods A total of 82 lung cancer patients treated with SBRT in our hospital between February 2023 and February 2025 were randomly selected as study subjects. Using a random number table, they were divided into two groups. The conventional group underwent positioning verification using traditional three-dimensional cone-beam CT, while the study group underwent verification using 4D-CBCT. Setup errors, target dose-volume parameters, organ at risk dose-volume parameters, and adverse reactions were compared between the two groups. Results The setup errors in the X, Y, and Z axes in the study group were 0.21, 0.19, and 0.23 mm, respectively, which were significantly lower than 0.58, 0.62, and 0.59 mm in the conventional group (P<0.05). The three-dimensional vector error was 0.34 (0.21, 0.48) mm in the study group, which was significantly lower than 0.98 (0.65, 1.32) mm in the conventional group (P<0.05). The rotational errors in left-right, anteroposterior, and superior-inferior directions in the study group were (0.25±0.12)°, (0.21±0.10)°, and (0.23±0.11)°, respectively; these values were significantly lower than (0.48±0.18)°, (0.42±0.15)°, and (0.45±0.16)° in the conventional group (P<0.05). The minimum dose received by 95% of the target volume [(59.45±0.85) Gy] and the percentage of the target volume receiving at least 100% of the prescription dose [(95.82±2.65)%] in the study group were higher than those in the conventional group [(58.90±1.20) Gy and (93.65±3.85)%]. The homogeneity index and conformity index in the study group were 1.07±0.03 and 1.15±0.05, respectively, which were lower than 1.12±0.05 and 1.23±0.08 in the conventional group (P<0.05). No significant differences were observed between the two groups in the volume of the lung receiving 5 Gy [(28.11±5.52)% vs. (28.85±6.24)%], the volume of the lung receiving 20 Gy [(12.84±3.56)% vs. (13.45±3.90)%], mean lung dose [(8.65±2.11) Gy vs. (8.95±2.34) Gy], maximum spinal cord dose [(18.54±3.62) Gy vs. (19.13±4.25) Gy], or mean heart dose[(14.85±4.22) Gy vs. (16.27±4.83) Gy](P>0.05). The incidence rates of radiation pneumonitis, radiation esophagitis, and skin reactions in the study group were 12.20%, 7.32%, and 4.88%, respectively, which were not significantly different from 17.07%, 9.76%, and 7.32% in the conventional group (P>0.05). Conclusion The 4D-CBCT can reduce setup errors, improve target dose accuracy and conformity in lung cancer patients undergoing SBRT, and minimize radiation exposure to normal tissues, making it worthy of clinical promotion.

Objective This study aims to assess the impact of four-dimensional cone-beam computed tomography (4D-CBCT) image guidance on setup error correction and target dose distribution optimization in patients receiving stereotactic body radiotherapy for lung cancer. Methods A total of 82 lung cancer patients treated with SBRT in our hospital between February 2023 and February 2025 were randomly selected as study subjects. Using a random number table, they were divided into two groups. The conventional group underwent positioning verification using traditional three-dimensional cone-beam CT, while the study group underwent verification using 4D-CBCT. Setup errors, target dose-volume parameters, organ at risk dose-volume parameters, and adverse reactions were compared between the two groups. Results The setup errors in the X, Y, and Z axes in the study group were 0.21, 0.19, and 0.23 mm, respectively, which were significantly lower than 0.58, 0.62, and 0.59 mm in the conventional group (P<0.05). The three-dimensional vector error was 0.34 (0.21, 0.48) mm in the study group, which was significantly lower than 0.98 (0.65, 1.32) mm in the conventional group (P<0.05). The rotational errors in left-right, anteroposterior, and superior-inferior directions in the study group were (0.25±0.12)°, (0.21±0.10)°, and (0.23±0.11)°, respectively; these values were significantly lower than (0.48±0.18)°, (0.42±0.15)°, and (0.45±0.16)° in the conventional group (P<0.05). The minimum dose received by 95% of the target volume [(59.45±0.85) Gy] and the percentage of the target volume receiving at least 100% of the prescription dose [(95.82±2.65)%] in the study group were higher than those in the conventional group [(58.90±1.20) Gy and (93.65±3.85)%]. The homogeneity index and conformity index in the study group were 1.07±0.03 and 1.15±0.05, respectively, which were lower than 1.12±0.05 and 1.23±0.08 in the conventional group (P<0.05). No significant differences were observed between the two groups in the volume of the lung receiving 5 Gy [(28.11±5.52)% vs. (28.85±6.24)%], the volume of the lung receiving 20 Gy [(12.84±3.56)% vs. (13.45±3.90)%], mean lung dose [(8.65±2.11) Gy vs. (8.95±2.34) Gy], maximum spinal cord dose [(18.54±3.62) Gy vs. (19.13±4.25) Gy], or mean heart dose[(14.85±4.22) Gy vs. (16.27±4.83) Gy](P>0.05). The incidence rates of radiation pneumonitis, radiation esophagitis, and skin reactions in the study group were 12.20%, 7.32%, and 4.88%, respectively, which were not significantly different from 17.07%, 9.76%, and 7.32% in the conventional group (P>0.05). Conclusion The 4D-CBCT can reduce setup errors, improve target dose accuracy and conformity in lung cancer patients undergoing SBRT, and minimize radiation exposure to normal tissues, making it worthy of clinical promotion.

Autism spectrum disorder (ASD) is a neurodevelopmental condition with a steadily rising global prevalence, yet effective pharmacological interventions remain notably limited, highlighting an urgent need for safe, accessible, and mechanism-based therapeutic strategies. Physical exercise has emerged as a promising non-pharmacological intervention that ameliorates both core symptoms—social communication deficits and restricted repetitive behaviors—and associated features including cognitive dysfunction and motor impairments, in children and adolescents with ASD. However, the molecular mechanisms mediating these beneficial effects remain incompletely defined, impeding the development of evidence-based exercise prescriptions and biomarker-driven rehabilitation protocols. MicroRNAs (miRNAs) are evolutionarily conserved small non-coding RNAs that post-transcriptionally regulate approximately 60% of protein-coding genes. Within the central nervous system, miRNAs orchestrate diverse neurobiological processes including neural progenitor proliferation, neuronal differentiation, dendritic spine morphogenesis, synaptic plasticity, and neuroinflammatory homeostasis. Notably, miRNAs are remarkably stable in biological fluids and can be packaged into extracellular vesicles, rendering them attractive candidates as both mechanistic mediators and non-invasive peripheral biomarkers. Among the hundreds of miRNAs expressed in the brain, three—miR-132, miR-34a, and miR-146a—have emerged as particularly relevant to ASD pathophysiology. This review focuses on these three miRNAs for the following reasons: miR-132 is a master regulator of activity-dependent synaptic plasticity through its modulation of BDNF/MeCP2/PTEN signaling and has been consistently downregulated in ASD prefrontal cortex; miR-34a functions as a pro-apoptotic factor that suppresses Bcl-2-mediated neuronal survival pathways and is upregulated in ASD cerebellum; and miR-146a serves as a key brake on neuroinflammation via TLR7/IRAK1 signaling and shows region-specific dysregulation in ASD temporal lobe. We first summarize evidence from human post-mortem brain tissues and ASD animal models demonstrating the consistent dysregulation of these three miRNAs. Notably, the pathological consequences of these miRNA alterations—impaired synaptic plasticity, excessive neuronal apoptosis, and sustained neuroinflammation—are interconnected and collectively contribute to the heterogeneous symptomatology of ASD. We then present a synthesis of emerging evidence demonstrating that various exercise modalities, including swimming, treadmill running, and voluntary wheel running, can concurrently reverse these ASD-like behavioral phenotypes and normalize the expression of the three key miRNAs. These data provide the first direct experimental evidence linking exercise-induced miRNA modulation to ASD symptom improvement. On the basis of these findings, we propose an integrative “exercise-miRNA-ASD” framework wherein exercise functions as a multi-targeted modulator—simultaneously enhancing synaptic plasticity, promoting neuronal survival, and attenuating neuroinflammation—through coordinated regulation of the three miRNAs. Importantly, this framework is not merely descriptive but offers testable predictions: exercise-induced miRNA changes should be dose-dependent, show temporal correlation with behavioral improvements, and be blunted by miRNA-specific antagonists or CRISPR/Cas9-mediated knockout. Beyond its specific application to ASD, this framework has broader implications. The miR-132/BDNF, miR-34a/Bcl-2, and miR-146a/TLR7 pathways are not ASD-specific but represent fundamental neural stress and repair mechanisms that are dysregulated across Alzheimer’s disease (AD), traumatic brain injury, Parkinson’s disease (PD), and major depressive disorder. Exercise has been shown to modulate these same miRNAs in several of these conditions, suggesting that the “exercise-miRNA-neural function” axis may represent a conserved neuroprotective mechanism that transcends diagnostic boundaries. Thus, we propose that ASD serves as an ideal model disease for elucidating this universal mechanism, with findings potentially generalizable to other neurological disorders. We also critically evaluate current translational barriers: the near-absence of human clinical trials with serial miRNA profiling; the undefined dose-response relationships between exercise parameters and miRNA expression; the unresolved causality issue (current evidence demonstrates association, not causation); and the uncertain correlation between peripheral exosomal miRNA levels and brain miRNA dynamics. We argue that future research must prioritize CRISPR/Cas9-based miRNA manipulation in animal models combined with longitudinal exercise interventions to establish causality, and that cross-disease validation studies are essential to determine whether exercise-induced miRNA changes represent a shared neuroprotective signature or disease-specific responses. Ultimately, we envision a paradigm where a simple blood test measuring exosomal miR-132, miR-34a, and miR-146a levels could guide personalized exercise prescriptions, enabling precision rehabilitation for individuals with ASD and potentially other neurological conditions.