Reset of hippocampal-prefrontal circuitry facilitates learning.

The ability to rapidly adapt to novel situations is essential for survival, and this flexibility is impaired in many neuropsychiatric disorders1. Thus, understanding whether and how novelty prepares, or primes, brain circuitry to facilitate cognitive flexibility has important translational relevance. Exposure to novelty recruits the hippocampus and medial prefrontal cortex (mPFC)2 and may prime hippocampal-prefrontal circuitry for subsequent learning-associated plasticity. Here we show that novelty resets the neural circuits that link the ventral hippocampus (vHPC) and the mPFC, facilitating the ability to overcome an established strategy. Exposing mice to novelty disrupted a previously encoded strategy by reorganizing vHPC activity to local theta (4-12 Hz) oscillations and weakening existing vHPC-mPFC connectivity. As mice subsequently adapted to a new task, vHPC neurons developed new task-associated activity, vHPC-mPFC connectivity was strengthened, and mPFC neurons updated to encode the new rules. Without novelty, however, mice adhered to their established strategy. Blocking dopamine D1 receptors (D1Rs) or inhibiting novelty-tagged cells that express D1Rs in the vHPC prevented these behavioural and physiological effects of novelty. Furthermore, activation of D1Rs mimicked the effects of novelty. These results suggest that novelty promotes adaptive learning by D1R-mediated resetting of vHPC-mPFC circuitry, thereby enabling subsequent learning-associated circuit plasticity.

Field-programmable gate array and deep neural network-accelerated spatial-spectral interferometry for rapid optical dispersion analysis.

Spatial-spectral interferometry (SSI) is a technique used to reconstruct the electrical field of an ultrafast laser. By analyzing the spectral phase distribution, SSI provides valuable information about the optical dispersion affecting the spectral phase, which is related to the energy distribution of the laser pulses. SSI is a single-shot measurement process and has a low laser power requirement. However, the reconstruction algorithm involves numerous Fourier transform and filtering operations, which limits the applicability of SSI for real-time dispersion analysis. To address this issue, this Letter proposes a field-programmable gate array (FPGA)-based deep neural network to accelerate the spectral phase reconstruction and dispersion estimation process. The results show that the analysis time is improved from 124 to 9.27 ms, which represents a 13.4-fold improvement on the standard Fourier transform-based reconstruction algorithm.

Adult-born neurons maintain hippocampal cholinergic inputs and support working memory during aging.

Adult neurogenesis is reduced during aging and impaired in disorders of stress, memory, and cognition though its normal function remains unclear. Moreover, a systems level understanding of how a small number of young hippocampal neurons could dramatically influence brain function is lacking. We examined whether adult neurogenesis sustains hippocampal connections cumulatively across the life span. Long-term suppression of neurogenesis as occurs during stress and aging resulted in an accelerated decline in hippocampal acetylcholine signaling and a slow and progressing emergence of profound working memory deficits. These deficits were accompanied by compensatory reorganization of cholinergic dentate gyrus inputs with increased cholinergic innervation to the ventral hippocampus and recruitment of ventrally projecting neurons by the dorsal projection. While increased cholinergic innervation was dysfunctional and corresponded to overall decreases in cholinergic levels and signaling, it could be recruited to correct the resulting memory dysfunction even in old animals. Our study demonstrates that hippocampal neurogenesis supports memory by maintaining the septohippocampal cholinergic circuit across the lifespan.  It also provides a systems level explanation for the progressive nature of memory deterioration during normal and pathological aging and indicates that the brain connectome is malleable by experience.

Real-time adaptive ultrashort pulse compressor for dynamic group delay dispersion compensation.

The optical dispersion effect in ultrafast pulse laser systems broadens the laser pulse duration and reduces the theoretical peak power. The present study proposes an adaptive ultrashort pulse compressor for compensating the optical dispersion using a direct optical-dispersion estimation by spectrogram (DOES) method. The DOES has fast and accurate computation time which is suitable for real time controller design. In the proposed approach, the group delay dispersion (GDD) and its polarity are estimated directly from the delay marginal of the trace obtained from a single-shot frequency-resolved optical gating (FROG). The estimated GDD is then processed by a closed-loop controller, which generates a command signal to drive a linear deformable mirror as required to achieve the desired laser pulse compression. The dispersion analysis, control computation, and deformable mirror control processes are implemented on a single field programmable gate array (FPGA). It is shown that the DOES dispersion computation process requires just 0.5 ms to complete. Moreover, the proposed pulse compressor compensates for both static dispersion and dynamic dispersion within five time steps when closed-loop controller is performed at a frequency of 100 Hz. The experimental results show that the proposed pulse compressor yields an effective fluorescence intensity improvement in a multiphoton excited fluorescence microscope (MPEFM).

Two-Photon-Near Infrared-II Antimicrobial Graphene-Nanoagent for Ultraviolet-Near Infrared Imaging and Photoinactivation.

Nitrogen doping and amino group functionalization through chemical modification lead to strong electron donation. Applying these processes to a large π-conjugated system of graphene quantum dot (GQD)-based materials as electron donors increases the charge transfer efficiency of nitrogen-doped amino acid-functionalized GQDs (amino-N-GQDs), resulting in enhanced two-photon absorption, post-two-photon excitation (TPE) stability, TPE cross-sections, and two-photon luminescence through the radiative pathway when the lifetime decreases and the quantum yield increases. Additionally, it leads to the generation of reactive oxygen species through two-photon photodynamic therapy (PDT). The sorted amino-N-GQDs prepared in this study exhibited excitation-wavelength-independent two-photon luminescence in the near-infrared region through TPE in the near-infrared-II region. The increase in size resulted in size-dependent photochemical and electrochemical efficacy, increased photoluminescence quantum yield, and efficient two-photon PDT. Therefore, the sorted amino-N-GQDs can be applicable as two-photon contrast probes to track and localize analytes in in-depth two-photon imaging executed in a biological environment along with two-photon PDT to eliminate infectious or multidrug-resistant microbes.

Adaptive optics for dynamic aberration compensation using parallel model-based controllers based on a field programmable gate array.

Adaptive optics (AO) is an effective technique for compensating the aberrations in optical systems and restoring their performance for various applications such as image formation, laser processing, and beam shaping. To reduce the controller complexity and extend the compensation capacity from static aberrations to dynamic disturbances, the present study proposes an AO system consisting of a self-built Shack-Hartmann wavefront sensor (SHWS), a deformable mirror (DM), and field programmable gate array (FPGA)-based controllers. This AO system is developed for tracking static and dynamic disturbances and tuning the controller parameters as required to achieve rapid compensation of the incoming wavefront. In the proposed system, the FPGA estimates the coefficients of the eight Zernike modes based on the SHWS with CameraLink operated at 200 Hz. The estimated coefficients are then processed by eight parallel independent discrete controllers to generate the voltage vectors to drive the DM to compensate the aberrations. To have the DM model for controller design, the voltage vectors are identified offline and are optimized by closed-loop controllers. Furthermore, the controller parameters are tuned dynamically in accordance with the main frequency of the aberration as determined by a fast Fourier transform (FFT) process. The experimental results show that the AO system provides a low complexity and effective means of compensating both static aberrations and dynamic disturbance up to 20 Hz.

Not Just a Bystander: The Emerging Role of Astrocytes and Research Tools in Studying Cognitive Dysfunctions in Schizophrenia.

Cognitive dysfunction is one of the core symptoms in schizophrenia, and it is predictive of functional outcomes and therefore useful for treatment targets. Rather than improving cognitive deficits, currently available antipsychotics mainly focus on positive symptoms, targeting dopaminergic/serotoninergic neurons and receptors in the brain. Apart from investigating the neural mechanisms underlying schizophrenia, emerging evidence indicates the importance of glial cells in brain structure development and their involvement in cognitive functions. Although the etiopathology of astrocytes in schizophrenia remains unclear, accumulated evidence reveals that alterations in gene expression and astrocyte products have been reported in schizophrenic patients. To further investigate the role of astrocytes in schizophrenia, we highlighted recent progress in the investigation of the effect of astrocytes on abnormalities in glutamate transmission and impairments in the blood-brain barrier. Recent advances in animal models and behavioral methods were introduced to examine schizophrenia-related cognitive deficits and negative symptoms. We also highlighted several experimental tools that further elucidate the role of astrocytes. Instead of focusing on schizophrenia as a neuron-specific disorder, an additional astrocytic perspective provides novel and promising insight into its causal mechanisms and treatment. The involvement of astrocytes in the pathogenesis of schizophrenia and other brain disorders is worth further investigation.

Nitrogen Functionalities of Amino-Functionalized Nitrogen-Doped Graphene Quantum Dots for Highly Efficient Enhancement of Antimicrobial Therapy to Eliminate Methicillin-Resistant Staphylococcus aureus and Utilization as a Contrast Agent.

There is an urgent need for materials that can efficiently generate reactive oxygen species (ROS) and be used in photodynamic therapy (PDT) as two-photon imaging contrast probes. In this study, graphene quantum dots (GQDs) were subjected to amino group functionalization and nitrogen doping (amino-N-GQDs) via annealing and hydrothermal ammonia autoclave treatments. The synthesized dots could serve as a photosensitizer in PDT and generate more ROS than conventional GQDs under 60-s low-energy (fixed output power: 0.07 W·cm-2) excitation exerted by a 670-nm continuous-wave laser. The generated ROS were used to completely eliminate a multidrug-resistant strain of methicillin-resistant Staphylococcus aureus (MRSA), a Gram-positive bacterium. Compared with conventional GQDs, the amino-N-GQDs had superior optical properties, including stronger absorption, higher quantum yield (0.34), stronger luminescence, and high stability under exposure. The high photostability and intrinsic luminescence of amino-N-GQDs contribute to their suitability as contrast probes for use in biomedical imaging, in addition to their bacteria tracking and localization abilities. Herein, the dual-modality amino-N-GQDs in PDT easily eliminated multidrug-resistant bacteria, ultimately revealing their potential for use in future clinical applications.

miR-29a-3p/THBS2 Axis Regulates PAH-Induced Cardiac Fibrosis.

Pulmonary artery hypertension (PAH) pathology involves extracellular matrix (ECM) remodeling in cardiac tissues, thus promoting cardiac fibrosis progression. miR-29a-3p reportedly inhibits lung progression and liver fibrosis by regulating ECM protein expression; however, its role in PAH-induced fibrosis remains unclear. In this study, we aimed to investigate the role of miR-29a-3p in cardiac fibrosis progression in PAH and its influence on ECM protein thrombospondin-2 (THBS2) expression. The diagnostic and prognostic values of miR-29a-3p and THBS2 in PAH were evaluated. The expressions and effects of miR-29a-3p and THBS2 were assessed in cell culture, monocrotaline-induced PAH mouse model, and patients with PAH. The levels of circulating miR-29a-3p and THBS2 in patients and mice with PAH decreased and increased, respectively. miR-29a-3p directly targets THBS2 and regulates THBS2 expression via a direct anti-fibrotic effect on PAH-induced cardiac fibrosis. The circulating levels of miR-29a-3p and THBS2 were correlated with PAH diagnostic parameters, suggesting their independent prognostic value. miR-29a-3p targeted THBS2 expression via a direct anti-fibrotic effect on PAH-induced cardiac fibrosis, indicating miR-29a-3p acts as a messenger with promising therapeutic effects.

High Mobility Group Box 1 Promotes Lung Cancer Cell Migration and Motility via Regulation of Dynamin-Related Protein 1.

High mobility group box 1 (HMGB1) has been demonstrated to promote the migration and invasion of non-small cell lung cancer (NSCLC). However, the mechanism of action of HMGB1 in regulating tumor mobility remains unclear. Therefore, we aimed to investigate whether HMGB1 affects mitochondria distribution and regulates dynamin-related protein 1 (DRP1)-mediated lamellipodia/filopodia formation to promote NSCLC migration. The regulation of mitochondrial membrane tension, dynamics, polarization, fission process, and cytoskeletal rearrangements in lung cancer cells by HMGB1 was analyzed using confocal microscopy. The HMGB1-mediated regulation of DRP1 phosphorylation and colocalization was determined using immunostaining and co-immunoprecipitation assays. The tumorigenic potential of HMGB1 was assessed in vivo and further confirmed using NSCLC patient samples. Our results showed that HMGB1 increased the polarity and mobility of cells (mainly by regulating the cytoskeletal system actin and microtubule dynamics and distribution), promoted the formation of lamellipodia/filopodia, and enhanced the expression and phosphorylation of DRP1 in both the nucleus and cytoplasm. In addition, HMGB1 and DRP1 expressions were positively correlated and exhibited poor prognosis and survival in patients with lung cancer. Collectively, HMGB1 plays a key role in the formation of lamellipodia and filopodia by regulating cytoskeleton dynamics and DRP1 expression to promote lung cancer migration.

Briarenols Q-T: Briaranes from A Cultured Octocoral Briareum stechei (Kükenthal, 1908).

Our continuous chemical study of a cultured octocoral Briareum stechei led to the isolation of four new briarane diterpenoids, briarenols Q-T (1-4). The structures of new metabolites 1-4 were established by spectroscopic methods, and compounds 3 and 4 were found to inhibit the generation of inducible nitric oxide synthase (iNOS) from RAW 264.7 stimulated by lipopolysaccharides (LPS).

Amino-Functionalized Nitrogen-Doped Graphene-Quantum-Dot-Based Nanomaterials with Nitrogen and Amino-Functionalized Group Content Dependence for Highly Efficient Two-Photon Bioimaging.

We fabricated nanomaterials comprising amino-functionalized and nitrogen-doped graphene quantum dots (amino-N-GQDs) and investigated their photostability and intrinsic luminescence in the near-infrared spectrum to determine their suitability as contrast agents in two-photon imaging (TPI). We observed that amino-N-GQDs with a higher amount of bonded nitrogen and amino-functionalized groups (6.2%) exhibited superior two-photon properties to those with a lower amount of such nitrogen and groups (4.9%). These materials were conjugated with polymers containing sulfur (polystyrene sulfonate, PSS) and nitrogen atoms (polyethylenimine, PEI), forming amino-N-GQD-PSS-PEI specimens (amino-N-GQD-polymers). The polymers exhibited a high quantum yield, remarkable stability, and notable two-photon properties and generated no reactive oxygen species, rendering them excellent two-photon contrast agents for bioimaging. An antiepidermal growth factor receptor (AbEGFR) was used for labeling to increase specificity. Two-photon imaging (TPI) of amino-N-GQD (6.2%)-polymer-AbEGFR-treated A431 cancer cells revealed remarkable brightness, intensity, and signal-to-noise ratios for each observation at a two-photon excitation power of 16.9 nJ pixel-1 under 30 scans and a three-dimensional (3D) depth of 105 µm, indicating that amino-N-GQD (6.2%)-polymer-AbEGFR-treated cells can achieve two-photon luminescence with 71 times less power required for two-photon autofluorescence (1322.8 nJ pixel-1 with 500 scans) of similar intensity. This economy can minimize photodamage to cells, rendering amino-N-GQD-polymers suitable for noninvasive 3D bioimaging.

The sodium-glucose co-transporter 2 inhibitor empagliflozin attenuates cardiac fibrosis and improves ventricular hemodynamics in hypertensive heart failure rats.

BACKGROUND: Sodium glucose co-transporter 2 inhibitor (SGLT2i), a new class of anti-diabetic drugs acting on inhibiting glucose resorption by kidneys, is shown beneficial in reduction of heart failure hospitalization and cardiovascular mortality. The mechanisms remain unclear. We hypothesized that SGLT2i, empagliflozin can improve cardiac hemodynamics in non-diabetic hypertensive heart failure. METHODS AND RESULTS: The hypertensive heart failure model had been created by feeding spontaneous hypertensive rats (SHR) with high fat diet for 32 weeks (total n = 13). Half SHRs were randomized to be administered with SGLT2i, empagliflozin at 20 mg/kg/day for 12 weeks. After evaluation of electrocardiography and echocardiography, invasive hemodynamic study was performed and followed by blood sample collection and tissue analyses. Empagliflozin exhibited cardiac (improved atrial and ventricular remodeling) and renal protection, while plasma glucose level was not affected. Empagliflozin normalized both end-systolic and end-diastolic volume in SHR, in parallel with parameters in echocardiographic evaluation. Empagliflozin also normalized systolic dysfunction, in terms of the reduced maximal velocity of pressure incline and the slope of end-systolic pressure volume relationship in SHR. In histological analysis, empagliflozin significantly attenuated cardiac fibrosis in both atrial and ventricular tissues. The upregulation of atrial and ventricular expression of PPARα, ACADM, natriuretic peptides (NPPA and NPPB), and TNF-α in SHR, was all restored by treatment of empagliflozin. CONCLUSIONS: Empagliflozin improves hemodynamics in our hypertensive heart failure rat model, associated with renal protection, attenuated cardiac fibrosis, and normalization of HF genes. Our results contribute some understanding of the pleiotropic effects of empagliflozin on improving heart function.

Running exercise delays neurodegeneration in amygdala and hippocampus of Alzheimer's disease (APP/PS1) transgenic mice.

Alzheimer's disease (AD) is an age-related neurodegenerative disease. Post-mortem examination and brain imaging studies indicate that neurodegeneration is evident in the hippocampus and amygdala of very early stage AD patients. Exercise training is known to enhance hippocampus- and amygdala-associated neuronal function. Here, we investigated the effects of exercise (running) on the neuronal structure and function of the hippocampus and amygdala in APP/PS1 transgenic (Tg) mice. At 4-months-old, an age before amyloid deposition, the amygdala-associated, but not the hippocampus-associated, long-term memory was impaired in the Tg mice. The dendritic complexities of the amygdalar basolateral neurons, but not those in the hippocampal CA1 and CA3 neurons, were reduced. Furthermore, the levels of BDNF/TrkB signaling molecules (i.e. p-TrkB, p-Akt and p-PKC) were reduced in the amygdala, but not in the hippocampus of the 4-month-old Tg mice. The concentrations of Aß40 and Aß42 in the amygdala were higher than those in the hippocampus. Ten weeks of treadmill training (from 1.5- to 4-month-old) increased the hippocampus-associated memory and dendritic arbor of the CA1 and CA3 neurons, and also restored the amygdala-associated memory and the dendritic arbor of amygdalar basolateral neurons in the Tg mice. Similarly, exercise training also increased the levels of p-TrkB, p-AKT and p-PKC in the hippocampus and amygdala. Furthermore, exercise training reduced the levels of soluble Aß in the amygdala and hippocampus. Exercise training did not change the levels of APP or RAGE, but significantly increased the levels of LRP-1 in both brain regions of the Tg mice. In conclusion, our results suggest that tests of amygdala function should be incorporated into subject selection for early prevention trials. Long-term exercise protects neurons in the amygdala and hippocampus against AD-related degeneration, probably via enhancements of BDNF signaling pathways and Aß clearance. Physical exercise may serve as a means to delay the onset of AD.

Graphene oxide-based micropatterns via high-throughput multiphoton-induced reduction and ablation.

In this study, a developed temporal focusing-based femtosecond laser system provides high-throughput multiphoton-induced reduction and ablation of graphene oxide (GO) films. Integrated with a digital micromirror device to locally control the laser pulse numbers, GO-based micropatterns can be quickly achieved instantly. Furthermore, the degree of reduction and ablation can be precisely adjusted via controlling the laser wavelength, power, and pulse number. Compared to point-by-point scanning laser direct writing, this approach offers a high-throughput and multiple-function approach to accomplish a large area of micro-scale patterns on GO films. The high-throughput micropatterning of GO via the temporal focusing-based femtosecond laser system fulfills the requirement of mass production for GO-based applications in microelectronic devices.

Curcumin regulates pulmonary extracellular matrix remodeling and mitochondrial function to attenuate pulmonary fibrosis by regulating the miR-29a-3p/DNMT3A axis.

Epigenetic regulation and mitochondrial dysfunction are essential to the progression of idiopathic pulmonary fibrosis (IPF). Curcumin (CCM) in inhibits the progression of pulmonary fibrosis by regulating the expression of specific miRNAs and pulmonary fibroblast mitochondrial function; however, the underlying mechanism is unclear. C57BL/6 mice were intratracheally injected with bleomycin (5 mg/kg) and treated with CCM (25 mg/kg body weight/3 times per week, intraperitoneal injection) for 28 days. Verhoeff-Van Gieson, Picro sirius red, and Masson's trichrome staining were used to examine the expression and distribution of collagen and elastic fibers in the lung tissue. Pulmonary fibrosis was determined using micro-computed tomography and transmission electron microscopy. Human pulmonary fibroblasts were transfected with miR-29a-3p, and RT-qPCR, immunostaining, and western blotting were performed to determine the expression of DNMT3A and extracellular matrix collagen-1 (COL1A1) and fibronectin-1 (FN1) levels. The expression of mitochondrial electron transport chain complex (MRC) and mitochondrial function were detected using western blotting and Seahorse XFp Technology. CCM in increased the expression of miR-29a-3p in the lung tissue and inhibited the DNMT3A to reduce the COL1A1 and FN1 levels leading to pulmonary extracellular matrix remodeling. In addition, CCM inhibited pulmonary fibroblasts MRC and mitochondrial function via the miR-29a-3p/DNMT3A pathway. CCM attenuates pulmonary fibrosis via the miR-29a-3p/DNMT3A axis to regulate extracellular matrix remodeling and mitochondrial function and may provide a new therapeutic intervention for preventing pulmonary fibrosis.

Piezo bender controller for precise optical dispersion compensation based on single-shot optical interferometry.

Ultrafast lasers concentrate the energy in a short pulse with a duration of several tens to hundreds of femtoseconds. The resulting high peak power induces various nonlinear optical phenomena that find use in many different fields. However, in practical applications, the optical dispersion broadens the laser pulse width and spreads the energy in time, thereby reducing the peak power. Accordingly, the present study develops a piezo bender-based pulse compressor to compensate for this dispersion effect and restore the laser pulse width. The piezo bender has a rapid response time and a large deformation capacity and thus provides a highly effective means of performing dispersion compensation. However, due to hysteresis and creep effects, the piezo bender is unable to maintain a stable shape over time and hence the compensation effect is gradually degraded. To address this problem, this study further proposes a single-shot modified laterally sampled laser interferometer to estimate the parabolic shape of the piezo bender. The curvature variation of the bender is then sent as a feedback signal to a closed-loop controller to restore the bender to the desired shape. It is shown that the steady-state error of the converged group delay dispersion is around 530 fs2. Moreover, the ultrashort laser pulse is compressed from 1620 fs in the original condition to 140 fs in the compressed condition, corresponding to a 12-fold improvement.

Towards Fair Patient-Trial Matching via Patient-Criterion Level Fairness Constraint.

Clinical trials are indispensable in developing new treatments, but they face obstacles in patient recruitment and retention, hindering the enrollment of necessary participants. To tackle these challenges, deep learning frameworks have been created to match patients to trials. These frameworks calculate the similarity between patients and clinical trial eligibility criteria, considering the discrepancy between inclusion and exclusion criteria. Recent studies have shown that these frameworks outperform earlier approaches. However, deep learning models may raise fairness issues in patient-trial matching when certain sensitive groups of individuals are underrepresented in clinical trials, leading to incomplete or inaccurate data and potential harm. To tackle the issue of fairness, this work proposes a fair patient-trial matching framework by generating a patient-criterion level fairness constraint. The proposed framework considers the inconsistency between the embedding of inclusion and exclusion criteria among patients of different sensitive groups. The experimental results on real-world patient-trial and patient-criterion matching tasks demonstrate that the proposed framework can successfully alleviate the predictions that tend to be biased.

Multi-Task Learning for Post-transplant Cause of Death Analysis: A Case Study on Liver Transplant.

Organ transplant is the essential treatment method for some end-stage diseases, such as liver failure. Analyzing the post-transplant cause of death (CoD) after organ transplant provides a powerful tool for clinical decision making, including personalized treatment and organ allocation. However, traditional methods like Model for End-stage Liver Disease (MELD) score and conventional machine learning (ML) methods are limited in CoD analysis due to two major data and model-related challenges. To address this, we propose a novel framework called CoD-MTL leveraging multi-task learning to model the semantic relationships between various CoD prediction tasks jointly. Specifically, we develop a novel tree distillation strategy for multi-task learning, which combines the strength of both the tree model and multi-task learning. Experimental results are presented to show the precise and reliable CoD predictions of our framework. A case study is conducted to demonstrate the clinical importance of our method in the liver transplant.

Enhancing the Performance of Pathological Voice Quality Assessment System Through the Attention-Mechanism Based Neural Network.

OBJECTIVE: Doctors, nowadays, primarily use auditory-perceptual evaluation, such as the grade, roughness, breathiness, asthenia, and strain scale, to evaluate voice quality and determine the treatment. However, the results predicted by individual physicians often differ, because of subjective perceptions, and diagnosis time interval, if the patient's symptoms are hard to judge. Therefore, an accurate computerized pathological voice quality assessment system will improve the quality of assessment. METHOD: This study proposes a self_attention-based system, with a deep learning technology, named self_attention-based bidirectional long-short term memory (SA BiLSTM). Different pitches [low, normal, high], and vowels [/a/, /i/, /u/], were added into the proposed model, to make it learn how professional doctors evaluate the grade, roughness, breathiness, asthenia, and strain scale, in a high dimension view. RESULTS: The experimental results showed that the proposed system provided higher performance than the baseline system. More specifically, the macro average of the F1 score, presented as decimal, was used to compare the accuracy of classification. The (G, R, and B) of the proposed system were (0.768±0.011, 0.820±0.009, and 0.815±0.009), which is higher than the baseline systems: deep neural network (0.395±0.010, 0.312±0.019, 0.321±0.014) and convolution neural network (0.421±0.052, 0.306±0.043, 0.3250±0.032) respectively. CONCLUSIONS: The proposed system, with SA BiLSTM, pitches, and vowels, provides a more accurate way to evaluate the voice. This will be helpful for clinical voice evaluations and will improve patients' benefits from voice therapy.