Boundary attention with multi-task consistency constraints for semi-supervised 2D echocardiography segmentation.

The 2D echocardiography semantic automatic segmentation technique is important in clinical applications for cardiac function assessment and diagnosis of cardiac diseases. However, automatic segmentation of 2D echocardiograms also faces the problems of loss of image boundary information, loss of image localization information, and limitations in data acquisition and annotation. To address these issues, this paper proposes a semi-supervised echocardiography segmentation method. It consists of two models: (1) a boundary attention transformer net (BATNet) and (2) a multi-task level semi-supervised model with consistency constraints on boundary features (semi-BATNet). BATNet is able to capture the location and spatial information of the input feature maps by using the self-attention mechanism. The multi-task level semi-supervised model with boundary feature consistency constraints (semi-BATNet) encourages consistent predictions of boundary features at different scales from the student and teacher networks to calculate the multi-scale consistency loss for unlabeled data. The proposed semi-BATNet was extensively evaluated on the dataset of cardiac acquisitions for multi-structure ultrasound segmentation (CAMUS) and self-collected echocardiography dataset from the First Affiliated Hospital of Chongqing Medical University. Experimental results on the CAMUS dataset showed that when only 25% of the images are labeled, the proposed method greatly improved the segmentation performance by utilizing unlabeled images, and it also outperformed five state-of-the-art semi-supervised segmentation methods. Moreover, when only 50% of the images labeled, semi-BATNet achieved the Dice coefficient values of 0.936, the Jaccard similarity of 0.881 on self-collected echocardiography dataset. Semi-BATNet can complete a more accurate segmentation of cardiac structures in 2D echocardiograms, indicating that it has the potential to accurately and efficiently assist cardiologists.

Detection of Coronary Artery Disease Based on Clinical Phonocardiogram and Multiscale Attention Convolutional Compression Network.

Heart sound is an important physiological signal that contains rich pathological information related with coronary stenosis. Thus, some machine learning methods are developed to detect coronary artery disease (CAD) based on phonocardiogram (PCG). However, current methods lack sufficient clinical dataset and fail to achieve efficient feature utilization. Besides, the methods require complex processing steps including empirical feature extraction and classifier design. To achieve efficient CAD detection, we propose the multiscale attention convolutional compression network (MACCN) based on clinical PCG dataset. Firstly, PCG dataset including 102 CAD subjects and 82 non-CAD subjects was established. Then, a multiscale convolution structure was developed to catch comprehensive heart sound features and a channel attention module was developed to enhance key features in multiscale attention convolutional block (MACB). Finally, a separate downsampling block was proposed to reduce feature losses. MACCN combining the blocks can automatically extract features without empirical and manual feature selection. It obtains good classification results with accuracy 93.43%, sensitivity 93.44%, precision 93.48%, and F1 score 93.42%. The study implies that MACCN performs effective PCG feature mining aiming for CAD detection. Further, it integrates feature extraction and classification and provides a simplified PCG processing case.

Analysis and recognition of post-exercise cardiac state based on heart sound features and cardiac troponin I.

PURPOSE: Excessive intensity exercises can bring irreversible damage to the heart. We explore whether heart sounds can evaluate cardiac function after high-intensity exercise and hope to prevent overtraining through the changes of heart sound in future training. METHODS: The study population consisted of 25 male athletes and 24 female athletes. All subjects were healthy and had no history of cardiovascular disease or family history of cardiovascular disease. The subjects were required to do high-intensity exercise for 3 days, with their blood sample and heart sound (HS) signals being collected and analysed before and after exercise. We then developed a Kernel extreme learning machine (KELM) model that can distinguish the state of heart by using the pre- and post-exercise data. RESULTS: There was no significant change in serum cardiac troponin I after 3 days of load cross-country running, which indicates that there was no myocardial injury after the race. The statistical analysis of time-domain characteristics and multi-fractal characteristic parameters of HS showed that the cardiac reserve capacity of the subjects was enhanced after the cross-country running, and the KELM is an effective classifier to recognize HS and the state of the heart after exercise. CONCLUSION: Through the results, we can draw the conclusion that this intensity of exercise will not cause profound damage to the athlete's heart. The findings of this study are of great significance for evaluating the condition of the heart with the proposed index of heart sound and prevention of excessive training that causes damage to the heart.

Phonocardiogram transfer learning-based CatBoost model for diastolic dysfunction identification using multiple domain-specific deep feature fusion.

Left ventricular diastolic dyfunction detection is particularly important in cardiac function screening. This paper proposed a phonocardiogram (PCG) transfer learning-based CatBoost model to detect diastolic dysfunction noninvasively. The Short-Time Fourier Transform (STFT), Mel Frequency Cepstral Coefficients (MFCCs), S-transform and gammatonegram were utilized to perform four different representations of spectrograms for learning the representative patterns of PCG signals in two-dimensional image modality. Then, four pre-trained convolutional neural networks (CNNs) such as VGG16, Xception, ResNet50 and InceptionResNetv2 were employed to extract multiple domain-specific deep features from PCG spectrograms using transfer learning, respectively. Further, principal component analysis and linear discriminant analysis (LDA) were applied to different feature subsets, respectively, and then these different selected features are fused and fed into CatBoost for classification and performance comparison. Finally, three typical machine learning classifiers such as multilayer perceptron, support vector machine and random forest were employed to compared with CatBoost. The hyperparameter optimization of the investigated models was determined through grid search. The visualized result of the global feature importance showed that deep features extracted from gammatonegram by ResNet50 contributed most to classification. Overall, the proposed multiple domain-specific feature fusion based CatBoost model with LDA achieved the best performance with an area under the curve of 0.911, accuracy of 0.882, sensitivity of 0.821, specificity of 0.927, F1-score of 0.892 on the testing set. The PCG transfer learning-based model developed in this study could aid in diastolic dysfunction detection and could contribute to non-invasive evaluation of diastolic function.

Heart function grading evaluation based on heart sounds and convolutional neural networks.

Accurate and rapid cardiac function assessment is critical for disease diagnosis and treatment strategy. However, the current cardiac function assessment methods have their adaptability and limitations. Heart sounds (HS) can reflect changes in heart function. Therefore, HS signals were proposed to assess cardiac function, and a specially designed pruning convolutional neural network (CNN) was applied to recognize subjects' cardiac function at different levels in this paper. Firstly, the adaptive wavelet denoising algorithm and logistic regression based hidden semi-Markov model were utilized for signal denoising and segmentation. Then, the continuous wavelet transform (CWT) was employed to convert the preprocessed HS signals into spectra as input to the convolutional neural network, which can extract features automatically. Finally, the proposed method was compared with AlexNet, Resnet50, Xception, GhostNet and EfficientNet to verify the superiority of the proposed method. Through comprehensive comparison, the proposed approach achieves the best classification performance with an accuracy of 94.34%. The study indicates HS analysis is a non-invasive and effective method for cardiac function classification, which has broad research prospects.

Copper-based metal-organic framework impedes triple-negative breast cancer metastasis via local estrogen deprivation and platelets blockade.

Metastasis is one of the main causes of failure in the treatment of triple-negative breast cancer (TNBC). Abnormally estrogen level and activated platelets are the key driving forces for TNBC metastasis. Herein, an "ion/gas" bioactive nanogenerator (termed as IGBN), comprising a copper-based MOF and loaded cisplatin-arginine (Pt-Arg) prodrug is developed for metastasis-promoting tumor microenvironment reprogramming and TNBC therapy. The copper-based MOF not only serves as a drug carrier, but also specifically produces Cu2+ in tumors, which catalytic oxidizing estrogen to reduce estrogen levels in situ. Meanwhile, the rationally designed Pt-Arg prodrug reduced into cisplatin to significantly promote the generation of H2O2 in the tumor, then permitting self-augmented cascade NO gas generation by oxidizing Arg through a H2O2 self-supplied way, thus blocking platelet activation in tumor. We clarified that IGBN inhibited TNBC metastasis through local estrogen deprivation and platelets blockade, affording 88.4% inhibition of pulmonary metastasis in a 4T1 mammary adenocarcinoma model. Notably, the locally copper ion interference, NO gas therapy and cisplatin chemotherapy together resulted in an enhanced therapeutic efficacy in primary tumor ablation without significant toxicity. This "ion/gas" bioactive nanogenerator offers a robust and safe strategy for TNBC therapy.

A multi-scale and multi-domain heart sound feature-based machine learning model for ACC/AHA heart failure stage classification.

Objective.Heart sounds can reflect detrimental changes in cardiac mechanical activity that are common pathological characteristics of chronic heart failure (CHF). The ACC/AHA heart failure (HF) stage classification is essential for clinical decision-making and the management of CHF. Herein, a machine learning model that makes use of multi-scale and multi-domain heart sound features was proposed to provide an objective aid for ACC/AHA HF stage classification.Approach.A dataset containing phonocardiogram (PCG) signals from 275 subjects was obtained from two medical institutions and used in this study. Complementary ensemble empirical mode decomposition and tunable-Q wavelet transform were used to construct self-adaptive sub-sequences and multi-level sub-band signals for PCG signals. Time-domain, frequency-domain and nonlinear feature extraction were then applied to the original PCG signal, heart sound sub-sequences and sub-band signals to construct multi-scale and multi-domain heart sound features. The features selected via the least absolute shrinkage and selection operator were fed into a machine learning classifier for ACC/AHA HF stage classification. Finally, mainstream machine learning classifiers, including least-squares support vector machine (LS-SVM), deep belief network (DBN) and random forest (RF), were compared to determine the optimal model.Main results. The results showed that the LS-SVM, which utilized a combination of multi-scale and multi-domain features, achieved better classification performance than the DBN and RF using multi-scale or/and multi-domain features alone or together, with average sensitivity, specificity, and accuracy of 0.821, 0.955 and 0.820 on the testing set, respectively.Significance.PCG signal analysis provides efficient measurement information regarding CHF severity and is a promising noninvasive method for ACC/AHA HF stage classification.

An automatic approach for heart failure typing based on heart sounds and convolutional recurrent neural networks.

Heart failure (HF) is a complex clinical syndrome that poses a major hazard to human health. Patients with different types of HF have great differences in pathogenesis and treatment options. Therefore, HF typing is of great significance for timely treatment of patients. In this paper, we proposed an automatic approach for HF typing based on heart sounds (HS) and convolutional recurrent neural networks, which provides a new non-invasive and convenient way for HF typing. Firstly, the collected HS signals were preprocessed with adaptive wavelet denoising. Then, the logistic regression based hidden semi-Markov model was utilized to segment HS frames. For the distinction between normal subjects and the HF patients with preserved ejection fraction or reduced ejection fraction, a model based on convolutional neural network and recurrent neural network was built. The model can automatically learn the spatial and temporal characteristics of HS signals. The results show that the proposed model achieved a superior performance with an accuracy of 97.64%. This study suggests the proposed method could be a useful tool for HF recognition and as a supplement for HF typing.

Distinct binding kinetics of E-, P- and L-selectins to CD44.

Molecular-level selectin-cluster of differentiation 44 (CD44) interactions are far from clear because of the complexity and diversity of CD44 glycosylation and isoforms expressed on various types of cells. By combining experimental measurements and simulation predictions, the binding kinetics of three selectin members to the recombinant CD44 were quantified and the corresponding microstructural mechanisms were explored, respectively. Experimental results showed that the E-selectin-CD44 interactions mainly mediated the firm adhesion of microbeads under shear flow with the strongest rupture force. P- and L-selectins had similar interaction strength but different association and dissociation rates by mediating stable rolling and transient adhesions of microbeads, respectively. Molecular docking and molecular dynamics (MD) simulations predicted that the binding epitopes of CD44 to selectins are all located at the side face of each selectin, although the interfaces denoted as the hinge region are between lectin and epidermal growth factor domains of E-selectin, Lectin domain side of P-selectin and epidermal growth factor domain side of L-selectin, respectively. The lowest binding free energy, the largest rupture force and the longest lifetime for E-selectin, as well as the comparable values for P- and L-selectins, demonstrated in both equilibration and steered MD simulations, supported the above experimental results. These results offer basic data for understanding the functional differences of selectin-CD44 interactions.

Deep Learning-Based Heart Sound Analysis for Left Ventricular Diastolic Dysfunction Diagnosis.

The aggravation of left ventricular diastolic dysfunction (LVDD) could lead to ventricular remodeling, wall stiffness, reduced compliance, and progression to heart failure with a preserved ejection fraction. A non-invasive method based on convolutional neural networks (CNN) and heart sounds (HS) is presented for the early diagnosis of LVDD in this paper. A deep convolutional generative adversarial networks (DCGAN) model-based data augmentation (DA) method was proposed to expand a HS database of LVDD for model training. Firstly, the preprocessing of HS signals was performed using the improved wavelet denoising method. Secondly, the logistic regression based hidden semi-Markov model was utilized to segment HS signals, which were subsequently converted into spectrograms for DA using the short-time Fourier transform (STFT). Finally, the proposed method was compared with VGG-16, VGG-19, ResNet-18, ResNet-50, DenseNet-121, and AlexNet in terms of performance for LVDD diagnosis. The result shows that the proposed method has a reasonable performance with an accuracy of 0.987, a sensitivity of 0.986, and a specificity of 0.988, which proves the effectiveness of HS analysis for the early diagnosis of LVDD and demonstrates that the DCGAN-based DA method could effectively augment HS data.

[Anti-interference hemoglobin analysis system by high performance liquid chromatography].

High performance liquid chromatography (HPLC) is currently the mainstream technology for detecting hemoglobin. Glycated hemoglobin (HbA1c) is a gold indicator for diagnosing diabetes, however, the accuracy of HbA1c test is affected by thalassemia factor hemoglobin F (HbF)/hemoglobin A2 (HbA2) and variant hemoglobin during HPLC analysis. In this study, a new anti-interference hemoglobin analysis system of HPLC is proposed. In this system, the high-pressure three-gradient elution method was improved, and the particle size and sieve plate aperture in the high-pressure chromatography column and the structure of the double-plunger reciprocating series high-pressure pump were optimized. The system could diagnose both HbA1c and thalassemia factor HbF/HbA2 and variant hemoglobin, and the performance of the system was anti-interference and stable. It is expected to achieve industrialization. In this study, the HbA1c and thalassemia factor HbF/HbA2 detection performance was compared between this system and the world's first-line brand products such as Tosoh G8, Bio-Rad Ⅶ and D10 glycosylated hemoglobin analysis system. The results showed that the linear correlation between this system and the world-class system was good. The system is the first domestic hemoglobin analysis system by HPLC for screening of HbA1c and thalassemia factor HbF/HbA2 rapidly and accurately.

Study of the Correlation Between the Ratio of Diastolic to Systolic Durations and Echocardiography Measurements and Its Application to the Classification of Heart Failure Phenotypes.

BACKGROUND: This study aimed to investigate the correlation between the ratio of diastolic to systolic durations (D/S) and echocardiographic parameters of patients with chronic heart failure (CHF) and evaluate whether the D/S can be used as a supplementary biomarker for the classification of heart failure (HF) phenotypes. METHODS: In total, 122 CHF patients with a left ventricular ejection fraction (LVEF) <40%, 40%≤LVEF<50%, or ≥50% were categorized as having HF with a reduced ejection fraction (HFrEF) (N=32), HF with a mid-range ejection fraction (HFmrEF) (N=21) or HF with a preserved ejection fraction (HFpEF) (N=69), respectively. All patients underwent echocardiography for assessment of nineteen structural and functional echocardiographic parameters and digital phonocardiography for the measurement of D/S. Spearman correlation was used to analyse the associations between the D/S and echocardiographic parameters. Multivariate logistic regression analysis was performed to examine the associations between the D/S and HF phenotypes, and receiver operating characteristic (ROC) curve analysis was employed to evaluate the predictive value of the D/S in the classification of HF phenotypes. RESULTS: The D/S values of patients with HFrEF, HFmrEF and HFpEF were 1.32±0.06, 1.44±0.11 and 1.54±0.08, respectively, which were significantly different (All P<0.05). A close correlation between the D/S and LVEF was found (r=0.777, P<0.001). The multivariate analysis indicated that the D/S was an independent risk factor for CHF phenotypes (OR=4.927, 95% CI 2.532-9.587; P<0.001). The area under the ROC curve for distinguishing between HFmrEF and HFpEF using the D/S was 0.764 (95% CI 0.707-0.845; P < 0.001) and that for distinguishing between HFmrEF and HFrEF using the D/S was 0.821 (95% CI 0.755-0.882; P < 0.001). CONCLUSION: The D/S was significantly associated with LVEF, and as LVEF decreased, the D/S tended to decrease, which could also serve as a noninvasive supplementary indicator for detecting systolic and diastolic dysfunction.

Prediction of exercise sudden death in rabbit exhaustive swimming using deep neural network.

BACKGROUND AND OBJECTIVE: Moderate exercise contributes to good health. However, excessive exercise may lead to cardiac fatigue, myocardial damage and even exercise sudden death. Monitoring the heart health has important implication to prevent exercise sudden death. Diagnosis methods such as electrocardiogram, echocardiogram, blood pressure and histological analysis have shown that arrhythmia and left ventricular fibrosis are early warning symptoms of exercise sudden death. Heart sounds (HS) can reflect the changes of cardiac valve, cardiac blood flow and myocardial function. Deep learning has drawn wide attention because of its ability to recognize disease. Therefore, a deep learning method combined with HS was proposed to predict exercise sudden death in New Zealand rabbits. The objective is to develop a method to predict exercise sudden death in New Zealand rabbits. METHODS: This paper proposed a method to predict exercise sudden death in New Zealand rabbits based on convolutional neural network (CNN) and gated recurrent unit (GRU). The weight-bearing exhaustive swimming experiment was conducted to obtain the HS of exercise sudden death and surviving New Zealand rabbits (n = 11/10) at four different time points. Then, the improved Viola integral method and double threshold method were employed to segment HS signals. The segmented HS frames at different time points were taken as the input of a combined CNN and GRU called CNN-GRU network to complete the prediction of exercise sudden death. RESULTS: In order to evaluate the performance of proposed network, CNN and GRU were used for comparison. When the fourth time point segmented HS frames were taken as input, the result shows that the proposed network has better performance with an accuracy of 89.57%, a sensitivity of 89.38% and a specificity of 92.20%. In addition, the segmented HS frames at different time points were input into CNN-GRU network, and the result shows that with the progress of the experiment, the prediction accuracy of exercise sudden death in New Zealand rabbits increased from 50.98 to 89.57%. CONCLUSION: The proposed network shows good performance in classifying HS, which proves the feasibility of deep learning in exploring exercise sudden death. Further, it may have important implications in helping humans explore exercise sudden death.

Gated recurrent unit-based heart sound analysis for heart failure screening.

BACKGROUND: Heart failure (HF) is a type of cardiovascular disease caused by abnormal cardiac structure and function. Early screening of HF has important implication for treatment in a timely manner. Heart sound (HS) conveys relevant information related to HF; this study is therefore based on the analysis of HS signals. The objective is to develop an efficient tool to identify subjects of normal, HF with preserved ejection fraction and HF with reduced ejection fraction automatically. METHODS: We proposed a novel HF screening framework based on gated recurrent unit (GRU) model in this study. The logistic regression-based hidden semi-Markov model was adopted to segment HS frames. Normalized frames were taken as the input of the proposed model which can automatically learn the deep features and complete the HF screening without de-nosing and hand-crafted feature extraction. RESULTS: To evaluate the performance of proposed model, three methods are used for comparison. The results show that the GRU model gives a satisfactory performance with average accuracy of 98.82%, which is better than other comparison models. CONCLUSION: The proposed GRU model can learn features from HS directly, which means it can be independent of expert knowledge. In addition, the good performance demonstrates the effectiveness of HS analysis for HF early screening.

An Automatic Approach Using ELM Classifier for HFpEF Identification Based on Heart Sound Characteristics.

Heart failure with preserved ejection fraction (HFpEF) is a complex and heterogeneous clinical syndrome. For the purpose of assisting HFpEF diagnosis, a non-invasive method using extreme learning machine and heart sound (HS) characteristics was provided in this paper. Firstly, the improved wavelet denoising method was used for signal preprocessing. Then, the logistic regression based hidden semi-Markov model algorithm was utilized to locate the boundary of the first HS and the second HS, therefore, the ratio of diastolic to systolic duration can be calculated. Eleven features were extracted based on multifractal detrended fluctuation analysis to analyze the differences of multifractal behavior of HS between healthy people and HFpEF patients. Afterwards, the statistical analysis was implemented on the extracted HS characteristics to generate the diagnostic feature set. Finally, the extreme learning machine was applied for HFpEF identification by the comparison of performances with support vector machine. The result shows an accuracy of 96.32%, a sensitivity of 95.48% and a specificity of 97.10%, which demonstrates the effectiveness of HS for HFpEF diagnosis.

Improved bioleaching of copper and zinc from brake pad waste by low-temperature thermal pretreatment and its mechanisms.

A considerable amount of brake pad waste which is composed of phenolic resin and a variety of toxic heavy metals is produced both in China and around the world owing to the flourishing automobile industry. The safe, low cost and eco-sound bioleaching was utilized to extract the valuable metals Cu and Zn from the waste. The results showed that although bioleaching is more efficient in the extraction of Cu and Zn than the chemical counterpart, rather low bioleaching yields of 34% for Cu and 72% for Zn were obtained because of the complicated components and refractory nature of the waste. However, a low-temperature thermal pretreatment at 400 °C notably lifted the bioleaching efficiencies of Cu and Zn to 98% and nearly 100%, respectively. The thermal treatment removed the oil substances, transformed the acid insoluble Cu0 into acid soluble CuO and destroyed the chelation/complexation of the phenolic resin to loose Cu and Zn, promoting bioleaching performance of Cu and Zn. The combined processes of low-temperature thermal pretreatment and bioleaching is totally qualified for the extraction of Cu and Zn from the refractory waste.

Structural and biochemical insights into the catalytic mechanisms of two insect chitin deacetylases of the carbohydrate esterase 4 family.

Insect chitin deacetylases (CDAs) catalyze the removal of acetyl groups from chitin and modify this polymer during its synthesis and reorganization. CDAs are essential for insect survival and therefore represent promising targets for insecticide development. However, the structural and biochemical characteristics of insect CDAs have remained elusive. Here, we report the crystal structures of two insect CDAs from the silk moth Bombyx mori: BmCDA1, which may function in cuticle modification, and BmCDA8, which may act in modifying peritrophic membranes in the midgut. Both enzymes belong to the carbohydrate esterase 4 (CE4) family. Comparing their overall structures at 1.98-2.4 Å resolution with those from well-studied microbial CDAs, we found that two unique loop regions in BmCDA1 and BmCDA8 contribute to the distinct architecture of their substrate-binding clefts. These comparisons revealed that both BmCDA1 and BmCDA8 possess a much longer and wider substrate-binding cleft with a very open active site in the center than the microbial CDAs, including VcCDA from Vibrio cholerae and ArCE4A from Arthrobacter species AW19M34-1. Biochemical analyses indicated that BmCDA8 is an active enzyme that requires its substrates to occupy subsites 0, +1, and +2 for catalysis. In contrast, BmCDA1 also required accessory proteins for catalysis. To the best of our knowledge, our work is the first to unveil the structural and biochemical features of insect proteins belonging to the CE4 family.

Biochemical characterization of three midgut chitin deacetylases of the Lepidopteran insect Bombyx mori.

Peritrophic membrane (PM) is a chitin and protein-containing extracellular matrix that lines the midgut in most insect species, functioning as a barrier to exogenous toxins and pathogens. Midgut chitin deacetylases (CDAs) are chitin-modifying enzymes known to alter the mechanical property and permeability of PM. However, biochemical properties and specific roles of these enzymes remain elusive. In this study, the midgut-expressed CDAs (BmCDA6, BmCDA7 and BmCDA8) from Bombyx mori were cloned, recombinantly expressed and purified and their enzymatic activities toward PM chitin were determined. Of the three enzymes, BmCDA7 exhibited the highest activity (0.284 µmol/min/µmol), while BmCDA8 showed lower activity of 0.061 µmol/min/µmol. BmCDA6 was inactive towards PM chitin. Gene expression patterns indicated that although all three CDA genes were specifically expressed in the anterior midgut, they differed in their temporal expression patterns. BmCDA6 was expressed almost exclusively at the mid-molt stage, the stage when the PM was thick and with multiple chitin layers. Unlike BmCDA6, high expression levels of BmCDA7 and BmCDA8 were observed only at the feeding stage, the stage when the PM is thin and with fewer chitin layers. The different gene expression patterns and biochemical characteristics provide new information about the functional specialization among BmCDA6, BmCDA7 and BmCDA8 proteins.

Hierarchically stimuli-responsive nanovectors for improved tumor penetration and programed tumor therapy.

Poor drug delivery to solid tumors remains a great challenge for effective antitumor therapy. Herein, multistage stimuli-responsive nanovectors based on hollow mesoporous silica nanoparticles (HMSNs) were prepared to avoid delivery barriers for improved penetration and programmed tumor therapy. The versatile nanosystem was constructed through electrostatic complexation between the functional HMSNs loaded with gemcitabine (GEM) and the small-sized platinum prodrug-conjugated poly(amidoamine) dendrimer (PAMAM-Pt). The HMSNs were functionalized with dimethylmaleic anhydride tethered chitosan oligosaccharide to endow the particles of HMSN-CS(DMA) with charge-reversal properties. The as-prepared nanosystem had a stable structure of size ∼130 nm at pH 7.4, which is beneficial for blood circulation and tumor vessel extravasation of nanocarriers. Once it reaches the tumor site, the nanosystem can dissociate into HMSN@GEM-CS (∼120 nm) and PAMAM-Pt dendrimer nanocarriers (∼5 nm) in response to the acidic tumor microenvironment because of the acid-mediated charge-reversal, then the HMSN@GEM can play the antitumor role in surface tumor tissues. The dissociated PAMAM-Pt showed excellent performance in tumor penetration, cell uptake and intracellular trafficking due to the small size and positive charge, which was supported by the study of three-dimensional multicellular spheroids in vitro. Finally, the active cisplatin was released from the PAMAM-Pt dendrimer under the intracellular reducing environment to kill cells in deep tumor tissues. The significant tumor suppression of this system in vivo was validated in the A549 tumor xenografted mouse model. Such a stimuli-responsive nanosystem that integrates simple preparation, biocompatibility, biodegradability and programmed tumor therapy manifests great potential for clinical trials.