Machine Learning Based Non-Enhanced CT Radiomics for the Identification of Orbital Cavernous Venous Malformations: An Innovative Tool.

PURPOSE: To evaluate the capability of non-enhanced computed tomography (CT) images for distinguishing between orbital cavernous venous malformations (OCVM) and non-OCVM, and to identify the optimal model from radiomics-based machine learning (ML) algorithms. METHODS: A total of 215 cases of OCVM and 120 cases of non- OCVM were retrospectively analyzed in this study. A stratified random sample of 268 patients (80%) was used as the training set (172 OCVM and 96 non-OCVM); the remaining data were used as the testing set. Six feature selection techniques and thirteen ML models were evaluated to construct an optimal classification model. RESULTS: There were statistically significant differences between the OCVM and non-OCVM groups in the density and tumor location (P  < 0.05), whereas other indicators were comparable (age, gender, sharp, P > 0.05). Linear regression (area under the curve [AUC] = 0.9351; accuracy = 0.8657) and Stochastic Gradient Descent (AUC = 0.9448; accuracy = 0.8806) classifiers, both of which coupled with the f test and L1-based feature selection method, achieved optimal performance. The support vector machine (AUC = 0.9186; accuracy = 0.8806), Random Forest (AUC = 0.9288; accuracy = 0.8507) and eXtreme Gradient Boosting (AUC = 0.9147; accuracy = 0.8507) classifier combined with f test method showed excellent average performance among our study, respectively. CONCLUSIONS: The effect of non-enhanced CT images in OCVM not only can help ophthalmologist to find and locate lesion, but also bring great help for the qualitative diagnosis value using radiomic- based ML algorithms.

Improved Stability and Photothermal Performance of Polydopamine-Modified Fe3 O4 Nanocomposites for Highly Efficient Magnetic Resonance Imaging-Guided Photothermal Therapy.

Magnetic nanomaterials are a promising class of contrast agents for magnetic resonance imaging (MRI). However, their poor stability and low relaxivity are major challenges hindering their clinical applications. In this study, magnetic theranostic nanoagents based on polydopamine-modified Fe3 O4 (Fe3 O4 @PDA) nanocomposites are fabricated for MRI-guided photothermal therapy (PTT) cancer treatments. Their high transverse relaxivity of 337.8 mM-1 s-1 makes these Fe3 O4 @PDA nanocomposites a promising T2 -weighted MRI contrast agent for cancer diagnosis and image-guided cancer therapy. Due to the good photothermal effect of polydopamine (PDA), the tumors of 4T1 tumor-bearing mice are completely excised by PTT. Most importantly, the PDA shell also improves the stability of the Fe3 O4 @PDA nanocomposites, which contributes to their excellent, long-term performance in MRI and PTT applications. Their good stability, high T2 relaxivity, robust biocompatibility, and satisfactory treatment effect give these Fe3 O4 @PDA nanocomposites great potential for use in cancer theranostics.

Fe-doped copper sulfide nanoparticles for in vivo magnetic resonance imaging and simultaneous photothermal therapy.

Multifunctional theranostic agents are widely applied in cancer diagnosis and treatment. These agents can significantly improve therapeutic outcomes and reduce adverse effects in current cancer therapy. Here, we have designed and synthesized iron-doped copper sulfide nanoparticles with polyvinylpyrollidone (FCS@PVP NPs) for magnetic resonance imaging (MRI) guided photothermal therapy. The biocompatible FCS@PVP NPs with strong near-infrared absorption could be used as the photothermal agent and the magnetic characteristic of Fe3+ ions could be applied to T 1-weighted magnetic resonance imaging (MRI). The T 1-weighted MRI, high photothermal performance, and the biodistribution of FCS@PVP NPs were investigated in mice after intravenous administration. The data showed that there was a high accumulation of FCS@PVP NPs in the tumor sites because of the enhanced permeability and retention (EPR) effect. This result also indicated that the tumors in tumor-bearing mice were effectively suppressed after FCS@PVP NPs treatment under 808 nm laser irradiation. More importantly, FCS@PVP NPs show low cytotoxicity and few side effects because of the quick and safe elimination through the hepatobiliary/fecal route. This work provided a foundation for the clinical application of FCS@PVP NPs as a promising multifunctional theranostic agent for the MRI guided photothermal therapy of cancer.

Using amide proton transfer-weighted magnetic resonance imaging (MRI) in peritumor tissue to predict parametrial infiltration of cervical cancer: a case-control study.

Background: Parametrial infiltration (PMI) is an important indicator for staging and treatment of cervical cancer (CC). The potential of amide proton transfer-weighted (APTw) parameters of peritumor tissue in predicting PMI is still uncertain. This study aims to explore whether the APTw parameters of peritumor tissue can improve diagnostic value of diffusion-weighted imaging (DWI) in magnetic resonance imaging (MRI). Methods: Eighty-one patients with pathologic analysis-confirmed CC were enrolled in this retrospective study. All patients underwent APTw MRI and DWI. The APTw values of tumor (APTw-t), APTw values in peritumor tissues (APTw-p) and apparent diffusion coefficient (ADC) values were independently reviewed by two radiologists to map the regions of interest and measure the corresponding values. Receiver operating characteristic curves were generated to evaluate the diagnostic performance of these quantitative parameters. Results: The study patients were divided into the PMI group (n=22) and non-PMI group (n=59). The APTw-t and APTw-p values (%) of PMI group were higher than those of the non-PMI group [3.71 (interquartile range, IQR, 3.60-3.98) and 2.75 (IQR, 2.68-2.77) vs. 3.33 (IQR, 3.24-3.60) and 1.98 (IQR, 1.82-2.36); P<0.001]. The ADC values of PMI group were lower than those of non-PMI group [0.88 (IQR, 0.83-0.94) ×10-3 vs. 0.95 (IQR, 0.88-1.04)×10-3 mm2/sec; P<0.001]. The area under the curve (AUC) of APTw-t, APTw-p and ADC value for PMI diagnosis were 0.810, 0.831 and 0.806 respectively. In addition, the AUC value (0.918) of APTw-p + ADC was optimal, with a sensitivity and specificity of 91.20% and 87.20% respectively. Conclusions: APTw in peritumor tissues, combined with ADC value can be used to efficiently distinguish PMI of CC.

In vivo multimodality imaging and cancer therapy by near-infrared light-triggered trans-platinum pro-drug-conjugated upconverison nanoparticles.

Controlling anticancer drug activity and release on demand is very significant in cancer therapy. The photoactivated platinum(IV) pro-drug is stable in the dark and can be activated by UV light. In this study, we develop a multifunctional drug delivery system combining upconversion luminescence/magnetic resonance/computer tomography trimodality imaging and NIR-activated platinum pro-drug delivery. We use the core-shell structured upconversion nanoparticles to convert the absorbed NIR light into UV to activate the trans-platinum(IV) pro-drug, trans,trans,trans-[Pt(N3)2(NH3)(py)(O2CCH2CH2COOH)2]. Compared with using the UV directly, the NIR has a higher tissue penetration depth and is less harmful to health. Meanwhile, the upconversion nanoparticles can effectively deliver the platinum(IV) pro-drugs into the cells by endocytosis. The mice treated with pro-drug-conjugated nanoparticles under near-infrared (NIR) irradiation demonstrated better inhibition of tumor growth than that under direct UV irradiation. This multifunctional nanocomposite could be used as multimodality bioimaging contrast agents and transducers by converting NIR light into UV for control of drug activity in practical cancer therapy.

A new biomarker combining multimodal MRI radiomics and clinical indicators for differentiating inverted papilloma from nasal polyp invaded the olfactory nerve possibly.

Background and purpose: Inverted papilloma (IP) and nasal polyp (NP), as two benign lesions, are difficult to distinguish on MRI imaging and clinically, especially in predicting whether the olfactory nerve is damaged, which is an important aspect of treatment and prognosis. We plan to establish a new biomarker to distinguish IP and NP that may invade the olfactory nerve, and to analyze its diagnostic efficacy. Materials and methods: A total of 74 cases of IP and 55 cases of NP were collected. A total of 80% of 129 patients were used as the training set (59 IP and 44 NP); the remaining were used as the testing set. As a multimodal study (two MRI sequences and clinical indicators), preoperative MR images including T2-weighted magnetic resonance imaging (T2-WI) and contrast-enhanced T1-weighted magnetic resonance imaging (CE-T1WI) were collected. Radiomic features were extracted from MR images. Then, the least absolute shrinkage and selection operator (LASSO) regression method was used to decrease the high degree of redundancy and irrelevance. Subsequently, the radiomics model is constructed by the rad scoring formula. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the model have been calculated. Finally, the decision curve analysis (DCA) is used to evaluate the clinical practicability of the model. Results: There were significant differences in age, nasal bleeding, and hyposmia between the two lesions (p < 0.05). In total, 1,906 radiomic features were extracted from T2-WI and CE-T1WI images. After feature selection, using 12 key features to bulid model. AUC, sensitivity, specificity, and accuracy on the testing cohort of the optimal model were, respectively, 0.9121, 0.828, 0.9091, and 0.899. AUC on the testing cohort of the optimal model was 0.9121; in addition, sensitivity, specificity, and accuracy were, respectively, 0.828, 0.9091, and 0.899. Conclusion: A new biomarker combining multimodal MRI radiomics and clinical indicators can effectively distinguish between IP and NP that may invade the olfactory nerve, which can provide a valuable decision basis for individualized treatment.

Clinical application of CT-based radiomics model in differentiation between laryngeal squamous cell carcinoma and squamous cell hyperplasia.

Objective: To evaluate the clinical application of the CT-based radiomics prediction model for discriminating SCC and SCH. Methods: A total of 254 clinical samples were selected from 291 patients with larynx-occupying lesions who underwent primary surgery. All lesions were validated via histopathological examination at The Second Hospital of Jilin University between June 2004 and December 2019. All patients were randomly allocated to the training (n = 177) and validation (n = 77) cohorts. After the acquisition of CT images, manual 3D tumor segmentation was performed using the CT images of the arterial, venous, and non-contrast phases via ITK-SNAP software. Subsequently, radiomics features were extracted using A.K. software. Based on the above features, three different diagnostic models (CTN, CTA+CTV, and CTN+CTA+CTV) were constructed to classify squamous cell carcinoma (SCC) and squamous cell hyperplasia (SCH). Additionally, receiver operating characteristic (ROC) and decision curve analysis (DCA) curves were measured to evaluate the diagnostic characteristics and clinical safety of the proposed three prognostic models. Results: In the radiomic prediction Model 1 (CTN), the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of the training cohorts in differentiating SCC and SCH were 0.883, 0.785, 0.645, 1.000, 1.000, and 0.648, while in the testing cohorts, these values were 0.852, 0.792, 0.66, 1.000, 1.000, and 0.652, respectively. In the radiomic prediction Model 2 (CTA+CTV), the AUC, accuracy, sensitivity, specificity, PPV, and NPV values of the training cohorts were 0.965, 0.91, 0.916, 0.9, 0.933, and 0.875, respectively, while in the testing cohorts, the corresponding values were 0.902, 0.805, 0.851, 0.733, 0.833, and 0.759, respectively. In the radiomic prediction Model 3(CTN+CTA+CTV), the AUC, accuracy, sensitivity, specificity, PPV, and NPV values of the training cohorts were 0.985, 0.944, 0.953, 0.929, 0.953, and 0.929, while in the testing cohorts, the corresponding values were 0.965, 0.857, 0.894, 0.8, 0.875, and 0.828, respectively. Conclusion: The radiomic prediction Model 3, based on the arterial-venous-plain combined scan phase of CT, achieved promising diagnostic performance, expected to be regarded as a preoperative imaging tool in classifying SCC and SCH to guide clinicians to develop individualized treatment programs.

Advances in differential diagnosis of cerebrovascular diseases in magnetic resonance imaging: a narrative review.

Background and Objective: Cerebrovascular diseases (CVDs), particularly cerebral stroke, remain a primary cause of disability and death worldwide. Accurate diagnosis of CVDs is essential to guide therapeutic decisions and foresee the prognosis. Different CVDs have different pathological processes while they have many signs in common with some other brain diseases. Thus, differential diagnoses of strokes from other primary and secondary CVDs are especially important and challenging. Methods: This review is composed mainly based on searching PubMed articles between September, 2013 and December 26, 2022 in English. Key Content and Findings: Neuroimaging is a powerful tool for CVD diagnosis including cerebral angiography, ultrasound, computed tomography, and positron emission tomography as well as magnetic resonance imaging (MRI). MRI excels other imaging techniques by its features of non-invasive, diverse sequences and high spatiotemporal resolution. It can detect hemodynamic, structural alterations of intracranial arteries and metabolic status of their associated brain regions. In acute stroke, differential diagnosis of ischemic from hemorrhagic stroke and other intracranial vasculopathies is a common application of MRI. By providing information about the pathological characteristics of cerebral diseases exhibiting different degrees of behavioral alterations, cognitive impairment, motor dysfunction and other indications, MRI can differentiate strokes from other primary CVDs involving cerebral small vessels and identify vascular dementia from hyponatremia, brain tumors and other secondary or non-primary CVDs. Conclusions: Recent advances in MRI technology allow clinical neuroimaging to provide unique reference for differentiating many previously inconclusive CVDs. MRI technology is worthy of full exploration while breaking its limitations in clinical applications should be considered.

Aptamer-capped multifunctional mesoporous strontium hydroxyapatite nanovehicle for cancer-cell-responsive drug delivery and imaging.

A novel cancer-cells-triggered controlled-release gadolinium-doped luminescent and mesoporous strontium hydroxyapatite nanorods (designated as Gd:SrHap nanorods) system using cell-type-specific aptamers as caps has been constructed. Aptamers behave as a dual-functional molecule that acts as not only a lid but also a targeted molecular that can be used in an effective way for therapeutically special cancer cells. After incubated with cancer cells, for example, MCF-7 cells, the doxorubicin-loaded and aptamer-capped Gd:SrHap nanorods (designated as Gd:SrHap-Dox-aptamer) can be internalized into MCF-7 cells, resulting in the pore opening and drug releasing. Furthermore, the high biocompatibility and biodegradability Gd:SrHap nanorods with blue autofluorescence and paramagnetism could serve as a good contrast agent of targeting fluorescence and magnetic resonance imaging. We envision that this Gd:SrHap system could play a significant role in developing new generations of site-selective, controlled-release delivery and interactive sensory nanodevices.

Correction: Rational design of Fe3O4@C nanoparticles for simultaneous bimodal imaging and chemo-photothermal therapy in vitro and in vivo.

Correction for 'Rational design of Fe3O4@C nanoparticles for simultaneous bimodal imaging and chemo-photothermal therapy in vitro and in vivo' by Qinghe Han et al., J. Mater. Chem. B, 2018, 6, 5443-5450, DOI: 10.1039/C8TB01184B.

Ultrasmall PEI-Decorated Bi2Se3 Nanodots as a Multifunctional Theranostic Nanoplatform for in vivo CT Imaging-Guided Cancer Photothermal Therapy.

Bi-based nanomaterials, such as Bi2Se3, play an important part in biomedicine, such as photothermal therapy (PTT) and computed tomography (CT) imaging. Polyethylenimine (PEI)-modified ultrasmall Bi2Se3 nanodots were prepared using an ultrafast synthetic method at room temperature (25°C). Bi2Se3 nanodots exhibited superior CT imaging performance, and could be used as effective photothermal reagents owing to their broad absorption in the ultraviolet-visible-near infrared region. Under irradiation at 808 nm, PEI-Bi2Se3 nanodots exhibited excellent photothermal-conversion efficiency of up to 41.3%. Good biocompatibility and significant tumor-ablation capabilities were demonstrated in vitro and in vivo. These results revealed that PEI-Bi2Se3 nanodots are safe and a good nanotheranostic platform for CT imaging-guided PTT of cancer.

To Explore MR Imaging Radiomics for the Differentiation of Orbital Lymphoma and IgG4-Related Ophthalmic Disease.

Among orbital lymphoproliferative disorders, about 55% of diagnosed cancerous tumors are orbital lymphomas, and nearly 50% of benign cases are immunoglobulin G4-related ophthalmic disease (IgG4-ROD). However, due to nonspecific characteristics, the differentiation of the two diseases is challenging. In this study, conventional magnetic resonance imaging-based radiomics approaches were explored for clinical recognition of orbital lymphomas and IgG4-ROD. We investigated the value of radiomics features of axial T1- (T1WI-) and T2-weighted (T2WI), contrast-enhanced T1WI in axial (CE-T1WI) and coronal (CE-T1WI-cor) planes, and 78 patients (orbital lymphoma, 36; IgG4-ROD, 42) were retrospectively reviewed. The mass lesions were manually annotated and represented with 99 features. The performance of elastic net-based radiomics models using single or multiple modalities with or without feature selection was compared. The demographic features showed orbital lymphoma patients were significantly older than IgG4-ROD patients (p < 0.01), and most of the patients were male (72% in the orbital lymphoma group vs. 23% in the IgG4-ROD group; p = 0.03). The MR imaging findings revealed orbital lymphomas were mostly unilateral (81%, p = 0.02) and wrapped eyeballs or optic nerves frequently (78%, p = 0.02). In addition, orbital lymphomas showed isointense in T1WI (100%, p < 0.01), and IgG4-ROD was isointense (60%, p < 0.01) or hyperintense (40%, p < 0.01) in T1WI with well-defined shape (64%, p < 0.01). The experimental comparison indicated that using CE-T1WI radiomics features achieved superior results, and the features in combination with CE-T1WI-cor features and the feature preselection method could further improve the classification performance. In conclusion, this study comparatively analyzed orbital lymphoma and IgG4-ROD from demographic features, MR imaging findings, and radiomics features. It might deepen our understanding and benefit disease management.

Prediction of squamous cell carcinoma cases from squamous cell hyperplasia in throat lesions using CT radiomics model.

OBJECTIVES: To differentiate squamous cell hyperplasia (SCH) (benign) from squamous cell carcinoma (SCC) malignant) using textural features extracted from CT images and thereby, facilitate the preoperative medical diagnosis and treatment of throat cancers without the need for sample biopsies. METHODS: In total, 100 throat cancer patients were selected for this retrospective study. The cases were collected from the Second Hospital of Jilin University, Changchun, China, from June 2017 to January 2019. The patients were separated into a training and validation cohort consisting of 70 and 30 cases, respectively. The Artificial Intelligence Kit software (A.K. software) was used to extract the radiomics features from the CT images. These features were further processed using the minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) methods to obtain a subset of optimal features. The radiomics model was validated based on area-under-the-curve (AUC) values, accuracy, specificity, and sensitivity using the R-studio software. RESULTS: The diagnostic accuracy, specificity, PPV, NPV, and AUC values obtained for the training cohort was 0.91, 0.9, 0.93, 0.9, and 0.96 CT angiography (CTA), 0.93, 0.93, 0.95, 0.90, and 0.96 computed tomography normal (CTN), and 0.92, 0.87, 0.91, 0.96, and 0.96 CT venogram (CTV). These values were subsequently confirmed in the validation cohort. CONCLUSION: The radiomics-based prediction model proposed in this study successfully differentiated between SCH and SCC throat cancers using CT imaging, thereby facilitating the development of accurate preoperative diagnosis based on specific biomarkers and cancer phenotypes.

Facile Synthesis of Holmium-Based Nanoparticles as a CT and MRI Dual-Modal Imaging for Cancer Diagnosis.

The rapid development of medical imaging has boosted the abilities of modern medicine. As single modality imaging limits complex cancer diagnostics, dual-modal imaging has come into the spotlight in clinical settings. The rare earth element Holmium (Ho) has intrinsic paramagnetism and great X-ray attenuation due to its high atomic number. These features endow Ho with good potential to be a nanoprobe in combined x-ray computed tomography (CT) and T2-weighted magnetic resonance imaging (MRI). Herein, we present a facile strategy for preparing HoF3 nanoparticles (HoF3 NPs) with modification by PEG 4000. The functional PEG-HoF3 NPs have good water solubility, low cytotoxicity, and biocompatibility as a dual-modal contrast agent. Currently, there is limited systematic and intensive investigation of Ho-based nanomaterials for dual-modal imaging. Our PEG-HoF3 NPs provide a new direction to realize in vitro and vivo CT/MRI imaging, as well as validation of Ho-based nanomaterials will verify their potential for biomedical applications.

Correction: 6-Shogaol attenuates LPS-induced inflammation in BV2 microglia cells by activating PPAR-γ.

[This corrects the article DOI: 10.18632/oncotarget.16719.].

Oridonin increases anticancer effects of lentinan in HepG2 human hepatoblastoma cells.

The aim of the present study was to investigate whether oridonin is able to increase the effects of lentinan (LNT) in HepG2 human hepatoblastoma cells by MTT, flow cytometry, reverse transcription-quantitative polymerase chain reaction and western blot analysis. The in vitro results demonstrated that 20 µg/ml of oridonin was a nontoxic concentration for L02 normal liver cells and HepG2 liver cancer cells. Furthermore, treatment with 0-200 µg/ml LNT was only able to decrease the viability of HepG2 liver cancer cells. The growth inhibitory rate of the LNT-L (100 µg/ml) treatment group was 20.7% and the rate of the LNT-H (200 µg/ml) treatment group was 54.8%. Notably, the growth inhibitory rate of the oridonin + LNT-H group was 84.3%. The highest percentage of apoptotic cells was observed in the oridonin + LNT-H group (20 µg/ml oridonin and 200 µg/ml LNT). The percentage of apoptotic cells in the oridonin + LNT-H group was significantly different from the percentage of apoptotic cells in the LNT-H (26.1%) and the LNT-L (16.8%) groups. Treatment with LNT produced an increase in caspase-3, caspase-9, Bcl-2-like protein 4, p53, p21, nuclear factor κB inhibitor-α mRNA and protein expression and a decrease in B-cell lymphoma 2 and nuclear factor-κB expression in HepG2 cells compared with untreated control cells. Treatment with a combination of oridonin and LNT-H induced a further increase in expression with the biggest differences in expression observed between the oridonin + LNT-H group and control. It was observed that treatment with oridonin was able to increase the anticancer effects of LNT in HepG2 cells. Therefore, oridonin may be used to sensitize cells to LNT.

Rational design of Fe3O4@C nanoparticles for simultaneous bimodal imaging and chemo-photothermal therapy in vitro and in vivo.

We report a facile strategy to fabricate well-dispersed Fe3O4@C eccentric core-shell nanoparticles (NPs). The resulting Fe3O4@C eccentric core-shell NPs possess a high payload of doxorubicin (DOX) for use as synergetic pH/near-infrared (NIR)-sensitive drug delivery vehicles, and were applied for dual-modal magnetic resonance imaging (MRI)/photoacoustic imaging (PAI) and synergistic photothermal cancer therapy in vitro and in vivo.

6-Shogaol attenuates LPS-induced inflammation in BV2 microglia cells by activating PPAR-γ.

6-Shogaol, a pungent agent isolated from Zingiber officinale Roscoe, has been known to have anti-tumor and anti-inflammatory effects. However, the anti-inflammatory effects and biological mechanism of 6-Shogaol in LPS-activated BV2 microglia remains largely unknown. In this study, we evaluated the anti-inflammatory effects of 6-Shogaol in LPS-activated BV2 microglia. 6-Shogaol was administrated 1 h before LPS treatment. The production of inflammatory mediators were detected by ELISA. The expression of NF-κB and PPAR-γ were detected by western blot analysis. Our results revealed that 6-Shogaol inhibited LPS-induced TNF-α, IL-1ß, IL-6, and PGE2 production in a concentration dependent manner. Furthermore, 6-Shogaol inhibited LPS-induced NF-κB activation by inhibiting phosphorylation and nuclear translocation of NF-κB p65. In addition, 6-Shogaol could increase the expression of PPAR-γ. Moreover, inhibition of PPAR-γ by GW9662 could prevent the inhibition of 6-Shogaol on LPS-induced inflammatory mediator production. In conclusion, 6-Shogaol inhibits LPS-induced inflammation by activating PPAR-γ.

MnO2-Functionalized Co-P Nanocomposite: A New Theranostic Agent for pH-Triggered T1/T2 Dual-Modality Magnetic Resonance Imaging-Guided Chemo-photothermal Synergistic Therapy.

Construction of stimuli-responsive theranostic nanoagents that can increase the accuracy of imaging diagnosis and boost the therapeutic efficacy has been demonstrated for a promising approach for diagnosis and treatment of cancer. Herein, we constructed a novel theranostic agent with Co-P nanocomposites as core, mesoporous silica as shell, and manganese dioxide (MnO2) nanosheets as gatekeeper, which have been employed for pH-activatable T1/T2 dual-modality magnetic resonance imaging (MRI)-guided chemotherapeutical and photothermal combination anticancer therapy in vitro and in vivo. Co-P core-enabled theranostic platform could be applied for both photothermal therapy and T2-weighted MRI in the normal circulation owing to its strong  near-infrared absorbance and intrinsic magnetic properties. In the acidic environment of tumors, MnO2 cap could be dissolved into Mn2+ ions to not only realize pH-responsive on-demand drug release but also activate T1-weighted MRI contrast enhancement. Such T1/T2 dual-mode MR imaging provides further comprehensive details and accurate information for tumor diagnosis, and the on-demand chemo-photothermal synergetic therapy greatly improved the therapeutic effectiveness and effectively mitigated side effects. These findings demonstrate that Co-P@mSiO2@DOX-MnO2 are promising as pH-responsive theranostic agents for tumor diagnosis and treatment, and stimulate interest in exploration of novel stimuli-responsive theranostic nanoagents which posssess good potential for clinical application in the future.