Current trends of artificial intelligence in cancer imaging

In this editorial,we discussed the current research status of artificial intelligence(AI)in Oncology,reviewing the basics of machine learning(ML)and deep learning(DL)techniques and their emerging applications on clinical and imaging cancer workflow.The growing amounts of available“big data”coupled to the increasing computational power have enabled the development of computerbased systems capable to perform advanced tasks in many areas of clinical care,especially in medical imaging.ML is a branch of data science that allows the creation of computer algorithms that can learn and make predictions without prior instructions.DL is a subgroup of artificial neural network algorithms configurated to automatically extract features and perform high-level tasks;convolutional neural networks are the most common DL models used in medical image analysis.AI methods have been proposed in many areas of oncology granting promising results in radiology-based clinical applications.In detail,we explored the emerging applications of AI in oncological risk assessment,lesion detection,characterization,staging,and therapy response.Critical issues such as the lack of reproducibility and generalizability need to be addressed to fully implement AI systems in clinical practice.Nevertheless,AI impact on cancer imaging has been driving the shift of oncology towards a precision diagnostics and personalized cancer treatment.

Simultaneous Morphologies and Luminescence Control of NaYF_(4)∶Yb/Er Nanophosphors by Surfactants for Cancer Cell Imaging

Hydrophilic rare-earth up-conversion nanophosphors(UCNPs)with small sizes and a strong up-conversion luminescence have attracted much interest.Herein the simultaneous control of morphologies and the up-conversion luminescence intensities was reported for NaYF_(4)∶Yb/Er nanophosphors by a facile hydrothermal procedure with different surfactants.With the change of the surfactants from polyvinylpyrrolidone(PVP)to sodium citrate(CIT),edetate disodium(EDTA)or sodium dodecyl benzenesulfonate(SDBS),the morphology of NaYF_(4)∶Yb/Er nanophosphors transformed from nanoparticles with a diameter of about 70.0 nm to hexagonal nanoblocks with a thickness of about 125.0 nm and a length of about 240.0 nm,nanorods with a diameter of about 700.0 nm and a length of about 2.6μm,or nanowires with a diameter of 250.0 nm and a length of about 3.2μm.Simultaneously,their up-conversion luminescence intensity went down gradually under laser irradiation at a wavelength of 980 nm due to the increase of photobleaching.PVP-capped NaYF_(4)∶Yb/Er nanoparticles exhibited the smallest size and the strongest up-conversion luminescence intensity.Biological experiment results revealed that NaYF_(4)∶Yb/Er nanophosphors exhibited a high biocompatibility and could be used as biological labels with a perfect signal-to-noise ratio for cancer cell imaging.

A Swin Transformer and Residualnetwork Combined Model for Breast Cancer Disease Multi-Classification Using Histopathological Images

Breast cancer has become a killer of women's health nowadays.In order to exploit the potential representational capabilities of the models more comprehensively,we propose a multi-model fusion strategy.Specifically,we combine two differently structured deep learning models,ResNet101 and Swin Transformer(SwinT),with the addition of the Convolutional Block Attention Module(CBAM)attention mechanism,which makes full use of SwinT's global context information modeling ability and ResNet101's local feature extraction ability,and additionally the cross entropy loss function is replaced by the focus loss function to solve the problem of unbalanced allocation of breast cancer data sets.The multi-classification recognition accuracies of the proposed fusion model under 40X,100X,200X and 400X BreakHis datasets are 97.50%,96.60%,96.30 and 96.10%,respectively.Compared with a single SwinT model and ResNet 101 model,the fusion model has higher accuracy and better generalization ability,which provides a more effective method for screening,diagnosis and pathological classification of female breast cancer.

Imaging in translational cancer research

This review is aimed at presenting some of the recent developments in translational cancer imaging research,with a focus on novel,recently established,or soon to be established cross-sectional imaging techniques for computed tomography(CT),magnetic resonance imaging(MRI),and positron-emission tomography(PET)imaging,including computational investigations based on machine-learning techniques.

Alkaline Phosphatase-Initiated Sensitive Responsiveness of Activatable Probes to Hydrogen Sulfide for Accurate Cancer Imaging and Differentiation

Optical imaging with molecular probes is becoming an essential tool for advancing biological research and clinical applications.However,most currently available molecular probes show limited sensitivity,specificity,and accuracy due to their typical responsiveness to a single stimulation for biomarker-based imaging.In this study,we develop a novel molecular probe that shows alkaline phosphatase(ALP)-instructed sensitive responsiveness to hydrogen sulfide for accurate cancer imaging and differentiation.This designed probe in an aggregated state under physiological conditions bears negatively charged surfaces,giving poor optical response to H_(2)S.The ALP-mediated dephosphorylation reaction yields an assembled product with a positively charged surface,affording significantly aggregation-enhanced responsiveness to H_(2)S with light-up NIR fluorescence at 755 nm.Such charge reversal of assembled probe from negative to positive plays a vital role in allowing precise visualization and differentiation of cancers based on differences in ALP upregulation and H_(2)S content.We envisage that our charge-reversal strategy for multiple-parameter-activated molecule probes will facilitate boosting the specificity and precision of cancer imaging.

Tumor microenvironment-responsive contrast agents for specific cancer imaging:a narrative review

Molecular imaging is of great significance for early diagnosis and timely treatment of cancer and disease,as well as basic medical and biological research.As personalized cancer treatment has become increasingly popular,the demand for more advanced imaging technologies has also significantly increased.Taking advantage of differences between the tumor microenvironment and normal tissue cells,tumor microenvironment-responsive or"turn-on"contrast agents have a higher signal-to-noise ratio and lower background interference compared with"turn-off"probes,which can remarkably improve the performance of tumor diagnostics.Thus,tumor microenvironment-responsive contrast agents can not only detect changes in the tumor microenvironment,but also have important significance for tumor diagnosis,prediction of invasion potential,evaluation of treatment effectiveness,planning of therapeutic regimens,and tumor prognosis.Herein,this review focuses on recent research progress of tumor microenvironment-responsive intelligent probes,and highlights future research directions of tumor microenvironment-responsive contrast agents for precision diagnostics.

Biomarker-targeted fluorescent probes for breast cancer imaging

Breast cancer has become a common tumor worldwide which seriously endangers people＇s health. Earlydiagnosis and treatment are particularly urgent in order to reduce the onset risk, mortality, and prolongthe five-year survival rate. Therefore, we need a kind of diagnosis and treatment technology with highspecificity, sensitivity and selectivity. In recent years, because of its unique properties in biologicalapplications, fluorescence imaging has become an attractive research subject. Fluorescence imagingoffers innovative ideas of targetable recognition of breast cancer cells, breast cancer imaging in vivoanimal models, anticancer drugs delivery for guiding the mammary surgery via a noninvasive way withhigh sensitively and specifically. In this review, we summarized the recent advances of fluorescent probesfor breast cancer imaging, which were classified according to different biomarkers the probes recognized.Moreover, we discussed the strengths, built-in problems as well as the challenges about the fluorescentprobe as a unique potential method for the better application in breast cancer diagnosis and treatment.~ 2018 Chinese Chemical Society and Institute of Materia Medica, Chinese Academy of Medical Sciences.

Value of MRI diffusion weighted imaging in localization of prostate cancer with whole-mount step section pathology

Objective To evaluate the value of MRI diffusion weighted imaging in localization of prostate cancer with whole-mount step section pathology. Methods We treated 36 patients using laparoscopic radical prostatectomy from Oct. 2009 to Jun. 2010. Patients who did not have an MRL /DWI examination or a surgical history of pros-

Biomimetic manganese-based theranostic nanoplatform for cancer multimodal imaging and twofold immunotherapy

The limited clinical response and serious side effect have been challenging in cancer immunotherapy resulting from immunosuppressive tumor microenvironment(TME)and inferior drug targeting.Herein,an active targeting TME nanoplatform capable of revising the immunosuppressive TME microenvironment is designed.Briefly,gold nanorods(GNRs)are covered with silica dioxide(SiO_(2))and then coated manganese dioxide(MnO_(2))to obtain GNRs@SiO_(2)@MnO_(2)(GSM).Myeloid-derived suppressor cells(MDSCs)membrane is further camouflaged on the surface of GSM to obtain GNRs@SiO_(2)@MnO_(2)@MDSCs(GSMM).In this system,GSMM inherits active targeting TME capacity of MDSCs.The localized surface plasmon resonance of GNRs is developed in near-infraredⅡwindow by MnO_(2)layer coating,realizing NIR-Ⅱwindow photothermal imaging and photoacoustic imaging of GSMM.Based on the release of Mn^(2+)in acidic TME,GSMM can be also used for magnetic resonance imaging.In cancer cells,Mn^(2+)catalyzes H_(2)O_(2)into·OH for(chemodynamic therapy)CDT leading to activate cGAS-STING,but also directly acts on STING inducing secretion of typeⅠinterferons,pro-inflammatory cytokines and chemokines.Additionally,photothermal therapy and CDT-mediated immunogenic cell death of tumor cells can further enhance anti-tumor immunity via exposure of CRT,HMGB1 and ATP.In summary,our nanoplatform realizes multimodal cancer imaging and dual immunotherapy.

Aptamer-Anchored Rubrene-Loaded Organic Nanoprobes for Cancer Cell Targeting and Imaging

Fluorescence imaging has become an indispensable technique in cancer research because it can reveal informative molecular,cellular,anatomical,and func-tional insights.Development of advanced fluores-cent probes with superior sensitivity and biological selectivity for fluorescence imaging is thus impera-tive.To move forward in this direction,we developed an easy self-assembly method for fabricating apta-mer-anchored rubrene-loaded organic fluorescent nanoprobes.The aptamer-modified organic nanop-robes integrated the best features of the organic light-emitting materials and the aptamers,thus endowing them with excellent cell-targeting capabil-ity,high stability,and good biocompatibility.By using this general method,a variety of biocompatible and highly bright organic fluorescent nanoprobes based on novel organic light-emitting materials with specific recognition could be easily constructed for real-time biosensing and long-term biomedical imaging.

Gold nanoprisms as a hybrid in vivo cancer theranostic platform for in situ photoacoustic imaging, angiography, and localized hyperthermia

The development of high-resolution nanosized photoacoustic contrast agents is an exciting yet challenging technological advance. Herein, antibody （breast cancer-associated antigen I （Brcaal） monoclonal antibody）- and peptide （RGD）- functionalized gold nanoprisms （AuNprs） were used as a combinatorial methodology for in situ photoacoustic imaging, angiography, and localized hyperthermia using orthotopic and subcutaneous murine gastric carcinoma models. RGD-conjugated PEGylated AuNprs are available for tumor angiography, and Brcaal monodonal antibody-conjugated PEGylated AuNprs are used for targeting and for in situ imaging of gastric carcinoma in orthotopic tumor models. In situ photoacoustic imaging allowed for anatomical and functional imaging at the tumor site. In vivo tumor angiography imaging showed enhancement of the photoacoustic signal in a time-dependent manner. Furthermore, photoacoustic imaging demonstrated that tumor vessels were clearly damaged after localized hyperthermia. This is the first proof-of-concept using two AuNprs probes as highly sensitive contrasts and therapeutic agents for in situ tumor detection and inhibition. These smart antibody/peptide AuNprs can be used as an efficient nanotheranostic platform for in vivo tumor detection with high sensitivity, as well as for tumor targeting therapy which, with a single-dose injection, results in tumor size reduction and increases mice survival after localized hyperthermia treatment.

A GSH-responsive PET-based fluorescent probe for cancer cells imaging

An efficient PET-based probe,in which the ferrocene quencher and the naphthalimide fluorophore are linked by a disulfide bond,has been developed.This probe can be activated by GSH with fluorescence a turn-on response for blocking the PET process.In addition,it was successfully applied for distinguishing cancer cells from normal cells。

Multifunctional lymph-targeted platform based Mn@mSiO2 nanocomposites： Combining PFOB dual-mode imaging and DOX for cancer diagnose treatment on for and

A universal platform with M_n doping and hyaluronic acid （HA） modification, based on mesoporous silica （mSiO2）, was designed and used as a basic multifunctional material with magnetic resonance （MR） imaging. Furthermore, we added flexible functions through the addition of functional molecules. Specially, two typical compounds, hydrophobic perfluorooctyl bromide （PFOB） and hydrophilic doxorubicin （DOX）, were loaded into the channels to obtain PFOB@Mn@mSiO2@HA （PMMH） or DOX@Mn@mSiO2@HA （DMMH） or imaging and therapy, respectively. The were highly targeted to the lymph system in nanoparticles for dual-mode imaging PMMH and DMMH nanoparticles vitro and in vivo. MR and ultrasound imaging of PMMH nanoparticles were performed in the lymph system, while MR imaging and chemotherapy of DMMH nanoparticles was used to detect cancer. These results showed that both PMMH and DMMH nanoparficles can be designed with high lymph targeting efficiency. PMMH nanoparticles are a dual-mode contrast agent for both ultrasound and MR imaging for the lymph system and DMMH nanoparticles are powerful agents for the combined diagnosis and therapy of cancer in vivo.

A pH-Activatable Fluorescent Aptamer Probe for Imaging of Target Cancer Cells

Early cancer diagnosis in molecular level shows great promise in relevant prevention and clinical treatment. Herein, we developed a novel method to detect and evaluate biomarkers on cancer cell surface. Based on the excellent selectivity of AS1411 aptamer to targeted nucleolin-overexpressed cells, we used a fluorescent probe with a pH-sensitive function to label the AS1411 aptamer modified with azide by click-reaction. The spectral characteristics of fluorophore naphthalimide has a good pH dependence. By this way, nucleolin-overexpressed cell could be discriminated from normal cell. Further, this strategy could also discriminate the breast cancer tissue from the adjacent benign tissue in formalin-fixed and parrffin-embedded（FFPE） tissue specimens. It is considered that our method has the potential to be applied in medical detection.

Classification of Cancer Cells Using Neural Networks in Combination with Expert Experience

This paper briefly reviews some neural networks and discusses their drawbacks, the main defaults is that these neural networks do not use expert experience (or knowledge) and have the human flexibility, therefore, a new better method for the combination of neural networks with expert experience (or knowledge) was proposed. Probabilistic neural networks (PNNs) classification of cancer cell image is described. This networks is simpler and faster than back propagating neural networks (BPNNs) during training and learning. Neural networks combined with expert experience is presented in order to improve the classification accuracy of the networks and the simulation experiments were performed and the results have shown that the method presented is very efficient and feasible.

Surface-enhanced Raman nanoparticles for tumor theranostics applications

Raman spectroscopy, amplified by surface-enhanced Raman scattering(SERS) nanoparticles,can provide an in vivo imaging modality due to its high molecular specificity, high sensitivity, and negligible autofluorescence. The basis, composition, and methodologies developed for SERS nanoparticles are herein described. The research hotspots that are the focus in this paper are tumor imaging-guided theranostics and biosensing. The next breakthrough may be the development of biocompatible SERS nanoparticles and spectroscopic devices for clinical applications.