BLSTM convolution and self-attention network enabled recursive and direct prediction for optical chaos.

Chaotic time series prediction has attracted much attention in recent years because of its important applications, such as security analysis for random number generators and chaos synchronization in private communications. Herein, we propose a BLSTM convolution and self-attention network model to predict the optical chaos. We validate the model's capability for direct and recursive prediction, and the model dramatically reduces the accumulation of errors. Moreover, the time duration prediction of optical chaos is increased with comparative accuracy where the predicted sequence length reaches 4 ns with normalized mean squared error (NMSE) of less than 0.01.

High-accuracy, direct aberration determination using self-attention-armed deep convolutional neural networks.

Optical microscopes have long been essential for many scientific disciplines. However, the resolution and contrast of such microscopic images are dramatically affected by aberrations. In this study, compacted with adaptive optics, we propose a machine learning technique, called the 'phase-retrieval deep convolutional neural networks (PRDCNNs)'. This aberration determination architecture is direct and exhibits high accuracy and certain generalisation ability. Notably, its performance surpasses those of similar, existing methods, with fewer fluctuations and greater robustness against noise. We anticipate future application of the proposed PRDCNNs to super-resolution microscopes.

High-generalization deep sparse pattern reconstruction: feature extraction of speckles using self-attention armed convolutional neural networks.

Light scattering is a pervasive problem in many areas. Recently, deep learning was implemented in speckle reconstruction. To better investigate the key feature extraction and generalization abilities of the networks for sparse pattern reconstruction, we develop the "one-to-all" self-attention armed convolutional neural network (SACNN). It can extract the local and global speckle properties of different types of sparse patterns, unseen glass diffusers, and untrained detection positions. We quantitatively analyzed the performance and generalization ability of the SACNN using scientific indicators and found that, compared with convolutional neural networks, the Pearson correlation coefficient, structural similarity measure, and Jaccard index for the validation datasets increased by more than 10% when SACNN was used. Moreover, SACNN is capable of reconstructing features 75 times beyond the memory effect range for a 120 grits diffuser. Our work paves the way to boost the field of view and depth of field for various sparse patterns with complex scatters, especially in deep tissue imaging.

Corrigendum: Low-Dose Total Body Irradiation Can Enhance Systemic Immune Related Response Induced by Hypo-Fractionated Radiation.

[This corrects the article DOI: 10.3389/fimmu.2019.00317.].

Pre-treatment with Bifidobacterium infantis and its specific antibodies enhance targeted radiosensitization in a murine model for lung cancer.

PURPOSE: The hypoxic microenvironments of solid tumours are complex and reduce the susceptibility of cancer cells to chemo- and radiotherapy. Conventional radiosensitisers have poor specificity, unsatisfactory therapeutic effects, and significant side effects. Anaerobic bacteria colonise and destroy hypoxic areas of the tumour and consequently enhance the effects of radiation. METHODS: In this study, we treated a Lewis lung carcinoma transplant mouse model with Bifidobacterium infantis (Bi) combined with its specific monoclonal antibody (mAb) and radiotherapy (RT) to investigate its ability to radiosensitise the tumour. The tumour metabolism and hypoxia in the tumour tissue were monitored by micro-18F-FDG and 18F-FMISO PET/CT imaging. Immunohistochemistry was used to detect phosphorylated histone (γ-H2AX), proliferation (Ki-67), platelet endothelial cell adhesion molecules (CD31), tumour necrosis factor-α (TNF-α), hypoxia-inducible factor-1α (HIF-1α), and glucose transporter 1 (Glut-1) levels. RESULTS: Tumour growth was slowed and survival time was markedly prolonged in mice subjected to the combination of B. infantis, specific antibody, and radiotherapy. Levels of HIF-1α, Glut-1, Ki-67, and CD31 expression, as well as uptake of FDG and FMISO, were the lowest in the combination-treated mice. In contrast, γ-H2AX and TNF-α expression levels were elevated and hypoxia in tumour tissue was reduced compared with controls. CONCLUSION: In conclusion, our data indicated that the curative effect of radiotherapy for lung cancer was enhanced by pre-treating mice with a combination of B. infantis and its specific monoclonal antibody.

Enhanced Anti-Cancer Effect of Folate-Conjugated Olaparib Nanoparticles Combined with Radiotherapy in Cervical Carcinoma.

BACKGROUND: Radiotherapy (RT), one of the main treatments for cervical cancer, has tremendous potential for improvement in the efficacy. Poly (ADP-ribose) polymerase (PARP) is a key enzyme in the repair of DNA strand breaks (DSB). Olaparib (Ola) is a PARP inhibitor that is involved in preventing the release of PARP from RT-induced damaged DNA to potentiate the effect of RT. Although the basic mechanism of Ola's radiosensitization is well known, the radiosensitization mechanism of its nanomedicine is still unclear. In addition, the lack of tumor tissue targeting is a major obstacle for the clinical success of Ola. MATERIALS AND METHODS: In this study, we developed folate-conjugated active targeting olaparib nanoparticles (ATO) and investigated the anti-tumor effect of ATO combined with radiotherapy (RT) in nude mice using cervical cancer xenograft models. We used folate (FA)-conjugated poly (ε-caprolactone)-poly (ethyleneglycol)-poly (e-caprolactone) (PCEC) copolymer to prepare ATO via emulsification/solvent diffusion. Further, we evaluated ATO particle size, potential, encapsulation efficiency, and in vitro release characteristics, and evaluated the shape of ATO via transmission electron microscopy (TEM). We then performed MTT and cell uptake assays to detect cytotoxicity and targeting uptake in vitro. We investigated the anti-tumor properties of ATO in vivo by apoptosis test, 18 F-FDG PET/CT, and immunohistochemical analysis. Finally, the xenografted tumor in nude mice was subjected to RT and/or ATO treatment. RESULTS: The results confirmed that ATO in combination with RT significantly inhibited tumor growth and prolonged survival time of tumor-bearing mice. This may be related to the inhibition of tumor proliferation and DNA damage repair and induction of cell apoptosis in vivo. CONCLUSION: The ATO developed in this study may represent a novel formulation for olaparib delivery and have promising potential for treating tumors with an over-expression of folate receptors.

Low-Dose Total Body Irradiation Can Enhance Systemic Immune Related Response Induced by Hypo-Fractionated Radiation.

A systemic immune related response (SIME) of radiotherapy has been occasionally observed on metastatic tumors, but the clinical outcomes remain poor. Novel treatment approaches are therefore needed to improve SIME ratio. We used a combination of hypo-fractionated radiation therapy (H-RT) with low-dose total body irradiation (L-TBI) in a syngeneic mouse model of breast and colon carcinoma. The combination therapy of H-RT and L-TBI potentially enhanced SIME by infiltration of CD8+ T cell and altering the immunosuppressive microenvironment in non-irradiated subcutaneous tumor lesions. The frequency of IFN-γ, as a tumor-specific CD8+ T cells producing, significantly inhibited the secondary tumor growth of breast and colon. Our findings suggest that L-TBI could serve as a potential therapeutic agent for metastatic breast and colon cancer and, together with H-RT, their therapeutic potential is enhanced significantly.

Olaparib nanoparticles potentiated radiosensitization effects on lung cancer.

BACKGROUND: Poly (ADP-ribose) polymerase (PARP) is a key enzyme in the repair process of DNA strand breaks (DSBs). Olaparib (Ola) is a PARP inhibitor that is involved in arresting PARP release from radiotherapy (RT)-induced damaged DNA to potentiate the effect of RT. Although the underlying mechanisms for the radiosensitization effects of Ola are well understood in vitro, the radiosensitization effects in vivo are still unclear. Moreover, poor water solubility and severe toxicity are two major impediments for the clinical success of Ola. MATERIALS AND METHODS: Here, we developed olaparib nanoparticles (Ola-NPs) and investigated their radiosensitization mechanisms and toxicity using human non-small-cell lung cancer xenograft models in mice. RESULTS: The prepared Ola-NPs showed a mean size of 31.96±1.54 nm and a lower polydispersity index of about 0.126±0.014. In addition, the sensitization enhancement ratio of Ola-NPs (3.81) was much higher than that of free Ola (1.66). The combination of Ola-NPs and RT (Ola-NPs + RT) significantly inhibited tumor growth and prolonged survival in mice. The mechanism of enhanced antitumor efficacy might be related to the inhibition of DSB repair and the promotion of cell apoptosis in vivo. No additional toxicity caused by Ola-NPs was observed. CONCLUSION: This study demonstrated the principle of using Ola-NPs as a potent radiosensitizer to improve the therapeutic effect of RT relative to free Ola (P<0.05 in all cases).