Enzymatic deamination of the epigenetic nucleoside N6-methyladenosine regulates gene expression.

N6-methyladenosine (m6A) modification is the most extensively studied epigenetic modification due to its crucial role in regulating an array of biological processes. Herein, Bsu06560, formerly annotated as an adenine deaminase derived from Bacillus subtilis 168, was recognized as the first enzyme capable of metabolizing the epigenetic nucleoside N6-methyladenosine. A model of Bsu06560 was constructed, and several critical residues were putatively identified via mutational screening. Two mutants, F91L and Q150W, provided a superiorly enhanced conversion ratio of adenosine and N6-methyladenosine. The CRISPR-Cas9 system generated Bsu06560-knockout, F91L, and Q150W mutations from the B. subtilis 168 genome. Transcriptional profiling revealed a higher global gene expression level in BS-F91L and BS-Q150W strains with enhanced N6-methyladenosine deaminase activity. The differentially expressed genes were categorized using GO, COG, KEGG and verified through RT-qPCR. This study assessed the crucial roles of Bsu06560 in regulating adenosine and N6-methyladenosine metabolism, which influence a myriad of biological processes. This is the first systematic research to identify and functionally annotate an enzyme capable of metabolizing N6-methyladenosine and highlight its significant roles in regulation of bacterial metabolism. Besides, this study provides a novel method for controlling gene expression through the mutations of critical residues.

Facile cell patterning induced by combined surface topography and chemistry on polydopamine-defined nanosubstrates.

Cell patterning holds significant implications for cell-based analysis and high-throughput screening. The challenge and key factor for formation of cell patterns is to precisely modulate the interaction between cells and substrate surfaces. Many nanosubstrates have been developed to control cell adhesion and patterning, however, requirements of complicated fabrication procedures, harsh reaction conditions, and delicate manipulation are not routinely feasible. Here, we developed a hierarchical polydimethylsiloxane nanosubstrate (HPNS) coated with mussel-inspired polydopamine (PDA) micropatterns for effective cell patterning, depending on both surface topography and chemistry. HPNSs obtained by facile template-assisted replication brought enhanced topographic interaction between cells and substrates, but they were innately hydrophobic and cell-repellent. The hydrophobic nanosubstrates were converted to be hydrophilic after PDA coatings formed via spontaneous self-polymerization, which greatly facilitated cell adhesion. As such, without resorting to any external forces or physical constraints, cells selectively adhered and spread on spatially defined PDA regions with high efficiency, and well-defined cell microarrays could be formed within 20 min. Therefore, this easy-to-fabricate nanosubstrate with no complex chemical modification will afford a facile yet effective platform for rapid cell patterning.

Rox-DNA Functionalized Silicon Nanodots for Ratiometric Detection of Mercury Ions in Live Cells.

A ratiometric fluorescent sensor for mercury ions (Hg2+) has been constructed via covalent functionalization of silicon nanodot (SiND) with Hg2+-specific 6-carboxy-X-rhodamine (Rox)-tagged DNA. For the Rox-DNA functionalized SiND, the red fluorescence of Rox can be quenched by the blue-emitting SiND in the presence of Hg2+ due to structural change in DNA, which serves as the response signal. Meawhile, the fluorescence of SiND is insensitive to Hg2+ and acts as the reference signal. The wavelength difference in the optimal emission peak is as large as 190 nm between SiND (422 nm) and Rox (612 nm), which can efficaciously exclude the interference of the two emission peaks, and facilitates dual-color visualization of Hg2+ ions. The biofunctionalization of SiND improves the acid-base stability of SiND significantly, which is favorable for its application in the intracellular environment. Accordingly, a sensitive, simple, precise and rapid method for tracing Hg2+ was proposed. The limit of detection and precision of this method for Hg2+ was 9.2 nM and 8.8% (50 nM, n = 7), respectively. The increase of Hg2+ concentration in the range of 10-1500 nM was in accordance with linearly increase of the I422/ I612 ratio. As for practical application, the recoveries in spiked human urine and serum samples were in the range of 81-107%. Moreover, this fluorescent nanosensor was utilized to the ratiometric detection of Hg2+ in HeLa cells.

Whole-lesion Apparent Diffusion Coefficient First- and Second-Order Texture Features for the Characterization of Rectal Cancer Pathological Factors.

OBJECTIVE: The objective of this study was to explore the value of whole-volume apparent diffusion coefficient (ADC) features in characterizing pathologic features of rectal cancer. METHODS: A total of 50 patients who were diagnosed with rectal cancer via biopsy underwent 3-T pretreatment diffusion-weighted imaging. Apparent diffusion coefficient features, including mean, 10th-90th percentile, Entropy and Entropy(H), derived from whole-lesion volumes were compared between pathologic T1-2 and T3 stages, perineural invasion (PNI) present and absent, lymphangiovascular invasion present and absent, and pathological N0 and N+ stage groups. RESULTS: Entropy and Entropy(H) were significantly lower in rectal cancers at T1-2 stages than T3. The 90th percentile of rectal cancers with PNI was significantly lower than that of those without PNI. All P < 0.05. CONCLUSIONS: Whole-lesion ADC Entropy and Entropy(H) have potential in evaluating different T stages, and 90th percentile can be helpful for determining PNI presence of rectal cancers.

5-Formyluracil as a Multifunctional Building Block in Biosensor Designs.

In organisms 5-formyluracil (5fU), which is known as a vital natural nucleobase, is widely present. Despite the recent development of sensor designs for organic fluorescent molecules for selective targeting applications, biocompatible and easily operated probe designs that are based on natural nucleobase modifications have rarely been reported. Here, we introduce the idea of 5fU as a multifunctional building block to facilitate the design and synthetic development of biosensors. The azide group was derived from the sugar of a nucleoside, which can be further used in the selective binding of cells or organelles through click chemistry with alkynyl-modified targeting groups. The aldehyde group of 5fU can react with different chemicals to generate environmentally sensitive nucleobases that have obvious characteristics, which precious reactants cannot achieve for selective fluorogenic switch-on detection of a specific target. We first synthesized 5fU analogues that had aggregation-induced emission properties, and then we used triphenylphosphonium as a mitochondria-targeting group to selectively image mitochondria in cancer cells and mouse embryonic stem cells. Additionally, the reagents exhibit a high selectivity for reaction with 5fU, which means that the method can also be used for the detection of 5fU. Combining the two characteristics, the idea of 5fU as a multifunctional building block in biosensor designs may potentially be applicable in 5fU site-specific microenvironment detection in future research.

Whole-Lesion Histogram Analysis of Apparent Diffusion Coefficient for the Assessment of Cervical Cancer.

OBJECTIVE: The aim of this study was to explore the application of whole-lesion histogram analysis of apparent diffusion coefficient (ADC) values of cervical cancer. METHODS: A total of 54 women (mean age, 53 years) with cervical cancers underwent 3-T diffusion-weighted imaging with b values of 0 and 800 s/mm prospectively. Whole-lesion histogram analysis of ADC values was performed. Paired sample t test was used to compare differences in ADC histogram parameters between cervical cancers and normal cervical tissues. Receiver operating characteristic curves were constructed to identify the optimal threshold of each parameter. RESULTS: All histogram parameters in this study including ADCmean, ADCmin, ADC10%-ADC90%, mode, skewness, and kurtosis of cervical cancers were significantly lower than those of normal cervical tissues (all P < 0.0001). ADC90% had the largest area under receiver operating characteristic curve of 0.996. CONCLUSIONS: Whole-lesion histogram analysis of ADC maps is useful in the assessment of cervical cancer.

A review on 4D cone-beam CT (4D-CBCT) in radiation therapy: Technical advances and clinical applications.

Cone-beam CT (CBCT) is the most commonly used onboard imaging technique for target localization in radiation therapy. Conventional 3D CBCT acquires x-ray cone-beam projections at multiple angles around the patient to reconstruct 3D images of the patient in the treatment room. However, despite its wide usage, 3D CBCT is limited in imaging disease sites affected by respiratory motions or other dynamic changes within the body, as it lacks time-resolved information. To overcome this limitation, 4D-CBCT was developed to incorporate a time dimension in the imaging to account for the patient's motion during the acquisitions. For example, respiration-correlated 4D-CBCT divides the breathing cycles into different phase bins and reconstructs 3D images for each phase bin, ultimately generating a complete set of 4D images. 4D-CBCT is valuable for localizing tumors in the thoracic and abdominal regions where the localization accuracy is affected by respiratory motions. This is especially important for hypofractionated stereotactic body radiation therapy (SBRT), which delivers much higher fractional doses in fewer fractions than conventional fractionated treatments. Nonetheless, 4D-CBCT does face certain limitations, including long scanning times, high imaging doses, and compromised image quality due to the necessity of acquiring sufficient x-ray projections for each respiratory phase. In order to address these challenges, numerous methods have been developed to achieve fast, low-dose, and high-quality 4D-CBCT. This paper aims to review the technical developments surrounding 4D-CBCT comprehensively. It will explore conventional algorithms and recent deep learning-based approaches, delving into their capabilities and limitations. Additionally, the paper will discuss the potential clinical applications of 4D-CBCT and outline a future roadmap, highlighting areas for further research and development. Through this exploration, the readers will better understand 4D-CBCT's capabilities and potential to enhance radiation therapy.

Hybrid-supervised deep learning for domain transfer 3D protoacoustic image reconstruction.

Objective. Protoacoustic imaging showed great promise in providing real-time 3D dose verification of proton therapy. However, the limited acquisition angle in protoacoustic imaging induces severe artifacts, which impairs its accuracy for dose verification. In this study, we developed a hybrid-supervised deep learning method for protoacoustic imaging to address the limited view issue.Approach. We proposed a Recon-Enhance two-stage deep learning method. In the Recon-stage, a transformer-based network was developed to reconstruct initial pressure maps from raw acoustic signals. The network is trained in a hybrid-supervised approach, where it is first trained using supervision by the iteratively reconstructed pressure map and then fine-tuned using transfer learning and self-supervision based on the data fidelity constraint. In the enhance-stage, a 3D U-net is applied to further enhance the image quality with supervision from the ground truth pressure map. The final protoacoustic images are then converted to dose for proton verification.Main results. The results evaluated on a dataset of 126 prostate cancer patients achieved an average root mean squared errors (RMSE) of 0.0292, and an average structural similarity index measure (SSIM) of 0.9618, out-performing related start-of-the-art methods. Qualitative results also demonstrated that our approach addressed the limit-view issue with more details reconstructed. Dose verification achieved an average RMSE of 0.018, and an average SSIM of 0.9891. Gamma index evaluation demonstrated a high agreement (94.7% and 95.7% for 1%/3 mm and 1%/5 mm) between the predicted and the ground truth dose maps. Notably, the processing time was reduced to 6 s, demonstrating its feasibility for online 3D dose verification for prostate proton therapy.Significance. Our study achieved start-of-the-art performance in the challenging task of direct reconstruction from radiofrequency signals, demonstrating the great promise of PA imaging as a highly efficient and accurate tool forinvivo3D proton dose verification to minimize the range uncertainties of proton therapy to improve its precision and outcomes.

Patient-specific deep learning for 3D protoacoustic image reconstruction and dose verification in proton therapy.

BACKGROUND: Protoacoustic (PA) imaging has the potential to provide real-time 3D dose verification of proton therapy. However, PA images are susceptible to severe distortion due to limited angle acquisition. Our previous studies showed the potential of using deep learning to enhance PA images. As the model was trained using a limited number of patients' data, its efficacy was limited when applied to individual patients. PURPOSE: In this study, we developed a patient-specific deep learning method for protoacoustic imaging to improve the reconstruction quality of protoacoustic imaging and the accuracy of dose verification for individual patients. METHODS: Our method consists of two stages: in the first stage, a group model is trained from a diverse training set containing all patients, where a novel deep learning network is employed to directly reconstruct the initial pressure maps from the radiofrequency (RF) signals; in the second stage, we apply transfer learning on the pre-trained group model using patient-specific dataset derived from a novel data augmentation method to tune it into a patient-specific model. Raw PA signals were simulated based on computed tomography (CT) images and the pressure map derived from the planned dose. The reconstructed PA images were evaluated against the ground truth by using the root mean squared errors (RMSE), structural similarity index measure (SSIM) and gamma index on 10 specific prostate cancer patients. The significance level was evaluated by t-test with the p-value threshold of 0.05 compared with the results from the group model. RESULTS: The patient-specific model achieved an average RMSE of 0.014 ( p < 0.05 ${{{p}}}<{0.05}$ ), and an average SSIM of 0.981 ( p < 0.05 ${{{p}}}<{0.05}$ ), out-performing the group model. Qualitative results also demonstrated that our patient-specific approach acquired better imaging quality with more details reconstructed when comparing with the group model. Dose verification achieved an average RMSE of 0.011 ( p < 0.05 ${{{p}}}<{0.05}$ ), and an average SSIM of 0.995 ( p < 0.05 ${{{p}}}<{0.05}$ ). Gamma index evaluation demonstrated a high agreement (97.4% [ p < 0.05 ${{{p}}}<{0.05}$ ] and 97.9% [ p < 0.05 ${{{p}}}<{0.05}$ ] for 1%/3  and 1%/5 mm) between the predicted and the ground truth dose maps. Our approach approximately took 6 s to reconstruct PA images for each patient, demonstrating its feasibility for online 3D dose verification for prostate proton therapy. CONCLUSIONS: Our method demonstrated the feasibility of achieving 3D high-precision PA-based dose verification using patient-specific deep-learning approaches, which can potentially be used to guide the treatment to mitigate the impact of range uncertainty and improve the precision. Further studies are needed to validate the clinical impact of the technique.

Acoustic-holography-patterned primary hepatocytes possess liver functions.

Acoustic holography (AH), a promising approach for cell patterning, emerges as a powerful tool for constructing novel invitro 3D models that mimic organs and cancers features. However, understanding changes in cell function post-AH remains limited. Furthermore, replicating complex physiological and pathological processes solely with cell lines proves challenging. Here, we employed acoustical holographic lattice to assemble primary hepatocytes directly isolated from mice into a cell cluster matrix to construct a liver-shaped tissue sample. For the first time, we evaluated the liver functions of AH-patterned primary hepatocytes. The patterned model exhibited large numbers of self-assembled spheroids and superior multifarious core hepatocyte functions compared to cells in 2D and traditional 3D culture models. AH offers a robust protocol for long-term in vitro culture of primary cells, underscoring its potential for future applications in disease pathogenesis research, drug testing, and organ replacement therapy.

Liver bioprinting within a novel support medium with functionalized spheroids, hepatic vein structures, and enhanced post-transplantation vascularization.

Cell-laden bioprinting is a promising biofabrication strategy for regenerating bioactive transplants to address organ donor shortages. However, there has been little success in reproducing transplantable artificial organs with multiple distinctive cell types and physiologically relevant architecture. In this study, an omnidirectional printing embedded network (OPEN) is presented as a support medium for embedded 3D printing. The medium is state-of-the-art due to its one-step preparation, fast removal, and versatile ink compatibility. To test the feasibility of OPEN, exceptional primary mouse hepatocytes (PMHs) and endothelial cell line-C166, were used to print hepatospheroid-encapsulated-artificial livers (HEALs) with vein structures following predesigned anatomy-based printing paths in OPEN. PMHs self-organized into hepatocyte spheroids within the ink matrix, whereas the entire cross-linked structure remained intact for a minimum of ten days of cultivation. Cultivated HEALs maintained mature hepatic functions and marker gene expression at a higher level than conventional 2D and 3D conditions in vitro. HEALs with C166-laden vein structures promoted endogenous neovascularization in vivo compared with hepatospheroid-only liver prints within two weeks of transplantation. Collectively, the proposed platform enables the manufacture of bioactive tissues or organs resembling anatomical architecture, and has broad implications for liver function replacement in clinical applications.

Prediction of Clinical Precision Chemotherapy by Patient-Derived 3D Bioprinting Models of Colorectal Cancer and Its Liver Metastases.

Methods accurately predicting the responses of colorectal cancer (CRC) and colorectal cancer liver metastasis (CRLM) to personalized chemotherapy remain limited due to tumor heterogeneity. This study introduces an innovative patient-derived CRC and CRLM tumor model for preclinical investigation, utilizing 3d-bioprinting (3DP) technology. Efficient construction of homogeneous in vitro 3D models of CRC/CRLM is achieved through the application of patient-derived primary tumor cells and 3D bioprinting with bioink. Genomic and histological analyses affirm that the CRC/CRLM 3DP tumor models effectively retain parental tumor biomarkers and mutation profiles. In vitro tests evaluating chemotherapeutic drug sensitivities reveal substantial tumor heterogeneity in chemotherapy responses within the 3DP CRC/CRLM models. Furthermore, a robust correlation is evident between the drug response in the CRLM 3DP model and the clinical outcomes of neoadjuvant chemotherapy. These findings imply a significant potential for the application of patient-derived 3DP cancer models in precision chemotherapy prediction and preclinical research for CRC/CRLM.

Hybrid-Supervised Deep Learning for Domain Transfer 3D Protoacoustic Image Reconstruction.

Protoacoustic imaging showed great promise in providing real-time 3D dose verification of proton therapy. However, the limited acquisition angle in protoacoustic imaging induces severe artifacts, which significantly impairs its accuracy for dose verification. In this study, we developed a deep learning method with a Recon- Enhance two-stage strategy for protoacoustic imaging to address the limited view issue. Specifically, in the Recon-stage, a transformer-based network was developed to reconstruct initial pressure maps from radiofrequency signals. The network is trained in a hybrid-supervised approach, where it is first trained using supervision by the iteratively reconstructed pressure map and then fine-tuned using transfer learning and self-supervision based on the data fidelity constraint. In the Enhance-stage, a 3D U-net is applied to further enhance the image quality with supervision from the ground truth pressure map. The final protoacoustic images are then converted to dose for proton verification. The results evaluated on a dataset of 126 prostate cancer patients achieved an average RMSE of 0.0292, and an average SSIM of 0.9618, significantly out-performing related start-of-the-art methods. Qualitative results also demonstrated that our approach addressed the limit-view issue with more details reconstructed. Dose verification achieved an average RMSE of 0.018, and an average SSIM of 0.9891. Gamma index evaluation demonstrated a high agreement (94.7% and 95.7% for 1%/3 mm and 1%/5 mm) between the predicted and the ground truth dose maps. Notably, the processing time was reduced to 6 seconds, demonstrating its feasibility for online 3D dose verification for prostate proton therapy.

A feasibility study of enhanced prompt gamma imaging for range verification in proton therapy using deep learning.

Background and objective. Range uncertainty is a major concern affecting the delivery precision in proton therapy. The Compton camera (CC)-based prompt-gamma (PG) imaging is a promising technique to provide 3Din vivorange verification. However, the conventional back-projected PG images suffer from severe distortions due to the limited view of the CC, significantly limiting its clinical utility. Deep learning has demonstrated effectiveness in enhancing medical images from limited-view measurements. But different from other medical images with abundant anatomical structures, the PGs emitted along the path of a proton pencil beam take up an extremely low portion of the 3D image space, presenting both the attention and the imbalance challenge for deep learning. To solve these issues, we proposed a two-tier deep learning-based method with a novel weighted axis-projection loss to generate precise 3D PG images to achieve accurate proton range verification.Materials and methods: the proposed method consists of two models: first, a localization model is trained to define a region-of-interest (ROI) in the distorted back-projected PG image that contains the proton pencil beam; second, an enhancement model is trained to restore the true PG emissions with additional attention on the ROI. In this study, we simulated 54 proton pencil beams (energy range: 75-125 MeV, dose level: 1 × 109protons/beam and 3 × 108protons/beam) delivered at clinical dose rates (20 kMU min-1and 180 kMU min-1) in a tissue-equivalent phantom using Monte-Carlo (MC). PG detection with a CC was simulated using the MC-Plus-Detector-Effects model. Images were reconstructed using the kernel-weighted-back-projection algorithm, and were then enhanced by the proposed method.Results. The method effectively restored the 3D shape of the PG images with the proton pencil beam range clearly visible in all testing cases. Range errors were within 2 pixels (4 mm) in all directions in most cases at a higher dose level. The proposed method is fully automatic, and the enhancement takes only ∼0.26 s.Significance. Overall, this preliminary study demonstrated the feasibility of the proposed method to generate accurate 3D PG images using a deep learning framework, providing a powerful tool for high-precisionin vivorange verification of proton therapy.

Radiation-induced Acoustic Signal Denoising using a Supervised Deep Learning Framework for Imaging and Therapy Monitoring.

Radiation-induced acoustic (RA) imaging is a promising technique for visualizing radiation energy deposition in tissues, enabling new imaging modalities and real-time therapy monitoring. However, it requires measuring hundreds or even thousands of averages to achieve satisfactory signal-to-noise ratios (SNRs). This repetitive measurement increases ionizing radiation dose and degrades the temporal resolution of RA imaging, limiting its clinical utility. In this study, we developed a general deep inception convolutional neural network (GDI-CNN) to denoise RA signals to substantially reduce the number of averages. The multi-dilation convolutions in the network allow for encoding and decoding signal features with varying temporal characteristics, making the network generalizable to signals from different radiation sources. The proposed method was evaluated using experimental data of X-ray-induced acoustic, protoacoustic, and electroacoustic signals, qualitatively and quantitatively. Results demonstrated the effectiveness and generalizability of GDI-CNN: for all the enrolled RA modalities, GDI-CNN achieved comparable SNRs to the fully-averaged signals using less than 2% of the averages, significantly reducing imaging dose and improving temporal resolution. The proposed deep learning framework is a general method for few-frame-averaged acoustic signal denoising, which significantly improves RA imaging's clinical utilities for low-dose imaging and real-time therapy monitoring.

Radiation-induced acoustic signal denoising using a supervised deep learning framework for imaging and therapy monitoring.

Radiation-induced acoustic (RA) imaging is a promising technique for visualizing the invisible radiation energy deposition in tissues, enabling new imaging modalities and real-time therapy monitoring. However, RA imaging signal often suffers from poor signal-to-noise ratios (SNRs), thus requiring measuring hundreds or even thousands of frames for averaging to achieve satisfactory quality. This repetitive measurement increases ionizing radiation dose and degrades the temporal resolution of RA imaging, limiting its clinical utility. In this study, we developed a general deep inception convolutional neural network (GDI-CNN) to denoise RA signals to substantially reduce the number of frames needed for averaging. The network employs convolutions with multiple dilations in each inception block, allowing it to encode and decode signal features with varying temporal characteristics. This design generalizes GDI-CNN to denoise acoustic signals resulting from different radiation sources. The performance of the proposed method was evaluated using experimental data of x-ray-induced acoustic, protoacoustic, and electroacoustic signals both qualitatively and quantitatively. Results demonstrated the effectiveness of GDI-CNN: it achieved x-ray-induced acoustic image quality comparable to 750-frame-averaged results using only 10-frame-averaged measurements, reducing the imaging dose of x-ray-acoustic computed tomography (XACT) by 98.7%; it realized proton range accuracy parallel to 1500-frame-averaged results using only 20-frame-averaged measurements, improving the range verification frequency in proton therapy from 0.5 to 37.5 Hz; it reached electroacoustic image quality comparable to 750-frame-averaged results using only a single frame signal, increasing the electric field monitoring frequency from 1 fps to 1k fps. Compared to lowpass filter-based denoising, the proposed method demonstrated considerably lower mean-squared-errors, higher peak-SNR, and higher structural similarities with respect to the corresponding high-frame-averaged measurements. The proposed deep learning-based denoising framework is a generalized method for few-frame-averaged acoustic signal denoising, which significantly improves the RA imaging's clinical utilities for low-dose imaging and real-time therapy monitoring.

New insights into nitrogen control strategies in sewage sludge pyrolysis toward environmental and economic sustainability.

Sewage sludge (SS) contains a certain amount of nitrogen (N), resulting in various content of N in the pyrolysis products. Investigates on how to control the generation of NH3 and HCN (deleterious gas-N species) or convert it to N2 and maximize transforming N in sewage sludge (SS-N) into potentially valuable N-containing products (such as char-N and/or liquid-N) are of great significance for SS management. Understanding the nitrogen migration and transformation (NMT) mechanisms in SS during the pyrolysis process is essential for investigating the aforementioned issues. Therefore, in this review, the N content and species in SS are summarized, and the influencing factors during the SS pyrolysis process (such as temperature, minerals, atmosphere, and heating rate) that affect NMT in char, gas, and liquid products are analyzed. Furthermore, N control strategies in SS pyrolysis products are proposed toward environmental and economic sustainability. Finally, the state-of-the-art of current research and future prospects are summarized, with a focus on the generation of value-added liquid-N and char-N products, while concurrently reducing NOx emission.

Real-time Markerless Tracking of Lung Tumors based on 2-D Fluoroscopy Imaging using Convolutional LSTM.

Purpose: To investigate the feasibility of tracking targets in 2D fluor images using a novel deep learning network. Methods: Our model design aims to capture the consistent motion of tumors in fluoroscopic images by neural network. Specifically, the model is trained by generative adversarial methods. The network is a coarse-to-fine architecture design. Convolutional LSTM (Long Short-term Memory) modules are introduced to account for the time correlation between different frames of the fluoroscopic images. The model was trained and tested on a digital X-CAT phantom in two studies. Series of coherent 2D fluoroscopic images representing the full respiration cycle were fed into the model to predict the localized tumor regions. In first study to test on massive scenarios, phantoms of different scales, tumor positions, sizes, and respiration amplitudes were generated to evaluate the accuracy of the model comprehensively. In second study to test on specific sample, phantoms were generated with fixed body and tumor sizes but different respiration amplitudes to investigate the effects of motion amplitude on the tracking accuracy. The tracking accuracy was quantitatively evaluated using intersection over union (IOU), tumor area difference, and centroid of mass difference (COMD). Results: In the first comprehensive study, the mean IOU and dice coefficient achieved 0.93±0.04 and 0.96±0.02. The mean tumor area difference was 4.34%±4.04%. And the COMD was 0.16 cm and 0.07 cm on average in SI (superior-interior) and LR (left-right) directions, respectively. In the second amplitude study, the mean IOU and dice coefficient achieved 0.98 and 0.99. The mean tumor difference was 0.17%. And the COMD was 0.03cm and 0.01 cm on average in SI and LR directions, respectively. Results demonstrated the robustness of our model against breathing variations. Conclusion: Our study showed the feasibility of using deep learning to track targets in x-ray fluoroscopic projection images without the aid of markers. The technique can be valuable for both pre- and during-treatment real-time target verification using fluoroscopic imaging in lung SBRT treatments.

Fast four-dimensional cone-beam computed tomography reconstruction using deformable convolutional networks.

BACKGROUND: Although four-dimensional cone-beam computed tomography (4D-CBCT) is valuable to provide onboard image guidance for radiotherapy of moving targets, it requires a long acquisition time to achieve sufficient image quality for target localization. To improve the utility, it is highly desirable to reduce the 4D-CBCT scanning time while maintaining high-quality images. Current motion-compensated methods are limited by slow speed and compensation errors due to the severe intraphase undersampling. PURPOSE: In this work, we aim to propose an alternative feature-compensated method to realize the fast 4D-CBCT with high-quality images. METHODS: We proposed a feature-compensated deformable convolutional network (FeaCo-DCN) to perform interphase compensation in the latent feature space, which has not been explored by previous studies. In FeaCo-DCN, encoding networks extract features from each phase, and then, features of other phases are deformed to those of the target phase via deformable convolutional networks. Finally, a decoding network combines and decodes features from all phases to yield high-quality images of the target phase. The proposed FeaCo-DCN was evaluated using lung cancer patient data. RESULTS: (1) FeaCo-DCN generated high-quality images with accurate and clear structures for a fast 4D-CBCT scan; (2) 4D-CBCT images reconstructed by FeaCo-DCN achieved 3D tumor localization accuracy within 2.5 mm; (3) image reconstruction is nearly real time; and (4) FeaCo-DCN achieved superior performance by all metrics compared to the top-ranked techniques in the AAPM SPARE Challenge. CONCLUSION: The proposed FeaCo-DCN is effective and efficient in reconstructing 4D-CBCT while reducing about 90% of the scanning time, which can be highly valuable for moving target localization in image-guided radiotherapy.

Multiplexed Identification of Bacterial Biofilm Infections Based on Machine-Learning-Aided Lanthanide Encoding.

Pathogenic biofilms are up to 1000-fold more drug-resistant than planktonic pathogens and cause about 80% of all chronic infections worldwide. The lack of prompt and reliable biofilm identification methods seriously prohibits the diagnosis and treatment of biofilm infections. Here, we developed a machine-learning-aided cocktail assay for prompt and reliable biofilm detection. Lanthanide nanoparticles with different emissions, surface charges, and hydrophilicity are formulated into the cocktail kits. The lanthanide nanoparticles in the cocktail kits can offer competitive interactions with the biofilm and further maximize the charge and hydrophilicity differences between biofilms. The physicochemical heterogeneities of biofilms were transformed into luminescence intensity at different wavelengths by the cocktail kits. The luminescence signals were used as learning data to train the random forest algorithm, and the algorithm could identify the unknown biofilms within minutes after training. Electrostatic attractions and hydrophobic-hydrophobic interactions were demonstrated to dominate the binding of the cocktail kits to the biofilms. By rationally designing the charge and hydrophilicity of the cocktail kit, unknown biofilms of pathogenic clinical isolates were identified with an overall accuracy of over 80% based on the random forest algorithm. Moreover, the antibiotic-loaded cocktail nanoprobes efficiently eradicated biofilms since the nanoprobes could penetrate deep into the biofilms. This work can serve as a reliable technique for the diagnosis of biofilm infections and it can also provide instructions for the design of multiplex assays for detecting biochemical compounds beyond biofilms.