Multiscale knowledge distillation with attention based fusion for robust human activity recognition.

Knowledge distillation is an effective approach for training robust multi-modal machine learning models when synchronous multimodal data are unavailable. However, traditional knowledge distillation techniques have limitations in comprehensively transferring knowledge across modalities and models. This paper proposes a multiscale knowledge distillation framework to address these limitations. Specifically, we introduce a multiscale semantic graph mapping (SGM) loss function to enable more comprehensive knowledge transfer between teacher and student networks at multiple feature scales. We also design a fusion and tuning (FT) module to fully utilize correlations within and between different data types of the same modality when training teacher networks. Furthermore, we adopt transformer-based backbones to improve feature learning compared to traditional convolutional neural networks. We apply the proposed techniques to multimodal human activity recognition and compared with the baseline method, it improved by 2.31% and 0.29% on the MMAct and UTD-MHAD datasets. Ablation studies validate the necessity of each component.

Image-Domain Material Decomposition for Dual-energy CT using Unsupervised Learning with Data-fidelity Loss.

BACKGROUND: Dual-energy CT (DECT) and material decomposition play vital roles in quantitative medical imaging. However, the decomposition process may suffer from significant noise amplification, leading to severely degraded image signal-to-noise ratios (SNRs). While existing iterative algorithms perform noise suppression using different image priors, these heuristic image priors cannot accurately represent the features of the target image manifold. Although deep learning-based decomposition methods have been reported, these methods are in the supervised-learning framework requiring paired data for training, which is not readily available in clinical settings. PURPOSE: This work aims to develop an unsupervised-learning framework with data-measurement consistency for image-domain material decomposition in DECT.

One-step Iterative Estimation of Effective Atomic Number and Electron Density for Dual Energy CT.

Dual-energy computed tomography (DECT) is a promising technology that has shown a number of clinical advantages over conventional X-ray CT, such as improved material identification, artifact suppression, etc. For proton therapy treatment planning, besides material-selective images, maps of effective atomic number (Z) and relative electron density to that of water ($\rho_e$) can also be achieved and further employed to improve stopping power ratio accuracy and reduce range uncertainty. In this work, we propose a one-step iterative estimation method, which employs multi-domain gradient $L_0$-norm minimization, for Z and $\rho_e$ maps reconstruction. The algorithm was implemented on GPU to accelerate the predictive procedure and to support potential real-time adaptive treatment planning. The performance of the proposed method is demonstrated via both phantom and patient studies.

Noise correlation and its impact on the performance of multi-material decomposition-based spectral imaging in photon-counting CT.

PURPOSE: It has been known that noise correlation plays an important role in the determination of the performance of spectral imaging based on two-material decomposition (2-MD). To further understand the basics of spectral imaging in photon-counting CT toward optimal design and implementation, we study the noise correlation in multi-MD (m-MD) and its impact on the performance of spectral imaging. METHOD: We derive the equations that characterize the noise and noise correlation in the material-specific (basis) images in m-MD, followed by a simulation study to verify the derived equations and study the noise correlation's impact on the performance of spectral imaging. Using a specially designed digital phantom, the study of noise correlation runs over the cases of two-, three-, and four-MD (2-MD, 3-MD, and 4-MD). Then, the noise correlation's impact on the performance of spectral imaging in photon-counting CT is investigated, using a modified Shepp-Logan phantom. RESULTS: The results in 2-MD show that, in-line with what has been reported in the literature, the noise correlation coefficient between the material-specific images corresponding to the basis materials approaches -1. The results in m-MD (m ≥ 3) are more complicated and interesting, as the noise correlation coefficients between a pair of the material-specific images alternate between ±1, and so do in the case of 4-MD. The m-MD data show that the noise in virtual monochromatic imaging (a form of spectral imaging) is moderate even though the noises in material-specific (basis) images vary drastically. CONCLUSIONS: The observation of noise correlation in 3-MD, 4-MD, and beyond (i.e., m-MD) is informative to the community. The relationship between noise correlation and the performance of spectral imaging revealed in this work may help clinical medical physicists understand the fundamentals of spectral imaging based on MD and optimize the performance of spectral imaging in photon-counting CT and other X-ray imaging modalities.

A Mid-term Follow-up Study on the Reimplantation of Autoclaved Femoral and Tibial Components as Spacers for Treating Infected Total Knee Arthroplasty.

OBJECTIVE: Infection after total knee arthroplasty (TKA) is a rare but devastating complication. Different types of spaces have been used in two-stage revision. The study aimed to evaluate the effect of autoclaved femoral and tibial components as spacers for treating periprosthetic infections after TKA. METHODS: A retrospective study was performed for 13 patients (five males, eight females) with a mean age of 69 ± 6 (range, 57-80) years and suffering from periprosthetic infection after TKA. They were treated with unconventional two-stage revision from May 2008 to June 2017. In the first-stage surgery, the autoclaved femoral and tibial components were reimplanted with a new liner as a spacer after a thorough debridement. After 4-6 months, the second-stage surgery was performed according to the patients' requirements. The knee society score (KSS) and knee range of motion (ROM) were assessed before and after surgery. The reinfection rate was calculated. RESULTS: The mean duration of follow-up was 5.7 ± 2.1 (range, 3.1-8.8) years. Culture-positive infections comprised 69% of the cohort. All patients were able to walk 24 h after the first stage surgery, and the knee ROM could reach 90° in 1 week. Two patients (15.4%) experienced an infection recurrence. One patient was reinfected 1 year after the first stage surgery. Another patient developed reinfection 3 years after surgery but did not choose re-revision and died of pneumonia. Only one patient underwent the second stage revision. The remaining 10 patients refused to receive a new prosthesis. At the time of the final follow-up, six patients had slight pain in the knee while walking, and one patient required crutches to walk. There were no signs of prosthesis dislocation, rupture, deep vein thrombosis, pulmonary embolism, or delayed wound healing. No radiolucent lines or osteolysis were found. The mean KSS improved from 51 ± 10 (range, 35-63) points preoperatively to 79 ± 5 (range, 60-85) points at the final follow-up. The average ROM before and after the first stage surgery were 62° ± 29° (range, 10°-100°) and 104° ± 9° (range, 90°-120°) (t = 4.659, P < 0.01) respectively. The infection control rate was 84.6%. CONCLUSION: Reimplantation of the autoclaved original femoral and tibial components as an articulating spacer during the first stage surgery is a valuable addition for treating an infected TKA.

Tetrahydroxydiboron and Nickel Chloride Cocatalyzed Rapid Radical Cyclization toward Pyrrolizidine and Indolizidine Alkaloids.

A novel tetrahydroxydiboron and nickel chloride cocatalyzed radical cyclization cascade with a broad substrate scope and an ultrashort reaction time was developed. The mechanistic investigation indicated that the reaction might involve a homocleavage of tetrahydroxydiboron and nickel hydride intermediates. This approach enables the simple and efficient synthesis of a series of heteropolycycles.

Photon-counting CT via interleaved/gapped spectral channels: Feasibility and imaging performance.

PURPOSE: Compared to energy integration, photon-counting x-ray detection facilitates the spectral channelization (energy binning) in spectral CT and thus offers the opportunity to implement data acquisition via sophisticated schemes, for example, gapping or interleaving in spectral channels. In this article, we report our investigation of the performance of material decomposition based spectral imaging in photon-counting CT implemented in such data acquisition schemes, and their comparison with the benchmark scheme and other schemes without spectral gapping or interleaving. MATERIALS AND METHODS: Using a deliberately designed anthropomorphic head phantom that mimics the intracranial soft tissues and bony structures, a simulation study is carried out with the focus on two-material decomposition based spectral imaging in photon-counting computed tomography (CT), under both ideal and realistic detector spectral responses. The projection data are acquired in four spectral channels, and then are sorted to implement the schemes of gapping ((ch1 , ch3 ); (ch2 , ch4 ); (ch1 , ch4 )) and interleaving ((ch1 , ch3 ) + (ch2 , ch4 ); (ch1 , ch4 ) + (ch2 , ch3 ); ((ch1 + ch3 ), (ch2 + ch4 )); ((ch1 + ch4 ), (ch2 + ch3 ))) in spectral channels, in addition to the benchmark scheme ((ch1 + ch2 ), (ch3 + ch4 )) and other conventional schemes (ch1 , ch2 ), (ch2 , ch3 ) and (ch3 , ch4 ), where ''ch'' denotes channel, ''+'' denote addition, and (·,·) the operation of material decomposition and image reconstruction. Using the contrast-to-noise ratio between targeted regions of interest as the figure of merit, we study the performance of spectral imaging (material specific and virtual monochromatic) associated with these spectral channelization schemes. RESULTS: Under ideal detector spectral response, the scheme (ch1 , ch4 ) outperforms the benchmark scheme ((ch1 + ch2 ), (ch3 + ch4 )) and others in gapped and/or interleaved spectral channelization in material specific imaging, while the interleaved scheme (ch1 , ch4 ) + (ch2 , ch3 ) performs the best in virtual monochromatic imaging. Notably, only about half x-ray dose is utilized in the scheme (ch1 , ch4 ) for image formation. Under realistic detector spectral response, the difference in imaging performance over all spectral channelization schemes diminishes, along with degradation in each scheme's individual performance. The results suggest that (i) different strategy in spectral channelization may have to be exercised in material specific imaging and virtual monochromatic imaging, respectively, and (ii) the spectral distortion in realistic detector's response due to charge-sharing, Compton scattering, and fluorescent escaping should be mitigated as much as possible. CONCLUSION: The spectral channelization schemes and associated imaging performance reported herein are novel and thus informative to the community, which may further the understanding of physical fundamentals and design principles for material decomposition based spectral imaging in photon-counting CT and other x-ray related imaging modalities.

Achieving High Efficiency at High Luminance in Fluorescent Organic Light-Emitting Diodes through Triplet-Triplet Fusion Based on Phenanthroimidazole-Benzothiadiazole Derivatives.

Achieving high efficiency at high luminance is one of the most important prerequisites towards practical application of any kind of light-emitting diode (LED). Herein, we report highly emissive organic fluorescent molecules based on phenanthroimidazole-benzothiadiazole derivatives capable of maintaining high external quantum efficiency (EQE) at high luminance enabled by triplet-triplet fusion (TTF) in doped organic LEDs. The PIBzP-, PIBzPCN-, and PIBzTPA-based devices showed EQEs of 8.27, 9.15, and 8.64 %, respectively, at luminance of higher than 1000 cd m-2 , with little efficiency roll-off.

Highly Efficient and Thickness Insensitive Inverted Triple-Cation Perovskite Solar Cells Fabricated by Gas Pumping Method.

The gas pumping method (GP) holds the potential of outperforming the antisolvent method (AS) for fabricating perovskite solar cells (PSCs) in many ways such as free of toxic solvents, improved film uniformity, and device reproducibility. Most of the highest power conversion efficiencies (PCEs) of PSCs are still achieved by AS. Successful demonstrations of inverted PSCs produced by GP as well as the corresponding mechanisms are still lacking. Herein, we fabricate highly efficient inverted PSCs by GP delivering an overall efficiency of 21.54%, on par with that of the devices by AS (21.41%), and a superior reproducibility at the optimal film thickness. Nevertheless, as the perovskite film thickness increases, the PCE of GP devices slightly dropped while the AS devices decreased significantly. We found that the AS method tends to produce horizontal grain boundaries due to the heterogeneous solvent extraction while they can be effectively suppresed by the GP method.

High through-plane resolution CT imaging with self-supervised deep learning.

CT images for radiotherapy planning are usually acquired in thick slices to reduce the imaging dose, especially for pediatric patients, and to lessen the need for contouring and treatment planning on more slices. However, low through-plane resolution may degrade the accuracy of dose calculations. In this paper, a self-supervised deep learning workflow is proposed to synthesize high through-plane resolution CT images by learning from their high in-plane resolution features. The proposed workflow was designed to facilitate neural networks to learn the mapping from low-resolution (LR) to high-resolution (HR) images in the axial plane. During the inference step, the HR sagittal and coronal images were generated by feeding two parallel-trained neural networks with the respective LR sagittal and coronal images to the trained neural networks. The CT simulation images of a cohort of 75 patients with head and neck cancer (1 mm slice thickness) and 200 CT images of a cohort of 20 lung cancer patients (3 mm slice thickness) were retrospectively investigated in a cross-validation manner. The HR images generated with the proposed method were qualitatively (visual quality, image intensity profiles and preliminary observer study) and quantitatively (mean absolute error, edge keeping index, structural similarity index measurement, information fidelity criterion and visual information fidelity in pixel domain) inspected, while taking the original CT images of the head and neck and lung cancer patients as the reference. The qualitative results showed the capability of the proposed method for generating high through-plane resolution CT images with data from both groups of cancer patients. All the improvements in the measure metrics were confirmed to be statistically significant with paired two-samplet-test analysis. The innovative point of the work is that the proposed deep learning workflow for CT image generation with high through-plane resolution in radiotherapy is self-supervised, meaning that it does not rely on ground truth CT images to train the network. In addition, the assumption that the in-plane HR information can supervise the through-plane HR generation is confirmed. We hope that this will inspire more research on this topic to further improve the through-plane resolution of medical images.

Hydrogen-Bonding Controlled Nickel-Catalyzed Regioselective Cyclotrimerization of Terminal Alkynes.

Herein we report a hydrogen-bonding controlled nickel-catalyzed regioselective cyclotrimerization of terminal alkynes in moderate to excellent yields with high regioselectivities toward 1,3,5-trisubstituted benzenes. This method features a cheap catalyst, mild reaction conditions, and excellent functional group compatibility. The Ni-B(OH)2 complex in situ generated from NiCl2·DME and tetrahydroxydiboron might act as an active catalyst. After three consecutive cis-additions of terminal alkynes, internal migratory insertion cyclization, and ß-boron elimination induced aromatization, 1,3,5-trisubstituted benzenes were selectively established.

Efficient Red Electroluminescence From Phenanthro[9,10-d]imidazole-Naphtho[2,3-c][1,2,5]thiadiazole Donor-Acceptor Derivatives.

Red emission is one of the three primary colors and is indispensable for full color displays. Fluorescent materials that can generate efficient red electroluminescence (EL) are limited and need to be developed. In this work, we report efficient red emitters based on phenanthro[9,10-d]imidazole-naphtho[2,3-c][1,2,5]thiadiazole donor-acceptor derivatives. The molecules, abbreviated as PINzP and PINzPCN, exhibited high photoluminescence quantum yield (PLQY) up to unity in doped films. They can also reach a relatively high PLQY of ∼30% in neat films. PINzP and PINzPCN were capable of generating efficient red EL in doped devices with a maximum external quantum efficiency (EQE) of 6.96% and 5.92%, respectively.

Direct Synthesis of N-Difluoromethyl-2-pyridones from Pyridines.

A novel method for the synthesis of N-difluoromethyl-2-pyridones was described. This protocol enables the synthesis of N-difluoromethyl-2-pyridones from readily available pyridines using mild reaction conditions that are compatible with a wide range of functional groups. The preliminary mechanistic study revealed that N-difluoromethylpyridinium salts were the key intermediates to complete this conversion.

Metal-Free Difunctionalization of Pyridines: Selective Construction of N-CF2H and N-CHO Dihydropyridines.

The reactivity of N-difluoromethylpyridinium salts is seldom explored because of their instability and low availability. Here we present a novel nucleophilic addition of N-difluoromethylpyridinium salts with nitroalkanes to synthesize N-CF2H-dihydropyridines and N-CHO-dihydropyridines in a highly efficient and regioselective pathway. This protocol exhibits good functional group tolerance and good to excellent yields.

On the conditioning of basis materials and its impact on multimaterial decomposition-based spectral imaging in photon-counting CT.

PURPOSE: Material-specific imaging and virtual monochromatic imaging/analysis are the two forms of spectral imaging in CT implemented via either energy-integration or photon-counting data acquisition. Aimed at further understanding the fundamentals and providing guidelines on its design and implementation, we quantitatively investigate the conditioning (sufficiency in dimensionality, well-posedness in basis functions, and matching of K-edge materials) of basis materials and its impact on the performance of spectral imaging in photon-counting CT. MATERIALS AND METHODS: Initially, singular value decomposition (SVD) is employed to investigate the dimensionality of material space for multimaterial decomposition-based spectral imaging in photon-counting CT over the energy range [18 150] keV. Then, the SVD is extended to study the well-posedness of basis functions, its relationship with the dimensionality of materials to be imaged, and its impact on imaging performance. A number of phantoms are designed to mimic the soft and bony tissues in the head and contrast enhancement materials (iodine and gadolinium). Simulation studies, in which the geometry of photon-counting CT is similar to a clinical CT, are carried out to evaluate and verify the proposed approach of conditioning analysis and the relationship between the conditioning of basis materials and the performance of spectral imaging in photon-counting CT. RESULTS: The preliminary data show that the dimensionality of biological tissues, including both soft and bony tissues, is effectively equal to two. The dimensionality increments with inclusion of K-edge materials into the materials to be imaged. The well-posedness of basis functions depends on the correlation between the functions and impacts the noise in material decomposition substantially, but affects the noise in virtual monochromatic imaging/analysis moderately. If a K-edge material is in the materials to be imaged, the same K-edge material has to be one of the basis materials, but its concentration does not affect the accuracy of material decomposition significantly. Moreover, inclusion of K-edge material into the basis material makes the tuning of correlation among the basis functions feasible and thus improves the performance of spectral imaging in photon-counting CT. CONCLUSION: The extension of SVD for systematic analysis of multimaterial decomposition-based spectral imaging in photon-counting CT is of innovation and significance. In addition to providing more information on the fundamentals, the approach used in this study and the data obtained so far may provide guidelines on the implementation of spectral imaging in either photon-counting or energy-integration CT, as well as other x-ray-related imaging modalities such as radiography and tomosynthesis.

On the Conditioning of Spectral Channelization (Energy Binning) and Its Impact on Multi-Material Decomposition Based Spectral Imaging in Photon-Counting CT.

OBJECTIVE: The conditioning (well-posedness) of basis materials (functions) and spectral channelization play important roles in determining the performance of spectral imaging (material specific imaging and virtual monochromatic imaging/analysis) in photon-counting CT. Aimed at further understanding the fundamentals of photon-counting spectral CT and providing guidelines on its design and implementation, we propose a singular value decomposition (SVD) and analysis based approach in this work to assess the conditioning of spectral channelization and its impact on the performance of spectral imaging under both ideal and realistic detector spectral response. METHODS: Via simulation studies, in which the geometry of photon-counting CT is similar to a clinical CT, the condition number acquired via SVD and analysis is employed to assess the conditioning of spectral channelization in photon-counting CT and its impact on the performance of spectral imaging. The simulation study runs over two- and three-material decom-position based spectral imaging (material specific imaging and virtual monochromatic imaging/analysis over the energy range [18] [150] keV). Under both ideal and realistic detector spectral response, a specially designed phantom that mimics the soft and bony tissues in the head is utilized to quantitatively reveal the relationship between the conditioning (condition number) of spectral channelization and the performance (mainly noise and contrast-to-noise ratio) of spectral imaging in photon-counting CT. The simulation study is also extended over the cases wherein up to 50% spectral overlapping occurs. RESULTS: The results show that, under ideal detector spectral response, the condition number of spectral channelization reaches the minimum while no overlapping occurs in spectral channels. The condition number of spectral channelization increments with increasing spectral overlapping in the channels. The distortion in detector's spectral response induced by scattering, charge-sharing and fluorescent escaping results in spectral overlapping in spectral channels and thus degrades the conditioning (larger condition number) of spectral channelization. Respectively, the noise increases and contrast-to-noise ratio decreases in material- specific imaging and virtual monochromatic imaging/analysis, while the condition number of spectral channelization increments with increasing spectral overlapping. CONCLUSION: The SVD and analysis based approach can be utilized to systematically analyze the conditioning of spectral channelization and its impact on the performance of spectral imaging in photon-counting CT. SIGNIFICANCE: The approach proposed by us brings innovation and has significance. In addition to providing information for insightful understanding of the fundamentals, the approach proposed in this study and the data obtained so far may provide guidelines on the implementation of spectral imaging in photon-counting CT and energy-integration CT as well, along with its applicability to other x-ray related imaging modalities such as radiography and tomosynthesis.

Principal Component Analysis in Projection and Image Domains-Another Form of Spectral Imaging in Photon-Counting CT.

OBJECTIVE: We explore the feasibility of principal component analysis (PCA) as a form of spectral imaging in photon-counting CT. METHODS: Using the data acquired by a prototype system and simulated by computer, we investigate the feasibility of spectral imaging in photon-counting CT via PCA for feature extraction and study the impacts made by data standardization and de-noising on its performance. RESULTS: The PCA in the projection domain maintains the data consistence that is essential for tomographic image reconstruction and performs virtually the same as that in the image domain. The first three primary components account for more than 99.99% covariance of the data. Within anticipation, the contrast-to-noise ratio (CNR) between the target and background in the first principal component image can be larger than that in the image generated from the data acquired in each energy bin. More importantly, the CNR in the first principal component image may be larger than that in the image formed by the summed data acquired in all energy bins (i.e., the conventional polychromatic CT image). In addition, de-noising can not only reduce the noise in images but also improve the effectiveness/efficiency of PCA in feature extraction. CONCLUSION: The PCA in either projection or image domain provides another form of spectral imaging in photon-counting CT that fits the essential requirements on spectral imaging in true color. SIGNIFICANCE: The verification of PCA's feasibility in CT as a form spectral imaging and observation of its potential superiority in CNR over conventional polychromatic CT are meaningful in theory and practice.

Synthesis of Indolizines from Pyridinium Salts and Ethyl Bromodifluoroacetate.

Here we present a novel annulation of pyridinium salts with BrCF2CO2Et to access the indolizine derivatives with high efficiency. The α substitution of pyridine plays a key role in determining the reaction pathways. Various types of indolizines can be conveniently accessed from easily available pyridinium salts under mild and simple reaction conditions.

Slicing and Splicing of Bromodifluoro-N-arylacetamides: Dearomatization and Difunctionalization of Pyridines.

Copper-catalyzed dearomatization and difunctionalization of pyridines have been disclosed, in which bromodifluoro-N-arylacetamide was sliced into five fragments and three or four of them were transferred to pyridine partners. Through this reaction, novel N-difluoromethyl-2-imine dihydropyridine derivatives can be conveniently accessed from commercially available 4-amino substituted pyridines. This strategy demonstrates a novel fluorination method featuring high atom economy, environmental friendliness, an easily available catalyst, and simple operation.

CT-based multi-organ segmentation using a 3D self-attention U-net network for pancreatic radiotherapy.

PURPOSE: Segmentation of organs-at-risk (OARs) is a weak link in radiotherapeutic treatment planning process because the manual contouring action is labor-intensive and time-consuming. This work aimed to develop a deep learning-based method for rapid and accurate pancreatic multi-organ segmentation that can expedite the treatment planning process. METHODS: We retrospectively investigated one hundred patients with computed tomography (CT) simulation scanned and contours delineated. Eight OARs including large bowel, small bowel, duodenum, left kidney, right kidney, liver, spinal cord and stomach were the target organs to be segmented. The proposed three-dimensional (3D) deep attention U-Net is featured with a deep attention strategy to effectively differentiate multiple organs. Performance of the proposed method was evaluated using six metrics, including Dice similarity coefficient (DSC), sensitivity, specificity, Hausdorff distance 95% (HD95), mean surface distance (MSD) and residual mean square distance (RMSD). RESULTS: The contours generated by the proposed method closely resemble the ground-truth manual contours, as evidenced by encouraging quantitative results in terms of DSC, sensitivity, specificity, HD95, MSD and RMSD. For DSC, mean values of 0.91 ± 0.03, 0.89 ± 0.06, 0.86 ± 0.06, 0.95 ± 0.02, 0.95 ± 0.02, 0.96 ± 0.01, 0.87 ± 0.05 and 0.93 ± 0.03 were achieved for large bowel, small bowel, duodenum, left kidney, right kidney, liver, spinal cord and stomach, respectively. CONCLUSIONS: The proposed method could significantly expedite the treatment planning process by rapidly segmenting multiple OARs. The method could potentially be used in pancreatic adaptive radiotherapy to increase dose delivery accuracy and minimize gastrointestinal toxicity.