Small Imaging Research Articles

Imaging quality enhancement in photon-counting single-pixel imaging via an ADMM-based deep unfolding network in small animal fluorescence imaging

Photon-counting single-pixel imaging (SPI) can image under low-light conditions with high-sensitivity detection. However, the imaging quality of these systems will degrade due to the undersampling and intrinsic photon-noise in practical applications. Here, we propose a deep unfolding network based on the Bayesian maximum a posterior (MAP) estimation and alternating direction method of multipliers (ADMM) algorithm. The reconstruction framework adopts a learnable denoiser by convolutional neural network (CNN) instead of explicit function with hand-crafted prior. Our method enhances the imaging quality compared to traditional methods and data-driven CNN under different photon-noise levels at a low sampling rate of 8%. Using our method, the sensitivity of photon-counting SPI prototype system for fluorescence imaging can reach 7.4 pmol/ml. In-vivo imaging of a mouse bearing tumor demonstrates an 8-times imaging efficiency improvement.

An Infrared Aircraft Detection Algorithm Based on Context Perception Feature Enhancement

To address the issue of insufficient extraction of target features and the resulting impact on detection performance in long-range infrared aircraft target detection caused by small imaging area and weak radiation intensity starting from the idea of perceiving target context to enhance the features extracted by convolutional neural network, this paper proposes a detecting algorithm based on AWFGLC (adaptive weighted fusion of global–local context). Based on the mechanism of AWFGLC, the input feature map is randomly reorganized and partitioned along the channel dimension, resulting in two feature maps. One feature map is utilized by self-attention for global context modeling, establishing the correlation between target features and background features to highlight the salient features of the target, thereby enabling the detecting algorithm to better perceive the global features of the target. The other feature map is subjected to window partitioning, with max pooling and average pooling performed within each window to highlight the local features of the target. Subsequently, self-attention is applied to the pooled feature map for local context modeling, establishing the correlation between the target and its surrounding neighborhood, further enhancing the weaker parts of the target features, and enabling the detecting algorithm to better perceive the local features of the target. Based on the characteristics of the target, an adaptive weighted fusion strategy with learnable parameters is employed to aggregate the global context and local context feature maps. This results in a feature map containing more complete target information, enhancing the ability of the detection algorithm to distinguish between target and background. Finally, this paper integrates the mechanism of AWFGLC into YOLOv7 for the detection of infrared aircraft targets. The experiments indicate that the proposed algorithm achieves mAP50 scores of 97.8% and 88.7% on self-made and publicly available infrared aircraft datasets, respectively. Moreover, the mAP50:95 scores reach 65.7% and 61.2%, respectively. These results outperform those of classical target detection algorithms, indicating the effective realization of infrared aircraft target detection.

Seracam: characterisation of a new small field of view hybrid gamma camera for nuclear medicine

BackgroundPortable gamma cameras are being developed for nuclear medicine procedures such as thyroid scintigraphy. This article introduces Seracam® – a new technology that combines small field of view gamma imaging with optical imaging – and reports its performance and suitability for small organ imaging.MethodsThe count rate capability, uniformity, spatial resolution, and sensitivity for 99mTc are reported for four integrated pinhole collimators of nominal sizes of 1 mm, 2 mm, 3 mm and 5 mm. Characterisation methodology is based on NEMA guidelines, with some adjustments necessitated by camera design. Two diagnostic scenarios – thyroid scintigraphy and gastric emptying – are simulated using clinically relevant activities and geometries to investigate application-specific performance. A qualitative assessment of the potential benefits and disadvantages of Seracam is also provided.ResultsSeracam’s performance across the measured characteristics is appropriate for small field of view applications in nuclear medicine. At an imaging distance of 50 mm, corresponding to a field of view of 77.6 mm × 77.6 mm, spatial resolution ranged from 4.6 mm to 26 mm and sensitivity from 3.6 cps/MBq to 52.2 cps/MBq, depending on the collimator chosen. Results from the clinical simulations were particularly promising despite the challenging scenarios investigated. The optimal collimator choice was strongly application dependent, with gastric emptying relying on the higher sensitivity of the 5 mm pinhole whereas thyroid imaging benefitted from the enhanced spatial resolution of the 1 mm pinhole. Signal to noise ratio in images was improved by pixel binning. Seracam has lower measured sensitivity when compared to a traditional large field of view gamma camera, for the simulated applications this is balanced by advantages such as high spatial resolution, portability, ease of use and real time gamma-optical image fusion and display.ConclusionThe results show that Seracam has appropriate performance for small organ 99mTc imaging. The results also show that the performance of small field of view systems must be considered holistically and in clinically appropriate scenarios.

Efficient characterization of multiple binding sites of small molecule imaging ligands on amyloid-beta, tau and alpha-synuclein

PurposeThere is an unmet need for compounds to detect fibrillar forms of alpha-synuclein (αSyn) and 4-repeat tau, which are critical in many neurodegenerative diseases. Here, we aim to develop an efficient surface plasmon resonance (SPR)-based assay to facilitate the characterization of small molecules that can bind these fibrils.MethodsSPR measurements were conducted to characterize the binding properties of fluorescent ligands/compounds toward recombinant amyloid-beta (Aβ)42, K18-tau, full-length 2N4R-tau and αSyn fibrils. In silico modeling was performed to examine the binding pockets of ligands on αSyn fibrils. Immunofluorescence staining of postmortem brain tissue slices from Parkinson’s disease patients and mouse models was performed with fluorescence ligands and specific antibodies.ResultsWe optimized the protocol for the immobilization of Aβ42, K18-tau, full-length 2N4R-tau and αSyn fibrils in a controlled aggregation state on SPR-sensor chips and for assessing their binding to ligands. The SPR results from the analysis of binding kinetics suggested the presence of at least two binding sites for all fibrils, including luminescent conjugated oligothiophenes, benzothiazole derivatives, nonfluorescent methylene blue and lansoprazole. In silico modeling studies for αSyn (6H6B) revealed four binding sites with a preference for one site on the surface. Immunofluorescence staining validated the detection of pS129-αSyn positivity in the brains of Parkinson’s disease patients and αSyn preformed-fibril injected mice, 6E10-positive Aβ in arcAβ mice, and AT-8/AT-100-positivity in pR5 mice.ConclusionSPR measurements of small molecules binding to Aβ42, K18/full-length 2N4R-tau and αSyn fibrils suggested the existence of multiple binding sites. This approach may provide efficient characterization of compounds for neurodegenerative disease-relevant proteinopathies.

Making Sense of Emoji

AbstractMany online messages now contain emoji – these small images have quickly become an important means of communicating. Yet they have not yet been taken seriously in philosophy of language. In this exploratory paper, I attempt to remedy this neglect by analysing the communicative functions of emoji. I argue that emoji have at least three communicative functions. Firstly, they can serve a replicative function, in that they can play the same role as words and punctuation, thereby replicating the function of existing written communicative devices. Secondly, they can serve a compensatory function, in the sense that they can be used to make up for features of face-to-face conversation which are lost in written online conversation. Thirdly, they can serve supplementary functions, in that we can perform new communicative acts with emoji which we could not previously perform either in written or face-to-face communication.

Small Sample Image Segmentation by Coupling Convolutions and Transformers

Small Sample Image Segmentation by Coupling Convolutions and Transformers

The association between air pollutant exposure and cerebral small vessel disease imaging markers with modifying effects of PRS-defined genetic susceptibility

Studies have highlighted a possible link between air pollution and cerebral small vessel disease (CSVD) imaging markers. However, the exact association and effects of polygenic risk score (PRS) defined genetic susceptibility remains unclear. This cross-sectional study used data from the UK Biobank. Participants aged 40–69 years were recruited between the year 2006 and 2010. The annual average concentrations of NOX, NO2, PM2.5, PM2.5–10, PM2.5 absorbance, and PM10, were estimated, and joint exposure to multiple air pollutants was reflected in the air pollution index (APEX). Air pollutant exposure was classified into the low (T1), intermediate (T2), and high (T3) tertiles. Three CSVD markers were used: white matter hyper-intensity (WMH), mean diffusivity (MD), and fractional anisotropy (FA). The first principal components of the MD and FA measures in the 48 white matter tracts were analysed. The sample consisted of 44,470 participants from the UK Biobank. The median (T1–T3) concentrations of pollutants were as follows: NO2, 25.5 (22.4–28.7) μg/m3; NOx, 41.3 (36.2–46.7) μg/m3; PM10, 15.9 (15.4–16.4) μg/m3; PM2.5, 9.9 (9.5–10.3) μg/m3; PM2.5 absorbance, 1.1 (1.0–1.2) per metre; and PM2.5–10, 6.1 (5.9–6.3) μg/m3. Compared with the low group, the high group’s APEX, NOX, and PM2.5 levels were associated with increased WMH volumes, and the estimates (95 %CI) were 0.024 (0.003, 0.044), 0.030 (0.010, 0.050), and 0.032 (0.011, 0.053), respectively, after adjusting for potential confounders. APEX, PM10, PM2.5 absorbance, and PM2.5–10 exposure in the high group were associated with increased FA values compared to that in the low group. Sex-specific analyses revealed associations only in females. Regarding the combined associations of air pollutant exposure and PRS-defined genetic susceptibility with CSVD markers, the associations of NO2, NOX, PM2.5, and PM2.5–10 with WMH were more profound in females with low PRS-defined genetic susceptibility, and the associations of PM10, PM2.5, and PM2.5 absorbance with FA were more profound in females with higher PRS-defined genetic susceptibility. Our study demonstrated that air pollutant exposure may be associated with CSVD imaging markers, with females being more susceptible, and that PRS-defined genetic susceptibility may modify the associations of air pollutants.

Raman micro-spectroscopy reveals the spatial distribution of fumarate in cells and tissues

Aberrantly accumulated metabolites elicit intra- and inter-cellular pro-oncogenic cascades, yet current measurement methods require sample perturbation/disruption and lack spatio-temporal resolution, limiting our ability to fully characterize their function and distribution. Here, we show that Raman spectroscopy (RS) can directly detect fumarate in living cells in vivo and animal tissues ex vivo, and that RS can distinguish between Fumarate hydratase (Fh1)-deficient and Fh1-proficient cells based on fumarate concentration. Moreover, RS reveals the spatial compartmentalization of fumarate within cellular organelles in Fh1-deficient cells: consistent with disruptive methods, we observe the highest fumarate concentration (37 ± 19 mM) in mitochondria, where the TCA cycle operates, followed by the cytoplasm (24 ± 13 mM) and then the nucleus (9 ± 6 mM). Finally, we apply RS to tissues from an inducible mouse model of FH loss in the kidney, demonstrating RS can classify FH status. These results suggest RS could be adopted as a valuable tool for small molecule metabolic imaging, enabling in situ non-destructive evaluation of fumarate compartmentalization.

Clinical boundary conditions for propagation-based X-ray phase contrast imaging: from bio-sample models targeting to clinical applications.

Typical propagation-based X-ray phase contrast imaging (PB-PCI) experiments using polyenergetic sources are tested in very ideal conditions: low-energy spectrum (mainly characteristic X-rays), small thickness and homogeneous materials considered weakly absorbing objects, large object-to-detector distance, long exposure times and non-clinical detector. Explore PB-PCI features using boundary conditions imposed by a low power polychromatic X-ray source (X-ray spectrum without characteristic X-rays), thick and heterogenous materials and a small area imaging detector with high low-detection radiation threshold, elements commonly found in a clinical scenario. A PB-PCI setup implemented using a microfocus X-ray source and a dental imaging detector was characterized in terms of different spectra and geometric parameters on the acquired images. Test phantoms containing fibers and homogeneous materials with close attenuation characteristics and animal bone and mixed soft tissues (bio-sample models) were analyzed. Contrast to Noise Ratio (CNR), system spatial resolution and Kerma values were obtained for all images. Phase contrast images showed CNR up to 15% higher than conventional contact images. Moreover, it is better seen when large magnifications (>3) and object-to-detector distances (>13 cm) were used. The influence of the spectrum was not appreciable due to the low efficiency of the detector (thin scintillator screen) at high energies. Despite the clinical boundary condition used in this work, regarding the X-ray spectrum, thick samples, and detection system, it was possible to acquire phase contrast images of biological samples.

Dual-source dual-energy CT and deep learning for equivocal lymph nodes on CT images for thyroid cancer.

This study investigated the diagnostic performance of dual-energy computed tomography (CT) and deep learning for the preoperative classification of equivocal lymph nodes (LNs) on CT images in thyroid cancer patients. In this prospective study, from October 2020 to March 2021, 375 patients with thyroid disease underwent thin-section dual-energy thyroid CT at a small field of view (FOV) and thyroid surgery. The data of 183 patients with 281 LNs were analyzed. The targeted LNs were negative or equivocal on small FOV CT images. Six deep-learning models were used to classify the LNs on conventional CT images. The performance of all models was compared with pathology reports. Of the 281 LNs, 65.5% had a short diameter of less than 4 mm. Multiple quantitative dual-energy CT parameters significantly differed between benign and malignant LNs. Multivariable logistic regression analyses showed that the best combination of parameters had an area under the curve (AUC) of 0.857, with excellent consistency and discrimination, and its diagnostic accuracy and sensitivity were 74.4% and 84.2%, respectively (p < 0.001). The visual geometry group 16 (VGG16) based model achieved the best accuracy (86%) and sensitivity (88%) in differentiating between benign and malignant LNs, with an AUC of 0.89. The VGG16 model based on small FOV CT images showed better diagnostic accuracy and sensitivity than the spectral parameter model. Our study presents a noninvasive and convenient imaging biomarker to predict malignant LNs without suspicious CT features in thyroid cancer patients. Our study presents a deep-learning-based model to predict malignant lymph nodes in thyroid cancer without suspicious features on conventional CT images, which shows better diagnostic accuracy and sensitivity than the regression model based on spectral parameters. Many cervical lymph nodes (LNs) do not express suspicious features on conventional computed tomography (CT). Dual-energy CT parameters can distinguish between benign and malignant LNs. Visual geometry group 16 model shows superior diagnostic accuracy and sensitivity for malignant LNs.

Automatic classification of normal and abnormal cell division using deep learning

In recent years, there has been a surge in the development of methods for cell segmentation and tracking, with initiatives like the Cell Tracking Challenge driving progress in the field. Most studies focus on regular cell population videos in which cells are segmented and followed, and parental relationships annotated. However, DNA damage induced by genotoxic drugs or ionizing radiation produces additional abnormal events since it leads to behaviors like abnormal cell divisions (resulting in a number of daughters different from two) and cell death. With this in mind, we developed an automatic mitosis classifier to categorize small mitosis image sequences centered around one cell as “Normal” or “Abnormal.” These mitosis sequences were extracted from videos of cell populations exposed to varying levels of radiation that affect the cell cycle’s development. We explored several deep-learning architectures and found that a network with a ResNet50 backbone and including a Long Short-Term Memory (LSTM) layer produced the best results (mean F1-score: 0.93 ± 0.06). In the future, we plan to integrate this classifier with cell segmentation and tracking to build phylogenetic trees of the population after genomic stress.

Sex differences in asthma control, lung function and exacerbations: the ATLANTIS study

BackgroundAsthma is a heterogeneous disease with a prevalence and severity that differs between male and female patients.QuestionWhat are differences between male and female patients with asthma with regard to asthma...

Visual Communication Design of Weak and Small Target Images Based on Image Processing Model and Data Fusion

Visual Communication Design of Weak and Small Target Images Based on Image Processing Model and Data Fusion

Poster Design Research Based on Deep Learning Automatic Image Generation Algorithm

Although this research has made significant progress in image generation models, they still face issues such as insufficient diversity of generated images, poor quality of high-resolution images, and the need for a large amount of training data for model optimization. This paper studies poster design based on deep learning automatic image generation algorithm, using a recursive supervised image generation algorithm framework of generative adversarial networks for multi-view image generation and super-resolution generation tasks of small sample digital poster images. Various improvements have been proposed to enhance the performance of the GAN network model for poster design image generation tasks. Based on experimental research, this paper’s model uses generative adversarial networks to distinguish randomly cropped low resolution and high-resolution poster blocks, ensuring that high-resolution posters maintain their original resolution canvas texture and brush strokes, effectively improving the automatic generation effect of poster images. The evaluation results show that the quantitative evaluation of the proposed algorithm model in knowledge management is distributed in a reasonable range, which indicates that the proposed algorithm model has good performance in knowledge management. The poster design model based on deep learning automatic image generation algorithm proposed in this paper has certain effects. In subsequent practice, the automatic image generation algorithm can be combined with practical needs to improve the efficiency and design effect of poster design.

Impacted maxillary canine: Assessment of prevalence, severity and location of root resorption on maxillary incisors: A retrospective CBCT study

The maxillary permanent canine is one of the most frequently impacted teeth, which often requires multidisciplinary management. A common complication of canine impaction is root resorption of the adjacent dentition. The aim of this retrospective study was to report the prevalence of root resorption of maxillary incisors adjacent to impacted maxillary canines from small volume CBCT images by trained clinicians. A secondary objective was to report the location and severity of root resorption. CBCT images of patients with impacted maxillary canines (unilateral and bilateral) who attended a joint orthodontic/surgical multidisciplinary clinic were screened. Descriptive statistics were used to investigate associations of patient characteristics and presence of root resorption. Generalized estimating equations (GEE) logistic regression model were used to identify predictors of root resorption. In all, 148 impacted maxillary canines (122 patients) were analysed. The majority of patients were under 18 years of age (71.6%) with impacted canines present in more females (68.2%) than males (31.8%). Maxillary lateral incisors showed the highest prevalence of root resorption (38.5%). The apical region was the most common location of resorption for lateral incisors (20.9%) with a variable degree of severity evident: slight (10.1%), moderate (15.6%), and severe (12.8%). Although no significant predictors of root resorption were identified, a weak association was evident for age and root development. In this cohort of patients, the roots of maxillary lateral incisors are most likely to suffer from root resorption in the presence of an impacted maxillary canine. Clinicians should consider the extent, location and severity of resorption of adjacent teeth when planning treatment decisions and mechanics in cases of impacted maxillary canines.

Classification of Ground‐Based Auroral Images by Learning Deep Tensor Feature Representation on Riemannian Manifold

AbstractAutomatically classifying a huge amount of ground‐based auroral images is essential to facilitate aurora morphology statistical research and aid in comprehending the magnetospheric dynamics. However, facing the challenge of insufficient labeled images, deep learning methods perform suboptimally on small auroral image data sets, and traditional machine learning methods based on handcrafted features heavily rely on expert knowledge. In this paper, we propose a novel method that leverages the merits of both traditional machine learning and deep learning methods by extracting deep second‐order tensor features to train a support vector machine (SVM). To improve compactness and discriminative ability of the features, we comply the intrinsic data geometry on Riemannian manifold to employ dimensionality reduction and map the dimensionality‐reduced features from Riemannian space to Euclidean space for the SVM classifier. Experimental results on small aurora data sets conclusively demonstrate the effectiveness of our method, exhibiting competitive performance with recent aurora classification methods.

Fast Nano-IR Hyperspectral Imaging Empowered by Large-Dataset-Free Miniaturized Spatial-Spectral Network.

The emerging field of nanoscale infrared (nano-IR) offers label-free molecular contrast, yet its imaging speed is limited by point-by-point traverse acquisition of a three-dimensional (3D) data cube. Here, we develop a spatial-spectral network (SS-Net), a miniaturized deep-learning model, together with compressive sampling to accelerate the nano-IR imaging. The compressive sampling is performed in both the spatial and spectral domains to accelerate the imaging process. The SS-Net is trained to learn the mapping from small nano-IR image patches to the corresponding spectra. With this elaborated mapping strategy, the training can be finished quickly within several minutes using the subsampled data, eliminating the need for a large-labeled dataset of common deep learning methods. We also designed an efficient loss function, which incorporates the image and spectral similarity to enhance the training. We first validate the SS-Net on an open stimulated Raman-scattering dataset; the results exhibit the potential of 10-fold imaging speed improvement with state-of-the-art performance. We then demonstrate the versatility of this approach on atomic force microscopy infrared (AFM-IR) microscopy with 7-fold imaging speed improvement, even on nanoscale Fourier transform infrared (nano-FTIR) microscopy with up to 261.6 folds faster imaging speed. We further showcase the generalization of this method on AFM-force volume-based multiparametric nanoimaging. This method establishes a paradigm for rapid nano-IR imaging, opening new possibilities for cutting-edge research in materials, photonics, and beyond.

Classification of Dermoscopic Images Using CNN-SVM

Traditional machine learning methods like GLCM and ABCD rules have long been employed for image classification tasks. However, they come with inherent limitations, primarily the need for manual feature extraction. This manual feature extraction process is time-consuming and relies on expert domain knowledge, making it challenging for non-experts to use effectively. Deep learning methods, specifically Convolutional Neural Networks (CNN), have revolutionized image classification by automating the feature extraction. CNNs can learn hierarchical features directly from the raw pixel values, eliminating the need for manual feature engineering. Despite their powerful capabilities, CNNs have limitations, mainly when working with small image datasets. They may overfit the data or struggle to generalize effectively. In light of these considerations, this study adopts a hybrid approach that leverages the strengths of both deep learning and traditional machine learning. CNNs are automatic feature extractors, allowing the model to capture meaningful image patterns. These extracted features are then fed into a Support Vector Machine (SVM) classifier, known for its efficiency and effectiveness in handling small datasets. The results of this study are encouraging, with an accuracy of 0.94 and an AUC score of 0.94. Notably, these metrics outperform Abbas' previous research by a significant margin, underscoring the effectiveness of the hybrid CNN-SVM approach. This research reinforces that SVM classifiers are well-suited for tasks involving limited image data, yielding improved classification accuracy and highlighting the potential for broader applications in image analysis.

Matrix-assisted laser desorption/ionization matrix incorporation evaluation algorithm for improved peak coverage and signal-to-noise ratio in mass spectrometry imaging.

Despite decades of implementation, the selection of optimal sample preparation conditions for matrix-assisted laser desorption/ionization (MALDI) imaging is still ambiguous due to the lack of a universal and comprehensive evaluation methodology. Thus, numerous experiments with different matrix application conditions accompany a translation of the method to novel sample types and matrices. Mouse brain tissues were covered with 9-aminoacridine through sublimation, followed by recrystallization in vapors of 5% (v/v) methanol solution in water. The samples were analyzed by MALDI time-of-flight mass spectrometry, and the efficiency of lipid and small-molecule ionization was evaluated with different metrics. We first investigate the dependency of matrix density and recrystallization conditions on the thickness of an analyte-empty matrix layer to roughly evaluate the laser shot number required to obtain an intense signal with minimal noise. Then, we introduce metrics for the analysis of small imaging datasets (small sample regions) of model samples based on median quantity of peaks in spectra (medQP) and weighted median signal-to-noise ratio (wmSNR). The evaluation of small regions and taking median values for metrics help overcome the sample heterogeneity and allow for the simultaneous comparison of different acquisition parameters. Here, we propose a methodology based on gradual laser ablation of small regions of sample and further implementation of weighted signal-to-noise ratio to assess various matrix application conditions. The proposed approach helps reduce the number of test samples required to determine optimal sample preparation conditions and improve the overall quality of images.

Augmenting X-ray micro-CT data with MICP data for high resolution pore-scale simulations of flow properties of carbonate rocks

Pore-scale modeling is essential in understanding and predicting flow and transport properties of rocks. Generally, pore-scale modeling is dependent on imaging technologies such as Micro Computed Tomography (micro-CT), which provides visual confirmation into the pore microstructures of rocks at a representative scale. However, this technique is limited in the ability to provide high resolution images showing the pore-throats connecting pore bodies. Pore scale simulations of flow and transport properties of rocks are generally done on a single 3D pore microstructure image. As such, the simulated properties are only representative of the simulated pore-scale rock volume. These are the technological and computational limitations which we address here by using a stochastic pore-scale simulation approach. This approach consists of constructing hundreds of 3D pore microstructures of the same pore size distribution and overall porosity but different pore connectivity. The construction of the 3D pore microstructures incorporates the use of Mercury Injection Capillary Pressure (MICP) data to account for pore throat size distribution, and micro-CT images to account for pore body size distribution. The approach requires a small micro-CT image volume (7–19 mm3) to reveal key pore microstructural features that control flow and transport properties of highly heterogeneous rocks at the core-scale. Four carbonate rock samples were used to test the proposed approach. Permeability calculations from the introduced approach were validated by comparing laboratory measured permeability of rock cores and permeability estimated using five well-known core-scale empirical model equations. The results show that accounting for the stochastic connectivity of pores results in a probabilistic distribution of flow properties which can be used to upscale pore-scale simulated flow properties to the core-scale. The use of the introduced stochastic pore-scale simulation approach is more beneficial when there is a higher degree of heterogeneity in pore size distribution. This is shown to be the case with permeability and hydraulic tortuosity which are key controls of flow and transport processes in rocks.