Explore the vast range of titles available.

Biomedical photoacoustic tomography, which can provide high-resolution 3D soft tissue images based on optical absorption, has advanced to the stage at which translation from the laboratory to clinical settings is becoming possible. The need for rapid image formation and the practical restrictions on data acquisition that arise from the constraints of a clinical workflow are presenting new image reconstruction challenges. There are many classical approaches to image reconstruction, but ameliorating the effects of incomplete or imperfect data through the incorporation of accurate priors is challenging and leads to slow algorithms. Recently, the application of deep learning (DL), or deep neural networks, to this problem has received a great deal of attention. We review the literature on learned image reconstruction, summarizing the current trends and explain how these approaches fit within, and to some extent have arisen from, a framework that encompasses classical reconstruction methods. In particular, it shows how these techniques can be understood from a Bayesian perspective, providing useful insights. We also provide a concise tutorial demonstration of three prototypical approaches to learned image reconstruction. The code and data sets for these demonstrations are available to researchers. It is anticipated that it is in in vivo applications—where data may be sparse, fast imaging critical, and priors difficult to construct by hand—that DL will have the most impact. With this in mind, we conclude with some indications of possible future research directions.

Multispectral images (MSIs) are valuable for precision agriculture due to the extra spectral information acquired compared to natural color RGB (ncRGB) images. In this paper, we thus aim to generate high spatial MSIs through a robust, deep-learning-based reconstruction method using ncRGB images. Using the data from the agronomic research trial for maize and breeding research trial for rice, we first reproduced ncRGB images from MSIs through a rendering model, Model-True to natural color image (Model-TN), which was built using a benchmark hyperspectral image dataset. Subsequently, an MSI reconstruction model, Model-Natural color to Multispectral image (Model-NM), was trained based on prepared ncRGB (ncRGB-Con) images and MSI pairs, ensuring the model can use widely available ncRGB images as input. The integrated loss function of mean relative absolute error (MRAEloss) and spectral information divergence (SIDloss) were most effective during the building of both models, while models using the MRAEloss function were more robust towards variability between growing seasons and species. The reliability of the reconstructed MSIs was demonstrated by high coefficients of determination compared to ground truth values, using the Normalized Difference Vegetation Index (NDVI) as an example. The advantages of using “reconstructed” NDVI over Triangular Greenness Index (TGI), as calculated directly from RGB images, were illustrated by their higher capabilities in differentiating three levels of irrigation treatments on maize plants. This study emphasizes that the performance of MSI reconstruction models could benefit from an optimized loss function and the intermediate step of ncRGB image preparation. The ability of the developed models to reconstruct high-quality MSIs from low-cost ncRGB images will, in particular, promote the application for plant phenotyping in precision agriculture.

Hyperspectral imaging (HSI) has recently emerged as a promising tool for various agricultural applications. However, high equipment cost, instrumentation complexity, and data-intensive nature have limited its widespread adoption. To overcome these challenges, reconstructing hyperspectral data from simple, cost-effective color or RGB (red-green-blue) images using advanced deep learning algorithms offers a practically attractive solution for a wide range of applications in food quality control and assurance. Through advanced deep learning algorithms, it is possible to capture and reconstruct spectral information from simple, cost-effective RGB imaging to create a reliable, efficient, and scalable system with accuracy comparable to dedicated, expensive HSI systems. This review provides a comprehensive overview of recent advances in deep learning techniques for HSI reconstruction and highlights the transformative impact of deep learning-based hyperspectral image reconstruction on agricultural and food products and anticipates a future where these innovations will lead to more advanced and widespread applications in the agri-food industry.

Purpose To compare the image quality of brain computed tomography (CT) images reconstructed with deep learning–based image reconstruction (DLIR) and adaptive statistical iterative reconstruction-Veo (ASIR-V). Methods Sixty-two patients underwent routine noncontrast brain CT scans and datasets were reconstructed with 30% ASIR-V and DLIR with three selectable reconstruction strength levels (low, medium, high). Objective parameters including CT attenuation, noise, noise reduction rate, artifact index of the posterior cranial fossa, and contrast-to-noise ratio (CNR) were measured at the levels of the centrum semiovale and basal ganglia. Subjective parameters including gray matter-white matter differentiation, sharpness, and overall diagnostic quality were also assessed and compared with the interobserver agreement. Results There was a gradual reduction in the image noise and artifact index of the posterior cranial fossa as the strength levels of DLIR increased (all P  < 0.001) compared with that of ASIR-V. CNR in both the centrum semiovale and basal ganglia levels also improved from the low to high strength levels of DLIR compared with that of ASIR-V (all P  < 0.001). DLIR images with medium and high strength levels demonstrated the best subjective image quality scores among the reconstruction datasets. There was moderate to good interobserver agreement for the subjective image quality assessments with ASIR-V and DLIR. Conclusion On routine brain CT scans, optimized protocols with DLIR allowed significant reduction of noise and artifacts with improved subjective image quality compared with ASIR-V.

PurposeTo evaluate the usefulness of the deep learning image reconstruction (DLIR) to enhance the image quality of abdominal CT, compared to iterative reconstruction technique.MethodPre and post-contrast abdominal CT images in 50 patients were reconstructed with 2 different algorithms: hybrid iterative reconstruction (hybrid IR: ASiR-V 50%) and DLIR (TrueFidelity). Standard deviation of attenuation in normal liver parenchyma was measured as the image noise on pre and post-contrast CT. The contrast-to-noise ratio (CNR) for the aorta, and the signal-to-noise ratio (SNR) of the liver were calculated on post-contrast CT. The overall image quality was graded on a 5-point scale ranging from 1 (poor) to 5 (excellent).ResultsThe image noise was significantly decreased by DLIR compared to hybrid-IR [hybrid IR, median 8.3 Hounsfield unit (HU) (interquartile range (IQR) 7.6–9.2 HU); DLIR, median 5.2 HU (IQR 4.6–5.8), P < 0.0001 for post-contrast CT]. The CNR and SNR were significantly improved by DLIR [CNR, median 4.5 (IQR 3.8–5.6) vs 7.3 (IQR 6.2–8.8), P < 0.0001; SNR, median 9.4 (IQR 8.3–10.1) vs 15.0 (IQR 13.2–16.4), P < 0.0001]. The overall image quality score was also higher for DLIR compared to hybrid-IR (hybrid IR 3.1 ± 0.6 vs DLIR 4.6 ± 0.5, P < 0.0001 for post-contrast CT).ConclusionsImage noise, overall image quality, CNR and SNR for abdominal CT images are improved with DLIR compared to hybrid IR.

Super-resolution structured illumination microscopy (SR-SIM) is an outstanding method for visualizing the subcellular dynamics in living cells. To date, by using elaborately designed systems and algorithms, SR-SIM can achieve rapid, optically sectioned, SR observation with hundreds to thousands of time points. However, real-time observation is still out of reach for most SIM setups as conventional algorithms for image reconstruction involve a heavy computing burden. To address this limitation, an accelerated reconstruction algorithm was developed by implementing a simplified workflow for SR-SIM, termed joint space and frequency reconstruction. This algorithm results in an 80-fold improvement in reconstruction speed relative to the widely used Wiener-SIM. Critically, the increased processing speed does not come at the expense of spatial resolution or sectioning capability, as demonstrated by live imaging of microtubule dynamics and mitochondrial tubulation.

Diffuse optical tomography (DOT) is a promising noninvasive imaging modality and is capable of providing functional characteristics of biological tissue by quantifying optical parameters. The DOT image reconstruction is ill-posed and ill-conditioned, due to the highly diffusive nature of light propagation in biological tissues and limited boundary measurements. The widely used regularization technique for DOT image reconstruction is Tikhonov regularization, which tends to yield oversmoothed and low-quality images containing severe artifacts. It is necessary to accurately choose a regularization parameter for Tikhonov regularization. To overcome these limitations, we develop a noniterative reconstruction method, whereby optical properties are recovered based on a back-propagation neural network (BPNN). We train the parameters of BPNN before DOT image reconstruction based on a set of training data. DOT image reconstruction is achieved by implementing a single evaluation of the trained network. To demonstrate the performance of the proposed algorithm, we compare with the conventional Tikhonov regularization-based reconstruction method. The experimental results demonstrate that image quality and quantitative accuracy of reconstructed optical properties are significantly improved with the proposed algorithm.

Most camera images are saved as 8-bit standard RGB (sRGB) compressed JPEGs. Even when JPEG compression is set to its highest quality, the encoded sRGB image has been significantly processed in terms of color and tone manipulation. This makes sRGB–JPEG images undesirable for many computer vision tasks that assume a direct relationship between pixel values and incoming light. For such applications, the RAW image format is preferred, as RAW represents a minimally processed, sensor-specific RGB image that is linear with respect to scene radiance. The drawback with RAW images, however, is that they require large amounts of storage and are not well-supported by many imaging applications. To address this issue, we present a method to encode the necessary data within an sRGB–JPEG image to reconstruct a high-quality RAW image. Our approach requires no calibration of the camera’s colorimetric properties and can reconstruct the original RAW to within 0.5% error with a small memory overhead for the additional data (e.g., 128 KB). More importantly, our output is a fully self-contained 100% compliant sRGB–JPEG file that can be used as-is, not affecting any existing image workflow—the RAW image data can be extracted when needed, or ignored otherwise. We detail our approach and show its effectiveness against competing strategies.

The neuroanatomical architecture is considered to be the basis for understanding brain function and dysfunction. However, existing imaging tools have limitations for brainwide mapping of neural circuits at a mesoscale level. We developed a micro-optical sectioning tomography (MOST) system that can provide micrometer-scale tomography of a centimeter-sized whole mouse brain. Using MOST, we obtained a three-dimensional structural data set of a Golgi-stained whole mouse brain at the neurite level. The morphology and spatial locations of neurons and traces of neurites could be clearly distinguished. We found that neighboring Purkinje cells stick to each other.

Hyperspectral imaging has many applications. However, the high device costs and low hyperspectral image resolution are major obstacles limiting its wider application in agriculture and other fields. Hyperspectral image reconstruction from a single RGB image fully addresses these two problems. The robust HSCNN-R model with mean relative absolute error loss function and evaluated by the Mean Relative Absolute Error metric was selected through permutation tests from models with combinations of loss functions and evaluation metrics, using tomato as a case study. Hyperspectral images were subsequently reconstructed from single tomato RGB images taken by a smartphone camera. The reconstructed images were used to predict tomato quality properties such as the ratio of soluble solid content to total titratable acidity and normalized anthocyanin index. Both predicted parameters showed very good agreement with corresponding “ground truth” values and high significance in an F test. This study showed the suitability of hyperspectral image reconstruction from single RGB images for fruit quality control purposes, underpinning the potential of the technology—recovering hyperspectral properties in high resolution—for real-world, real time monitoring applications in agriculture any beyond.