Large‐depth‐of‐field full‐field optical angiography

A large‐depth‐of‐field full‐field optical angiography (LD‐FFOA) method is developed to expand the depth‐of‐field (DOF) using a contrast pyramid fusion algorithm (CPFA). The absorption intensity fluctuation modulation effect is utilized to obtain full‐field optical angiography (FFOA) images at different focus positions. The CPFA is used to process these FFOA images with different focuses. By selecting high‐contrast areas, the CPFA can highlight the characteristics and details of blood vessels to obtain LD‐FFOA images. In the optimal case of the proposed method, the DOF for FFOA is more than tripled using 10 differently focused FFOA images. Both the phantom and animal experimental results show that the LD‐FFOA resolves FFOA defocusing issues induced by surface and thickness inhomogeneities in biological samples. The proposed method can be potentially applied to practical biological experiments.      

Grayscale representation of infrared microscopy images by extended multiplicative signal correction for registration with histological images

Fourier‐transform infrared (FTIR) microspectroscopy is rounding the corner to become a label‐free routine method for cancer diagnosis. In order to build infrared‐spectral based classifiers, infrared images need to be registered with Hematoxylin and Eosin (H&E) stained histological images. While FTIR images have a deep spectral domain with thousands of channels carrying chemical and scatter information, the H&E images have only three color channels for each pixel and carry mainly morphological information. Therefore, image representations of infrared images are needed that match the morphological information in H&E images. In this paper, we propose a novel approach for representation of FTIR images based on extended multiplicative signal correction highlighting morphological features that showed to correlate well with morphological information in H&E images. Based on the obtained representations, we developed a strategy for global‐to‐local image registration for FTIR images and H&E stained histological images of parallel tissue sections.     

Dye free automated cell counting and analysis

We have developed an automated cell counting method that uses images obtained at multiple focal heights to enumerate cells in confluent culture. By taking the derivative of image intensity with respect to focal height using two complementary images, we are able to count high‐density monolayers of cells over a large image area. Our method resists errors arising from variability in the focal plane caused by flatness or tilt non‐uniformities with a minimal amount of focal plane alignment, allowing the automated collection of images across a large area. Biotechnol. Bioeng. © 2013 Wiley Periodicals, Inc.     

Kite aerial photography: a low‐cost method for monitoring seabird colonies

Obtaining aerial high‐resolution images of bird nesting colonies using remote‐sensing technology such as satellite‐based remote sensing, manned aircraft, or Unmanned Aerial Vehicles might not be possible for many researchers due to financial constraints. Kite Aerial Photography (KAP) provides a possible low‐cost alternative. We collected digital images of ground‐nesting seabirds (i.e., cormorants and penguins) in two different ecosystems using a kite‐based platform equipped with consumer‐grade digital cameras with time‐lapse capability to obtain estimates of breeding population size. KAP proved to be an efficient method for acquiring high‐resolution aerial images. We obtained images of colonies of seabirds ranging in size from hundreds to several hundreds of thousands breeding pairs during flights lasting from a few minutes up to three hours, from flat to very steep areas, and in contrasted wind conditions (from 0.5 to 6 Beaufort force). KAP is an efficient low‐cost method for acquiring high‐resolution aerial images and an alternative to ground‐based censuses, especially useful in rugged areas.     

Digital photography provides a fast,reliable, and noninvasive method to estimate anthocyanin pigment concentration in reproductive and vegetative plant tissues

Anthocyanin pigments have become a model trait for evolutionary ecology as they often provide adaptive benefits for plants. Anthocyanins have been traditionally quantified biochemically or more recently using spectral reflectance. However, both methods require destructive sampling and can be labor intensive and challenging with small samples. Recent advances in digital photography and image processing make it the method of choice for measuring color in the wild. Here, we use digital images as a quick, noninvasive method to estimate relative anthocyanin concentrations in species exhibiting color variation. Using a consumer‐level digital camera and a free image processing toolbox, we extracted RGB values from digital images to generate color indices. We tested petals, stems, pedicels, and calyces of six species, which contain different types of anthocyanin pigments and exhibit different pigmentation patterns. Color indices were assessed by their correlation to biochemically determined anthocyanin concentrations. For comparison, we also calculated color indices from spectral reflectance and tested the correlation with anthocyanin concentration. Indices perform differently depending on the nature of the color variation. For both digital images and spectral reflectance, the most accurate estimates of anthocyanin concentration emerge from anthocyanin content‐chroma ratio, anthocyanin content‐chroma basic, and strength of green indices. Color indices derived from both digital images and spectral reflectance strongly correlate with biochemically determined anthocyanin concentration; however, the estimates from digital images performed better than spectral reflectance in terms of r² and normalized root‐mean‐square error. This was particularly noticeable in a species with striped petals, but in the case of striped calyces, both methods showed a comparable relationship with anthocyanin concentration. Using digital images brings new opportunities to accurately quantify the anthocyanin concentrations in both floral and vegetative tissues. This method is efficient, completely noninvasive, applicable to both uniform and patterned color, and works with samples of any size.     

The use of digital images to evaluate the interobserver agreement on cervical smear readings in Italian cervical cancer screening

G. Tinacci, A. Biggeri, A. Pellegrini, M.P. Cariaggi, M.L. Schiboni and M. Confortini The use of digital images to evaluate the interobserver agreement on cervical smear readings in Italian cervical cancer screening Objective: The aim of this study was to measure interobserver agreement among cytologists on using a set of digital images. Methods: A set of 90 selected Papanicolaou‐stained cervical smears were digitalized and the digital images circulated among 117 readers, from laboratories spread across almost all Italian regions. Three representative fields of each smear were displayed at 20× and 40× magnification (overall six images for each case). The diagnoses made by the cytologists who provided the images were taken as target diagnoses. Results: The κ values were: very low for the categories atypical squamous cells of undetermined significance (ASC‐US), and atypical squamous cells – cannot exclude high‐grade squamous intraepithelial lesion (ASC‐H); poor for the categories atypical glandular cells (AGC), high‐grade squamous intraepithelial lesion (HSIL) and invasive cancer; and fair to good for the categories negative and low‐grade squamous intraepithelial lesion (LSIL). However, we found a cluster of 42 best concordant readers. The overall κ value and overall weighted κ with the target diagnosis for these 42 readers were 0.45 and 0.66, respectively. This finding is in contrast with the overall κ value and overall weighted κ for the other readers of 0.39 and 0.59, respectively. Conclusions: As this finding is an estimate of the accuracy of the readers, we can infer that it will be very important to reach this level of concordance for all the participating readers. Future effort will facilitate common experiences in order to improve the reproducibility of diagnostic criteria. Digital images could be the key to reach this aim.     

Deconvolution of images from 3D printed cells in layers on a chip

Layer‐by‐layer cell printing is useful in mimicking layered tissue structures inside the human body and has great potential for being a promising tool in the field of tissue engineering, regenerative medicine, and drug discovery. However, imaging human cells cultured in multiple hydrogel layers in 3D‐printed tissue constructs is challenging as the cells are not in a single focal plane. Although confocal microscopy could be a potential solution for this issue, it compromises the throughput which is a key factor in rapidly screening drug efficacy and toxicity in pharmaceutical industries. With epifluorescence microscopy, the throughput can be maintained at a cost of blurred cell images from printed tissue constructs. To rapidly acquire in‐focus cell images from bioprinted tissues using an epifluorescence microscope, we created two layers of Hep3B human hepatoma cells by printing green and red fluorescently labeled Hep3B cells encapsulated in two alginate layers in a microwell chip. In‐focus fluorescent cell images were obtained in high throughput using an automated epifluorescence microscopy coupled with image analysis algorithms, including three deconvolution methods in combination with three kernel estimation methods, generating a total of nine deconvolution paths. As a result, a combination of Inter‐Level Intra‐Level Deconvolution (ILILD) algorithm and Richardson‐Lucy (RL) kernel estimation proved to be highly useful in bringing out‐of‐focus cell images into focus, thus rapidly yielding more sensitive and accurate fluorescence reading from the cells in different layers. © 2017 American Institute of Chemical Engineers Biotechnol. Prog., 34:445–454, 2018     

Automated identification of live moths (Macrolepidoptera) using digital automated identification System (DAISY)

Two hundred and thirty‐seven species of Macrolepidoptera were light trapped at Treborth Botanical Garden, Gwynedd, UK. Live adults were digitally imaged using a simple, inexpensive method suitable for field use, then released. Inconsistent lighting, variation in resting posture and inclusion of worn individuals produced image sets high in intraspecific variation. Thirty‐five common species were selected to provide training images for the Digital Automated Identification SYstem (DAISY). Twenty individuals per species were pre‐processed to standardize size and posture and to enhance features. The right forewing of each was highlighted manually and the pattern rendered polar and greyscale for DAISY analysis. Despite poor quality of some images, 83% of unknown species were identified correctly. The best species had 100% correct identification and the worst 35%. The most poorly identified images were those of moths that had lost scales or been unevenly illuminated. The precision with which the forewing was highlighted affected performance. When highlighted carefully, Laothoe populi was identified correctly twice as successfully as when the same image was highlighted poorly. Size of the training set was also important. Sets of 5, 10, 15 and 20 training images, plotted against performance produced a curve of diminishing returns. Colourimages and inclusion of size should improve accuracy.     

Biomedical Image Processing with Containers and Deep Learning: An Automated Analysis Pipeline

Here, a streamlined, scalable, laboratory approach is discussed that enables medium‐to‐large dataset analysis. The presented approach combines data management, artificial intelligence, containerization, cluster orchestration, and quality control in a unified analytic pipeline. The unique combination of these individual building blocks creates a new and powerful analysis approach that can readily be applied to medium‐to‐large datasets by researchers to accelerate the pace of research. The proposed framework is applied to a project that counts the number of plasmonic nanoparticles bound to peripheral blood mononuclear cells in dark‐field microscopy images. By using the techniques presented in this article, the images are automatically processed overnight, without user interaction, streamlining the path from experiment to conclusions.     

Species‐level image classification with convolutional neural network enables insect identification from habitus images

1. Changes in insect biomass, abundance, and diversity are challenging to track at sufficient spatial, temporal, and taxonomic resolution. Camera traps can capture habitus images of ground‐dwelling insects. However, currently sampling involves manually detecting and identifying specimens. Here, we test whether a convolutional neural network (CNN) can classify habitus images of ground beetles to species level, and estimate how correct classification relates to body size, number of species inside genera, and species identity.
2. We created an image database of 65,841 museum specimens comprising 361 carabid beetle species from the British Isles and fine‐tuned the parameters of a pretrained CNN from a training dataset. By summing up class confidence values within genus, tribe, and subfamily and setting a confidence threshold, we trade‐off between classification accuracy, precision, and recall and taxonomic resolution.
3. The CNN classified 51.9% of 19,164 test images correctly to species level and 74.9% to genus level. Average classification recall on species level was 50.7%. Applying a threshold of 0.5 increased the average classification recall to 74.6% at the expense of taxonomic resolution. Higher top value from the output layer and larger sized species were more often classified correctly, as were images of species in genera with few species.
4. Fine‐tuning enabled us to classify images with a high mean recall for the whole test dataset to species or higher taxonomic levels, however, with high variability. This indicates that some species are more difficult to identify because of properties such as their body size or the number of related species.
5. Together, species‐level image classification of arthropods from museum collections and ecological monitoring can substantially increase the amount of occurrence data that can feasibly be collected. These tools thus provide new opportunities in understanding and predicting ecological responses to environmental change.

     

Validation of delay‐multiply‐and‐standard‐deviation weighting factor for improved photoacoustic imaging of sentinel lymph node

Delay‐and‐sum (DAS) is one of the most common algorithms used to construct the photoacoustic images due to its low complexity. However, it results in images with high sidelobes and low resolution. Delay‐and‐standard‐deviation (DASD) weighting factor can improve the contrast of the images compared to DAS. However, it still suffers from high sidelobes. In this work, a new weighting factor, named delay‐multiply‐and‐standard‐deviation (DMASD) is introduced to enhance the contrast of the reconstructed images compared to other mentioned methods. In the proposed method, the SD of the mutual multiplied delayed signals are calculated, normalized and multiplied to DAS beamformed data. The results show that DMASD improves the signal‐to‐noise‐ratio about 19.29 and 7.3 dB compared to DAS and DASD, respectively, for in vivo imaging of the sentinel lymph node. Moreover, the contrast ratio is improved by the DMASD about 23.61 and 10.81 dB compared to DAS and DASD, respectively.      

Performance of a cost‐effective and automated blood counting system for resource‐limited settings operated by trained and untrained users

Current flow‐based blood counting devices require expensive and centralized medical infrastructure and are not appropriate for field use. In this article we report a streamlined, easy‐to‐use method to count red blood cells (RBC), white blood cells (WBC), platelets (PLT) and 3‐part WBC differential through a cost‐effective and automated image‐based blood counting system. The approach consists of using a compact, custom‐built microscope with large field‐of‐view to record bright‐field and fluorescence images of samples that are diluted with a single, stable reagent mixture and counted using automatic algorithms. Sample collection utilizes volume‐controlled capillary tubes, which are then dropped into a premixed, shelf‐stable solution to stain and dilute in a single step. Sample measurement and analysis are fully automated, requiring no input from the user. Cost of the system is minimized through the use of custom‐designed motorized components. We compare the performance of our system, as operated by trained and untrained users, to the clinical gold standard on 120 adult blood samples, demonstrating agreement within Clinical Laboratory Improvement Amendments guidelines, with no statistical difference in performance among different operator groups. The system's cost‐effectiveness, automation and performance indicate that it can be successfully translated for use in low‐resource settings where central hematology laboratories are not accessible.      

Liver tissue classification of en face images by fractal dimension‐based support vector machine

Full‐field optical coherence tomography (FF‐OCT) has been reported with its label‐free subcellular imaging performance. To realize quantitive cancer detection, the support vector machine model of classifying normal and cancerous human liver tissue is proposed with en face tomographic images. Twenty samples (10 normal and 10 cancerous) were operated from humans and composed of 285 en face tomographic images. Six histogram features and one proposed fractal dimension parameter that reveal the refractive index inhomogeneities of tissue were extracted and made up the training set. The other different 16 samples (8 normal and 8 cancerous) were imaged (190 images) and employed as the test set with the same features. First, a subcellular‐resolution tomographic image library for four histopathological areas in liver tissue was established. Second, the area under the receiver operating characteristics of 0.9378, 0.9858, 0.9391, 0.9517 for prediction of the cancerous hepatic cell, central vein, fibrosis, and portal vein were measured with the test set. The results indicate that the proposed classifier from FF‐OCT images shows promise as a label‐free assessment of quantified tumor detection, suggesting the fractal dimension‐based classifier could aid clinicians in detecting tumor boundaries for resection in surgery in the future.     

Noise suppressed,multifocus image fusion for enhanced intraoperative navigation

Current intraoperative imaging systems are typically not able to provide ‘sharp’ images over entire large areas or entire organs. Distinct structures such as tissue margins or groups of malignant cells are therefore often difficult to detect, especially under low signal‐to‐noise‐ratio conditions. In this report, we introduce a noise suppressed multifocus image fusion algorithm, that provides detailed reconstructions even when images are acquired under sub‐optimal conditions, such is the case for real time fluorescence intraoperative surgery. The algorithm makes use of the Anscombe transform combined with a multi‐level stationary wavelet transform with individual threshold‐based shrinkage. While the imaging system is integrated with a respiratory monitor triggering system, it can be easily adapted to any commercial imaging system. The developed algorithm is made available as a plugin for Osirix. (© 2013 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

Improving 2‐DE gel image denoising using contourlets

One of the most commonly used methods for protein separation is 2‐DE. After 2‐DE gel scanning, images with a plethora of spot features emerge that are usually contaminated by inherent noise. The objective of the denoising process is to remove noise to the extent that the true spots are recovered correctly and accurately i.e. without introducing distortions leading to the detection of false‐spot features. In this paper we propose and justify the use of the contourlet transform as a tool for 2‐DE gel images denoising. We compare its effectiveness with state‐of‐the‐art methods such as wavelets‐based multiresolution image analysis and spatial filtering. We show that contourlets not only achieve better average S/N performance than wavelets and spatial filters, but also preserve better spot boundaries and faint spots and alter less the intensities of informative spot features, leading to more accurate spot volume estimation and more reliable spot detection, operations that are essential to differential expression proteomics for biomarkers discovery.     

Rapid acquisition of Raman spectral maps through minimal sampling: applications in tissue imaging

A method is presented for acquiring high‐spatial‐resolution spectral maps, in particular for Raman micro‐spectroscopy (RMS), by selectively sampling the spatial features of interest and interpolating the results. This method achieves up to 30 times reduction in the sampling time compared to raster‐scanning, the resulting images have excellent correlation with conventional histopathological staining, and are achieved with sufficient spectral signal‐to‐noise ratio to identify individual tissue structures. The benefits of this selective sampling method are not limited to tissue imaging however; it is expected that the method may be applied to other techniques which employ point‐by‐point mapping of large substrates. (© 2012 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

Evaluation of oral mucosa collagen condition with cross‐polarization optical coherence tomography

The goal of the research was analysis of the effect of collagen condition in formation of cross‐polarized CP OCT images. We used of the CP OCT technique for studying collagen condition on an example of oral mucosa. Special histologic picrosirius red (PSR) staining of cheek mucosa specimens was used with subsequent assessing of the result of collagen staining in polarized light. High correlation (r = 0.692, p = 0.0001) between OCT signal standard deviation (SD) in cross‐polarized images and brightness of PSR stained collagen fibers in cheek mucosa specimens was demonstrated in patients with inflammatory intestine and oral mucosa diseases. We have found that the OCT signal SD in cross‐polarized images reflects two boundary conditions of collagen disorganization, namely, loss of fiber properties at active inflammation which attenuates the signal and fibrosis that occurs due to synthesis of a new remodeled collagen which amplifies the OCT signal. (© 2013 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

Automated method for the rapid and precise estimation of adherent cell culture characteristics from phase contrast microscopy images

The quantitative determination of key adherent cell culture characteristics such as confluency, morphology, and cell density is necessary for the evaluation of experimental outcomes and to provide a suitable basis for the establishment of robust cell culture protocols. Automated processing of images acquired using phase contrast microscopy (PCM), an imaging modality widely used for the visual inspection of adherent cell cultures, could enable the non‐invasive determination of these characteristics. We present an image‐processing approach that accurately detects cellular objects in PCM images through a combination of local contrast thresholding and post hoc correction of halo artifacts. The method was thoroughly validated using a variety of cell lines, microscope models and imaging conditions, demonstrating consistently high segmentation performance in all cases and very short processing times (<1 s per 1,208 × 960 pixels image). Based on the high segmentation performance, it was possible to precisely determine culture confluency, cell density, and the morphology of cellular objects, demonstrating the wide applicability of our algorithm for typical microscopy image processing pipelines. Furthermore, PCM image segmentation was used to facilitate the interpretation and analysis of fluorescence microscopy data, enabling the determination of temporal and spatial expression patterns of a fluorescent reporter. We created a software toolbox (PHANTAST) that bundles all the algorithms and provides an easy to use graphical user interface. Source‐code for MATLAB and ImageJ is freely available under a permissive open‐source license. Biotechnol. Bioeng. 2014;111: 504–517. © 2013 Wiley Periodicals, Inc.     

Pixel classification method in optical coherence tomography for tumor segmentation and its complementary usage with OCT microangiography

A novel machine‐learning method to distinguish between tumor and normal tissue in optical coherence tomography (OCT) has been developed. Pre‐clinical murine ear model implanted with mouse colon carcinoma CT‐26 was used. Structural‐image‐based feature sets were defined for each pixel and machine learning classifiers were trained using “ground truth” OCT images manually segmented by comparison with histology. The accuracy of the OCT tumor segmentation method was then quantified by comparing with fluorescence imaging of tumors expressing genetically encoded fluorescent protein KillerRed that clearly delineates tumor borders. Because the resultant 3D tumor/normal structural maps are inherently co‐registered with OCT derived maps of tissue microvasculature, the latter can be color coded as belonging to either tumor or normal tissue. Applications to radiomics‐based multimodal OCT analysis are envisioned.      

Conditional generative adversarial networks to generate pseudo low monoenergetic CT image from a single-tube voltage CT scanner

PurposeTo generate pseudo low monoenergetic CT images of the abdomen from 120-kVp CT images with cGAN.Materials and MethodsWe retrospectively included 48 patients who underwent contrast-enhanced abdominal CT using dual-energy CT. We reconstructed paired data sets of 120 kVp CT images and virtual low monoenergetic (55-keV) CT images. cGAN was prepared to generate pseudo 55-keV CT images from 120-kVp CT images. The pseudo 55 keV CT images in epoch 10, 50, 100, and 500 were compared to the 55 keV images generated using peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM).ResultsThe PSNRs were 28.0, 28.5, 28.6, and 28.8 at epochs 10, 50, 100, and 500, respectively. The SSIM was approximately constant from epochs 50 to 500.ConclusionPseudo low monoenergetic abdominal CT images were generated from 120-kVp CT images using cGAN, and the images had good quality similar to that of monochromatic images obtained with DECT software.