Simple Image Research Articles

Magnetic resonance imaging-based prediction models for differentiating intraspinal schwannomas from meningiomas: classification and regression tree and random forest analysis.

Due to the variations in surgical approaches and prognosis between intraspinal schwannomas and meningiomas, it is crucial to accurately differentiate between the two prior to surgery. Currently, there is limited research exploring the implementation of machine learning (ML) methods for distinguishing between these two types of tumors. This study aimed to establish a classification and regression tree (CART) model and a random forest (RF) model for distinguishing schwannomas from meningiomas. We retrospectively collected 88 schwannomas (52 males and 36 females) and 51 meningiomas (10 males and 41 females) who underwent magnetic resonance imaging (MRI) examinations prior to the surgery. Simple clinical data and MRI imaging features, including age, sex, tumor location and size, T1-weighted images (T1WI) and T2-weighted images (T2WI) signal characteristics, degree and pattern of enhancement, dural tail sign, ginkgo leaf sign, and intervertebral foramen widening (IFW), were reviewed. Finally, a CART model and RF model were established based on the aforementioned features to evaluate their effectiveness in differentiating between the two types of tumors. Meanwhile, we also compared the performance of the ML models to the radiologists. The receiver operating characteristic (ROC) curve, accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were used to evaluate the models and clinicians' discrimination performance. Our investigation reveals significant variations in ten out of 11 variables in the training group and five out of 11 variables in the test group when comparing schwannomas and meningiomas (P<0.05). Ultimately, the CART model incorporated five variables: enhancement pattern, the presence of IFW, tumor location, maximum diameter, and T2WI signal intensity (SI). The RF model combined all 11 variables. The CART model, RF model, radiologist 1, and radiologist 2 achieved an area under the curve (AUC) of 0.890, 0.956, 0.681, and 0.723 in the training group, and 0.838, 0.922, 0.580, and 0.659 in the test group, respectively. The RF prediction model exhibits more exceptional performance than an experienced radiologist in discriminating intraspinal schwannomas from meningiomas. The RF model seems to be better in discriminating the two tumors than the CART model.

RGB Imaging as a Tool for Remote Sensing of Characteristics of Terrestrial Plants: A Review.

Approaches for remote sensing can be used to estimate the influence of changes in environmental conditions on terrestrial plants, providing timely protection of their growth, development, and productivity. Different optical methods, including the informative multispectral and hyperspectral imaging of reflected light, can be used for plant remote sensing; however, multispectral and hyperspectral cameras are technically complex and have a high cost. RGB imaging based on the analysis of color images of plants is definitely simpler and more accessible, but using this tool for remote sensing plant characteristics under changeable environmental conditions requires the development of methods to increase its informativity. Our review focused on using RGB imaging for remote sensing the characteristics of terrestrial plants. In this review, we considered different color models, methods of exclusion of background in color images of plant canopies, and various color indices and their relations to characteristics of plants, using regression models, texture analysis, and machine learning for the estimation of these characteristics based on color images, and some approaches to provide transformation of simple color images to hyperspectral and multispectral images. As a whole, our review shows that RGB imaging can be an effective tool for estimating plant characteristics; however, further development of methods to analyze color images of plants is necessary.

Insights into designing educational materials for persons living with dementia: a focus group study

BackgroundPersons living with dementia (PLWD) may experience communication difficulties that impact their ability to process written and pictorial information. Patient-facing education may help promote discontinuation of potentially inappropriate medications for older adults without dementia, but it is unclear how to adapt this approach for PLWD. Our objective was to solicit feedback from PLWD and their care partners to gain insights into the design of PLWD-facing deprescribing intervention materials and PLWD-facing education material more broadly.MethodsWe conducted 3 successive focus groups with PLWD aged ≥ 50 (n = 12) and their care partners (n = 10) between December 2022 and February 2023. Focus groups were recorded and transcripts were analyzed for overarching themes.ResultsWe identified 5 key themes: [1] Use images and language consistent with how PLWD perceive themselves; [2] Avoid content that might heighten fear or anxiety; [3] Use straightforward delivery with simple language and images; [4] Direct recipients to additional information; make the next step easy; and [5] Deliver material directly to the PLWD.ConclusionPLWD-facing educational material should be addressed directly to PLWD, using plain, non-threatening and accessible language with clean, straightforward formatting.

Full-Process Adaptive Encoding and Decoding Framework for Remote Sensing Images Based on Compression Sensing

Faced with the problem of incompatibility between traditional information acquisition mode and spaceborne earth observation tasks, starting from the general mathematical model of compressed sensing, a theoretical model of block compressed sensing was established, and a full-process adaptive coding and decoding compressed sensing framework for remote sensing images was proposed, which includes five parts: mode selection, feature factor extraction, adaptive shape segmentation, adaptive sampling rate allocation and image reconstruction. Unlike previous semi-adaptive or local adaptive methods, the advantages of the adaptive encoding and decoding method proposed in this paper are mainly reflected in four aspects: (1) Ability to select encoding modes based on image content, and maximizing the use of the richness of the image to select appropriate sampling methods; (2) Capable of utilizing image texture details for adaptive segmentation, effectively separating complex and smooth regions; (3) Being able to detect the sparsity of encoding blocks and adaptively allocate sampling rates to fully explore the compressibility of images; (4) The reconstruction matrix can be adaptively selected based on the size of the encoding block to alleviate block artifacts caused by non-stationary characteristics of the image. Experimental results show that the method proposed in this article has good stability for remote sensing images with complex edge textures, with the peak signal-to-noise ratio and structural similarity remaining above 35 dB and 0.8. Moreover, especially for ocean images with relatively simple image content, when the sampling rate is 0.26, the peak signal-to-noise ratio reaches 50.8 dB, and the structural similarity is 0.99. In addition, the recovered images have the smallest BRISQUE value, with better clarity and less distortion. In the subjective aspect, the reconstructed image has clear edge details and good reconstruction effect, while the block effect is effectively suppressed. The framework designed in this paper is superior to similar algorithms in both subjective visual and objective evaluation indexes, which is of great significance for alleviating the incompatibility between traditional information acquisition methods and satellite-borne earth observation missions.

PECULIARITIES OF NOISY IMAGE LOSSY COMPRESSION

This paper deals with lossy compression applied to grayscale noisy images using several coders. The case of additive white Gaussian noise is considered as the first step in studying the problem. A special attention is paid to quite new coders AVIF and HEIF for which, to the best of our knowledge, lossy compression of noisy images of different complexity has not been thoroughly considered yet. It is shown that optimal operation point is possible for all coders under certain conditions according to different quality metrics including conventional peak signal-to-noise ratio and visual quality metrics such as PSNR-HVS-M and MS-SSIM. The compression parameters (metrics) in optimal operation point significantly depend on image complexity and noise intensity where the existence of optimal operation point is more probable for simple structure images and/or intensive noise. Comparison of metric values in optimal operation point for the considered coders shows that slightly better characteristics are provided by better portable graphics (BPG) and advanced discrete cosine transform (ADCT) coders. The results for JPEG are significantly worse. The AVIF and HEIF encoders provide similar results and they outperform JPEG significantly. Optimal operation point for all studied coders is observed more rarely for visual quality metrics than for peak signal-to-noise ratio. General tendencies concerning dependence of optimal compression parameters on noise intensity are presented. It is shown that compression ratio in optimal operation point is often larger than 20 and can be as large as 60. The problem with AVIF and HEIF is that it is currently unclear how to choose quality factor for them to carry out lossy image compression in the neighborhood of the corresponding optimal operation point. Meanwhile, there is the tendency to optimal quality factor reduction if intensity of additive white Gaussian noise increases. The directions of further research are discussed.

Image schemas and (point)-to-point event model for the macro-event

Abstract The macro-event is a fundamental concept in Talmyan motion event typology. A large literature has been documented concerning the status of a particular language in the two-way typology that he proposes, but relatively little literature focusing on the morphosyntactic dimension of the macro-event per se, let alone on the cognitive motivation of the macro-event. This article analyzes the types of macro-events expressed by directional complement constructions in Mandarin, and argues that the macro-events are image-schema-based. The simple image schemas give rise to a more complex three-event-semantic-model, termed (point)-to-point , or to be more particular, (point a)-to-point b, in which to represents the affecting or intervening event, point a represents the original state of point b, point b is the resulting event. point a is usually implied, not explicitly expressed, so it is put in brackets. This model has advantages over Talmy’s main event and co-event structure in that it can largely predict the meaning-form mapping, and explain more constructions. The findings have some implications for cognitive semantics: In grammar, languages generally prioritize the third event; the complex event model might be motivated by simple image schemas.

Using a Slit to Suppress Optical Aberrations in Laser Triangulation Sensors.

In this paper, we present a laser triangulation sensor to measure the distance between the sensor and an object without contact using a diffraction slit rather than a traditional lens. We show that by replacing the lens with a slit, we can exploit the resulting diffraction pattern to have finer and yet simpler image analysis, yielding better estimation of the distance to the object. To test our hypothesis, we build a precision position table and a laser triangulation sensor, generate large data sets to test different estimation algorithms on various materials, and compare data acquisition using a traditional lens versus using a slit. We show that position estimation when using a slit is both more precise and more accurate than comparable methods using a lens.

Development of a hydrogen peroxide fluorescent probe for the rapid discrimination of IDH1 mutant gliomas from the wild-type

Isocitrate dehydrogenase (IDH) mutations are common in gliomas, and recent studies have suggested that these mutants have distinct microenvironments characterized by higher levels of reactive oxygen species (ROS) and a higher pH. The identification of IDH mutants is important for the diagnosis, individualized treatment, and clinical prognosis of gliomas. Sanger sequencing and immunohistochemistry are the standard methods for IDH mutation detection. As the mutations have several types, the detection of multiple gene sites and proteins are required, which means high cost and tedious operations. The high levels of ROS observed in mutIDH gliomas have not been used for mutIDH detection. Fluorescent probe-based detection techniques have emerged as a prevalent method to detect diverse analytes in living systems due to their distinctive benefits of simple operation, high sensitivity and selectivity, fast response, and real-time applicability. In the present study, we report the rapid discrimination of mutIDH1 from wild-type gliomas using the novel fluorescent probe BOD-G that varies in its fluorescence response to different levels of H2O2. BOD-G exhibits high sensitivity and selectivity in its turn-on response to H2O2, and its performance improves as the pH increases. The probe exhibits a much stronger fluorescence in IDH1 mutant U87 cells than in wild-type U87MG cells after 5 min. Importantly, BOD-G displays a bright fluorescence when exposed to fresh mutIDH1 human glioma specimens after 15 min but not with wild-type samples. Thus, BOD-G can be used to discriminate mutIDH1 from wild-type human glioma specimens rapidly by simple fluorescent imaging.

Smartphone-based digital image colorimetry for the determination of total capsaicinoid content in chili pepper extracts

A simple smartphone-based digital image colorimetry was proposed for the determination of total capsaicinoid content and the assessment of chili pepper pungency. The biobased solvent D-limonene was used for the first time to isolate analytes. Capsaicinoids were efficiently separated from chili pepper by solid–liquid extraction with D-limonene followed by partitioning of the analytes into the ammonium hydroxide solution to eliminate the matrix interference effect. For colorimetric detection of total capsaicinoid content, a selective chromogenic reaction was performed using Gibbs reagent (2,6-dichloroquinone-4-chloroimide). Measurements were performed using a smartphone-based setup and included image analysis with the program ImageJ. The limit of detection of the proposed procedure was 0.15 mg g−1. The intra-day repeatability did not exceed 10.0 %. The inter-day repeatability was less than 16.5 %. The comparison of the smartphone-based procedure with high-performance liquid chromatography showed satisfactory results.

Microfluidic Immunosensing Platform Based on a Rolling Circle Amplification-Assisted DNA Dendrimer Probe for Portable and Sensitive Detection of Allergen-Specific IgE.

The robust point-of-care platform for sensitive, multiplexed, and affordable detection of allergen-specific IgE (sIgE) is an urgent demand in component-resolved diagnostics. Here, we developed a microfluidic immunosensing platform based on a rolling circle amplification-assisted DNA dendrimer probe for sensitive detection of multiple sIgEs. The versatile multichannel microfluidic whole blood analytical device integrates cell filtration, recombinant antigen-modified magnetic enrichment, and DNA dendrimer probe-amplified signal transduction for portable on-chip analysis. Three sIgEs against common oyster allergens were simultaneously detected in blood samples by simple smartphone-based imaging without any pretreatment. The quantitative detection of multiple allergen-specific antibodies on the platform was achieved with limits of detection of less than 50 pg/mL, exhibiting superior sensitivity compared to most point-of-care testing. The detection results of 55 serum samples and 4 whole blood samples were 100% consistent with the ELISA results, confirming the accuracy and stability of our platform. Additionally, the reversible combination of hexahistidine6-tag and Ni-IMAC magbead was elegantly utilized on the immunosensing platform for desired reversibility. With the advantages of general applicability, high sensitivity, and reversibility, the DNA dendrimer-based microfluidic immunosensing platform provides great potential for the portable detection of immune proteins as a point-of-care platform in disease diagnostics and biological analysis.

Color Face Image Generation with Improved Generative Adversarial Networks

This paper focuses on the development of an improved Generative Adversarial Network (GAN) specifically designed for generating color portraits from sketches. The construction of the system involves using a GPU (Graphics Processing Unit) computing host as the primary unit for model training. The tasks that require high-performance calculations are handed over to the GPU host, while the user host only needs to perform simple image processing and use the model trained by the GPU host to generate images. This arrangement reduces the computer specification requirements for the user. This paper will conduct a comparative analysis of various types of generative networks which will serve as a reference point for the development of the proposed Generative Adversarial Network. The application part of the paper focuses on the practical implementation and utilization of the developed Generative Adversarial Network for the generation of multi-skin tone portraits. By constructing a face dataset specifically designed to incorporate information about ethnicity and skin color, this approach can overcome a limitation associated with traditional generation networks, which typically generate only a single skin color.

UV-SAM: Adapting Segment Anything Model for Urban Village Identification

Urban villages, defined as informal residential areas in or around urban centers, are characterized by inadequate infrastructures and poor living conditions, closely related to the Sustainable Development Goals (SDGs) on poverty, adequate housing, and sustainable cities. Traditionally, governments heavily depend on field survey methods to monitor the urban villages, which however are time-consuming, labor-intensive, and possibly delayed. Thanks to widely available and timely updated satellite images, recent studies develop computer vision techniques to detect urban villages efficiently. However, existing studies either focus on simple urban village image classification or fail to provide accurate boundary information. To accurately identify urban village boundaries from satellite images, we harness the power of the vision foundation model and adapt the Segment Anything Model (SAM) to urban village segmentation, named UV-SAM. Specifically, UV-SAM first leverages a small-sized semantic segmentation model to produce mixed prompts for urban villages, including mask, bounding box, and image representations, which are then fed into SAM for fine-grained boundary identification. Extensive experimental results on two datasets in China demonstrate that UV-SAM outperforms existing baselines, and identification results over multiple years show that both the number and area of urban villages are decreasing over time, providing deeper insights into the development trends of urban villages and sheds light on the vision foundation models for sustainable cities. The dataset and codes of this study are available at https://github.com/tsinghua-fib-lab/UV-SAM.

Canopeo app as image-based phenotyping tool in controlled environment utilizing Arabidopsis mutants.

Canopeo app was developed as a simple, accurate, rapid, and free tool to analyze ground cover fraction (GCF) from red-green-blue (RGB) images and videos captured in the field. With increasing interest in tools for plant phenotyping in controlled environments, the usefulness of Canopeo to identify differences in growth among Arabidopsis thaliana mutants in a controlled environment were explored. A simple imaging system was used to compare Arabidopsis mutants based on the FLAVIN-BINDING, KELCH REPEAT, F-BOX-1 (FKF1) mutation, which has been identified with increased biomass accumulation. Two FKF1 lines such as null expression (fkf1-t) and overexpression (FKF1-OE) lines were used along with wild type (Col-0). Canopeo was used to phenotype plants, based on biomass estimations. Under long-day photoperiod, fkf1-t had increased cellulose biosynthesis, and therefore biomass. Resource partitioning favored seedling vigor and delayed onset of senescence. In contrast, FKF1-OE illustrated a determinative growth habit where plant resources are primarily allocated for seed production. This study demonstrates the use of Canopeo for model plants and highlights its potential for phenotyping broadleaved crops in controlled environments. The value of adapting Canopeo for lab use is those with limited experience and resources have access to phenotyping methodology that is simple, accessible, accurate, and cost-efficient in a controlled environment setting.

Enhancing Diagnostic Precision: Evaluation of Preprocessing Filters in Simple Diffusion Kurtosis Imaging for Head and Neck Tumors.

Background: Our initial clinical study using simple diffusion kurtosis imaging (SDI), which simultaneously produces a diffusion kurtosis image (DKI) and an apparent diffusion coefficient map, confirmed the usefulness of SDI for tumor diagnosis. However, the obtained DKI had noticeable variability in the mean kurtosis (MK) values, which is inherent to SDI. We aimed to improve this variability in SDI by preprocessing with three different filters (Gaussian [G], median [M], and nonlocal mean) of the diffusion-weighted images used for SDI. Methods: The usefulness of filter parameters for diagnosis was examined in basic and clinical studies involving 13 patients with head and neck tumors. Results: The filter parameters, which did not change the median MK value, but reduced the variability and significantly homogenized the MK values in tumor and normal tissues in both basic and clinical studies, were identified. In the receiver operating characteristic curve analysis for distinguishing tumors from normal tissues using MK values, the area under curve values significantly improved from 0.627 without filters to 0.641 with G (σ = 0.5) and 0.638 with M (radius = 0.5). Conclusions: Thus, image pretreatment with G and M for SDI was shown to be useful for improving tumor diagnosis in clinical practice.

Alternating projection combined with fast gradient projection (FGP-AP) method for intensity-only measurement optical diffraction tomography in LED array microscopy.

Optical diffraction tomography (ODT) is a powerful label-free measurement tool that can quantitatively image the three-dimensional (3D) refractive index (RI) distribution of samples. However, the inherent "missing cone problem," limited illumination angles, and dependence on intensity-only measurements in a simplified imaging setup can all lead to insufficient information mapping in the Fourier domain, affecting 3D reconstruction results. In this paper, we propose the alternating projection combined with the fast gradient projection (FGP-AP) method to compensate for the above problem, which effectively reconstructs the 3D RI distribution of samples using intensity-only images captured from LED array microscopy. The FGP-AP method employs the alternating projection (AP) algorithm for gradient descent and the fast gradient projection (FGP) algorithm for regularization constraints. This approach is equivalent to incorporating prior knowledge of sample non-negativity and smoothness into the 3D reconstruction process. Simulations demonstrate that the FGP-AP method improves reconstruction quality compared to the original AP method, particularly in the presence of noise. Experimental results, obtained from mouse kidney cells and label-free blood cells, further affirm the superior 3D imaging efficacy of the FGP-AP method.

Magnetic Resonance Imaging Characteristics of LGI1-Antibody and CASPR2-Antibody Encephalitis

Rapid and accurate diagnosis of autoimmune encephalitis encourages prompt initiation of immunotherapy toward improved patient outcomes. However, clinical features alone may not sufficiently narrow the differential diagnosis, and awaiting autoantibody results can delay immunotherapy. To identify simple magnetic resonance imaging (MRI) characteristics that accurately distinguish 2 common forms of autoimmune encephalitis, LGI1- and CASPR2-antibody encephalitis (LGI1/CASPR2-Ab-E), from 2 major differential diagnoses, viral encephalitis (VE) and Creutzfeldt-Jakob disease (CJD). This cross-sectional study involved a retrospective, blinded analysis of the first available brain MRIs (taken 2000-2022) from 192 patients at Oxford University Hospitals in the UK and Mayo Clinic in the US. These patients had LGI1/CASPR2-Ab-E, VE, or CJD as evaluated by 2 neuroradiologists (discovery cohort; n = 87); findings were validated in an independent cohort by 3 neurologists (n = 105). Groups were statistically compared with contingency tables. Data were analyzed in 2023. MRI findings including T2 or fluid-attenuated inversion recovery (FLAIR) hyperintensities, swelling or volume loss, presence of gadolinium contrast enhancement, and diffusion-weighted imaging changes. Correlations with clinical features. Among 192 participants with MRIs reviewed, 71 were female (37%) and 121 were male (63%); the median age was 66 years (range, 19-92 years). By comparison with VE and CJD, in LGI1/CASPR2-Ab-E, T2 and/or FLAIR hyperintensities were less likely to extend outside the temporal lobe (3/42 patients [7%] vs 17/18 patients [94%] with VE; P < .001, and 3/4 patients [75%] with CJD; P = .005), less frequently exhibited swelling (12/55 [22%] with LGI1/CASPR2-Ab-E vs 13/22 [59%] with VE; P = .003), and showed no diffusion restriction (0 patients vs 16/22 [73%] with VE and 8/10 [80%] with CJD; both P < .001) and rare contrast enhancement (1/20 [5%] vs 7/17 [41%] with VE; P = .01). These findings were validated in an independent cohort and generated an area under the curve of 0.97, sensitivity of 90%, and specificity of 95% among cases with T2/FLAIR hyperintensity in the hippocampus and/or amygdala. In this study, T2 and/or FLAIR hyperintensities confined to the temporal lobes, without diffusion restriction or contrast enhancement, robustly distinguished LGI1/CASPR2-Ab-E from key differential diagnoses. These observations should assist clinical decision-making toward expediting immunotherapy. Their generalizability to other forms of autoimmune encephalitis and VE should be examined in future studies.

Early Predicting Osteogenic Differentiation of Mesenchymal Stem Cells Based on Deep Learning Within One Day.

Osteogenic differentiation of mesenchymal stem cells (MSCs) is proposed to be critical for bone tissue engineering and regenerative medicine. However, the current approach for evaluating osteogenic differentiation mainly involves immunohistochemical staining of specific markers which often can be detected at day 5-7 of osteogenic inducing. Deep learning (DL) is a significant technology for realizing artificial intelligence (AI). Computer vision, a branch of AI, has been proved to achieve high-precision image recognition using convolutional neural networks (CNNs). Our goal was to train CNNs to quantitatively measure the osteogenic differentiation of MSCs. To this end, bright-field images of MSCs during early osteogenic differentiation (day 0, 1, 3, 5, and 7) were captured using a simple optical phase contrast microscope to train CNNs. The results showed that the CNNs could be trained to recognize undifferentiated cells and differentiating cells with an accuracy of 0.961 on the independent test set. In addition, we found that CNNs successfully distinguished differentiated cells at a very early stage (only 1day). Further analysis showed that overall morphological features of MSCs were the main basis for the CNN classification. In conclusion, MSCs differentiation detection can be achieved early and accurately through simple bright-field images and DL networks, which may also provide a potential and novel method for the field of cell detection in the near future.

Optic Nerve Sheath MR Imaging Measurements in Patients with Orthostatic Headaches and Normal Findings on Conventional Imaging Predict the Presence of an Underlying CSF-Venous Fistula.

Spontaneous spinal CSF leaks typically cause orthostatic headache, but their detection may require specialized and invasive spinal imaging. We undertook a study to determine the value of simple optic nerve sheath MR imaging measurements in predicting the likelihood of finding a CSF-venous fistula, a type of leak that cannot be detected with routine spine MR imaging or CT myelography, among patients with orthostatic headache and normal conventional brain and spine imaging findings. This cohort study included a consecutive group of patients with orthostatic headache and normal conventional brain and spine imaging findings who underwent digital subtraction myelography under general anesthesia to look for spinal CSF-venous fistulas. The study group consisted of 93 patients (71 women and 22 men; mean age, 47.5 years; range, 17-84 years). Digital subtraction myelography demonstrated a CSF-venous fistula in 15 patients. The mean age of these 8 women and 7 men was 56 years (range, 23-83 years). The mean optic nerve sheath diameter was 4.0 mm, and the mean perioptic subarachnoid space was 0.5 mm in patients with a CSF-venous fistula compared with 4.9 and 1.2 mm, respectively, in patients without a fistula (P < .001). Optimal cutoff values were found at 4.4 mm for optic nerve sheath diameter and 1.0 mm for the perioptic subarachnoid space. Fistulas were detected in about 50% of patients with optic nerve sheath diameter or perioptic subarachnoid space measurements below these cutoff values compared with <2% of patients with optic nerve sheath diameter or perioptic subarachnoid space measurements above these cutoff values. Following surgical ligation of the fistula, optic nerve sheath diameter increased from 4.0 to 5.3 mm and the perioptic subarachnoid space increased from 0.5 to 1.2 mm (P < .001). Concerns about a spinal CSF leak should not be dismissed in patients with orthostatic headache when conventional imaging findings are normal, and simple optic nerve sheath MR imaging measurements can help decide if more imaging needs to be performed in this patient population.

Minimum intensity projection of embossed quadrant-detection images for improved photoreceptor mosaic visualisation.

Non-confocal split-detection imaging reveals the cone photoreceptor inner segment mosaic in a plethora of retinal conditions, with the potential of providing insight to ageing, disease, and response to treatment processes, in vivo, and allows the screening of candidates for cell rescue therapies. This imaging modality complements confocal reflectance adaptive optics scanning light ophthalmoscopy, which relies on the waveguiding properties of cones, as well as their orientation toward the pupil. Split-detection contrast, however, is directional, with each cone inner segment appearing as opposite dark and bright semicircles, presenting a challenge for either manual or automated cell identification. Quadrant-detection imaging, an evolution of split detection, could be used to generate images without directional dependence. Here, we demonstrate how the embossed-filtered quadrant-detection images, originally proposed by Migacz etal. for visualising hyalocytes, can also be used to generate photoreceptor mosaic images with better and non-directional contrast for improved visualisation. As a surrogate of visualisation improvement between legacy split-detection images and the images resulting from the method described herein, we provide preliminary results of simple image processing routines that may enable the automated identification of generic image features, as opposed to complex algorithms developed specifically for photoreceptor identification, in pathological retinas.

Deep learning-based automated lesion segmentation on pediatric focal cortical dysplasia II preoperative MRI: a reliable approach

ObjectivesFocal cortical dysplasia (FCD) represents one of the most common causes of refractory epilepsy in children. Deep learning demonstrates great power in tissue discrimination by analyzing MRI data. A prediction model was built and verified using 3D full-resolution nnU-Net for automatic lesion detection and segmentation of children with FCD II.MethodsHigh-resolution brain MRI structure data from 65 patients, confirmed with FCD II by pathology, were retrospectively studied. Experienced neuroradiologists segmented and labeled the lesions as the ground truth. Also, we used 3D full-resolution nnU-Net to segment lesions automatically, generating detection maps. The algorithm was trained using fivefold cross-validation, with data partitioned into training (N = 200) and testing (N = 15). To evaluate performance, detection maps were compared to expert manual labels. The Dice-Sørensen coefficient (DSC) and sensitivity were used to assess the algorithm performance.ResultsThe 3D nnU-Net showed a good performance for FCD lesion detection at the voxel level, with a sensitivity of 0.73. The best segmentation model achieved a mean DSC score of 0.57 on the testing dataset.ConclusionThis pilot study confirmed that 3D full-resolution nnU-Net can automatically segment FCD lesions with reliable outcomes. This provides a novel approach to FCD lesion detection.Critical relevance statementOur fully automatic models could process the 3D T1-MPRAGE data and segment FCD II lesions with reliable outcomes.Key points• Simplified image processing promotes the DL model implemented in clinical practice.• The histopathological confirmed lesion masks enhance the clinical credibility of the AI model.• The voxel-level evaluation metrics benefit lesion detection and clinical decisions.Graphical