An intuitive explanation of dermoscopic structures by digitally reconstructed pathological horizontal top-down view images.
Ontology highlight
ABSTRACT:
SUBMITTER: Kasuya A
PROVIDER: S-EPMC6934765 | biostudies-literature | 2019 Dec
REPOSITORIES: biostudies-literature
Publications
An intuitive explanation of dermoscopic structures by digitally reconstructed pathological horizontal top-down view images.
Kasuya Akira A Aoshima Masahiro M Fukuchi Kensuke K Shimauchi Takatoshi T Fujiyama Toshiharu T Tokura Yoshiki Y
Scientific reports 20191227 1
Dermoscopy is a convenient tool to diagnose melanocytic lesions, especially nevus and melanoma. Various pigmented structures, including pigment network, dots and globules, and streaks, are observed in dermoscopy. Usually, 2D vertical images are used to explain the correlation of dermoscopy and histopathology. However, because the image of dermoscopy is horizontal, it is difficult for the horizontal view of dermoscopy to refer to the vertical view of histopathology. In our study, we digitally rec ...[more]
Similar Datasets
Project description:To develop an algorithm for computing realistic digitally reconstructed radiographs (DRRs) that match real cone-beam CT (CBCT) projections with no artificial adjustments.The authors used measured attenuation data from cone-beam CT projection radiographs of different materials to obtain a function to convert CT number to linear attenuation coefficient (LAC). The effects of scatter, beam hardening, and veiling glare were first removed from the attenuation data. Using this conversion function the authors calculated the line integral of LAC through a CT along rays connecting the radiation source and detector pixels with a ray-tracing algorithm, producing raw DRRs. The effects of scatter, beam hardening, and veiling glare were then included in the DRRs through postprocessing.The authors compared actual CBCT projections to DRRs produced with all corrections (scatter, beam hardening, and veiling glare) and to uncorrected DRRs. Algorithm accuracy was assessed through visual comparison of projections and DRRs, pixel intensity comparisons, intensity histogram comparisons, and correlation plots of DRR-to-projection pixel intensities. In general, the fully corrected algorithm provided a small but nontrivial improvement in accuracy over the uncorrected algorithm. The authors also investigated both measurement- and computation-based methods for determining the beam hardening correction, and found the computation-based method to be superior, as it accounted for nonuniform bowtie filter thickness. The authors benchmarked the algorithm for speed and found that it produced DRRs in about 0.35 s for full detector and CT resolution at a ray step-size of 0.5 mm.The authors have demonstrated a DRR algorithm calculated from first principles that accounts for scatter, beam hardening, and veiling glare in order to produce accurate DRRs. The algorithm is computationally efficient, making it a good candidate for iterative CT reconstruction techniques that require a data fidelity term based on the matching of DRRs and projections.
| S-EPMC3532107 | biostudies-other
Project description:Blue laser/light imaging (BLI) is an image-enhanced endoscopy (IEE) technique that can provide an accurate diagnosis by closely observing the surface structure of various colonic lesions. However, complete correspondence between endoscopic images and pathological images has not been demonstrated. The aim of this study was to accurately compare endoscopic images and the pathological images using a three-dimensionally (3D) reconstructed pathological model. Continuous thin layer sections were prepared from colonic tissue specimens and immunohistochemically stained for CD34 and CAM5.2. Three-dimensional reconstructed images were created by superimposing immunohistochemically stained pathological images. The endoscopic image with magnifying BLI was compared with the top view of the 3D reconstructed image to identify any one-to-one correspondence between the endoscopic images and histopathological images using the gland orifices and microvessels as a guide. Using 3D reconstructed pathological images, we were able to identify the location on the endoscope image in cases of colonic adenocarcinoma, adenoma and normal mucosa. As a result, the horizontal plane of the endoscopic image and the vertical plane of the 2D pathological specimen were able to be compared, and we successfully determined the visible blood vessel depth and performed a detailed evaluation on magnifying BLI. Examples are as follows: (1) The median vasculature depth from the mucosal surface that could be recognized as vasculature on magnifying BLI was 29.4 μm. The median depth of unrecognizable vessels on magnifying BLI was 218.8 μm, which was significantly deeper than recognizable vessels. (2) Some brownish structures were suggested to potentially be not only dense vessels, vessel expansions, corrupted vessels but also bleeding or extravasation of erythrocytes. Overall, we demonstrated a new approach to matching endoscopic images and pathological findings using a 3D-reconstructed pathological model immunohistochemically stained for CD34 and CAM5.2. This approach may increase the overall understanding of endoscopic images and positively contribute to making more accurate endoscopic diagnoses.
| S-EPMC7323971 | biostudies-literature
Project description:Most people encounter art images as digital reproductions on a computer screen instead of as originals in a museum or gallery. With the development of digital technologies, high-resolution artworks can be accessed anywhere and anytime by a large number of viewers. Since these digital images depict the same content and are attributed to the same artist as the original, it is often implicitly assumed that their aesthetic evaluation will be similar. When it comes to the digital reproductions of art, however, it is also obvious that reproductions do differ from the originals in various aspects. Besides image quality, resolution, and format, the most obvious change is in the representation of color. The effects of subjectively varying surface-level image features on art evaluation have not been clearly assessed. To address this gap, we compare the evaluation of digital reproductions of 16 expressionist and impressionist paintings manipulated to have a high color saturation vs. a saturation similar to the original. We also investigate the impact of viewing time (100 ms vs. unrestricted viewing time) and expertise (art experts vs. laypersons), two other aspects that may impact the perception of art in online contexts. Moreover, we link these dimensions to a recent model of aesthetic experience [the Vienna Integrated Model of Top-Down and Bottom-Up Processes in Art Perception (VIMAP)]. Results suggest that color saturation does not exert a major influence on liking. Cognitive and emotional aspects (interest, confusion, surprise, and boredom), however, are affected - to different extents for experts and laypersons. For laypersons, the increase in color saturation led to more positive assessments of an artwork, whereas it resulted in increased confusion for art experts. This insight is particularly important when it comes to reproducing artworks digitally. Depending on the intended use, increasing or decreasing the color saturation of the digitally reproduced image might be most appropriate. We conclude with a discussion of these findings and address the question of why empirical aesthetics requires more precise dimensions to better understand the subtle processes that take place in the perception of today's digitally reproduced art environment.
| S-EPMC7759521 | biostudies-literature
Project description:Graph neural networks (GNNs) have been widely used in molecular property prediction, but explaining their black-box predictions is still a challenge. Most existing explanation methods for GNNs in chemistry focus on attributing model predictions to individual nodes, edges or fragments that are not necessarily derived from a chemically meaningful segmentation of molecules. To address this challenge, we propose a method named substructure mask explanation (SME). SME is based on well-established molecular segmentation methods and provides an interpretation that aligns with the understanding of chemists. We apply SME to elucidate how GNNs learn to predict aqueous solubility, genotoxicity, cardiotoxicity and blood-brain barrier permeation for small molecules. SME provides interpretation that is consistent with the understanding of chemists, alerts them to unreliable performance, and guides them in structural optimization for target properties. Hence, we believe that SME empowers chemists to confidently mine structure-activity relationship (SAR) from reliable GNNs through a transparent inspection on how GNNs pick up useful signals when learning from data.
| S-EPMC10160109 | biostudies-literature
Project description:Motivation:Fluorescence localization microscopy is extensively used to study the details of spatial architecture of subcellular compartments. This modality relies on determination of spatial positions of fluorophores, labeling an extended biological structure, with precision exceeding the diffraction limit. Several established models describe influence of pixel size, signal-to-noise ratio and optical resolution on the localization precision. The labeling density has been also recognized as important factor affecting reconstruction fidelity of the imaged biological structure. However, quantitative data on combined influence of sampling and localization errors on the fidelity of reconstruction are scarce. It should be noted that processing localization microscopy data is similar to reconstruction of a continuous (extended) non-periodic signal from a non-uniform, noisy point samples. In two dimensions the problem may be formulated within the framework of matrix completion. However, no systematic approach has been adopted in microscopy, where images are typically rendered by representing localized molecules with Gaussian distributions (widths determined by localization precision). Results:We analyze the process of two-dimensional reconstruction of extended biological structures as a function of the density of registered emitters, localization precision and the area occupied by the rendered localized molecule. We quantify overall reconstruction fidelity with different established image similarity measures. Furthermore, we analyze the recovered similarity measure in the frequency space for different reconstruction protocols. We compare the cut-off frequency to the limiting sampling frequency, as determined by labeling density. Availability and implementation:The source code used in the simulations along with test images is available at https://github.com/blazi13/qbioimages. Contact:bruszczy@nencki.gov.pl or t.bernas@nencki.gov.pl. Supplementary information:Supplementary data are available at Bioinformatics online.
| S-EPMC6192211 | biostudies-literature
Project description:ObjectivesThis study aims to develop a new diagnostic method for discriminating scalp psoriasis and seborrheic dermatitis based on a deep learning (DL) model, which uses the dermatoscopic image as input and achieved higher accuracy than dermatologists trained with dermoscopy.MethodsA total of 1,358 pictures (obtained from 617 patients) with pathological and diagnostic confirmed skin diseases (508 psoriases, 850 seborrheic dermatitides) were randomly allocated into the training, validation, and testing datasets (1,088/134/136) in this study. A DL model concerning dermatoscopic images was established using the transfer learning technique and trained for diagnosing two diseases.ResultsThe developed DL model exhibits good sensitivity, specificity, and Area Under Curve (AUC) (96.1, 88.2, and 0.922%, respectively), it outperformed all dermatologists in the diagnosis of scalp psoriasis and seborrheic dermatitis when compared to five dermatologists with various levels of experience. Furthermore, non-proficient doctors with the assistance of the DL model can achieve comparable diagnostic performance to dermatologists proficient in dermoscopy. One dermatology graduate student and two general practitioners significantly improved their diagnostic performance, where their AUC values increased from 0.600, 0.537, and 0.575 to 0.849, 0.778, and 0.788, respectively, and their diagnosis consistency was also improved as the kappa values went from 0.191, 0.071, and 0.143 to 0.679, 0.550, and 0.568, respectively. DL enjoys favorable computational efficiency and requires few computational resources, making it easy to deploy in hospitals.ConclusionsThe developed DL model has favorable performance in discriminating two skin diseases and can improve the diagnosis, clinical decision-making, and treatment of dermatologists in primary hospitals.
| S-EPMC9669613 | biostudies-literature
Project description:It is inevitable that some important specimens will become lost or damaged over time, conservation is therefore of vital importance. The Paluxy River dinosaur tracksite is among the most famous in the world. In 1940, Roland T. Bird described and excavated a portion of the site containing associated theropod and sauropod trackways. This excavated trackway was split up and housed in different institutions, and during the process a portion was lost or destroyed. We applied photogrammetric techniques to photographs taken by Bird over 70 years ago, before the trackway was removed, to digitally reconstruct the site as it was prior to excavation. The 3D digital model offers the opportunity to corroborate maps drawn by R.T. Bird when the tracksite was first described. More broadly, this work demonstrates the exciting potential for digitally recreating palaeontological, geological, or archaeological specimens that have been lost to science, but for which photographic documentation exists.
| S-EPMC3973721 | biostudies-literature
Project description:Predicting noise properties of iteratively reconstructed CT images is useful for analyzing reconstruction methods; for example, local noise power spectrum (NPS) predictions may be used to quantify the detectability of an image feature, to design regularization methods, or to determine dynamic tube current adjustment during a CT scan. This paper presents a method for fast prediction of reconstructed image variance and local NPS for statistical reconstruction methods using quadratic or locally quadratic regularization. Previous methods either require impractical computation times to generate an approximate map of the variance of each reconstructed voxel, or are restricted to specific CT geometries. Our method can produce a variance map of the entire image, for locally shift-invariant CT geometries with sufficiently fine angular sampling, using a computation time comparable to a single back-projection. The method requires only the projection data to be used in the reconstruction, not a reconstruction itself, and is reasonably accurate except near image edges where edge-preserving regularization behaves highly nonlinearly. We evaluate the accuracy of our method using reconstructions of both simulated CT data and real CT scans of a thorax phantom.
| S-EPMC5217761 | biostudies-literature
Project description:ImportanceConfocal microscopy has the potential to provide rapid bedside pathologic analysis, but clinical adoption has been limited in part by the need for physician retraining to interpret grayscale images. Digitally stained confocal mosaics (DSCMs) mimic the colors of routine histologic specimens and may increase adaptability of this technology.ObjectiveTo evaluate the accuracy and precision of 3 physicians using DSCMs before and after training to detect basal cell carcinoma (BCC) and squamous cell carcinoma (SCC) in Mohs micrographic surgery fresh-tissue specimens.DesignThis retrospective study used 133 DSCMs from 64 Mohs tissue excisions, which included clear margins, residual BCC, or residual SCC. Discarded tissue from Mohs surgical excisions from the dermatologic surgery units at Memorial Sloan Kettering Cancer Center and Oregon Health & Science University were collected for confocal imaging from 2006 to 2011. Final data analysis and interpretation took place between 2014 and 2016. Two Mohs surgeons and a Mohs fellow, who were blinded to the correlating gold standard frozen section diagnoses, independently reviewed the DSCMs for residual nonmelanoma skin cancer (NMSC) before and after a brief training session (about 5 minutes). The 2 assessments were separated by a 6-month washout period.Main outcomes and measuresDiagnostic accuracy was characterized by sensitivity and specificity of detecting NMSC using DSCMs vs standard frozen histopathologic specimens. The diagnostic precision was calculated based on interobserver agreement and κ scores. Paired 2-sample t tests were used for comparative means analyses before and after training.ResultsThe average respective sensitivities and specificities of detecting NMSC were 90% (95% CI, 89%-91%) and 79% (95% CI, 52%-100%) before training and 99% (95% CI, 99%-99%) (P = .001) and 93% (95% CI, 90%-96%) (P = .18) after training; for BCC, they were 83% (95% CI, 59%-100%) and 92% (95% CI, 81%-100%) before training and 98% (95% CI, 98%-98%) (P = .18) and 97% (95% CI, 95%-100%) (P = .15) after training; for SCC, they were 73% (95% CI, 65%-81%) and 89% (95% CI, 72%-100%) before training and 100% (P = .004) and 98% (95% CI, 95%-100%) (P = .21) after training. The pretraining interobserver agreement was 72% (κ = 0.58), and the posttraining interobserver agreement was 98% (κ = 0.97) (P = .04).Conclusions and relevanceDiagnostic use of DSCMs shows promising correlation to frozen histologic analysis, but image quality was affected by variations in image contrast and mosaic-stitching artifact. With training, physicians were able to read DSCMs with significantly improved accuracy and precision to detect NMSC.
| S-EPMC5757842 | biostudies-literature
Project description:BackgroundThe development of artificial intelligence (AI)-based algorithms and advances in medical domains rely on large datasets. A recent advancement in text-to-image generative AI is GLIDE (Guided Language to Image Diffusion for Generation and Editing). There are a number of representations available in the GLIDE model, but it has not been refined for medical applications.MethodsFor text-conditional image synthesis with classifier-free guidance, we have fine-tuned GLIDE using 10,015 dermoscopic images of seven diagnostic entities, including melanoma and melanocytic nevi. Photorealistic synthetic samples of each diagnostic entity were created by the algorithm. Following this, an experienced dermatologist reviewed 140 images (20 of each entity), with 10 samples originating from artificial intelligence and 10 from original images from the dataset. The dermatologist classified the provided images according to the seven diagnostic entities. Additionally, the dermatologist was asked to indicate whether or not a particular image was created by AI. Further, we trained a deep learning model to compare the diagnostic results of dermatologist versus machine for entity classification.ResultsThe results indicate that the generated images possess varying degrees of quality and realism, with melanocytic nevi and melanoma having higher similarity to real images than other classes. The integration of synthetic images improved the classification performance of the model, resulting in higher accuracy and precision. The AI assessment showed superior classification performance compared to dermatologist.ConclusionOverall, the results highlight the potential of synthetic images for training and improving AI models in dermatology to overcome data scarcity.
| S-EPMC10623307 | biostudies-literature