Using Delaunay triangulation to sample whole-specimen color from digital images.
Ontology highlight
ABSTRACT:
SUBMITTER: Valvo JJ
PROVIDER: S-EPMC8462138 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Colonoscopy is an effective tool to detect colorectal lesions and needs the support of pathological diagnosis. This study aimed to develop and validate deep learning models that automatically classify digital pathology images of colon lesions obtained from colonoscopy-related specimen. Histopathological slides of colonoscopic biopsy or resection specimens were collected and grouped into six classes by disease category: adenocarcinoma, tubular adenoma (TA), traditional serrated adenoma (TSA), sessile serrated adenoma (SSA), hyperplastic polyp (HP), and non-specific lesions. Digital photographs were taken of each pathological slide to fine-tune two pre-trained convolutional neural networks, and the model performances were evaluated. A total of 1865 images were included from 703 patients, of which 10% were used as a test dataset. For six-class classification, the mean diagnostic accuracy was 97.3% (95% confidence interval [CI], 96.0-98.6%) by DenseNet-161 and 95.9% (95% CI 94.1-97.7%) by EfficientNet-B7. The per-class area under the receiver operating characteristic curve (AUC) was highest for adenocarcinoma (1.000; 95% CI 0.999-1.000) by DenseNet-161 and TSA (1.000; 95% CI 1.000-1.000) by EfficientNet-B7. The lowest per-class AUCs were still excellent: 0.991 (95% CI 0.983-0.999) for HP by DenseNet-161 and 0.995 for SSA (95% CI 0.992-0.998) by EfficientNet-B7. Deep learning models achieved excellent performances for discriminating adenocarcinoma from non-adenocarcinoma lesions with an AUC of 0.995 or 0.998. The pathognomonic area for each class was appropriately highlighted in digital images by saliency map, particularly focusing epithelial lesions. Deep learning models might be a useful tool to help the diagnosis for pathologic slides of colonoscopy-related specimens.
| S-EPMC9329279 | biostudies-literature
Project description:Digital breast tomosynthesis (DBT) offers poor image quality along the depth direction. This paper presents a new method that improves the image quality of DBT considerably through the a priori information from automated ultrasound (AUS) images.DBT and AUS images of a complex breast-mimicking phantom are acquired by a DBT/AUS dual-modality system. The AUS images are taken in the same geometry as the DBT images and the gradient information of the in-slice AUS images is adopted into the new loss functional during the DBT reconstruction process. The additional data allow for new iterative equations through solving the optimization problem utilizing the gradient descent method. Both visual comparison and quantitative analysis are employed to evaluate the improvement on DBT images. Normalized line profiles of lesions are obtained to compare the edges of the DBT and AUS-corrected DBT images. Additionally, image quality metrics such as signal difference to noise ratio (SDNR) and artifact spread function (ASF) are calculated to quantify the effectiveness of the proposed method.In traditional DBT image reconstructions, serious artifacts can be found along the depth direction (Z direction), resulting in the blurring of lesion edges in the off-focus planes parallel to the detector. However, by applying the proposed method, the quality of the reconstructed DBT images is greatly improved. Visually, the AUS-corrected DBT images have much clearer borders in both in-focus and off-focus planes, fewer Z direction artifacts and reduced overlapping effect compared to the conventional DBT images. Quantitatively, the corrected DBT images have better ASF, indicating a great reduction in Z direction artifacts as well as better Z resolution. The sharper line profiles along the Y direction show enhancement on the edges. Besides, noise is also reduced, evidenced by the obviously improved SDNR values.The proposed method provides great improvement on the quality of DBT images. This improvement makes it easier to locate and to distinguish a lesion, which may help improve the accuracy of the diagnosis using DBT imaging.
| S-EPMC4032424 | biostudies-other
Project description:Digital whole slide images are Food and Drug Administration approved for clinical diagnostic use in pathology; however, integration is nascent. Trainees from 9 pathology training programs completed an online survey to ascertain attitudes toward and experiences with whole slide images for pathological interpretations. Respondents (n = 76) reported attending 63 unique medical schools (45 United States, 18 international). While 63% reported medical school exposure to whole slide images, most reported ≤ 5 hours. Those who began training more recently were more likely to report at least some exposure to digital whole slide image training in medical school compared to those who began training earlier: 75% of respondents beginning training in 2017 or 2018 reported exposure to whole slide images compared to 54% for trainees beginning earlier. Trainees exposed to whole slide images in medical school were more likely to agree they were comfortable using whole slide images for interpretation compared to those not exposed (29% vs 12%; P = .06). Most trainees agreed that accurate diagnoses can be made using whole slide images for primary diagnosis (92%; 95% CI: 86-98) and that whole slide images are useful for obtaining second opinions (93%; 95% CI: 88-99). Trainees reporting whole slide image experience during training, compared to those with no experience, were more likely to agree they would use whole slide images in 5 years for primary diagnosis (64% vs 50%; P = .3) and second opinions (86% vs 76%; P = .4). In conclusion, although exposure to whole slide images in medical school has increased, overall exposure is limited. Positive attitudes toward future whole slide image diagnostic use were associated with exposure to this technology during medical training. Curricular integration may promote adoption.
| S-EPMC7545516 | biostudies-literature
Project description:BackgroundTo assess reproducibility and accuracy of overall Nottingham grade and component scores using digital whole slide images (WSIs) compared to glass slides.MethodsTwo hundred and eight pathologists were randomized to independently interpret 1 of 4 breast biopsy sets using either glass slides or digital WSI. Each set included 5 or 6 invasive carcinomas (22 total invasive cases). Participants interpreted the same biopsy set approximately 9 months later following a second randomization to WSI or glass slides. Nottingham grade, including component scores, was assessed on each interpretation, providing 2045 independent interpretations of grade. Overall grade and component scores were compared between pathologists (interobserver agreement) and for interpretations by the same pathologist (intraobserver agreement). Grade assessments were compared when the format (WSI vs. glass slides) changed or was the same for the two interpretations.ResultsNottingham grade intraobserver agreement was highest using glass slides for both interpretations (73%, 95% confidence interval [CI]: 68%, 78%) and slightly lower but not statistically different using digital WSI for both interpretations (68%, 95% CI: 61%, 75%; P= 0.22). The agreement was lowest when the format changed between interpretations (63%, 95% CI: 59%, 68%). Interobserver agreement was significantly higher (P < 0.001) using glass slides versus digital WSI (68%, 95% CI: 66%, 70% versus 60%, 95% CI: 57%, 62%, respectively). Nuclear pleomorphism scores had the lowest inter- and intra-observer agreement. Mitotic scores were higher on glass slides in inter- and intra-observer comparisons.ConclusionsPathologists' intraobserver agreement (reproducibility) is similar for Nottingham grade using glass slides or WSI. However, slightly lower agreement between pathologists suggests that verification of grade using digital WSI may be more challenging.
| S-EPMC6489380 | biostudies-literature
Project description:The multicenter Nephrotic Syndrome Study Network (NEPTUNE) digital pathology scoring system employs a novel and comprehensive methodology to document pathologic features from whole-slide images, immunofluorescence and ultrastructural digital images. To estimate inter- and intra-reader concordance of this descriptor-based approach, data from 12 pathologists (eight NEPTUNE and four non-NEPTUNE) with experience from training to 30 years were collected. A descriptor reference manual was generated and a webinar-based protocol for consensus/cross-training implemented. Intra-reader concordance for 51 glomerular descriptors was evaluated on jpeg images by seven NEPTUNE pathologists scoring 131 glomeruli three times (Tests I, II, and III), each test following a consensus webinar review. Inter-reader concordance of glomerular descriptors was evaluated in 315 glomeruli by all pathologists; interstitial fibrosis and tubular atrophy (244 cases, whole-slide images) and four ultrastructural podocyte descriptors (178 cases, jpeg images) were evaluated once by six and five pathologists, respectively. Cohen's kappa for inter-reader concordance for 48/51 glomerular descriptors with sufficient observations was moderate (0.40<kappa?0.60) for 17 and good (0.60<kappa?0.80) for 8, for 52% with moderate or better kappas. Clustering of glomerular descriptors based on similar pathologic features improved concordance. Concordance was independent of years of experience, and increased with webinar cross-training. Excellent concordance was achieved for interstitial fibrosis and tubular atrophy. Moderate-to-excellent concordance was achieved for all ultrastructural podocyte descriptors, with good-to-excellent concordance for descriptors commonly used in clinical practice, foot process effacement, and microvillous transformation. NEPTUNE digital pathology scoring system enables novel morphologic profiling of renal structures. For all histologic and ultrastructural descriptors tested with sufficient observations, moderate-to-excellent concordance was seen for 31/54 (57%). Descriptors not sufficiently represented will require further testing. This study proffers the NEPTUNE digital pathology scoring system as a model for standardization of renal biopsy interpretation extendable outside the NEPTUNE consortium, enabling international collaborations.
| S-EPMC5515468 | biostudies-literature
Project description:High Dynamic Range (HDR) and Wide Color Gamut (WCG) screens are able to render brighter and darker pixels with more vivid colors than ever. To assess the quality of images and videos displayed on these screens, new quality assessment metrics adapted to this new content are required. Because most SDR metrics assume that the representation of images is perceptually uniform, we study the impact of three uniform color spaces developed specifically for HDR and WCG images, namely, I C t C p , J z a z b z and H D R - L a b on 12 SDR quality assessment metrics. Moreover, as the existing databases of images annotated with subjective scores are using a standard gamut, two new HDR databases using WCG are proposed. Results show that MS-SSIM and FSIM are among the most reliable metrics. This study also highlights the fact that the diffuse white of HDR images plays an important role when adapting SDR metrics for HDR content. Moreover, the adapted SDR metrics does not perform well to predict the impact of chrominance distortions.
| S-EPMC8320861 | biostudies-literature
Project description:There are more than 1.2 billion biological specimens in the world's museums and herbaria. These objects are particularly important forms of biological sample and observation. They underpin biological taxonomy but the data they contain have many other uses in the biological and environmental sciences. Nevertheless, from their conception they are almost entirely documented on paper, either as labels attached to the specimens or in catalogues linked with catalogue numbers. In order to make the best use of these data and to improve the findability of these specimens, these data must be transcribed digitally and made to conform to standards, so that these data are also interoperable and reusable. Through various digitization projects, the authors have experimented with transcription by volunteers, expert technicians, scientists, commercial transcription services and automated systems. We have also been consumers of specimen data for taxonomical, biogeographical and ecological research. In this paper, we draw from our experiences to make specific recommendations to improve transcription data. The paper is split into two sections. We first address issues related to database implementation with relevance to data transcription, namely versioning, annotation, unknown and incomplete data and issues related to language. We then focus on particular data types that are relevant to biological collection specimens, namely nomenclature, dates, geography, collector numbers and uniquely identifying people. We make recommendations to standards organizations, software developers, data scientists and transcribers to improve these data with the specific aim of improving interoperability between collection datasets.
| S-EPMC6901386 | biostudies-literature
Project description:For centuries, scientists have observed nature to understand the laws that govern the physical world. The traditional process of turning observations into physical understanding is slow. Imperfect models are constructed and tested to explain relationships in data. Powerful new algorithms can enable computers to learn physics by observing images and videos. Inspired by this idea, instead of training machine learning models using physical quantities, we used images, that is, pixel information. For this work, and as a proof of concept, the physics of interest are wind-driven spatial patterns. These phenomena include features in Aeolian dunes and volcanic ash deposition, wildfire smoke, and air pollution plumes. We use computer model simulations of spatial deposition patterns to approximate images from a hypothetical imaging device whose outputs are red, green, and blue (RGB) color images with channel values ranging from 0 to 255. In this paper, we explore deep convolutional neural network-based autoencoders to exploit relationships in wind-driven spatial patterns, which commonly occur in geosciences, and reduce their dimensionality. Reducing the data dimension size with an encoder enables training deep, fully connected neural network models linking geographic and meteorological scalar input quantities to the encoded space. Once this is achieved, full spatial patterns are reconstructed using the decoder. We demonstrate this approach on images of spatial deposition from a pollution source, where the encoder compresses the dimensionality to 0.02% of the original size, and the full predictive model performance on test data achieves a normalized root mean squared error of 8%, a figure of merit in space of 94% and a precision-recall area under the curve of 0.93.
| S-EPMC9876895 | biostudies-literature
Project description:PremiseEquisetum is a distinctive vascular plant genus with 15 extant species worldwide. Species identification is complicated by morphological plasticity and frequent hybridization events, leading to a disproportionately high number of misidentified specimens. These may be correctly identified by applying appropriate computer vision tools.MethodsWe hypothesize that aerial stem nodes can provide enough information to distinguish among Equisetum hyemale, E. laevigatum, and E . ×ferrissii, the latter being a hybrid between the other two. An object detector was trained to find nodes on a given image and to distinguish E. hyemale nodes from those of E. laevigatum. A classifier then took statistics from the detection results and classified the given image into one of the three taxa. Both detector and classifier were trained and tested on expert manually annotated images.ResultsIn our exploratory test set of 30 images, our detector/classifier combination identified all 10 E. laevigatum images correctly, as well as nine out of 10 E. hyemale images, and eight out of 10 E. ×ferrissii images, for a 90% classification accuracy.DiscussionOur results support the notion that computer vision may help with the identification of herbarium specimens once enough manual annotations become available.
| S-EPMC7328651 | biostudies-literature
Project description:Cancer pathology reflects disease progression (or regression) and associated molecular characteristics, and provides rich phenotypic information that is predictive of cancer grade and has potential implications in treatment planning and prognosis. According to the remarkable performance of computational approaches in the digital pathology domain, we hypothesized that machine learning can help to distinguish low-grade gliomas (LGG) from high-grade gliomas (HGG) by exploiting the rich phenotypic information that reflects the microvascular proliferation level, mitotic activity, presence of necrosis, and nuclear atypia present in digital pathology images. A set of 735 whole-slide digital pathology images of glioma patients (median age: 49.65 years, male: 427, female: 308, median survival: 761.26 days) were obtained from TCGA. Sub-images that contained a viable tumor area, showing sufficient histologic characteristics, and that did not have any staining artifact were extracted. Several clinical measures and imaging features, including conventional (intensity, morphology) and advanced textures features (gray-level co-occurrence matrix and gray-level run-length matrix), extracted from the sub-images were further used for training the support vector machine model with linear configuration. We sought to evaluate the combined effect of conventional imaging, clinical, and texture features by assessing the predictive value of each feature type and their combinations through a predictive classifier. The texture features were successfully validated on the glioma patients in 10-fold cross-validation (accuracy = 75.12%, AUC = 0.652). The addition of texture features to clinical and conventional imaging features improved grade prediction compared to the models trained on clinical and conventional imaging features alone (p = 0.045 and p = 0.032 for conventional imaging features and texture features, respectively). The integration of imaging, texture, and clinical features yielded a significant improvement in accuracy, supporting the synergistic value of these features in the predictive model. The findings suggest that the texture features, when combined with conventional imaging and clinical markers, may provide an objective, accurate, and integrated prediction of glioma grades. The proposed digital pathology imaging-based marker may help to (i) stratify patients into clinical trials, (ii) select patients for targeted therapies, and (iii) personalize treatment planning on an individual person basis.
| S-EPMC7139732 | biostudies-literature