scholarly journals Harnessing clinical annotations to improve deep learning performance in prostate segmentation

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0253829
Author(s):  
Karthik V. Sarma ◽  
Alex G. Raman ◽  
Nikhil J. Dhinagar ◽  
Alan M. Priester ◽  
Stephanie Harmon ◽  
...  
Keyword(s):  
Hausdorff Distance ◽  
Large Scale ◽  
State Of The Art ◽  
Learning Performance ◽  
Research Quality ◽  
Large Dataset ◽  
Template Model ◽  
Prostate Segmentation ◽  
Original Dataset ◽  
Entire Dataset

Purpose Developing large-scale datasets with research-quality annotations is challenging due to the high cost of refining clinically generated markup into high precision annotations. We evaluated the direct use of a large dataset with only clinically generated annotations in development of high-performance segmentation models for small research-quality challenge datasets. Materials and methods We used a large retrospective dataset from our institution comprised of 1,620 clinically generated segmentations, and two challenge datasets (PROMISE12: 50 patients, ProstateX-2: 99 patients). We trained a 3D U-Net convolutional neural network (CNN) segmentation model using our entire dataset, and used that model as a template to train models on the challenge datasets. We also trained versions of the template model using ablated proportions of our dataset, and evaluated the relative benefit of those templates for the final models. Finally, we trained a version of the template model using an out-of-domain brain cancer dataset, and evaluated the relevant benefit of that template for the final models. We used five-fold cross-validation (CV) for all training and evaluation across our entire dataset. Results Our model achieves state-of-the-art performance on our large dataset (mean overall Dice 0.916, average Hausdorff distance 0.135 across CV folds). Using this model as a pre-trained template for refining on two external datasets significantly enhanced performance (30% and 49% enhancement in Dice scores respectively). Mean overall Dice and mean average Hausdorff distance were 0.912 and 0.15 for the ProstateX-2 dataset, and 0.852 and 0.581 for the PROMISE12 dataset. Using even small quantities of data to train the template enhanced performance, with significant improvements using 5% or more of the data. Conclusion We trained a state-of-the-art model using unrefined clinical prostate annotations and found that its use as a template model significantly improved performance in other prostate segmentation tasks, even when trained with only 5% of the original dataset.

A large dataset for the evaluation of ontology matching

2009 ◽  
Vol 24 (2) ◽  
pp. 137-157 ◽  
Author(s):  
Fausto Giunchiglia ◽  
Mikalai Yatskevich ◽  
Paolo Avesani ◽  
Pavel Shivaiko
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
The State ◽  
Ontology Matching ◽  
Large Dataset ◽  
Scale Evaluation ◽  
Evaluation Dataset ◽  
Matching Techniques ◽  
Web Directories

AbstractRecently, the number of ontology matching techniques and systems has increased significantly. This makes the issue of their evaluation and comparison more severe. One of the challenges of the ontology matching evaluation is in building large-scale evaluation datasets. In fact, the number of possible correspondences between two ontologies grows quadratically with respect to the numbers of entities in these ontologies. This often makes the manual construction of the evaluation datasets demanding to the point of being infeasible for large-scale matching tasks. In this paper, we present an ontology matching evaluation dataset composed of thousands of matching tasks, called TaxME2. It was built semi-automatically out of the Google, Yahoo, and Looksmart web directories. We evaluated TaxME2 by exploiting the results of almost two-dozen of state-of-the-art ontology matching systems. The experiments indicate that the dataset possesses the desired key properties, namely it is error-free, incremental, discriminative, monotonic, and hard for the state-of-the-art ontology matching systems.

scholarly journals Impact of Image Resolution on Deep Learning Performance in Endoscopy Image Classification: An Experimental Study Using a Large Dataset of Endoscopic Images

Diagnostics ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 2183
Author(s):  
Vajira Thambawita ◽  
Inga Strümke ◽  
Steven A. Hicks ◽  
Pål Halvorsen ◽  
Sravanthi Parasa ◽  
...  
Keyword(s):  
Image Classification ◽  
Image Resolution ◽  
Lesion Detection ◽  
Learning Performance ◽  
Large Dataset ◽  
Endoscopic Image ◽  
And Performance ◽  
The Cost ◽  
Entire Dataset ◽  
Fold Cross Validation

Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image resolution to save computing resources at the cost of losing details. Today, no conventions between resolution and performance exist, and monitoring the performance of various CNN architectures as a function of image resolution provides insights into how subtleties of different lesions on endoscopy affect performance. This can help set standards for image or video characteristics for future CNN-based models in gastrointestinal (GI) endoscopy. This study examines the performance of CNNs on the HyperKvasir dataset, consisting of 10,662 images from 23 different findings. We evaluate two CNN models for endoscopic image classification under quality distortions with image resolutions ranging from 32 × 32 to 512 × 512 pixels. The performance is evaluated using two-fold cross-validation and F1-score, maximum Matthews correlation coefficient (MCC), precision, and sensitivity as metrics. Increased performance was observed with higher image resolution for all findings in the dataset. MCC was achieved at image resolutions between 512 × 512 pixels for classification for the entire dataset after including all subclasses. The highest performance was observed with an MCC value of 0.9002 when the models were trained on the highest resolution and tested on the same resolution. Different resolutions and their effect on CNNs are explored. We show that image resolution has a clear influence on the performance which calls for standards in the field in the future.

Microbloggers’ interest inference using a subgraph stream

2021 ◽  
Vol 25 (2) ◽  
pp. 397-417
Author(s):  
Xiaoling Huang ◽  
Hao Wang ◽  
Lei Li ◽  
Yi Zhu ◽  
Chengxiang Hu
Keyword(s):  
Real Time ◽  
Large Scale ◽  
State Of The Art ◽  
Dynamic Change ◽  
Massive Data ◽  
User Interest ◽  
Large Dataset ◽  
Topic Extraction ◽  
Sina Weibo ◽  
Effectiveness And Efficiency

Inferring user interest over large-scale microblogs have attracted much attention in recent years. However, the emergence of the massive data, dynamic change of information and persistence of microblogs pose challenges to interest inference. Most of the existing approaches rarely take into account the combination of these microbloggers’ characteristics within the model, which may incur information loss with nontrivial magnitude in real-time extraction of user interest and massive social data processing. To address these problems, in this paper, we propose a novel User-Networked Interest Topic Extraction in the form of Subgraph Stream (UNITE_SS) for microbloggers’ interest inference. To be specific, we develop several strategies for the construction of subgraph stream to select the better strategy for user interest inference. Moreover, the information of microblogs in each subgraph is utilized to obtain a real-time and effective interest for microbloggers. The experimental evaluation on a large dataset from Sina Weibo, one of the most popular microblogs in China, demonstrates that the proposed approach outperforms the state-of-the-art baselines in terms of precision, mean reciprocal rank (MRR) as well as runtime from the effectiveness and efficiency perspectives.

scholarly journals Adaptive Graph Guided Embedding for Multi-label Annotation

2018 ◽  
Author(s):  
Lichen Wang ◽  
Zhengming Ding ◽  
Yun Fu
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Unlabeled Data ◽  
Label Propagation ◽  
Experimental Results ◽  
Training Data ◽  
Learning Performance ◽  
Intrinsic Structure ◽  
Latent Space ◽  
Art Methods

Multi-label annotation is challenging since a large amount of well-labeled training data are required to achieve promising performance. However, providing such data is expensive while unlabeled data are widely available. To this end, we propose a novel Adaptive Graph Guided Embedding (AG2E) approach for multi-label annotation in a semi-supervised fashion, which utilizes limited labeled data associating with large-scale unlabeled data to facilitate learning performance. Specifically, a multi-label propagation scheme and an effective embedding are jointly learned to seek a latent space where unlabeled instances tend to be well assigned multiple labels. Furthermore, a locality structure regularizer is designed to preserve the intrinsic structure and enhance the multi-label annotation. We evaluate our model in both conventional multi-label learning and zero-shot learning scenario. Experimental results demonstrate that our approach outperforms other compared state-of-the-art methods.

scholarly journals Documentary data and the study of past droughts: a global state of the art

2018 ◽  
Vol 14 (12) ◽  
pp. 1915-1960 ◽  
Author(s):  
Rudolf Brázdil ◽  
Andrea Kiss ◽  
Jürg Luterbacher ◽  
David J. Nash ◽  
Ladislava Řezníčková
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Drought Indices ◽  
Documentary Evidence ◽  
Climatic Trends ◽  
Instrumental Observations ◽  
Spatio Temporal ◽  
Epigraphic Evidence ◽  
Administrative Evidence

Abstract. The use of documentary evidence to investigate past climatic trends and events has become a recognised approach in recent decades. This contribution presents the state of the art in its application to droughts. The range of documentary evidence is very wide, including general annals, chronicles, memoirs and diaries kept by missionaries, travellers and those specifically interested in the weather; records kept by administrators tasked with keeping accounts and other financial and economic records; legal-administrative evidence; religious sources; letters; songs; newspapers and journals; pictographic evidence; chronograms; epigraphic evidence; early instrumental observations; society commentaries; and compilations and books. These are available from many parts of the world. This variety of documentary information is evaluated with respect to the reconstruction of hydroclimatic conditions (precipitation, drought frequency and drought indices). Documentary-based drought reconstructions are then addressed in terms of long-term spatio-temporal fluctuations, major drought events, relationships with external forcing and large-scale climate drivers, socio-economic impacts and human responses. Documentary-based drought series are also considered from the viewpoint of spatio-temporal variability for certain continents, and their employment together with hydroclimate reconstructions from other proxies (in particular tree rings) is discussed. Finally, conclusions are drawn, and challenges for the future use of documentary evidence in the study of droughts are presented.

scholarly journals Psychiatric disorders in China: strengths and challenges of contemporary research and clinical services

2021 ◽  
pp. 1-14
Author(s):  
Xiao Chang ◽  
Qiyong Gong ◽  
Chunbo Li ◽  
Weihua Yue ◽  
Xin Yu ◽  
...  
Keyword(s):  
Psychiatric Disorders ◽  
Disease Burden ◽  
Large Scale ◽  
Well Being ◽  
Research Quality ◽  
Psychiatric Research ◽  
Clinical Services ◽  
Contributing Factors ◽  
Brain Functions ◽  
Neuroscience Research

Abstract China accounts for 17% of the global disease burden attributable to mental, neurological and substance use disorders. As a country undergoing profound societal change, China faces growing challenges to reduce the disease burden caused by psychiatric disorders. In this review, we aim to present an overview of progress in neuroscience research and clinical services for psychiatric disorders in China during the past three decades, analysing contributing factors and potential challenges to the field development. We first review studies in the epidemiological, genetic and neuroimaging fields as examples to illustrate a growing contribution of studies from China to the neuroscience research. Next, we introduce large-scale, open-access imaging genetic cohorts and recently initiated brain banks in China as platforms to study healthy brain functions and brain disorders. Then, we show progress in clinical services, including an integration of hospital and community-based healthcare systems and early intervention schemes. We finally discuss opportunities and existing challenges: achievements in research and clinical services are indispensable to the growing funding investment and continued engagement in international collaborations. The unique aspect of traditional Chinese medicine may provide insights to develop a novel treatment for psychiatric disorders. Yet obstacles still remain to promote research quality and to provide ubiquitous clinical services to vulnerable populations. Taken together, we expect to see a sustained advancement in psychiatric research and healthcare system in China. These achievements will contribute to the global efforts to realize good physical, mental and social well-being for all individuals.

scholarly journals Proteomic profiling dataset of chemical perturbations in multiple biological backgrounds

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Deborah O. Dele-Oni ◽  
Karen E. Christianson ◽  
Shawn B. Egri ◽  
Alvaro Sebastian Vaca Jacome ◽  
Katherine C. DeRuff ◽  
...  
Keyword(s):  
Large Scale ◽  
Cell Model ◽  
Cellular Responses ◽  
Proteomic Profiling ◽  
Reduced Representation ◽  
Link Type ◽  
Original Dataset ◽  
Quality Control Metrics ◽  
Biological Insight ◽  
Chromatin Profiling

AbstractWhile gene expression profiling has traditionally been the method of choice for large-scale perturbational profiling studies, proteomics has emerged as an effective tool in this context for directly monitoring cellular responses to perturbations. We previously reported a pilot library containing 3400 profiles of multiple perturbations across diverse cellular backgrounds in the reduced-representation phosphoproteome (P100) and chromatin space (Global Chromatin Profiling, GCP). Here, we expand our original dataset to include profiles from a new set of cardiotoxic compounds and from astrocytes, an additional neural cell model, totaling 5300 proteomic signatures. We describe filtering criteria and quality control metrics used to assess and validate the technical quality and reproducibility of our data. To demonstrate the power of the library, we present two case studies where data is queried using the concept of “connectivity” to obtain biological insight. All data presented in this study have been deposited to the ProteomeXchange Consortium with identifiers PXD017458 (P100) and PXD017459 (GCP) and can be queried at https://clue.io/proteomics.

scholarly journals VIPPrint: Validating Synthetic Image Detection and Source Linking Methods on a Large Scale Dataset of Printed Documents

2021 ◽  
Vol 7 (3) ◽  
pp. 50
Author(s):  
Anselmo Ferreira ◽  
Ehsan Nowroozi ◽  
Mauro Barni
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Child Pornography ◽  
Forensic Analysis ◽  
Synthetic Image ◽  
Image Detection ◽  
Face Images ◽  
Large Scale Dataset ◽  
Scanned Images ◽  
Analysis Of The Images

The possibility of carrying out a meaningful forensic analysis on printed and scanned images plays a major role in many applications. First of all, printed documents are often associated with criminal activities, such as terrorist plans, child pornography, and even fake packages. Additionally, printing and scanning can be used to hide the traces of image manipulation or the synthetic nature of images, since the artifacts commonly found in manipulated and synthetic images are gone after the images are printed and scanned. A problem hindering research in this area is the lack of large scale reference datasets to be used for algorithm development and benchmarking. Motivated by this issue, we present a new dataset composed of a large number of synthetic and natural printed face images. To highlight the difficulties associated with the analysis of the images of the dataset, we carried out an extensive set of experiments comparing several printer attribution methods. We also verified that state-of-the-art methods to distinguish natural and synthetic face images fail when applied to print and scanned images. We envision that the availability of the new dataset and the preliminary experiments we carried out will motivate and facilitate further research in this area.

scholarly journals SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

2021 ◽  
Vol 40 (3) ◽  
pp. 1-13
Author(s):  
Lumin Yang ◽  
Jiajie Zhuang ◽  
Hongbo Fu ◽  
Xiangzhi Wei ◽  
Kun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Large Scale ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Structure Information ◽  
Graph Neural Networks ◽  
Node Labels ◽  
Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

scholarly journals ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition

2021 ◽  
Author(s):  
Anil S. Baslamisli ◽  
Partha Das ◽  
Hoang-An Le ◽  
Sezer Karaoglu ◽  
Theo Gevers
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
State Of The Art ◽  
Image Decomposition ◽  
Natural Environments ◽  
Decomposition Algorithms ◽  
Ambient Light ◽  
Fine Grained ◽  
Large Scale Dataset ◽  
Direct Illumination

AbstractIn general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in distinguishing strong photometric effects from reflectance variations. Therefore, in this paper, we propose to decompose the shading component into direct (illumination) and indirect shading (ambient light and shadows) subcomponents. The aim is to distinguish strong photometric effects from reflectance variations. An end-to-end deep convolutional neural network (ShadingNet) is proposed that operates in a fine-to-coarse manner with a specialized fusion and refinement unit exploiting the fine-grained shading model. It is designed to learn specific reflectance cues separated from specific photometric effects to analyze the disentanglement capability. A large-scale dataset of scene-level synthetic images of outdoor natural environments is provided with fine-grained intrinsic image ground-truths. Large scale experiments show that our approach using fine-grained shading decompositions outperforms state-of-the-art algorithms utilizing unified shading on NED, MPI Sintel, GTA V, IIW, MIT Intrinsic Images, 3DRMS and SRD datasets.

Sign in / Sign up

Export Citation Format

Share Document