This repository contains the image dataset and the manual annotations used to develop the HEPASS algorithm for automated liver steatosis quantification:
- Salvi M., Molinaro M., Metovic J., Patrono D., Romagnoli R., Papotti M, and Molinari F., "Fully Automated Quantitative Assessment of Hepatic Steatosis in Liver Transplants", Computers in Biology and Medicine 2020 (DOI: 10.1016/j.compbiomed.2020.103836)
Background: The presence of macro- and microvesicular steatosis is one of the major risk factors for liver transplantation. An accurate assessment of the steatosis percentage is crucial for determining liver graft transplantability, which is currently based on the pathologists’ visual evaluations on liver histology specimens.
Method: The aim of this study was to develop and validate a fully automated algorithm, called HEPASS (HEPatic Adaptive Steatosis Segmentation), for both micro- and macro-steatosis detection in digital liver histological images. The proposed method employs a hybrid deep learning framework, combining the accuracy of an adaptive threshold with the semantic segmentation of a deep convolutional neural network. Starting from all white regions, the HEPASS algorithm was able to detect lipid droplets and classify them into micro- or macrosteatosis.
Results: The proposed method was developed and tested on 385 hematoxylin and eosin (H&E) stained images coming from 77 liver donors. Automated results were compared with manual annotations and nine state-of-the-art techniques designed for steatosis segmentation. In the TEST set, the algorithm was characterized by 97.27% accuracy in steatosis quantification (average error 1.07%, maximum average error 5.62%) and outperformed all the compared methods.
Conclusions: To the best of our knowledge, the proposed algorithm is the first fully automated algorithm for the assessment of both micro- and macrosteatosis in H&E stained liver tissue images. Being very fast (average computational time 0.72 seconds), this algorithm paves the way for automated, quantitative and real-time liver graft assessments.
This DB based on all available reports by the Communicational center of Government of the Russian Federation.
Official Russian COVID-19 data published daily by the Government of Russia (on the Russian language) in the form of raw data is a daily updated report in a pdf form. Each piece has daily updates. We are providing a working link on every cell of data in the dataset. This DB is an attempt to manually collect critical variables from the report into a machine-readable format. These datasets are ready to be used for analysis and modeling.
Variables: location; date; new cases [diagnosed]; cases [cumulative]; recovered [new]; recovered [cumulative]; deaths [new]; deaths [cumulative]; tests [new tests administered]; tests [cumulative]; test_positive [cumulative]; hospitalization [cumulative]; icu [cumulative or population]; on_invasive_ventilators [cumulative or population]; test_negative [cumulative]; hospital beds; web links.
All Data divided by date (time) and regions (Oblast) of the Russian Federation.
In the datasets, the scale of organizational culture based on eleven items of primary cultural values (PCV) and nine items of secondary cultural values (SCV). Work motivation variables in the datasets used four items of motive motivation (MM), seven items of expectation motivation (ME), and with nine items of incentive motivation (IM). Interpersonal communication variables were seven items of social sensitivity (SS), nine items of social insight (SI), and four items of social communication skills (SCM). The items, including labels and ratings, will be explained later, with more comprehensive details as supplementary material (see "Annotated Questionnaire" in supplementary material). This was because each item had different rankings and choices. To measure teacher performance used three scales from the book of effective teacher performance. The teacher performance scale used three variables of thirteen items of the learning process (LL), four items of scientific work (SW), and three items of service (S).
Contributors:Collin, J. Weber, Alexander Santowski, Peter Chifflard
Concertation of trace metals (Al, Fe) and heavy metals (V, Cr, Co, Ni, Cu, Sn, As, Cd, Pb) given in mg/kg soil dry weight and calculated pollution indices (Igeo: Geoaccumulation Index; PLI: Pollution load index; RI: Potential ecological risk index). For methods of analyses and index calculation see method chapter in above mentioned publication
Features of pavement joints in the inner-city of Marburg (Hesse, Germany) recorded during field work.
Distance_street: Distance (m) of each sampling point to next street.
Height: Heigth (m a.s.l.) taken from DEM.
Av_joint_size: Average joint size (cm) from 1 square meter pavement measured during field work.
Plant_coverage: Plant coverage classified from 0 to 5. For further description of classes see above mentioned publication.
Runoff:_accumulation: Runoff accumulation classified in three classes: 0 – 2.5 - 5. For further description of classes see above mentioned publication.
pH: pH (KCl) values of pavement joint soil material.
OM: Organic matter content (mass-%) of pavement joint soil material.
Contributors:Elena Zudilova-Seinstra, Alberto Zigoni 10711960, Wouter Haak
We conducted an analysis to confirm our observations that only a very small percentage of public research data is hosted in the Institutional Data Repositories, while the vast majority is published in the open domain-specific and generalist data repositories.
For this analysis, we selected 11 institutions, many of which have been our evaluation partners. For each institution, we counted the number of datasets published in their Institutional Data Repository (IDR) and tracked the number of public research datasets hosted in external data repositories via the Data Monitor API. External tracking was based on the corpus of 14+ mln data records checked against the institutional SciVal ID. One institution didn’t have an IDR.
We found out that 10 out of 11 institutions had most of their public research data hosted outside of their institution, where by research data we mean not only datasets, but a broader notion that includes, for example, software.
We will be happy to expand it by adding more institutions upon request.
Note: This is version 2 of the earlier published dataset. The number of datasets published and tracked in the Monash Institutional Data Repository has been updated based on the information provided by the Monash Library. The number of datasets in the NTU Institutional Data Repository now includes datasets only. Dataverses were excluded to avoid double counting.
The data were used in the paper entitled of "Analysis of Water Clarity Decrease in Xin’anjiang Reservoir, China, from 30-Year Landsat TM, ETM+, and OLI Observations". The uploaded dataset contains: (1) water clarity data and above-water remote sensing reflectance data which were collected in the Xin’anjiang Reservoir during 2013 to 2014. Specifically, the above-water remote sensing reflectance data were resampled to the remote sensing reflectance of different Landsat sensors (TM, ETM+ and OLI); (2) meteorological data in the Xin’anjiang Reservoir including air temperature and rainfall data were collected from 1960 to 2016; (3) socioeconomic data in the Xin’anjiang catchment including population, gross domestic product, chemical fertilizer usage and industrial sewage.
Supporting data (P. obliquiloculata ISNW data calculated from P. obliquiloculata SNW and SNWN. dutertrei-based deep-water Δ[CO32‒] at site WP7) for "Calcification of planktonic foraminifer Pulleniatina obliquiloculata controlled by seawater temperature rather than ocean acidification"