Dataset Information

Using deep learning to quantify the beauty of outdoor places.

ABSTRACT: Beautiful outdoor locations are protected by governments and have recently been shown to be associated with better health. But what makes an outdoor space beautiful? Does a beautiful outdoor location differ from an outdoor location that is simply natural? Here, we explore whether ratings of over 200?000 images of Great Britain from the online game Scenic-Or-Not, combined with hundreds of image features extracted using the Places Convolutional Neural Network, might help us understand what beautiful outdoor spaces are composed of. We discover that, as well as natural features such as 'Coast', 'Mountain' and 'Canal Natural', man-made structures such as 'Tower', 'Castle' and 'Viaduct' lead to places being considered more scenic. Importantly, while scenes containing 'Trees' tend to rate highly, places containing more bland natural green features such as 'Grass' and 'Athletic Fields' are considered less scenic. We also find that a neural network can be trained to automatically identify scenic places, and that this network highlights both natural and built locations. Our findings demonstrate how online data combined with neural networks can provide a deeper understanding of what environments we might find beautiful and offer quantitative insights for policymakers charged with design and protection of our built and natural environments.

SUBMITTER: Seresinhe CI

PROVIDER: S-EPMC5541537 | biostudies-literature | 2017 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using deep learning to quantify the beauty of outdoor places.

Seresinhe Chanuki Illushka CI Preis Tobias T Moat Helen Susannah HS

Royal Society open science 20170719 7

Beautiful outdoor locations are protected by governments and have recently been shown to be associated with better health. But what makes an outdoor space beautiful? Does a beautiful outdoor location differ from an outdoor location that is simply natural? Here, we explore whether ratings of over 200 000 images of Great Britain from the online game <i>Scenic-Or-Not</i>, combined with hundreds of image features extracted using the Places Convolutional Neural Network, might help us understand what ...[more]

PMID: 28791142

Similar Datasets

Project description:ImportanceA chronic shortage of donor kidneys is compounded by a high discard rate, and this rate is directly associated with biopsy specimen evaluation, which shows poor reproducibility among pathologists. A deep learning algorithm for measuring percent global glomerulosclerosis (an important predictor of outcome) on images of kidney biopsy specimens could enable pathologists to more reproducibly and accurately quantify percent global glomerulosclerosis, potentially saving organs that would have been discarded.ObjectiveTo compare the performances of pathologists with a deep learning model on quantification of percent global glomerulosclerosis in whole-slide images of donor kidney biopsy specimens, and to determine the potential benefit of a deep learning model on organ discard rates.Design, setting, and participantsThis prognostic study used whole-slide images acquired from 98 hematoxylin-eosin-stained frozen and 51 permanent donor biopsy specimen sections retrieved from 83 kidneys. Serial annotation by 3 board-certified pathologists served as ground truth for model training and for evaluation. Images of kidney biopsy specimens were obtained from the Washington University database (retrieved between June 2015 and June 2017). Cases were selected randomly from a database of more than 1000 cases to include biopsy specimens representing an equitable distribution within 0% to 5%, 6% to 10%, 11% to 15%, 16% to 20%, and more than 20% global glomerulosclerosis.Main outcomes and measuresCorrelation coefficient (r) and root-mean-square error (RMSE) with respect to annotations were computed for cross-validated model predictions and on-call pathologists' estimates of percent global glomerulosclerosis when using individual and pooled slide results. Data were analyzed from March 2018 to August 2020.ResultsThe cross-validated model results of section images retrieved from 83 donor kidneys showed higher correlation with annotations (r = 0.916; 95% CI, 0.886-0.939) than on-call pathologists (r = 0.884; 95% CI, 0.825-0.923) that was enhanced when pooling glomeruli counts from multiple levels (r = 0.933; 95% CI, 0.898-0.956). Model prediction error for single levels (RMSE, 5.631; 95% CI, 4.735-6.517) was 14% lower than on-call pathologists (RMSE, 6.523; 95% CI, 5.191-7.783), improving to 22% with multiple levels (RMSE, 5.094; 95% CI, 3.972-6.301). The model decreased the likelihood of unnecessary organ discard by 37% compared with pathologists.Conclusions and relevanceThe findings of this prognostic study suggest that this deep learning model provided a scalable and robust method to quantify percent global glomerulosclerosis in whole-slide images of donor kidneys. The model performance improved by analyzing multiple levels of a section, surpassing the capacity of pathologists in the time-sensitive setting of examining donor biopsy specimens. The results indicate the potential of a deep learning model to prevent erroneous donor organ discard.

Dataset Information

Using deep learning to quantify the beauty of outdoor places.

Publications

Using deep learning to quantify the beauty of outdoor places.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets