Dataset Information

Automatic detection of image manipulations in the biomedical literature.

ABSTRACT: Images in scientific papers are used to support the experimental description and the discussion of the findings since several centuries. In the field of biomedical sciences, in particular, the use of images to depict laboratory results is widely diffused, at such a level that one would not err in saying that there is barely any experimental paper devoid of images to document the attained results. With the advent of software for digital image manipulation, however, even photographic reproductions of experimental results may be easily altered by researchers, leading to an increasingly high rate of scientific papers containing unreliable images. In this paper I introduce a software pipeline to detect some of the most diffuse misbehaviours, running two independent tests on a random set of papers and on the full publishing record of a single journal. The results obtained by these two tests support the feasibility of the software approach and imply an alarming level of image manipulation in the published record.

SUBMITTER: Bucci EM

PROVIDER: S-EPMC5852055 | biostudies-literature | 2018 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic detection of image manipulations in the biomedical literature.

Bucci Enrico M EM

Cell death & disease 20180314 3

Images in scientific papers are used to support the experimental description and the discussion of the findings since several centuries. In the field of biomedical sciences, in particular, the use of images to depict laboratory results is widely diffused, at such a level that one would not err in saying that there is barely any experimental paper devoid of images to document the attained results. With the advent of software for digital image manipulation, however, even photographic reproductions ...[more]

PMID: 29540667

Similar Datasets

Project description:Current animal protection laws require replacement of animal experiments with alternative methods, whenever such methods are suitable to reach the intended scientific objective. However, searching for alternative methods in the scientific literature is a time-consuming task that requires careful screening of an enormously large number of experimental biomedical publications. The identification of potentially relevant methods, e.g. organ or cell culture models, or computer simulations, can be supported with text mining tools specifically built for this purpose. Such tools are trained (or fine tuned) on relevant data sets labeled by human experts. We developed the GoldHamster corpus, composed of 1,600 PubMed (Medline) articles (titles and abstracts), in which we manually identified the used experimental model according to a set of eight labels, namely: "in vivo", "organs", "primary cells", "immortal cell lines", "invertebrates", "humans", "in silico" and "other" (models). We recruited 13 annotators with expertise in the biomedical domain and assigned each article to two individuals. Four additional rounds of annotation aimed at improving the quality of the annotations with disagreements in the first round. Furthermore, we conducted various machine learning experiments based on supervised learning to evaluate the corpus for our classification task. We obtained more than 7,000 document-level annotations for the above labels. After the first round of annotation, the inter-annotator agreement (kappa coefficient) varied among labels, and ranged from 0.42 (for "others") to 0.82 (for "invertebrates"), with an overall score of 0.62. All disagreements were resolved in the subsequent rounds of annotation. The best-performing machine learning experiment used the PubMedBERT pre-trained model with fine-tuning to our corpus, which gained an overall f-score of 0.83. We obtained a corpus with high agreement for all labels, and our evaluation demonstrated that our corpus is suitable for training reliable predictive models for automatic classification of biomedical literature according to the used experimental models. Our SMAFIRA - "Smart feature-based interactive" - search tool ( https://smafira.bf3r.de ) will employ this classifier for supporting the retrieval of alternative methods to animal experiments. The corpus is available for download ( https://doi.org/10.5281/zenodo.7152295 ), as well as the source code ( https://github.com/mariananeves/goldhamster ) and the model ( https://huggingface.co/SMAFIRA/goldhamster ).

Project description:Underwater video monitoring systems are being widely used in fisheries to investigate fish behavior in relation to fishing gear and fishing gear performance during fishing. Such systems can be useful to evaluate the catch composition as well. In demersal trawl fisheries, however, their applicability can be challenged by low light conditions, mobilized sediment and scattering in murky waters. In this study, we introduce a novel observation system (called NepCon) which aims at reducing current limitations by combining an optimized image acquisition setup and tailored image analyses software. The NepCon system includes a high-contrast background to enhance the visibility of the target objects, a compact camera and an artificial light source. The image analysis software includes a machine learning algorithm which is evaluated here to test automatic detection and count of Norway lobster (Nephrops norvegicus). NepCon is specifically designed for applications in demersal trawls and this first phase aims at increasing the accuracy of N. norvegicus detection at the data acquisition level. To find the best contrasting background for the purpose we compared the output of four image segmentation methods applied to static images of N. norvegicus fixed in front of four test background colors. The background color with the best performance was then used to evaluate computer vision and deep learning approaches for automatic detection, tracking and counting of N. norvegicus in the videos. In this initial phase we tested the system in an experimental setting to understand the feasibility of the system for future implementation in real demersal fishing conditions. The N. norvegicus directed trawl fishery typically has no assistance from underwater observation technology and therefore are largely conducted blindly. The demonstrated perception system achieves 76% accuracy (F-score) in automatic detection and count of N. norvegicus, which provides a significant elevation of the current benchmark.

Dataset Information

Automatic detection of image manipulations in the biomedical literature.

Publications

Automatic detection of image manipulations in the biomedical literature.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets