Exploring the efficacy of caption search for bioscience journal search interfaces

Hearst, Marti A.; Divoli, Anna; Ye, Jerry; Wooldridge, Michael A.

doi:10.3115/1572392.1572406

Cited by 12 publications

(15 citation statements)

References 18 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To some extent, this mimics the results of Hearst et al [13] who performed a user study on the viability of using caption searching to find relevant papers in the bioscience literature and found that “7 out of 8 [users] said they would use a search system with this kind of feature.” Only one user found that the alternative search engine returned better results. Half found SLIF better and more relevant, and the other three thought the results were not directly comparable.…”

Section: User Studysupporting

confidence: 76%

Structured literature image finder: Parsing text and figures in biomedical literature

Ahmed

Arnold

Coelho

et al. 2010

Web Semantics: Science, Services and Agents on the World Wide W

View full text Add to dashboard Cite

The SLIF project combines text-mining and image processing to extract structured information from biomedical literature. SLIF extracts images and their captions from published papers. The captions are automatically parsed for relevant biological entities (protein and cell type names), while the images are classified according to their type (e.g., micrograph or gel). Fluorescence microscopy images are further processed and classified according to the depicted subcellular localization. The results of this process can be queried online using either a user-friendly web-interface or an XML-based web-service. As an alternative to the targeted query paradigm, SLIF also supports browsing the collection based on latent topic models which are derived from both the annotated text and the image data. The SLIF web application, as well as labeled datasets used for training system components, is publicly available at http://slif.cbi.cmu.edu.

show abstract

Section: User Studysupporting

confidence: 76%

Structured literature image finder: Parsing text and figures in biomedical literature

Ahmed

Arnold

Coelho

et al. 2010

Web Semantics: Science, Services and Agents on the World Wide W

View full text Add to dashboard Cite

show abstract

“…To some extent, this mimics the results of Hearst et al [13] who performed a user study on the viability of using caption searching to find relevant papers in the bioscience literature and found that "7 out of 8 [users] said they would use a search system with this kind of feature." Only one user found that the alternative search engine returned better results.…”

Section: User Studysupporting

confidence: 55%

Structured Literature Image Finder: Parsing Text and Figures in Biomedical Literature

et al. 2010

View full text Add to dashboard Cite

The SLIF project combines text-mining and image processing to extract structured information from biomedical literature.SLIF extracts images and their captions from published papers. The captions are automatically parsed for relevant biological entities (protein and cell type names), while the images are classified according to their type (e.g., micrograph or gel). Fluorescence microscopy images are further processed and classified according to the depicted subcellular localization.The results of this process can be queried online using either a user-friendly web-interface or an XML-based web-service. As an alternative to the targeted query paradigm, SLIF also supports browsing the collection based on latent topic models which are derived from both the annotated text and the image data.The SLIF web application, as well as labeled datasets used for training system components, is publicly available at http://slif.cbi.cmu.edu.

show abstract

“…They can fairly accurately form an opinion about the relevance of a publication to the clinical situation based on its title alone; however the title is not always sufficient in determining the evidence-based practice usefulness (henceforth evidence-based utility or clinical utility) of a publication [1]. There are indications that user experience can be improved by augmenting short bibliographic references with images [2].…”

Section: Introductionmentioning

confidence: 99%

<title>Exploring use of images in clinical articles for decision support in evidence-based medicine</title>

Demner‐Fushman

Srinivasan

et al. 2008

SPIE Proceedings

View full text Add to dashboard Cite

Essential information is often conveyed pictorially (images, illustrations, graphs, charts, etc.) in biomedical publications. A clinician's decision to access the full text when searching for evidence in support of clinical decision is frequently based solely on a short bibliographic reference. We seek to automatically augment these references with images from the article that may assist in finding evidence.In a previous study, the feasibility of automatically classifying images by usefulness (utility) in finding evidence was explored using supervised machine learning and achieved 84.3% accuracy using image captions for modality and 76.6% accuracy combining captions and image data for utility on 743 images from articles over 2 years from a clinical journal. Our results indicated that automatic augmentation of bibliographic references with relevant images was feasible. Other research in this area has determined improved user experience by showing images in addition to the short bibliographic reference. Multi-panel images used in our study had to be manually pre-processed for image analysis, however. Additionally, all image-text on figures was ignored.In this article, we report on developed methods for automatic multi-panel image segmentation using not only image features, but also clues from text analysis applied to figure captions. In initial experiments on 516 figure images we obtained 95.54% accuracy in correctly identifying and segmenting the sub-images. The errors were flagged as disagreements with automatic parsing of figure caption text allowing for supervised segmentation. For localizing text and symbols, on a randomly selected test set of 100 single panel images our methods reported, on the average, precision and recall of 78.42% and 89.38%, respectively, with an accuracy of 72.02%.

show abstract

Exploring the efficacy of caption search for bioscience journal search interfaces

Cited by 12 publications

References 18 publications

Structured literature image finder: Parsing text and figures in biomedical literature

Structured literature image finder: Parsing text and figures in biomedical literature

Structured Literature Image Finder: Parsing Text and Figures in Biomedical Literature

<title>Exploring use of images in clinical articles for decision support in evidence-based medicine</title>

Contact Info

Product

Resources

About