Dataset Information

Enabling automated herbarium sheet image post-processing using neural network models for color reference chart detection.

ABSTRACT: Premise:Large-scale efforts to digitize herbaria have resulted in more than 18 million publicly available Plantae images on sites such as iDigBio. The automation of image post-processing will lead to time savings in the digitization of biological specimens, as well as improvements in data quality. Here, new and modified neural network methodologies were developed to automatically detect color reference charts (CRC), enabling the future automation of various post-processing tasks. Methods and Results:We used 1000 herbarium specimen images from 52 herbaria to test our novel neural network model, ColorNet, which was developed to identify CRCs smaller than 4 cm2, resulting in a 30% increase in accuracy over the performance of other state-of-the-art models such as Faster R-CNN. For larger CRCs, we propose modifications to Faster R-CNN to increase inference speed. Conclusions:Our proposed neural networks detect a range of CRCs, which may enable the automation of post-processing tasks found in herbarium digitization workflows, such as image orientation or white balance correction.

SUBMITTER: Ledesma DA

PROVIDER: S-EPMC7073326 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Enabling automated herbarium sheet image post-processing using neural network models for color reference chart detection.

Ledesma Dakila A DA Powell Caleb A CA Shaw Joey J Qin Hong H

Applications in plant sciences 20200302 3

<h4>Premise</h4>Large-scale efforts to digitize herbaria have resulted in more than 18 million publicly available Plantae images on sites such as iDigBio. The automation of image post-processing will lead to time savings in the digitization of biological specimens, as well as improvements in data quality. Here, new and modified neural network methodologies were developed to automatically detect color reference charts (CRC), enabling the future automation of various post-processing tasks.<h4>Meth ...[more]

PMID: 32185122

Similar Datasets

Project description:BackgroundManually extracted data points from health records are collated on an institutional, provincial, and national level to facilitate clinical research. However, the labour-intensive clinical chart review process puts an increasing burden on healthcare system budgets. Therefore, an automated information extraction system is needed to ensure the timeliness and scalability of research data.MethodsWe used a dataset of 100 synoptic operative and 100 pathology reports, evenly split into 50 reports in training and test sets for each report type. The training set guided our development of a Natural Language Processing (NLP) extraction pipeline system, which accepts scanned images of operative and pathology reports. The system uses a combination of rule-based and transfer learning methods to extract numeric encodings from text. We also developed visualization tools to compare the manual and automated extractions. The code for this paper was made available on GitHub.ResultsA test set of 50 operative and 50 pathology reports were used to evaluate the extraction accuracies of the NLP pipeline. Gold standard, defined as manual extraction by expert reviewers, yielded accuracies of 90.5% for operative reports and 96.0% for pathology reports, while the NLP system achieved overall 91.9% (operative) and 95.4% (pathology) accuracy. The pipeline successfully extracted outcomes data pertinent to breast cancer tumor characteristics (e.g. presence of invasive carcinoma, size, histologic type), prognostic factors (e.g. number of lymph nodes with micro-metastases and macro-metastases, pathologic stage), and treatment-related variables (e.g. margins, neo-adjuvant treatment, surgical indication) with high accuracy. Out of the 48 variables across operative and pathology codebooks, NLP yielded 43 variables with F-scores of at least 0.90; in comparison, a trained human annotator yielded 44 variables with F-scores of at least 0.90.ConclusionsThe NLP system achieves near-human-level accuracy in both operative and pathology reports using a minimal curated dataset. This system uniquely provides a robust solution for transparent, adaptable, and scalable automation of data extraction from patient health records. It may serve to advance breast cancer clinical research by facilitating collection of vast amounts of valuable health data at a population level.

Dataset Information

Enabling automated herbarium sheet image post-processing using neural network models for color reference chart detection.

Publications

Enabling automated herbarium sheet image post-processing using neural network models for color reference chart detection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets