A large-scale optical microscopy image dataset of potato tuber for deep learning based plant cell assessment
Problem
Researchers lacked a large annotated microscopy image dataset for deep-learning-based assessment of plant cell microstructures in potato tubers.
Why it matters
Automated plant cell assessment could speed up crop quality evaluation and plant biology research.
What the AI did
A CNN (VGG16) performed multi-label cell classification on unstained and stained images to validate the dataset annotations, and a semantic segmentation algorithm verified ground-truth labels.
Results
Classification accuracy up to 0.94; F2-score 0.92
Impact
The validated dataset of 15,938 annotated images enables deep-learning-based plant cell assessment, per the abstract.
Record
| Venue | Scientific Data |
|---|---|
| Published | 2020 |
| Work type | data-paper |
| Authors | Sumona Biswas, Shovan Barma |
| Citations | 25 (OpenAlex, at import time) |
| References | 48 |
| Model or method | VGG16 (CNN) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41597-020-00706-9 |
| Open access | gold |
| Keywords | potato tuber, microscopy dataset, deep learning, VGG16, cell classification, semantic segmentation |
Importance rating
incremental / niche
Niche: annotated potato tuber microscopy dataset aiding plant cell research and crop quality evaluation; no scale of benefit stated.