Deep learning-based high-throughput detection of in vitro germination to assess pollen viability from microscopic images.

Abstract

In vitro pollen germination is considered the most efficient method to assess pollen viability. The pollen germination frequency and pollen tube length, which are key indicators of pollen viability, should be accurately measured during in vitro culture. In this study, a Mask R-CNN model trained using microscopic images of tree peony (Paeonia suffruticosa) pollen has been proposed to rapidly detect the pollen germination rate and pollen tube length. To reduce the workload during image acquisition, images of synthesized crossed pollen tubes were added to the training dataset, significantly improving the model accuracy in recognizing crossed pollen tubes. At an Intersection over Union threshold of 50%, a mean average precision of 0.949 was achieved. The performance of the model was verified using 120 testing images. The R2 value of the linear regression model using detected pollen germination frequency against the ground truth was 0.909 and that using average pollen tube length was 0.958. Further, the model was successfully applied to two other plant species, indicating a good generalizability and potential to be applied widely.

Plant phenotyping relevance

顕微鏡画像から花粉発芽率と花粉管長を自動推定するMask R-CNN手法を開発し、精度検証と他種への適用を行っており、植物表現型取得が研究の中心です。

Code and data availability

The paper's Data availability statement explicitly deposits the authors' Mask R-CNN pollen germination detection code in a public GitHub repository. Training/testing images are only available upon request (request_only), but the code asset qualifies as public and paper-specific. The makesense.ai URL is a generic third‑