A deep learning-based approach for high-throughput hypocotyl phenotyping
  • Metaadatok
Tartalom: http://real.mtak.hu/103504/
Archívum: REAL
Gyűjtemény: Status = Published
Subject = Q Science / természettudomány: QH Natural history / természetrajz: QH301 Biology / biológia: QH3011 Biochemistry / biokémia
Subject = Q Science / természettudomány: QK Botany / növénytan
Subject = Q Science / természettudomány: QH Natural history / természetrajz: QH301 Biology / biológia: QH3015 Molecular biology / molekuláris biológia
Type = Article
Cím:
A deep learning-based approach for high-throughput hypocotyl phenotyping
Létrehozó:
Dobos, Orsolya
Horváth, Péter
Nagy, Ferenc István
Danka, Tivadar
Viczián, András
Kiadó:
American Society of Plant Biologists
Dátum:
2019
Téma:
QH3011 Biochemistry / biokémia
QH3015 Molecular biology / molekuláris biológia
QK Botany / növénytan
Tartalmi leírás:
Hypocotyl length determination is a widely used method to phenotype young seedlings. The measurement itself has advanced from using rulers and millimetre papers to assessing digitized images but remains a labour-intensive, monotonous and time-consuming procedure. To make high-throughput plant phenotyping possible, we developed a deep learning-based approach to simplify and accelerate this method. Our pipeline does not require a specialized imaging system but works well with low-quality images produced with a simple flatbed scanner or a smartphone camera. Moreover, it is easily adaptable for a diverse range of datasets not restricted to Arabidopsis (Arabidopsis thaliana). Furthermore, we show that the accuracy of the method reaches human performance. We not only provide the full code at https://github.com/biomag-lab/hypocotyl-UNet, but also give detailed instructions on how the algorithm can be trained with custom data, tailoring it for the requirements and imaging setup of the user.
Nyelv:
angol
Típus:
Article
PeerReviewed
info:eu-repo/semantics/article
Formátum:
text
Azonosító:
Dobos, Orsolya and Horváth, Péter and Nagy, Ferenc István and Danka, Tivadar and Viczián, András (2019) A deep learning-based approach for high-throughput hypocotyl phenotyping. PLANT PHYSIOLOGY, AiP. ISSN 0032-0889
Kapcsolat:
MTMT:30866336 10.1104/pp.19.00728