Raghavendra Selvan

Dr. Raghavendra Selvan


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 February 2020 in Plant Methods
Verified
Journal Article
Open access
PDF file
ASAbraham George Smith
Abraham George Smith
JPJens Petersen
Jens Petersen
RSRaghavendra Selvan
Raghavendra Selvan
CRCamilla Ruø Rasmussen
Camilla Ruø Rasmussen
Background: Plant root research can provide a way to attain stress-tolerant crops that produce greater yield in a diverse array of conditions. Phenotyping roots in soil is often challenging due to the roots being difficult to access and the use of time consuming manual methods. Rhizotrons allow visual inspection of root growth through transparent surfaces. Agronomists currently manually label photographs of roots obtained from rhizotrons using a line-intersect method to obtain root length density and rooting depth measurements which are essential for their experiments. We investigate the effectiveness of an automated image segmentation method based on the U-Net Convolutional Neural Network (CNN) architecture to enable such measurements. We design a data-set of 50 annotated chicory (Cichorium intybus L.) root images which we use to train, validate and test the system and compare against a baseline built using the Frangi vesselness filter. We obtain metrics using manual annotations and line-intersect counts. Results: Our results on the held out data show our proposed automated segmentation system to be a viable solution for detecting and quantifying roots. We evaluate our system using 867 images for which we have obtained line-intersect counts, attaining a Spearman rank correlation of 0.9748 and an $$r^2$$r2 of 0.9217. We also achieve an $$F_1$$F1 of 0.7 when comparing the automated segmentation to the manual annotations, with our automated segmentation system producing segmentations with higher quality than the manual annotations for large portions of the image. Conclusion: We have demonstrated the feasibility of a U-Net based CNN system for segmenting images of roots in soil and for replacing the manual line-intersect method. The success of our approach is also a demonstration of the feasibility of deep learning in practice for small research groups needing to create their own custom labelled dataset from scratch.

31 May 2021 in Nature Communications
Verified
Journal Article
Open access
PDF file
IAIlary Allodi
Ilary Allodi
RMRoser Montañana-Rosell
Roser Montañana-Rosell
RSRaghavendra Selvan
Raghavendra Selvan
PLPeter Löw
Peter Löw
OKOle Kiehn
Ole Kiehn
ALS is characterized by progressive inability to execute movements. Motor neurons innervating fast-twitch muscle-fibers preferentially degenerate. The reason for this differential vulnerability and its consequences on motor output is not known. Here, we uncover that fast motor neurons receive stronger inhibitory synaptic inputs than slow motor neurons, and disease progression in the SOD1G93A mouse model leads to specific loss of inhibitory synapses onto fast motor neurons. Inhibitory V1 interneurons show similar innervation pattern and loss of synapses. Moreover, from postnatal day 63, there is a loss of V1 interneurons in the SOD1G93A mouse. The V1 interneuron degeneration appears before motor neuron death and is paralleled by the development of a specific locomotor deficit affecting speed and limb coordination. This distinct ALS-induced locomotor deficit is phenocopied in wild-type mice but not in SOD1G93A mice after appearing of the locomotor phenotype when V1 spinal interneurons are silenced. Our study identifies a potential source of non-autonomous motor neuronal vulnerability in ALS and links ALS-induced changes in locomotor phenotype to inhibitory V1-interneurons.

10 October 2019
Verified
Book Chapter
Closed access
PDF file
AJAntonio Garcia-Uceda Juarez
Antonio Garcia-Uceda Juarez
RSRaghavendra Selvan
Raghavendra Selvan
ZSZaigham Saghir
Zaigham Saghir
MBMarleen de Bruijne
Marleen de Bruijne

1 August 2020 in Medical Image Analysis
Verified
Journal Article
Closed access
RSRaghavendra Selvan
Raghavendra Selvan
TKThomas Kipf
Thomas Kipf
MWMax Welling
Max Welling
AJAntonio Garcia-Uceda Juarez
Antonio Garcia-Uceda Juarez
JPJesper H Pedersen
Jesper H Pedersen
MBMarleen de Bruijne
Marleen de Bruijne

27 July 2023 in Nature Neuroscience
Verified
Journal Article
Open access
PDF file
HGHaizea Goñi-Erro
Haizea Goñi-Erro
RSRaghavendra Selvan
Raghavendra Selvan
VCVittorio Caggiano
Vittorio Caggiano
RLRoberto Leiras
Roberto Leiras
OKOle Kiehn
Ole Kiehn
Arrest of ongoing movements is an integral part of executing motor programs. Behavioral arrest may happen upon termination of a variety of goal-directed movements or as a global motor arrest either in the context of fear or in response to salient environmental cues. The neuronal circuits that bridge with the executive motor circuits to implement a global motor arrest are poorly understood. We report the discovery that the activation of glutamatergic Chx10-derived neurons in the pedunculopontine nucleus (PPN) in mice arrests all ongoing movements while simultaneously causing apnea and bradycardia. This global motor arrest has a pause-and-play pattern with an instantaneous interruption of movement followed by a short-latency continuation from where it was paused. Mice naturally perform arrest bouts with the same combination of motor and autonomic features. The Chx10-PPN-evoked arrest is different to ventrolateral periaqueductal gray-induced freezing. Our study defines a motor command that induces a global motor arrest, which may be recruited in response to salient environmental cues to allow for a preparatory or arousal state, and identifies a locomotor-opposing role for rostrally biased glutamatergic neurons in the PPN.

16 September 2022
Verified
Book Chapter
Closed access
PDF file
RSRaghavendra Selvan
Raghavendra Selvan
NBNikhil Bhagwat
Nikhil Bhagwat
LALasse F. Wolff Anthony
Lasse F. Wolff Anthony
BKBenjamin Kanding
Benjamin Kanding
EDErik B. Dam
Erik B. Dam