SegRoot: A high throughput segmentation method for root image analysis

Wang, Tao; Rostamza, Mina; Song, Zhihang; Wang, Liangju; McNickle, Gordon G.; Iyer‐Pascuzzi, Anjali S.; Qiu, Zhengjun; Jin, Jian Xun

doi:10.1016/j.compag.2019.05.017

Cited by 74 publications

(69 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To test the performance of the SR models, we used a data set of 65 soybean (Glycine max (L.) Merr.) roots (https://github.com/wtwtw t0330/ SegRoot [accessed 11 June 2020]) (Wang et al, 2019).…”

Section: Data Setsmentioning

confidence: 99%

Super resolution for root imaging

et al. 2020

View full text Add to dashboard Cite

Over the past decade, advances in sensing devices and computer systems have allowed for the proliferation of high-throughput plant phenotyping systems (Das Choudhury et al., 2019). These systems are designed to acquire and analyze a large number of plant traits (Han et al., 2014; Krieger, 2014), including the measure of small structures, such as the venation network of leaves (Endler, 1998; Green et al., 2014). However, the characterization of plant roots is more challenging because they are "hidden" in the soil (Atkinson et al., 2019), which limits the type of sensors and techniques that can be applied. A number of types of methods have previously been used to analyze root traits. Non-imaging-based in situ methods estimate

show abstract

Section: Data Setsmentioning

confidence: 99%

Super resolution for root imaging

et al. 2020

View full text Add to dashboard Cite

show abstract

“…GiA Roots has been adopted to study components of seedling water deficit response [81][82][83] and linkage drag of genes underpinning seeding root system traits [84] in wheat. However, GiA Roots has slowly been rendered outdated by new software tools such as Digital Imaging of Root Traits (DIRT) [85] and the neural network driven programs SegRoot [86] and saRIA [87], described below.…”

Section: Software Applicable To Root Phenotyping In Wheatmentioning

confidence: 99%

“…The semi-automated saRIA [87] and the fully automated SegRoot [86] are recently published tools that can quantify useful traits in wheat root systems. Each of these tools was trained using a convolutional neural network (CNN) to identify roots in visually noisy images [45].…”

Section: Recent Advances In Root Phenotyping Using Deep Learningmentioning

confidence: 99%

“…SegRoot is fully automated and has its output traits limited only to length. However, SegRoot has a very low image quality requirement in that it is amenable to analyzing roots from complex, visually heterogeneous soil backgrounds [86]. Both SegRoot and saRIA were tested for accuracy against other published tools, and both outperformed GiA Roots in the identification of roots in heterogeneous growth media, demonstrating clear benefits of machine learning-informed approaches in root phenotyping.…”

Section: Recent Advances In Root Phenotyping Using Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Image-Based, Organ-Level Plant Phenotyping for Wheat Improvement

2020

View full text Add to dashboard Cite

Wheat was one of the first grain crops domesticated by humans and remains among the major contributors to the global calorie and protein budget. The rapidly expanding world population demands further enhancement of yield and performance of wheat. Phenotypic information has historically been instrumental in wheat breeding for improved traits. In the last two decades, a steadily growing collection of tools and imaging software have given us the ability to quantify shoot, root, and seed traits with progressively increasing accuracy and throughput. This review discusses challenges and advancements in image analysis platforms for wheat phenotyping at the organ level. Perspectives on how these collective phenotypes can inform basic research on understanding wheat physiology and breeding for wheat improvement are also provided.

show abstract

“…AirSurf-Lettuce combines computer vision algorithms and deep learning classifiers to automatically measure the distribution of field iceberg lettuce using super-scale NDVI aerial images, and it has been used to demonstrate the high value of this method in field crop segmentation (Bauer et al, 2019). Wang et al (2019) proposed a fully automatic root feature extraction method based on CNN called SegRoot and validated its segmentation performance on soybean root images using transfer learning.…”

Section: Introductionmentioning

confidence: 99%

High-Throughput in situ Root Image Segmentation Based on the Improved DeepLabv3+ Method

et al. 2020

View full text Add to dashboard Cite

The Rhizotrons method is an important means of detecting dynamic growth and development phenotypes of plant roots. However, the segmentation of root images is a critical obstacle restricting further development of this method. At present, researchers mostly use direct manual drawings or software-assisted manual drawings to segment root systems for analysis. Root systems can be segmented from root images obtained by the Rhizotrons method, and then, root system lengths and diameters can be obtained with software. This type of image segmentation method is extremely inefficient and very prone to human error. Here, we investigate the effectiveness of an automated image segmentation method based on the DeepLabv3+ convolutional neural network (CNN) architecture to streamline such measurements. We have improved the upsampling portion of the DeepLabv3+ network and validated it using in situ images of cotton roots obtained with a micro root window root system monitoring system. Segmentation performance of the proposed method utilizing WinRHIZO Tron MF analysis was assessed using these images. After 80 epochs of training, the final verification set F1-score, recall, and precision were 0.9773, 0.9847, and 0.9702, respectively. The Spearman rank correlation between the manually obtained Rhizotrons manual segmentation root length and automated root length was 0.9667 (p < 10 −8), with r 2 = 0.9449. Based on the comparison of our segmentation results with those of traditional manual and U-net segmentation methods, this novel method can more accurately segment root systems in complex soil environments. Thus, using the improved DeepLabv3+ to segment root systems based on micro-root images is an effective method for accurately and quickly segmenting root systems in a homogeneous soil environment and has clear advantages over traditional manual segmentation.

show abstract

SegRoot: A high throughput segmentation method for root image analysis

Cited by 74 publications

References 19 publications

Super resolution for root imaging

Super resolution for root imaging

Image-Based, Organ-Level Plant Phenotyping for Wheat Improvement

High-Throughput in situ Root Image Segmentation Based on the Improved DeepLabv3+ Method

Contact Info

Product

Resources

About