Abstract. Root phenotyping is a challenging task, mainly because of the hidden nature of this organ. Only recently, imaging technologies have become available that allow us to elucidate the dynamic establishment of root structure and function in the soil. In root tips, optical analysis of the relative elemental growth rates in root expansion zones of hydroponically-grown plants revealed that it is the maximum intensity of cellular growth processes rather than the length of the root growth zone that control the acclimation to dynamic changes in temperature. Acclimation of entire root systems was studied at high throughput in agar-filled Petri dishes. In the present study, optical analysis of root system architecture showed that low temperature induced smaller branching angles between primary and lateral roots, which caused a reduction in the volume that roots access at lower temperature. Simulation of temperature gradients similar to natural soil conditions led to differential responses in basal and apical parts of the root system, and significantly affected the entire root system. These results were supported by first data on the response of root structure and carbon transport to different root zone temperatures. These data were acquired by combined magnetic resonance imaging (MRI) and positron emission tomography (PET). They indicate acclimation of root structure and geometry to temperature and preferential accumulation of carbon near the root tip at low root zone temperatures. Overall, this study demonstrated the value of combining different phenotyping technologies that analyse processes at different spatial and temporal scales. Only such an integrated approach allows us to connect differences between genotypes obtained in artificial high throughput conditions with specific characteristics relevant for field performance. Thus, novel routes may be opened up for improved plant breeding as well as for mechanistic understanding of root structure and function.

RI is a powerful tool for diagnosis and screening of breast cancer (1). However, widespread use of breast MRI has been restricted because of the limited availability of sites that offer this method. One major reason for limited availability is the lack of radiologists who can offer substantial expertise in interpreting breast MR images. Sophisticated machine learning approaches show promise in complementing human diagnosis (2). Broadly speaking, machine learning can be divided into two major classes: one is radiomic analysis (RA), where handmade image features are extracted; and the other is the concept of convolutional neural networks (CNN), in which the computer learns to recognize image features on its own, usually on the basis of a set of labeled training examples. Both approaches have been pursued with considerable success for image interpretation, although in different areas: In the field of diagnostic radiology, RA has been successfully used to further classify tumor types (3,4). However, CNNs require a larger pool of training images before they achieve a clinically useful performance. Within radiology, breast imaging, specifically mammographic screening, lends itself to be used with CNNs because similarly large data sets are available (5,6). With such large mammographic data sets, and with the advent of increased computing power, deep learning may have the potential to outperform regular computer-assisted diagnosis systems for mammographic interpretation (5). Studies are limited regarding the use of RA or CNNs for diagnostic classification of contrast agent-enhancing breast lesions (ie, for differential diagnosis of benign vs malignant lesions). Bickelhaupt et al (7) used machine learning for further characterization of lesions suspicious for cancer that were found on digital mammographic images and used unenhanced and diffusion-weighted MRI for this purpose. However, the use of RA or CNNs for classification of enhancing lesions observed at regular, clinical, dynamic contrast agent-enhanced, or multiparametric breast MRI is not established. Because breast MRI is performed less than mammographic screening, available breast MRI data sets are smaller

identifying image features that are robust with respect to segmentation variability is a tough challenge in radiomics. So far, this problem has mainly been tackled in test-retest analyses. in this work we analyse radiomics feature reproducibility in two phases: first with manual segmentations provided by four expert readers and second with probabilistic automated segmentations using a recently developed neural network (pHiseg). We test feature reproducibility on three publicly available datasets of lung, kidney and liver lesions. We find consistent results both over manual and automated segmentations in all three datasets and show that there are subsets of radiomic features which are robust against segmentation variability and other radiomic features which are prone to poor reproducibility under differing segmentations. By providing a detailed analysis of robustness of the most common radiomics features across several datasets, we envision that more reliable and reproducible radiomic models can be built in the future based on this work.

No abstract