Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Genomic resources in plant breeding for sustainable agriculture.

In Journal of plant physiology

Climate change during the last 40 years has had a serious impact on agriculture and threatens global food and nutritional security. From over half a million plant species, cereals and legumes are the most important for food and nutritional security. Although systematic plant breeding has a relatively short history, conventional breeding coupled with advances in technology and crop management strategies has increased crop yields by 56 % globally between 1965-85, referred to as the Green Revolution. Nevertheless, increased demand for food, feed, fiber, and fuel necessitates the need to break existing yield barriers in many crop plants. In the first decade of the 21st century we witnessed rapid discovery, transformative technological development and declining costs of genomics technologies. In the second decade, the field turned towards making sense of the vast amount of genomic information and subsequently moved towards accurately predicting gene-to-phenotype associations and tailoring plants for climate resilience and global food security. In this review we focus on genomic resources, genome and germplasm sequencing, sequencing-based trait mapping, and genomics-assisted breeding approaches aimed at developing biotic stress resistant, abiotic stress tolerant and high nutrition varieties in six major cereals (rice, maize, wheat, barley, sorghum and pearl millet), and six major legumes (soybean, groundnut, cowpea, common bean, chickpea and pigeonpea). We further provide a perspective and way forward to use genomic breeding approaches including marker-assisted selection, marker-assisted backcrossing, haplotype based breeding and genomic prediction approaches coupled with machine learning and artificial intelligence, to speed breeding approaches. The overall goal is to accelerate genetic gains and deliver climate resilient and high nutrition crop varieties for sustainable agriculture.

Thudi Mahendar, Palakurthi Ramesh, Schnable James C, Chitikineni Annapurna, Dreisigacker Susanne, Mace Emma, Srivastava Rakesh K, Satyavathi C Tara, Odeny Damaris, Tiwari Vijay K, Lam Hon-Ming, Hong Yan Bin, Singh Vikas K, Li Guowei, Xu Yunbi, Chen Xiaoping, Kaila Sanjay, Nguyen Henry, Sivasankar Sobhana, Jackson Scott A, Close Timothy J, Shubo Wan, Varshney Rajeev K


Genomic breeding, Genomic selection, Genomics, Genomics-assisted breeding, Genotyping platforms, Sequence-based trait mapping, Sequencing

Radiology Radiology

[Artificial Intelligence in Radiology - Definition, Potential and Challenges].

In Praxis

Artificial Intelligence in Radiology - Definition, Potential and Challenges Abstract. Artificial Intelligence (AI) is omnipresent. It has neatly permeated our daily life, even if we are not always fully aware of its ubiquitous presence. The healthcare sector in particular is experiencing a revolution which will change our daily routine considerably in the near future. Due to its advanced digitization and its historical technical affinity radiology is especially prone to these developments. But what exactly is AI and what makes AI so potent that established medical disciplines such as radiology worry about their future job perspectives? What are the assets of AI in radiology today - and what are the major challenges? This review article tries to give some answers to these questions.

Baessler Bettina


Artificial Intelligence, Bildgebung, Deep Learning, Intelligence artificielle, K√ľnstliche Intelligenz, Radiologie, apprentissage machine, apprentissage profond, deep learning, imagerie, imaging, machine learning, maschinelles Lernen, radiologie, radiology

General General

Inhibiting ferroptosis: A novel approach for stroke therapeutics.

In Drug discovery today ; h5-index 68.0

Stroke ranks as the second leading cause of death across the globe. Despite advances in stroke therapeutics, no US Food and Drug Administration (FDA)-approved drugs that can minimize neuronal injury and restore neurological function are clinically available. Ferroptosis, a regulated iron-dependent form of nonapoptotic cell death, has been shown to contribute to stroke-mediated neuronal damage. Inhibitors of ferroptosis have also been validated in several stroke models of ischemia or intracerebral hemorrhage. Herein, we review the therapeutic activity of inhibitors of ferroptosis in stroke models. We further summarize previously reported neuroprotectants that show protective effects in stroke models that have been recently validated as ferroptosis inhibitors. These findings reveal new mechanisms for neuroprotection and highlight the importance of ferroptosis during stroke processes.

Jin Yizhen, Zhuang Yuxin, Liu Mei, Che Jinxin, Dong Xiaowu


Ophthalmology Ophthalmology

Pathological myopia classification with simultaneous lesion segmentation using deep learning.

In Computer methods and programs in biomedicine

BACKGROUND AND OBJECTIVES : Pathological myopia (PM) is the seventh leading cause of blindness, with a reported global prevalence up to 3%. Early and automated PM detection from fundus images could aid to prevent blindness in a world population that is characterized by a rising myopia prevalence. We aim to assess the use of convolutional neural networks (CNNs) for the detection of PM and semantic segmentation of myopia-induced lesions from fundus images on a recently introduced reference data set.

METHODS : This investigation reports on the results of CNNs developed for the recently introduced Pathological Myopia (PALM) dataset, which consists of 1200 images. Our CNN bundles lesion segmentation and PM classification, as the two tasks are heavily intertwined. Domain knowledge is also inserted through the introduction of a new Optic Nerve Head (ONH)-based prediction enhancement for the segmentation of atrophy and fovea localization. Finally, we are the first to approach fovea localization using segmentation instead of detection or regression models. Evaluation metrics include area under the receiver operating characteristic curve (AUC) for PM detection, Euclidean distance for fovea localization, and Dice and F1 metrics for the semantic segmentation tasks (optic disc, retinal atrophy and retinal detachment).

RESULTS : Models trained with 400 available training images achieved an AUC of 0.9867 for PM detection, and a Euclidean distance of 58.27 pixels on the fovea localization task, evaluated on a test set of 400 images. Dice and F1 metrics for semantic segmentation of lesions scored 0.9303 and 0.9869 on optic disc, 0.8001 and 0.9135 on retinal atrophy, and 0.8073 and 0.7059 on retinal detachment, respectively.

CONCLUSIONS : We report a successful approach for a simultaneous classification of pathological myopia and segmentation of associated lesions. Our work was acknowledged with an award in the context of the "Pathological Myopia detection from retinal images" challenge held during the IEEE International Symposium on Biomedical Imaging (April 2019). Considering that (pathological) myopia cases are often identified as false positives and negatives in glaucoma deep learning models, we envisage that the current work could aid in future research to discriminate between glaucomatous and highly-myopic eyes, complemented by the localization and segmentation of landmarks such as fovea, optic disc and atrophy.

Hemelings Ruben, Elen Bart, Blaschko Matthew B, Jacob Julie, Stalmans Ingeborg, De Boever Patrick


Pathological myopia, convolutional neural network, fovea localization, fundus image, glaucoma, peripapillary atrophy, retinal detachment

Surgery Surgery

Comparing the performance of a deep convolutional neural network with orthopaedic surgeons on the identification of total hip prosthesis design from plain radiographs.

In Medical physics ; h5-index 59.0

PURPOSE : A crucial step in the preoperative planning for a revision total hip replacement (THR) surgery is the accurate identification of the failed implant design, especially if one or more well-fixed/functioning components are to be retained. Manual identification of the implant design from preoperative radiographic images can be time-consuming and inaccurate, which can ultimately lead to increased operating room time, more complex surgery, and increased healthcare costs.

METHOD : In this study, we present a novel approach to identifying THR femoral implants' design from plain radiographs using a convolutional neural network (CNN). We evaluated a total of 402 radiographs of nine different THR implant designs including, Accolade II (130 radiographs), Corail (89 radiographs), M/L Taper (31 radiographs), Summit (31 radiographs), Anthology (26 radiographs), Versys (26 radiographs), S-ROM (24 radiographs), Taperloc Standard Offset (24 radiographs), and Taperloc High Offset (21 radiographs). We implemented a transfer learning approach and adopted a DenseNet-201 CNN architecture by replacing the final classifier with nine fully connected neurons. Furthermore, we used saliency maps to explain the CNN decision-making process by visualizing the most important pixels in a given radiograph on the CNN's outcome. We also compared the CNN's performance with three board-certified and fellowship-trained orthopaedic surgeons.

RESULTS : The CNN achieved the same or higher performance than at least one of the surgeons in identifying eight out of nine THR implant designs and underperformed all of the surgeons in identifying one THR implant design (Anthology). Overall, the CNN achieved a lower cohen's kappa (0.78) than surgeon 1 (1.00), the same cohen's kappa as surgeon 2 (0.78), and a slightly higher cohen's kappa than surgeon 3 (0.76) in identifying all the nine THR implant designs. Furthermore, the saliency maps showed that the CNN generally focused on each implant's unique design features to make a decision. Regarding the time spent performing the implant identification, the CNN accomplished this task in ~0.06 seconds per radiograph. The surgeon's identification time varied based on the method they utilized. When using their personal experience to identify the THR implant design, they spent negligible time. However, the identification time increased to an average of 8.4 minutes (standard deviation 6.1 minutes) per radiograph when they used another identification method (online search, consulting with the orthopaedic company representative, and using image atlas), which occurred in about 17% of cases in the test subset (40 radiographs).

CONCLUSIONS : CNNs such as the one developed in this study can be used to automatically identify the design of a failed THR femoral implant pre-operatively in just a fraction of a second, saving time and in some cases improving identification accuracy.

Borjali Alireza, Chen Antonia F, Bedair Hany S, Melnic Christopher M, Muratoglu Orhun K, Morid Mohammad A, Varadarajan Kartik M


Artificial Intelligence, Deep Learning, Implant Identification, Orthopaedic, Saliency Map, Total Hip Arthroplasty, Total Hip Replacement

General General

Quantifying people's experience during flood events with implications for hazard risk communication.

In PloS one ; h5-index 176.0

Semantic drift is a well-known concept in distributional semantics, which is used to demonstrate gradual, long-term changes in meanings and sentiments of words and is largely detectable by studying the composition of large corpora. In our previous work, which used ontological relationships between words and phrases, we established that certain kinds of semantic micro-changes can be found in social media emerging around natural hazard events, such as floods. Our previous results confirmed that semantic drift in social media can be used to for early detection of floods and to increase the volume of 'useful' geo-referenced data for event monitoring. In this work we use deep learning in order to determine whether images associated with 'semantically drifted' social media tags reflect changes in crowd navigation strategies during floods. Our results show that alternative tags can be used to differentiate naïve and experienced crowds witnessing flooding of various degrees of severity.

Tkachenko Nataliya, Procter Rob, Jarvis Stephen