DeepTetrad: high-throughput image analysis of meiotic tetrads by deep learning in Arabidopsis thaliana.

Meiotic crossovers facilitate chromosome segregation and create new combinations of alleles in gametes. Crossover frequency varies along chromosomes and crossover interference limits the coincidence of closely spaced crossovers. Crossovers can be measured by observing the inheritance of linked transgenes expressing different colors of fluorescent protein in Arabidopsis pollen tetrads. Here we establish DeepTetrad, a deep learning-based image recognition package for pollen tetrad analysis that enables high-throughput measurements of crossover frequency and interference in individual plants. DeepTetrad will accelerate the genetic dissection of mechanisms that control meiotic recombination.

Trowel: a fast and accurate error correction module for Illumina sequencing reads.

MOTIVATION: The ability to accurately read the order of nucleotides in DNA and RNA is fundamental for modern biology. Errors in next-generation sequencing can lead to many artifacts, from erroneous genome assemblies to mistaken inferences about RNA editing. Uneven coverage in datasets also contributes to false corrections. RESULT: We introduce Trowel, a massively parallelized and highly efficient error correction module for Illumina read data. Trowel both corrects erroneous base calls and boosts base qualities based on the k-mer spectrum. With high-quality k-mers and relevant base information, Trowel achieves high accuracy for different short read sequencing applications.The latency in the data path has been significantly reduced because of efficient data access and data structures. In performance evaluations, Trowel was highly competitive with other tools regardless of coverage, genome size read length and fragment size. AVAILABILITY AND IMPLEMENTATION: Trowel is written in C++ and is provided under the General Public License v3.0 (GPLv3). It is available at http://trowel-ec.sourceforge.net. CONTACT: euncheon.lim@tue.mpg.de or weigel@tue.mpg.de SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Feasibility of video-based real-time nystagmus tracking: a lightweight deep learning model approach using ocular object segmentation.

Background: Eye movement tests remain significantly underutilized in emergency departments and primary healthcare units, despite their superior diagnostic sensitivity compared to neuroimaging modalities for the differential diagnosis of acute vertigo. This underutilization may be attributed to a potential lack of awareness regarding these tests and the absence of appropriate tools for detecting nystagmus. This study aimed to develop a nystagmus measurement algorithm using a lightweight deep-learning model that recognizes the ocular regions. Method: The deep learning model was used to segment the eye regions, detect blinking, and determine the pupil center. The model was trained using images extracted from video clips of a clinical battery of eye movement tests and synthesized images reproducing real eye movement scenarios using virtual reality. Each eye image was annotated with segmentation masks of the sclera, iris, and pupil, with gaze vectors of the pupil center for eye tracking. We conducted a comprehensive evaluation of model performance and its execution speeds in comparison to various alternative models using metrics that are suitable for the tasks. Results: The mean Intersection over Union values of the segmentation model ranged from 0.90 to 0.97 for different classes (sclera, iris, and pupil) across types of images (synthetic vs. real-world images). Additionally, the mean absolute error for eye tracking was 0.595 for real-world data and the F1 score for blink detection was ≥ 0.95, which indicates our model is performing at a very high level of accuracy. Execution speed was also the most rapid for ocular object segmentation under the same hardware condition as compared to alternative models. The prediction for horizontal and vertical nystagmus in real eye movement video revealed high accuracy with a strong correlation between the observed and predicted values (r = 0.9949 for horizontal and r = 0.9950 for vertical; both p < 0.05). Conclusion: The potential of our model, which can automatically segment ocular regions and track nystagmus in real time from eye movement videos, holds significant promise for emergency settings or remote intervention within the field of neurotology.

DeepParcellation: A novel deep learning method for robust brain magnetic resonance imaging parcellation in older East Asians.

Accurate parcellation of cortical regions is crucial for distinguishing morphometric changes in aged brains, particularly in degenerative brain diseases. Normal aging and neurodegeneration precipitate brain structural changes, leading to distinct tissue contrast and shape in people aged >60 years. Manual parcellation by trained radiologists can yield a highly accurate outline of the brain; however, analyzing large datasets is laborious and expensive. Alternatively, newly-developed computational models can quickly and accurately conduct brain parcellation, although thus far only for the brains of Caucasian individuals. To develop a computational model for the brain parcellation of older East Asians, we trained magnetic resonance images of dimensions 256 × 256 × 256 on 5,035 brains of older East Asians (Gwangju Alzheimer's and Related Dementia) and 2,535 brains of Caucasians. The novel N-way strategy combining three memory reduction techniques inception blocks, dilated convolutions, and attention gates was adopted for our model to overcome the intrinsic memory requirement problem. Our method proved to be compatible with the commonly used parcellation model for Caucasians and showed higher similarity and robust reliability in older aged and East Asian groups. In addition, several brain regions showing the superiority of the parcellation suggest that DeepParcellation has a great potential for applications in neurodegenerative diseases such as Alzheimer's disease.

Feasibility of Eye Tracking Assisted Vestibular Rehabilitation Strategy Using Immersive Virtual Reality.

OBJECTIVES: Even though vestibular rehabilitation therapy (VRT) using head-mounted display (HMD) has been highlighted recently as a popular virtual reality platform, we should consider that HMD itself do not provide interactive environment for VRT. This study aimed to test the feasibility of interactive components using eye tracking assisted strategy through neurophysiologic evidence. METHODS: HMD implemented with an infrared-based eye tracker was used to generate a virtual environment for VRT. Eighteen healthy subjects participated in our experiment, wherein they performed a saccadic eye exercise (SEE) under two conditions of feedback-on (F-on, visualization of eye position) and feedback-off (F-off, non-visualization of eye position). Eye position was continuously monitored in real time on those two conditions, but this information was not provided to the participants. Electroencephalogram recordings were used to estimate neural dynamics and attention during SEE, in which only valid trials (correct responses) were included in electroencephalogram analysis. RESULTS: SEE accuracy was higher in the F-on than F-off condition (P=0.039). The power spectral density of beta band was higher in the F-on condition on the frontal (P=0.047), central (P=0.042), and occipital areas (P=0.045). Beta-event-related desynchronization was significantly more pronounced in the F-on (-0.19 on frontal and -0.22 on central clusters) than in the F-off condition (0.23 on frontal and 0.05 on central) on preparatory phase (P=0.005 for frontal and P=0.024 for central). In addition, more abundant functional connectivity was revealed under the F-on condition. CONCLUSION: Considering substantial gain may come from goal directed attention and activation of brain-network while performing VRT, our preclinical study from SEE suggests that eye tracking algorithms may work efficiently in vestibular rehabilitation using HMD.

Developing a Diagnostic Decision Support System for Benign Paroxysmal Positional Vertigo Using a Deep-Learning Model.

Background: Diagnosis of benign paroxysmal positional vertigo (BPPV) depends on the accurate interpretation of nystagmus induced by positional tests. However, difficulties in interpreting eye-movement often can arise in primary care practice or emergency room. We hypothesized that the use of machine learning would be helpful for the interpretation. Methods: From our clinical data warehouse, 91,778 nystagmus videos from 3467 patients with dizziness were obtained, in which the three-dimensional movement of nystagmus was annotated by four otologic experts. From each labeled video, 30 features changed into 255 grid images fed into the input layer of the neural network for the training dataset. For the model validation, video dataset of 3566 horizontal, 2068 vertical, and 720 torsional movements from 1005 patients with BPPV were collected. Results: The model had a sensitivity and specificity of 0.910 ± 0.036 and 0.919 ± 0.032 for horizontal nystagmus; of 0.879 ± 0.029 and 0.894 ± 0.025 for vertical nystagmus; and of 0.783 ± 0.040 and 0.799 ± 0.038 for torsional nystagmus, respectively. The affected canal was predicted with a sensitivity of 0.806 ± 0.010 and a specificity of 0.971 ± 0.003. Conclusions: As our deep-learning model had high sensitivity and specificity for the classification of nystagmus and localization of affected canal in patients with BPPV, it may have wide clinical applicability.