Search

Computer vision (CV) has been proposed as a powerful technology to collect individual measurements of livestock animals, such as body weight or body condition score, to name a few. In all these tasks, the first step of image processing is semantic segmentation (SS), which represents the use of deep neural networks to locate pixels that belong to the animal body, while removing the background which may add noise and other information that are not needed to compute body biometrics. Despite the generalization abilities of CV, oftentimes SS models need to be re-trained on the specific dataset at hand in order to maximize performance, and thus require labor-intensive annotations. With the rise of foundation models like GPT-4, LLaMA, DALL-E, among others, we aim to explore whether a foundation model for SS called SegGPT performs well in a highly specific agricultural scenario, in comparison with a model trained using domain-specific data, i.e., a U-net model trained on our datasets. Our evaluation is carried out over 9 different datasets of top-down depth images over bodies of calves and cows. The combined datasets amount to a total of 4,328 images (average count = 541) from 485 animals (average count = 54) from 2 wk to 7 yr of age, and it was collected with a mix of RealSense D435 and Kinect V2 sensors at several farm settings (entering/exiting the milking parlor, in a chute, or during weighing on a scale or weighing cart). We investigated the performance of these two models under several scenarios: training on a single dataset and validating within the same dataset (Same Dataset Internal Validation; SDIV), training on a single dataset and validating on an external dataset (Same Dataset External Validation; SDEV), and training on multiple datasets and validating on an external dataset (Multiple Datasets External Validation; MDEV). For the U-net trained in the SDIV approach, we used a 70/30 train/ test split over 100 epochs. SegGPT and U-net presented intersection over union of 0.84 and 0.95, 0.73 and 0.59, 0.84 and 0.91, for SDIV, SDEV, and MDEV, respectively. U-net was not able to segment the animal body with performance similar to SegGPT in a new dataset when trained with a single dataset, but it outperformed SegGPT when trained with multiple datasets. Although U-net performed slightly better on these scenarios, it’s important to highlight that SegGPT only received one prompt (one depth image with its annotation). per dataset and performed reasonably well on unseen (validation) datasets. In conclusion, foundation models for image processing tasks can be an alternative for training domain-specific deep neural networks, which demands labor, annotation, and large datasets to present satisfactory results. However, high performance still requires domain-specific models in similar agricultural scenarios. [ABSTRACT FROM AUTHOR]

Seismic attributes are derived measures from seismic data that help characterize subsurface geological features and enhance the interpretation of subsurface structures: we propose to exploit the hidden layers of Long–Short Time Memory neural network predictions as possible new reflection seismic attributes. The idea is based on the inference process of a neural network, which in its hidden layers stores information related to different features embedded in the input data and which usually are not considered. Neural network applications typically ignore such intermediate steps because the main interest lies in the final output, which is considered as the exclusive exploitable feature of the process. On the contrary, here we analyse the possibility to exploit the intermediate prediction steps, hereafter referred as 'deep attributes' because they are produced by a deep learning algorithm, to highlight features and emphasize characteristics embedded in the data but neither recognizable by traditional interpretation, nor evident with classical attributes or multi-attribute approaches. Nowadays, classical signal attributes are numerous and used for different purposes; we here propose an original strategy to calculate attributes previously never exploited, which are potentially complementary or a good alternative to the classical ones. We tested the proposed procedure on synthetic and field 2-D and 3-D reflection seismic data sets to test and demonstrate the stability, affordability and versatility of the entire approach. Furthermore, we evaluated the performance of deep attributes on a 4-D seismic data set to assess the applicability and effectiveness for time-monitoring purposes and comparing them with the sweetness attribute. [ABSTRACT FROM AUTHOR]

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as noise and galactic foreground contamination that pose a challenge for accurate detection. In this study, we present the SegU-Net v2 framework, an enhanced version of our convolutional neural network, built to identify neutral and ionized regions in the 21-cm signal contaminated with foreground emission. We trained our neural network on 21-cm image data processed by a foreground removal method based on Principal Component Analysis achieving an average classification accuracy of 71 per cent between redshift z  = 7 and 11. We tested SegU-Net v2 against various foreground removal methods, including Gaussian Process Regression, Polynomial Fitting, and Foreground-Wedge Removal. Results show comparable performance, highlighting SegU-Net v2 's independence on these pre-processing methods. Statistical analysis shows that a perfect classification score with |${\rm AUC}=95~{{\ \rm per\ cent}}$| is possible for 8 < z < 10. While the network prediction lacks the ability to correctly identify ionized regions at higher redshift and differentiate well the few remaining neutral regions at lower redshift due to low contrast between 21-cm signal, noise, and foreground residual in images. Moreover, as the photon sources driving reionization are expected to be located inside ionized regions, we show that SegU-Net v2 can be used to correctly identify and measure the volume of isolated bubbles with |$V_{\rm ion}\gt (10\, {\rm cMpc})^3$| at z > 9, for follow-up studies with infrared/optical telescopes to detect these sources. [ABSTRACT FROM AUTHOR]

In the realm of radio astronomy, the detection of radio frequency interference (RFI) stands as a pivotal pursuit. This study performs a novel comparative analysis of deep learning methodologies and introduces a novel transfer learning method, called fine-tuning. We compare various aspects and factors relating to this problem, including supervised fully convolutional network (FCN) architectures used within the literature, loss functions, regularization techniques, and training methodologies, to establish the most effective strategies for RFI detection. Moreover, the relationship between parameters, FLOPS, and inference times are examined. Fine-tuning involves pre-training models with low-quality aoflagger reference outputs, a very popular and accessible RFI flagging software package, and thereafter re-training the models with high-quality reference outputs. We utilize two data sets: real observations from LOFAR and simulated data from HERA. The mean squared error (MSE) loss function emerges as a robust performer if a high recall is desired. In contrast, the binary cross-entropy (BCE) loss function excels in generalization but falls short in classification performance. The Dice loss function emerges as the top performer, maximizing the F1 score and thereby serving as the choice for our further investigations. Notably, we highlight the important role of data quality and model capacity. In particular, we find that low-capacity models exhibit resilience when trained with low-quality flags from aoflagger , showcasing their ability to mitigate overfitting and overflagging tendencies. In contrast, high-capacity models excel when trained with high-quality flags. Fine-tuning proved to be an effective method to unlearn the overflagging tendencies of aoflagger , whilst requiring very little data. [ABSTRACT FROM AUTHOR]

Studying the Universe through radio telescope observation is crucial. However, radio telescopes capture not only signals from the universe but also various interfering signals, known as radio frequency interference (RFI). The presence of RFI can significantly impact data analysis. Ensuring the accuracy, reliability, and scientific integrity of research findings by detecting and mitigating or eliminating RFI in observational data, presents a persistent challenge in radio astronomy. In this study, we proposed a novel deep learning model called EMSCA-UNet for RFI detection. The model employs multiscale convolutional operations to extract RFI features of various scale sizes. Additionally, an attention mechanism is utilized to assign different weights to the extracted RFI feature maps, enabling the model to focus on vital features for RFI detection. We evaluated the performance of the model using real data observed from the 40 m radio telescope at Yunnan Observatory. Furthermore, we compared our results to other models, including U-Net, RFI-Net, and R-Net, using four commonly employed evaluation metrics: precision, recall, F1 score, and IoU. The results demonstrate that our model outperforms the other models on all evaluation metrics, achieving an average improvement of approximately 5 per cent compared to U-Net. Our model not only enhances the accuracy and comprehensiveness of RFI detection but also provides more detailed edge detection while minimizing the loss of useful signals. [ABSTRACT FROM AUTHOR]

Objectives To develop and validate a super-resolution (SR) algorithm generating clinically feasible chest radiographs from 64-fold reduced data. Methods An SR convolutional neural network was trained to produce original-resolution images (output) from 64-fold reduced images (input) using 128 × 128 patches (n  = 127 030). For validation, 112 radiographs—including those with pneumothorax (n  = 17), nodules (n  = 20), consolidations (n  = 18), and ground-glass opacity (GGO; n  = 16)—were collected. Three image sets were prepared: the original images and those reconstructed using SR and conventional linear interpolation (LI) using 64-fold reduced data. The mean-squared error (MSE) was calculated to measure similarity between the reconstructed and original images, and image noise was quantified. Three thoracic radiologists evaluated the quality of each image and decided whether any abnormalities were present. Results The SR-images were more similar to the original images than the LI-reconstructed images (MSE: 9269 ± 1015 vs. 9429 ± 1057; P =.02). The SR-images showed lower measured noise and scored better noise level by three radiologists than both original and LI-reconstructed images (P s <.01). The radiologists' pooled sensitivity with the SR-reconstructed images was not significantly different compared with the original images for detecting pneumothorax (SR vs. original, 90.2% [46/51] vs. 96.1% [49/51]; P =.19), nodule (90.0% [54/60] vs. 85.0% [51/60]; P =.26), consolidation (100% [54/54] vs. 96.3% [52/54]; P =.50), and GGO (91.7% [44/48] vs. 95.8% [46/48]; P =.69). Conclusions SR-reconstructed chest radiographs using 64-fold reduced data showed a lower noise level than the original images, with equivalent sensitivity for detecting major abnormalities. Advances in knowledge This is the first study applying super-resolution in data reduction of chest radiographs. [ABSTRACT FROM AUTHOR]

The Chinese Space Station Telescope (abbreviated as CSST) is a future advanced space telescope. Real-time identification of galaxy and nebula/star cluster (abbreviated as NSC) images is of great value during CSST survey. While recent research on celestial object recognition has progressed, the rapid and efficient identification of high-resolution local celestial images remains challenging. In this study, we conducted galaxy and NSC image classification research using deep learning methods based on data from the Hubble Space Telescope. We built a local celestial image data set and designed a deep learning model named HR-CelestialNet for classifying images of the galaxy and NSC. HR-CelestialNet achieved an accuracy of 89.09 per cent on the testing set, outperforming models such as AlexNet, VGGNet, and ResNet, while demonstrating faster recognition speeds. Furthermore, we investigated the factors influencing CSST image quality and evaluated the generalization ability of HR-CelestialNet on the blurry image data set, demonstrating its robustness to low image quality. The proposed method can enable real-time identification of celestial images during CSST survey mission. [ABSTRACT FROM AUTHOR]

Determination of individual age is one essential step in the accurate assessment of fish stocks. In non-tropical environments, the manual count of ring-like growth patterns in fish otoliths (ear stones) is the standard method. It relies on visual means and individual judgment and thus is subject to bias and interpretation errors. The use of automated pattern recognition based on machine learning may help to overcome this problem. Here, we employ two deep learning methods based on Convolutional Neural Networks (CNNs). The first approach utilizes the Mask R-CNN algorithm to perform object detection on the major otolith reading axes. The second approach employs the U-Net architecture to perform semantic segmentation on the otolith image in order to segregate the regions of interest. For both methods, we applied a simple postprocessing to count the rings on the output masks returned, which corresponds to the age prediction. Multiple benchmark tests indicate the promising performance of our implemented approaches, comparable to recently published methods based on classical image processing and traditional CNN implementation. Furthermore, our algorithms showed higher robustness compared to the existing methods, while also having the capacity to extrapolate missing age groups and to adapt to a new domain or data source. [ABSTRACT FROM AUTHOR]

Digital rock physics (DRP) offers an effective method of deriving elastic parameters from digital rock images, but its practical application is always limited to limited datasets. Recently, deep learning techniques have presented a promising avenue for generating more extensive and cost-effective samples. However, generating controllable samples according to user definition remains very difficult due to high dependence on sufficient datasets. To resolve this problem, a new network was proposed based on the UNet framework through image translation (UNet-IT) to expand rock castings by given porosity in relatively fewer datasets. Practical tests on carbonate rock images demonstrate that the proposed method can generate samples tailored to specific porosity requirements, which achieved a minimum porosity relative error of less than 1%. Compared with the unextended samples, the generated ones have completely different pore structures in terms of two-point probability, two-point cluster, and lineal path functions. Furthermore, the elastic parameters of the generated images obtained through the finite element method (FEM) and practical logging data matched well, with an average relative error of ∼9%. This indicates that the generated samples can be used as effective data to estimate fine rock physics templates and then improve inversion accuracy. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) and deep learning techniques are playing an increasing role in astronomy to deal with the data avalanche. Here we describe an application for finding resolved planetary nebulae (PNe) in crowded, wide-field, narrow-band Hα survey imagery in the Galactic plane, to test and facilitate more objective, reproducible, efficient and reliable trawls for them. PNe are important for studying the late-stage stellar evolution of low-mass to intermediate-mass stars. However, the confirmed ∼3800 Galactic PNe fall far short of the numbers expected. Traditional visual searching for resolved PNe is time-consuming because of the large data size and areal coverage of modern astronomical surveys. The training and validation data set of our algorithm was built with the INT Photometric Hα Survey (IPHAS) and true PNe from the Hong Kong/AAO/Strasbourg Hα (HASH) data base. Our algorithm correctly identified 444 PNe in the validation set of 454 PNe, with only 16 explicable 'false' positives, achieving a precision rate of 96.5 per cent and a recall rate of 97.8 per cent. After transfer learning, it was then applied to the VST Photometric Hα Survey of the Southern Galactic plane and bulge (VPHAS+), examining 979 out of 2284 survey fields, each covering 1° × 1°. It returned ∼20 000 detections, including 2637 known PNe and other kinds of catalogued non-PNe. A total of 815 new high-quality PNe candidates were found, 31 of which were selected as top-quality targets for optical spectroscopic follow-up. We found that 74 per cent of them are true, likely, and possible PNe. Representative preliminary confirmatory spectroscopy results are presented here to demonstrate the effectiveness of our techniques, with full details to be given in our forthcoming paper. [ABSTRACT FROM AUTHOR]

The growing demand for high-quality industrial products has led to a significant emphasis on image anomaly detection (AD). AD in industrial goods presents a formidable research challenge that demands the application of sophisticated techniques to identify and address deviations from the expected norm accurately. Manufacturers increasingly recognize the significance of employing intelligent systems to detect flaws and defects in product parts. However, industrial settings pose several challenges: diverse categories, limited abnormal samples and vagueness. Hence, there is a growing demand for advanced image AD techniques within industrial product manufacturing. In this paper, an intelligent industrial defective chips detection framework is proposed which mainly consists of three core components. First, the convolutional features of the efficient backbone model is effectively utilized to balance the computational complexity and performance of industrial resource-constrained devices. Secondly, a novel inverse feature matching followed by masking method is proposed to enhance the explanability that localizes the abnormal regions of the abnormal chips. Finally, to evaluate our proposed method a comprehensive ablation study is conducted, where different machine learning and deep learning algorithms are analysed to claim the superiority of our method. Furthermore, to help the research community, a benchmark dataset is collected from real-world industry manufacturing for defective chip detection. The empirical results from the dataset demonstrate the strength and effectiveness of the proposed model compared to the other models. [ABSTRACT FROM AUTHOR]

During quality inspection in manufacturing, the gaze of a worker provides pivotal information for identifying surface defects of a product. However, it is challenging to digitize the gaze information of workers in a dynamic environment where the positions and postures of the products and workers are not fixed. A robust, deep learning-based system, ISGOD (Integrated System with worker's Gaze and Object Detection), is proposed, which analyzes data to determine which part of the object is observed by integrating object detection and eye-tracking information in dynamic environments. The ISGOD employs a six-dimensional pose estimation algorithm for object detection, considering the location, orientation, and rotation of the object. Eye-tracking data were obtained from Tobii Glasses, which enable real-time video transmission and eye-movement tracking. A latency reduction method is proposed to overcome the time delays between object detection and eye-tracking information. Three evaluation indices, namely, gaze score, accuracy score, and concentration index are suggested for comprehensive analysis. Two experiments were conducted: a robustness test to confirm the suitability for real-time object detection and eye-tracking, and a trend test to analyze the difference in gaze movement between experts and novices. In the future, the proposed method and system can transfer the expertise of experts to enhance defect detection efficiency significantly. [ABSTRACT FROM AUTHOR]

Radio galaxies exhibit a rich diversity of morphological characteristics, which make their classification into distinct types a complex challenge. To address this challenge effectively, we introduce an innovative approach for radio galaxy classification using COSFIRE filters. These filters possess the ability to adapt to both the shape and orientation of prototype patterns within images. The COSFIRE approach is explainable, learning-free, rotation-tolerant, efficient, and does not require a large training set. To assess the efficacy of our method, we conducted experiments on a benchmark radio galaxy data set comprising of 1180 training samples and 404 test samples. Notably, our approach achieved an average accuracy rate of 93.36 per cent. This achievement outperforms contemporary deep learning models, and it is the best result ever achieved on this data set. Additionally, COSFIRE filters offer better computational performance, ∼20 × fewer operations than the DenseNet-based competing method (when comparing at the same accuracy). Our findings underscore the effectiveness of the COSFIRE filter-based approach in addressing the complexities associated with radio galaxy classification. This research contributes to advancing the field by offering a robust solution that transcends the orientation challenges intrinsic to radio galaxy observations. Our method is versatile in that it is applicable to various image classification approaches. [ABSTRACT FROM AUTHOR]

Motivation Accurate segmentation and recognition of C.elegans cells are critical for various biological studies, including gene expression, cell lineages, and cell fates analysis at single-cell level. However, the highly dense distribution, similar shapes, and inhomogeneous intensity profiles of whole-body cells in 3D fluorescence microscopy images make automatic cell segmentation and recognition a challenging task. Existing methods either rely on additional fiducial markers or only handle a subset of cells. Given the difficulty or expense associated with generating fiducial features in many experimental settings, a marker-free approach capable of reliably segmenting and recognizing C.elegans whole-body cells is highly desirable. Results We report a new pipeline, called automated segmentation and recognition (ASR) of cells, and applied it to 3D fluorescent microscopy images of L1-stage C.elegans with 558 whole-body cells. A novel displacement vector field based deep learning model is proposed to address the problem of reliable segmentation of highly crowded cells with blurred boundary. We then realize the cell recognition by encoding and exploiting statistical priors on cell positions and structural similarities of neighboring cells. To the best of our knowledge, this is the first method successfully applied to the segmentation and recognition of C.elegans whole-body cells. The ASR-segmentation module achieves an F 1-score of 0.8956 on a dataset of 116 C.elegans image stacks with 64 728 cells (accuracy 0.9880, AJI 0.7813). Based on the segmentation results, the ASR recognition module achieved an average accuracy of 0.8879. We also show ASR's applicability to other cell types, e.g. platynereis and rat kidney cells. Availability and implementation The code is available at https://github.com/reaneyli/ASR. [ABSTRACT FROM AUTHOR]

Motivation Continuous advancements in single-cell RNA sequencing (scRNA-seq) technology have enabled researchers to further explore the study of cell heterogeneity, trajectory inference, identification of rare cell types, and neurology. Accurate scRNA-seq data clustering is crucial in single-cell sequencing data analysis. However, the high dimensionality, sparsity, and presence of "false" zero values in the data can pose challenges to clustering. Furthermore, current unsupervised clustering algorithms have not effectively leveraged prior biological knowledge, making cell clustering even more challenging. Results This study investigates a semisupervised clustering model called scTPC, which integrates the t riplet constraint, p airwise constraint, and c ross-entropy constraint based on deep learning. Specifically, the model begins by pretraining a denoising autoencoder based on a zero-inflated negative binomial distribution. Deep clustering is then performed in the learned latent feature space using triplet constraints and pairwise constraints generated from partial labeled cells. Finally, to address imbalanced cell-type datasets, a weighted cross-entropy loss is introduced to optimize the model. A series of experimental results on 10 real scRNA-seq datasets and five simulated datasets demonstrate that scTPC achieves accurate clustering with a well-designed framework. Availability and implementation scTPC is a Python-based algorithm, and the code is available from https://github.com/LF-Yang/Code or https://zenodo.org/records/10951780. [ABSTRACT FROM AUTHOR]

The morphological diversity of galaxies is a relevant probe of galaxy evolution and cosmological structure formation. However, in large sky surveys, even the morphological classification of galaxies into two classes, like late-type (LT) and early-type (ET), still represents a significant challenge. In this work, we present a Deep Learning (DL) based morphological catalogue built from images obtained by the Southern Photometric Local Universe Survey (S-PLUS) Data Release 3 (DR3). Our DL method achieves a purity rate of 98.5 per cent in accurately distinguishing between spiral, as part of the larger category of LT galaxies, and elliptical, belonging to ET galaxies. Additionally, we have implemented a secondary classifier that evaluates the quality of each galaxy stamp, which allows to select only high-quality images when studying properties of galaxies on the basis of their DL morphology. From our LT/ET catalogue of galaxies, we recover the expected colour–magnitude diagram in which LT galaxies display bluer colours than ET ones. Furthermore, we also investigate the clustering of galaxies based on their morphology, along with their relationship to the surrounding environment. As a result, we deliver a full morphological catalogue with 164 314 objects complete up to r petro < 18, covering ∼1800 deg2, from which ∼55 000 are classified as high reliability, including a significant area of the Southern hemisphere that was not covered by previous morphology catalogues. [ABSTRACT FROM AUTHOR]

Motivation Rapid spread of viral diseases such as Coronavirus disease 2019 (COVID-19) highlights an urgent need for efficient surveillance of virus mutation and transmission dynamics, which requires fast, inexpensive and accurate viral lineage assignment. The first two goals might be achieved through low-coverage whole-genome sequencing (LC-WGS) which enables rapid genome sequencing at scale and at reduced costs. Unfortunately, LC-WGS significantly diminishes the genomic details, rendering accurate lineage assignment very challenging. Results We present ViTAL, a novel deep learning algorithm specifically designed to perform lineage assignment of low coverage-sequenced genomes. ViTAL utilizes a combination of MinHash for genomic feature extraction and Vision Transformer for fine-grain genome classification and lineage assignment. We show that ViTAL outperforms state-of-the-art tools across diverse coverage levels, reaching up to 87.7% lineage assignment accuracy at 1 × coverage where state-of-the-art tools such as UShER and Kraken2 achieve the accuracy of 5.4% and 27.4% respectively. ViTAL achieves comparable accuracy results with up to 8 × lower coverage than state-of-the-art tools. We explore ViTAL's ability to identify the lineages of novel genomes, i.e. genomes the Vision Transformer was not trained on. We show how ViTAL can be applied to preliminary phylogenetic placement of novel variants. Availability and implementation The data underlying this article are available in https://github.com/zuherJahshan/vital and can be accessed with 10.5281/zenodo.10688110. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a novel data augmentation methodology based on Conditional Progressive Generative Adversarial Networks (CPGAN) to generate diverse black hole (BH) images, accounting for variations in spin and electron temperature prescriptions. These generated images are valuable resources for training deep learning algorithms to accurately estimate black hole parameters from observational data. Our model can generate BH images for any spin value within the range of [−1, 1], given an electron temperature distribution. To validate the effectiveness of our approach, we employ a convolutional neural network to predict the BH spin using both the GRMHD images and the images generated by our proposed model. Our results demonstrate a significant performance improvement when training is conducted with the augmented data set while testing is performed using GRMHD simulated data, as indicated by the high R 2 score. Consequently, we propose that GANs can be employed as cost-effective models for black hole image generation and reliably augment training data sets for other parametrization algorithms. [ABSTRACT FROM AUTHOR]

It is of great significance to study the plant morphological structure for improving crop yield and achieving efficient use of resources. Three dimensional (3D) information can more accurately describe the morphological and structural characteristics of crop plants. Automatic acquisition of 3D information is one of the key steps in plant morphological structure research. Taking wheat as the research object, we propose a point cloud data-driven 3D reconstruction method that achieves 3D structure reconstruction and plant morphology parameterization at the phytomer scale. Specifically, we use the MVS-Pheno platform to reconstruct the point cloud of wheat plants and segment organs through the deep learning algorithm. On this basis, we automatically reconstructed the 3D structure of leaves and tillers and extracted the morphological parameters of wheat. The results show that the semantic segmentation accuracy of organs is 95.2%, and the instance segmentation accuracy AP50 is 0.665. The R 2 values for extracted leaf length, leaf width, leaf attachment height, stem leaf angle, tiller length, and spike length were 0.97, 0.80, 1.00, 0.95, 0.99, and 0.95, respectively. This method can significantly improve the accuracy and efficiency of 3D morphological analysis of wheat plants, providing strong technical support for research in fields such as agricultural production optimization and genetic breeding. [ABSTRACT FROM AUTHOR]

Motivation Classification of samples using biomedical omics data is a widely used method in biomedical research. However, these datasets often possess challenging characteristics, including high dimensionality, limited sample sizes, and inherent biases across diverse sources. These factors limit the performance of traditional machine learning models, particularly when applied to independent datasets. Results To address these challenges, we propose a novel classifier, Deep Centroid, which combines the stability of the nearest centroid classifier and the strong fitting ability of the deep cascade strategy. Deep Centroid is an ensemble learning method with a multi-layer cascade structure, consisting of feature scanning and cascade learning stages that can dynamically adjust the training scale. We apply Deep Centroid to three precision medicine applications—cancer early diagnosis, cancer prognosis, and drug sensitivity prediction—using cell-free DNA fragmentations, gene expression profiles, and DNA methylation data. Experimental results demonstrate that Deep Centroid outperforms six traditional machine learning models in all three applications, showcasing its potential in biological omics data classification. Furthermore, functional annotations reveal that the features scanned by the model exhibit biological significance, indicating its interpretability from a biological perspective. Our findings underscore the promising application of Deep Centroid in the classification of biomedical omics data, particularly in the field of precision medicine. Availability and implementation Deep Centroid is available at both github (github.com/xiexiexiekuan/DeepCentroid) and Figshare (https://figshare.com/articles/software/Deep_Centroid_A_General_Deep_Cascade_Classifier_for_Biomedical_Omics_Data_Classification/24993516). [ABSTRACT FROM AUTHOR]

Direct imaging is an active research topic in astronomy for the detection and the characterization of young substellar objects. The very high contrast between the host star and its companions makes the observations particularly challenging. In this context, post-processing methods combining several images recorded with the pupil tracking mode of telescope are needed. In previous works, we have presented a data-driven algorithm, PACO , capturing locally the spatial correlations of the data with a multivariate Gaussian model. PACO delivers better detection sensitivity and confidence than the standard post-processing methods of the field. However, there is room for improvement due to the approximate fidelity of the PACO statistical model to the time evolving observations. In this paper, we propose to combine the statistical model of PACO with supervised deep learning. The data are first pre-processed with the PACO framework to improve the stationarity and the contrast. A convolutional neural network (CNN) is then trained in a supervised fashion to detect the residual signature of synthetic sources. Finally, the trained network delivers a detection map. The photometry of detected sources is estimated by a second CNN. We apply the proposed approach to several data sets from the VLT/SPHERE instrument. Our results show that its detection stage performs significantly better than baseline methods (cADI and PCA), and leads to a contrast improvement up to half a magnitude compared to PACO. The characterization stage of the proposed method performs on average on par with or better than the comparative algorithms (PCA and PACO) for angular separation above 0.5 arcsec. [ABSTRACT FROM AUTHOR]

Summary Python is the most commonly used language for deep learning (DL). Existing Python packages for mass spectrometry imaging (MSI) data are not optimized for DL tasks. We, therefore, introduce pyM2aia, a Python package for MSI data analysis with a focus on memory-efficient handling, processing and convenient data-access for DL applications. pyM2aia provides interfaces to its parent application M2aia, which offers interactive capabilities for exploring and annotating MSI data in imzML format. pyM2aia utilizes the image input and output routines, data formats, and processing functions of M2aia, ensures data interchangeability, and enables the writing of readable and easy-to-maintain DL pipelines by providing batch generators for typical MSI data access strategies. We showcase the package in several examples, including imzML metadata parsing, signal processing, ion-image generation, and, in particular, DL model training and inference for spectrum-wise approaches, ion-image-based approaches, and approaches that use spectral and spatial information simultaneously. Availability and implementation Python package, code and examples are available at (https://m2aia.github.io/m2aia) [ABSTRACT FROM AUTHOR]

Background The application of deep learning (DL) to diagnostic dermatology has been the subject of numerous studies, with some reporting skin lesion classification performance on curated datasets comparable to that of experienced dermatologists. Most skin disease images encountered in clinical settings are macroscopic, without dermoscopic information, and exhibit considerable variability. Further research is necessary to determine the generalizability of DL algorithms across populations and acquisition settings. Objectives To assess the extent to which DL can generalize to nondermoscopic datasets acquired at the primary–secondary care interface in the National Health Service (NHS); to explore how to obtain a clinically satisfactory performance on nonstandardized, real-world local data without the availability of large diagnostically labelled local datasets; and to measure the impact of pretraining DL algorithms on external, public datasets. Methods Diagnostic macroscopic image datasets were created from previous referrals from primary to secondary care. These included 2213 images referred from primary care practitioners in NHS Tayside and 1510 images from NHS Forth Valley acquired by medical photographers. Two further datasets with identical diagnostic labels were obtained from sources in the public domain, namely the International Skin Imaging Collaboration (ISIC) dermoscopic dataset and the SD-260 nondermoscopic dataset. DL algorithms, specifically EfficientNets and Self-attention with Window-wise Inner-product based Network (SWIN) transformers, were trained using data from each of these datasets. Algorithms were also fine-tuned on images from the NHS datasets after pretraining on different data combinations, including the larger public-domain datasets. Receiver operating characteristic curves and the area under such curves (AUC) were used to assess performance. Results SWIN transformers tested on Forth Valley data had AUCs of 0.85 and 0.89 when trained on SD-260 and Forth Valley data, respectively. Training on SD-260 followed by fine tuning of Forth Valley data gave an AUC of 0.91. Similar effects of pretraining and tuning on local data were observed using Tayside data and EfficientNets. Pretraining on the larger dermoscopic image dataset (ISIC 2019) provided no additional benefit. Conclusions Pretraining on public macroscopic images followed by tuning to local data gave promising results. Further improvements are needed to afford deployment in real clinical pathways. Larger datasets local to the target domain might be expected to yield further improved performance. [ABSTRACT FROM AUTHOR]