IEEE Trans Neural Netw Learn Syst. 2024 Feb 7;PP. doi: 10.1109/TNNLS.2024.3356310. Online ahead of print.

ABSTRACT

This article studies the generalization of neural networks (NNs) by examining how a network changes when trained on a training sample with or without out-of-distribution (OoD) examples. If the network's predictions are less influenced by fitting OoD examples, then the network learns attentively from the clean training set. A new notion, dataset-distraction stability, is proposed to measure the influence. Extensive CIFAR-10/100 experiments on the different VGG, ResNet, WideResNet, ViT architectures, and optimizers show a negative correlation between the dataset-distraction stability and generalizability. With the distraction stability, we decompose the learning process on the training set S into multiple learning processes on the subsets of S drawn from simpler distributions, i.e., distributions of smaller intrinsic dimensions (IDs), and furthermore, a tighter generalization bound is derived. Through attentive learning, miraculous generalization in deep learning can be explained and novel algorithms can also be designed.

PMID:38324433 | DOI:10.1109/TNNLS.2024.3356310

IEEE Trans Med Imaging. 2024 Feb 7;PP. doi: 10.1109/TMI.2024.3363416. Online ahead of print.

ABSTRACT

Optical coherence tomography (OCT) can perform non-invasive high-resolution three-dimensional (3D) imaging and has been widely used in biomedical fields, while it is inevitably affected by coherence speckle noise which degrades OCT imaging performance and restricts its applications. Here we present a novel speckle-free OCT imaging strategy, named toward-ground-truth OCT (tGT-OCT), that utilizes unsupervised 3D deep-learning processing and leverages OCT 3D imaging features to achieve speckle-free OCT imaging. Specifically, our proposed tGT-OCT utilizes an unsupervised 3D-convolution deep-learning network trained using random 3D volumetric data to distinguish and separate speckle from real structures in 3D imaging volumetric space; moreover, tGT-OCT effectively further reduces speckle noise and reveals structures that would otherwise be obscured by speckle noise while preserving spatial resolution. Results derived from different samples demonstrated the high-quality speckle-free 3D imaging performance of tGT-OCT and its advancement beyond the previous state-of-the-art. The code is available online: https://github.com/Voluntino/tGT-OCT.

PMID:38324426 | DOI:10.1109/TMI.2024.3363416

JMIR Res Protoc. 2024 Feb 7;13:e46493. doi: 10.2196/46493.

ABSTRACT

BACKGROUND: Artificial intelligence (AI)-powered digital therapies that detect methamphetamine cravings via consumer devices have the potential to reduce health care disparities by providing remote and accessible care solutions to communities with limited care solutions, such as Native Hawaiian, Filipino, and Pacific Islander communities. However, Native Hawaiian, Filipino, and Pacific Islander communities are understudied with respect to digital therapeutics and AI health sensing despite using technology at the same rates as other racial groups.

OBJECTIVE: In this study, we aimed to understand the feasibility of continuous remote digital monitoring and ecological momentary assessments in Native Hawaiian, Filipino, and Pacific Islander communities in Hawaii by curating a novel data set of longitudinal Fitbit (Fitbit Inc) biosignals with the corresponding craving and substance use labels. We also aimed to develop personalized AI models that predict methamphetamine craving events in real time using wearable sensor data.

METHODS: We will develop personalized AI and machine learning models for methamphetamine use and craving prediction in 40 individuals from Native Hawaiian, Filipino, and Pacific Islander communities by curating a novel data set of real-time Fitbit biosensor readings and the corresponding participant annotations (ie, raw self-reported substance use data) of their methamphetamine use and cravings. In the process of collecting this data set, we will gain insights into cultural and other human factors that can challenge the proper acquisition of precise annotations. With the resulting data set, we will use self-supervised learning AI approaches, which are a new family of machine learning methods that allows a neural network to be trained without labels by being optimized to make predictions about the data. The inputs to the proposed AI models are Fitbit biosensor readings, and the outputs are predictions of methamphetamine use or craving. This paradigm is gaining increased attention in AI for health care.

RESULTS: To date, more than 40 individuals have expressed interest in participating in the study, and we have successfully recruited our first 5 participants with minimal logistical challenges and proper compliance. Several logistical challenges that the research team has encountered so far and the related implications are discussed.

CONCLUSIONS: We expect to develop models that significantly outperform traditional supervised methods by finetuning according to the data of a participant. Such methods will enable AI solutions that work with the limited data available from Native Hawaiian, Filipino, and Pacific Islander populations and that are inherently unbiased owing to their personalized nature. Such models can support future AI-powered digital therapeutics for substance abuse.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/46493.

PMID:38324375 | DOI:10.2196/46493

J Cell Sci. 2024 Feb 1;137(3):jcs261545. doi: 10.1242/jcs.261545. Epub 2024 Feb 7.

ABSTRACT

Fluorescence microscopy is essential for studying living cells, tissues and organisms. However, the fluorescent light that switches on fluorescent molecules also harms the samples, jeopardizing the validity of results - particularly in techniques such as super-resolution microscopy, which demands extended illumination. Artificial intelligence (AI)-enabled software capable of denoising, image restoration, temporal interpolation or cross-modal style transfer has great potential to rescue live imaging data and limit photodamage. Yet we believe the focus should be on maintaining light-induced damage at levels that preserve natural cell behaviour. In this Opinion piece, we argue that a shift in role for AIs is needed - AI should be used to extract rich insights from gentle imaging rather than recover compromised data from harsh illumination. Although AI can enhance imaging, our ultimate goal should be to uncover biological truths, not just retrieve data. It is essential to prioritize minimizing photodamage over merely pushing technical limits. Our approach is aimed towards gentle acquisition and observation of undisturbed living systems, aligning with the essence of live-cell fluorescence microscopy.

PMID:38324353 | DOI:10.1242/jcs.261545

J Orthop Res. 2024 Feb 7. doi: 10.1002/jor.25800. Online ahead of print.

ABSTRACT

In this study, we investigated the discriminative capacity of knee morphology in automatic detection of osteophytes defined by the Osteoarthritis Research Society International atlas, using X-ray and magnetic resonance imaging (MRI) data. For the X-ray analysis, we developed a deep learning (DL) based model to segment femur and tibia. In case of MRIs, we utilized previously validated segmentations of femur, tibia, corresponding cartilage tissues, and menisci. Osteophyte detection was performed using DL models in four compartments: medial femur (FM), lateral femur (FL), medial tibia (TM), and lateral tibia (TL). To analyze the confounding effects of soft tissues, we investigated their morphology in combination with bones, including bones+cartilage, bones+menisci, and all the tissues. From X-ray-based 2D morphology, the models yielded balanced accuracy of 0.73, 0.69, 0.74, and 0.74 for FM, FL, TM, TL, respectively. Using 3D bone morphology from MRI, balanced accuracy was 0.80, 0.77, 0.71, and 0.76, respectively. The performance was higher than in 2D for all the compartments except for TM, with significant improvements observed for femoral compartments. Adding menisci or cartilage morphology consistently improved balanced accuracy in TM, with the greatest improvement seen for small osteophyte. Otherwise, the models performed similarly to bones-only. Our experiments demonstrated that MRI-based models show higher detection capability than X-ray based models for identifying knee osteophytes. This study highlighted the feasibility of automated osteophyte detection from X-ray and MRI data and suggested further need for development of osteophyte assessment criteria in addition to OARSI, particularly, for early osteophytic changes.

PMID:38323840 | DOI:10.1002/jor.25800

Med Phys. 2024 Feb 7. doi: 10.1002/mp.16976. Online ahead of print.

ABSTRACT

BACKGROUND: MR-only radiotherapy treatment planning is an attractive alternative to conventional workflow, reducing scan time and ionizing radiation. It is crucial to derive the electron density map or synthetic CT (sCT) from MR data to perform dose calculations to enable MR-only treatment planning. Automatic segmentation of relevant organs in MR images can accelerate the process by preventing the time-consuming manual contouring step. However, the segmentation label is available only for CT data in many cases.

PURPOSE: We propose CycleSeg, a unified framework that generates sCT and corresponding segmentation from MR images without access to MR segmentation labels METHODS: CycleSeg utilizes the CycleGAN formulation to perform unpaired synthesis of sCT and image alignment. To enable MR (sCT) segmentation, CycleSeg incorporates unsupervised domain adaptation by using a pseudo-labeling approach with feature alignment in semantic segmentation space. In contrast to previous approaches that perform segmentation on MR data, CycleSeg could perform segmentation on both MR and sCT. Experiments were performed with data from prostate cancer patients, with 78/7/10 subjects in the training/validation/test sets, respectively.

RESULTS: CycleSeg showed the best sCT generation results, with the lowest mean absolute error of 102.2 and the lowest Fréchet inception distance of 13.0. CycleSeg also performed best on MR segmentation, with the highest average dice score of 81.0 and 81.1 for MR and sCT segmentation, respectively. Ablation experiments confirmed the contribution of the proposed components of CycleSeg.

CONCLUSION: CycleSeg effectively synthesized CT and performed segmentation on MR images of prostate cancer patients. Thus, CycleSeg has the potential to expedite MR-only radiotherapy treatment planning, reducing the prescribed scans and manual segmentation effort, and increasing throughput.

PMID:38323835 | DOI:10.1002/mp.16976

Pest Manag Sci. 2024 Feb 7. doi: 10.1002/ps.7990. Online ahead of print.

ABSTRACT

BACKGROUND: Machine vision-based precision weed management is a promising solution to substantially reduce herbicide input and weed control cost. The objective of this research was to compare two different deep learning-based approaches for detecting weeds in cabbage: (1) detecting weeds directly, and (2) detecting crops by generating the bounding boxes covering the crops and any green pixels outside the bounding boxes were deemed as weeds.

RESULTS: The precision, recall, F1-score, mAP0.5 , mAP0.5:0.95 of You Only Look Once (YOLO) v5 for detecting cabbage were 0.986, 0.979, 0.982, 0.995, and 0.851, respectively, while these metrics were 0.973, 0.985, 0.979, 0.993, and 0.906 for YOLOv8, respectively. However, none of these metrics exceeded 0.891 when detecting weeds. The reduced performances for directly detecting weeds could be attributed to the diverse weed species at varying densities and growth stages with different plant morphologies. A segmentation procedure demonstrated its effectiveness for extracting weeds outside the bounding boxes covering the crops, and thereby realizing effective indirect weed detection.

CONCLUSION: The indirect weed detection approach demands less manpower as the need for constructing a large training dataset containing a variety of weed species is unnecessary. However, in a certain case, weeds are likely to remain undetected due to their growth in close proximity with crops and being situated within the predicted bounding boxes that encompass the crops. The models generated in this research can be used in conjunction with the machine vision subsystem of a smart sprayer or mechanical weeder. © 2024 Society of Chemical Industry.

PMID:38323798 | DOI:10.1002/ps.7990

AJR Am J Roentgenol. 2024 Feb 7. doi: 10.2214/AJR.23.30272. Online ahead of print.

ABSTRACT

Background: Cine cardiac MRI sequences require repeated breath-holds, which can be difficult in patients with ischemic heart disease (IHD). Objective: To compare a free-breathing accelerated cine sequence using deep-learning (DL) reconstruction and a standard breath-hold cine sequence in terms of image quality and left-ventricular (LV) measurements in patients with IHD undergoing cardiac MRI. Methods: This prospective study included patients undergoing 1.5-T or 3-T cardiac MRI for evaluation of IHD between March 15, 2023, and June 21, 2023. Examinations included an investigational free-breathing cine short-axis sequence with DL reconstruction (cine-DL). Two radiologists (R1, R2), in blinded fashion, independently assessed LV ejection fraction (LVEF), LV end-diastolic volume (LVEDV), LV end-systolic volume (LVESV), and subjective image quality, for cine-DL sequence and standard breath-hold balanced SSFP sequences; R1 assessed artifacts. Results: The analysis included 26 patients (mean age, 64.3±11.7 years; 14 men, 12 women). Acquisition was shorter for cine-DL than standard sequence (0.6±0.1 min vs 2.4±0.6 min, p<.001). Cine-DL, in comparison with standard, showed no significant difference for LVEF for R1 (51.7±14.3% vs 51.3±14.7%, p=.56) or R2 (53.4±14.9% vs 52.8±14.6%, p=.53); significantly greater LVEDV for R2 (171.9±51.9 vs 160.6±49.4 ml, p=.01) but not R1 (171.8±53.7 vs 165.5±52.4 ml, p=.16); and no significant difference in LVESV for R1 (88.1±49.3 vs 86.0±50.5 ml, p=.45) or R2 (85.2±48.1 vs 81.3±48.2 ml, p=.10). Mean bias between cine-DL and standard was: LVEF, 0.4% for R1 and 0.7% for R2; LVEDV, 6.3 ml for R1 and 11.3 ml for R2; LVESV, 2.1 ml for R1 and 3.9 ml for R2. Subjective image quality was better for cine-DL than standard for R1 (2.3±0.5 vs 1.9±0.8, p=.02) and R2 (2.2±0.4 vs 1.9±0.7; p=.02). R1 reported no significant difference between cine-DL and standard for off-resonance (3.8% vs 23.1%, p=.10), and parallel-imaging (3.8% vs 19.2%, p=.19) artifacts; blurring artifacts were more frequent for cine-DL than standard (42.3% vs 7.7%; p=.008). Conclusion: Free-breathing cine-DL sequence, in comparison with standard breath-hold cine sequence, showed very small bias for LVEF measurements and better subjective quality. Cine-DL yielded greater LV volumes. Clinical Impact: Free-breathing cine-DL may yield reliable LVEF measurements in patients with IHD unable to repeatedly breath-hold.

PMID:38323784 | DOI:10.2214/AJR.23.30272

J Cutan Med Surg. 2024 Feb 7:12034754241229361. doi: 10.1177/12034754241229361. Online ahead of print.

ABSTRACT

BACKGROUND: Artificial intelligence (AI) in skin cancer is a promising research field to assist physicians and to provide support to patients remotely. Physicians' awareness to new developments in AI research is important to define the best practices and scope of integrating AI-enabled technologies within a clinical setting.

OBJECTIVES: To analyze the characteristics and trends of AI skin cancer publications from dermatology journals.

METHODS: AI skin cancer publications were retrieved in June 2022 from the Web of Science. Publications were screened by title, abstract, and keywords to assess eligibility. Publications were fully reviewed. Publications were divided between nonmelanoma skin cancer (NMSC), melanoma, and skin cancer studies. The primary measured outcome was the number of citations. The secondary measured outcomes were articles' general characteristics and features related to AI.

RESULTS: A total of 168 articles were included: 25 on NMSC, 77 on melanoma, and 66 on skin cancer. The most common types of skin cancers were melanoma (134, 79.8%), basal cell carcinoma (61, 36.3%), and squamous cell carcinoma (45, 26.9%). All articles were published between 2000 and 2022, with 49 (29.2%) of them being published in 2021. Original studies that developed or assessed an algorithm predominantly used supervised learning (66, 97.0%) and deep neural networks (42, 67.7%). The most used imaging modalities were standard dermoscopy (76, 45.2%) and clinical images (39, 23.2%).

CONCLUSIONS: Most publications focused on developing or assessing screening technologies with mainly deep neural network algorithms. This indicates the eminent need for dermatologists to label or annotate images used by novel AI systems.

PMID:38323537 | DOI:10.1177/12034754241229361

Curr Comput Aided Drug Des. 2024 Feb 6. doi: 10.2174/0115734099287389240126072433. Online ahead of print.

ABSTRACT

Traditional molecular de novo generation methods, such as evolutionary algorithms, generate new molecules mainly by linking existing atomic building blocks. The challenging issues in these methods include difficulty in synthesis, failure to achieve desired properties, and structural optimization requirements. Advances in deep learning offer new ideas for rational and robust de novo drug design. Deep learning, a branch of machine learning, is more efficient than traditional methods for processing problems, such as speech, image, and translation. This study provides a comprehensive overview of the current state of research in de novo drug design based on deep learning and identifies key areas for further development. Deep learning-based de novo drug design is pivotal in four key dimensions. Molecular databases form the basis for model training, while effective molecular representations impact model performance. Common DL models (GANs, RNNs, VAEs, CNNs, DMs) generate drug molecules with desired properties. The evaluation metrics guide research directions by determining the quality and applicability of generated molecules. This abstract highlights the foundational aspects of DL-based de novo drug design, offering a concise overview of its multifaceted contributions. Consequently, deep learning in de novo molecule generation has attracted more attention from academics and industry. As a result, many deep learning-based de novo molecule generation types have been actively proposed.

PMID:38321907 | DOI:10.2174/0115734099287389240126072433

Br J Radiol. 2024 Jan 13:tqae014. doi: 10.1093/bjr/tqae014. Online ahead of print.

ABSTRACT

OBJECTIVES: To review studies on deep learning (DL) models for classification, detection, and segmentation of rib fractures in CT data, to determine their risk of bias (ROB), and to analyse the performance of acute rib fracture detection models.

METHODS: Research articles written in English were retrieved from PubMed, Embase, and Web of Science in April 2023. A study was only included if a DL model was used to classify, detect, or segment rib fractures, and only if the model was trained with CT data from humans. For the ROB assessment, the Quality Assessment of Diagnostic Accuracy Studies tool was used. The performance of acute rib fracture detection models was meta-analysed with forest plots.

RESULTS: A total of 27 studies were selected. About 75% of the studies have ROB by not reporting the patient selection criteria, including control patients or using 5-mm slice thickness CT scans. The sensitivity, precision, and F1-score of the subgroup of low ROB studies were 89.60% (95%CI, 86.31%-92.90%), 84.89% (95%CI, 81.59%-88.18%), and 86.66% (95%CI, 84.62%-88.71%), respectively. The ROB subgroup differences test for the F1-score led to a p-value below 0.1.

CONCLUSION: ROB in studies mostly stems from an inappropriate patient and data selection. The studies with low ROB have better F1-score in acute rib fracture detection using DL models.

ADVANCES IN KNOWLEDGE: This systematic review will be a reference to the taxonomy of the current status of rib fracture detection with DL models, and upcoming studies will benefit from our data extraction, our ROB assessment, and our meta-analysis.

PMID:38323515 | DOI:10.1093/bjr/tqae014

J Biomed Opt. 2024 Jan;29(Suppl 1):S11521. doi: 10.1117/1.JBO.29.S1.S11521. Epub 2024 Feb 5.

ABSTRACT

SIGNIFICANCE: Photoacoustic microscopy (PAM) offers advantages in high-resolution and high-contrast imaging of biomedical chromophores. The speed of imaging is critical for leveraging these benefits in both preclinical and clinical settings. Ongoing technological innovations have substantially boosted PAM's imaging speed, enabling real-time monitoring of dynamic biological processes.

AIM: This concise review synthesizes historical context and current advancements in high-speed PAM, with an emphasis on developments enabled by ultrafast lasers, scanning mechanisms, and advanced imaging processing methods.

APPROACH: We examine cutting-edge innovations across multiple facets of PAM, including light sources, scanning and detection systems, and computational techniques and explore their representative applications in biomedical research.

RESULTS: This work delineates the challenges that persist in achieving optimal high-speed PAM performance and forecasts its prospective impact on biomedical imaging.

CONCLUSIONS: Recognizing the current limitations, breaking through the drawbacks, and adopting the optimal combination of each technology will lead to the realization of ultimate high-speed PAM for both fundamental research and clinical translation.

PMID:38323297 | PMC:PMC10846286 | DOI:10.1117/1.JBO.29.S1.S11521

J Undergrad Neurosci Educ. 2022 Jun 1;20(2):A120-A145. doi: 10.59390/FKXM3006. eCollection 2022 Winter.

ABSTRACT

Effective science communication has been identified as one of the core competencies of neuroscience education as articulated at the 2017 FUN Workshop. Yet most undergraduate students do not receive explicit instruction on how to effectively communicate science to a diversity of audiences. Instead, communication assignments typically help students become proficient at sharing scientific information with other scientists through research articles, poster presentations or oral presentations. This presents a missed opportunity to instruct students on the complexities of communicating to the general public, the importance of which has come into sharp focus during the COVID-19 pandemic. Translating research findings so they can be understood by a non-specialist audience requires practice and deep learning and can act as a powerful teaching tool to help students build science literacy skills. Here I share the blueprint to a broadly-oriented science communication assignment built to address the core competencies of neuroscience education. The assignment acts as the final project for a 400-level neuropharmacology course at a small public liberal arts university. Students work in small groups to identify a topic of interest and research, script, and record an audio podcast geared towards a general audience. The assignment is scaffolded to allow students to work towards the final submission in small steps and to receive feedback from the instructor and their peers. These feedback steps pair with opportunities to revise their work to further develop students' communication skills. Initial feedback from students suggests the assignment promoted deeper learning and higher engagement with course content.

PMID:38323063 | PMC:PMC10653229 | DOI:10.59390/FKXM3006

Front Bioinform. 2024 Jan 23;3:1296667. doi: 10.3389/fbinf.2023.1296667. eCollection 2023.

ABSTRACT

Introduction: Prostate cancer is a highly heterogeneous disease, presenting varying levels of aggressiveness and response to treatment. Angiogenesis is one of the hallmarks of cancer, providing oxygen and nutrient supply to tumors. Micro vessel density has previously been correlated with higher Gleason score and poor prognosis. Manual segmentation of blood vessels (BVs) In microscopy images is challenging, time consuming and may be prone to inter-rater variabilities. In this study, an automated pipeline is presented for BV detection and distribution analysis in multiplexed prostate cancer images. Methods: A deep learning model was trained to segment BVs by combining CD31, CD34 and collagen IV images. In addition, the trained model was used to analyze the size and distribution patterns of BVs in relation to disease progression in a cohort of prostate cancer patients (N = 215). Results: The model was capable of accurately detecting and segmenting BVs, as compared to ground truth annotations provided by two reviewers. The precision (P), recall (R) and dice similarity coefficient (DSC) were equal to 0.93 (SD 0.04), 0.97 (SD 0.02) and 0.71 (SD 0.07) with respect to reviewer 1, and 0.95 (SD 0.05), 0.94 (SD 0.07) and 0.70 (SD 0.08) with respect to reviewer 2, respectively. BV count was significantly associated with 5-year recurrence (adjusted p = 0.0042), while both count and area of blood vessel were significantly associated with Gleason grade (adjusted p = 0.032 and 0.003 respectively). Discussion: The proposed methodology is anticipated to streamline and standardize BV analysis, offering additional insights into the biology of prostate cancer, with broad applicability to other cancers.

PMID:38323039 | PMC:PMC10844485 | DOI:10.3389/fbinf.2023.1296667

Heliyon. 2024 Jan 24;10(3):e24727. doi: 10.1016/j.heliyon.2024.e24727. eCollection 2024 Feb 15.

ABSTRACT

In the digital age, where information is a cornerstone for decision-making, social media's not-so-regulated environment has intensified the prevalence of fake news, with significant implications for both individuals and societies. This study employs a bibliometric analysis of a large corpus of 9678 publications spanning 2013-2022 to scrutinize the evolution of fake news research, identifying leading authors, institutions, and nations. Three thematic clusters emerge: Disinformation in social media, COVID-19-induced infodemics, and techno-scientific advancements in auto-detection. This work introduces three novel contributions: 1) a pioneering mapping of fake news research to Sustainable Development Goals (SDGs), indicating its influence on areas like health (SDG 3), peace (SDG 16), and industry (SDG 9); 2) the utilization of Prominence percentile metrics to discern critical and economically prioritized research areas, such as misinformation and object detection in deep learning; and 3) an evaluation of generative AI's role in the propagation and realism of fake news, raising pressing ethical concerns. These contributions collectively provide a comprehensive overview of the current state and future trajectories of fake news research, offering valuable insights for academia, policymakers, and industry.

PMID:38322879 | PMC:PMC10844021 | DOI:10.1016/j.heliyon.2024.e24727

J Appl Crystallogr. 2024 Feb 1;57(Pt 1):1-2. doi: 10.1107/S1600576723010476. eCollection 2024 Feb 1.

ABSTRACT

Artificial intelligence is more present than ever, both in our society in general and in science. At the center of this development has been the concept of deep learning, the use of artificial neural networks that are many layers deep and can often reproduce human-like behavior much better than other machine-learning techniques. The articles in this collection are some recent examples of its application for X-ray photon science and crystallography that have been published in Journal of Applied Crystallography.

PMID:38322721 | PMC:PMC10840311 | DOI:10.1107/S1600576723010476

Front Neurorobot. 2024 Jan 23;17:1329589. doi: 10.3389/fnbot.2023.1329589. eCollection 2023.

ABSTRACT

INTRODUCTION: In the field of logistics warehousing robots, collaborative operation and coordinated control have always been challenging issues. Although deep learning and reinforcement learning methods have made some progress in solving these problems, however, current research still has shortcomings. In particular, research on adaptive sensing and real-time decision-making of multi-robot swarms has not yet received sufficient attention.

METHODS: To fill this research gap, we propose a YOLOv5-PPO model based on A3C optimization. This model cleverly combines the target detection capabilities of YOLOv5 and the PPO reinforcement learning algorithm, aiming to improve the efficiency and accuracy of collaborative operations among logistics and warehousing robot groups.

RESULTS: Through extensive experimental evaluation on multiple datasets and tasks, the results show that in different scenarios, our model can successfully achieve multi-robot collaborative operation, significantly improve task completion efficiency, and maintain target detection and environment High accuracy of understanding.

DISCUSSION: In addition, our model shows excellent robustness and adaptability and can adapt to dynamic changes in the environment and fluctuations in demand, providing an effective method to solve the collaborative operation problem of logistics warehousing robots.

PMID:38322650 | PMC:PMC10844514 | DOI:10.3389/fnbot.2023.1329589

Front Plant Sci. 2024 Jan 23;14:1305081. doi: 10.3389/fpls.2023.1305081. eCollection 2023.

ABSTRACT

Seed germination rate is one of the important indicators in measuring seed quality and seed germination ability, and it is also an important basis for evaluating the growth potential and planting effect of seeds. In order to detect seed germination rates more efficiently and achieve automated detection, this study focuses on wild rice as the research subject. A novel method for detecting wild rice germination rates is introduced, leveraging the SGR-YOLO model through deep learning techniques. The SGR-YOLO model incorporates the convolutional block attention module (efficient channel attention (ECA)) in the Backbone, adopts the structure of bi-directional feature pyramid network (BiFPN) in the Neck part, adopts the generalized intersection over union (GIOU) function as the loss function in the Prediction part, and adopts the GIOU function as the loss function by setting the weighting coefficient to accelerate the detection of the seed germination rate. In the Prediction part, the GIOU function is used as the loss function to accelerate the learning of high-confidence targets by setting the weight coefficients to further improve the detection accuracy of seed germination rate. The results showed that the accuracy of the SGR-YOLO model for wild rice seed germination discrimination was 94% for the hydroponic box and 98.2% for the Petri dish. The errors of germination potential, germination index, and average germination days detected by SGR-YOLO using the manual statistics were 0.4%, 2.2, and 0.9 days, respectively, in the hydroponic box and 0.5%, 0.5, and 0.24 days, respectively, in the Petri dish. The above results showed that the SGR-YOLO model can realize the rapid detection of germination rate, germination potential, germination index, and average germination days of wild rice seeds, which can provide a reference for the rapid detection of crop seed germination rate.

PMID:38322421 | PMC:PMC10844399 | DOI:10.3389/fpls.2023.1305081

J Pathol Inform. 2023 Dec 29;15:100359. doi: 10.1016/j.jpi.2023.100359. eCollection 2024 Dec.

ABSTRACT

In this study, we present a deep-learning-based multimodal classification method for lymphoma diagnosis in digital pathology, which utilizes a whole slide image (WSI) as the primary image data and flow cytometry (FCM) data as auxiliary information. In pathological diagnosis of malignant lymphoma, FCM serves as valuable auxiliary information during the diagnosis process, offering useful insights into predicting the major class (superclass) of subtypes. By incorporating both images and FCM data into the classification process, we can develop a method that mimics the diagnostic process of pathologists, enhancing the explainability. In order to incorporate the hierarchical structure between superclasses and their subclasses, the proposed method utilizes a network structure that effectively combines the mixture of experts (MoE) and multiple instance learning (MIL) techniques, where MIL is widely recognized for its effectiveness in handling WSIs in digital pathology. The MoE network in the proposed method consists of a gating network for superclass classification and multiple expert networks for (sub)class classification, specialized for each superclass. To evaluate the effectiveness of our method, we conducted experiments involving a six-class classification task using 600 lymphoma cases. The proposed method achieved a classification accuracy of 72.3%, surpassing the 69.5% obtained through the straightforward combination of FCM and images, as well as the 70.2% achieved by the method using only images. Moreover, the combination of multiple weights in the MoE and MIL allows for the visualization of specific cellular and tumor regions, resulting in a highly explanatory model that cannot be attained with conventional methods. It is anticipated that by targeting a larger number of classes and increasing the number of expert networks, the proposed method could be effectively applied to the real problem of lymphoma diagnosis.

PMID:38322152 | PMC:PMC10844119 | DOI:10.1016/j.jpi.2023.100359

J Big Data. 2024;11(1):25. doi: 10.1186/s40537-023-00842-0. Epub 2024 Feb 4.

ABSTRACT

The transformer model is a famous natural language processing model proposed by Google in 2017. Now, with the extensive development of deep learning, many natural language processing tasks can be solved by deep learning methods. After the BERT model was proposed, many pre-trained models such as the XLNet model, the RoBERTa model, and the ALBERT model were also proposed in the research community. These models perform very well in various natural language processing tasks. In this paper, we describe and compare these well-known models. In addition, we also apply several types of existing and well-known models which are the BERT model, the XLNet model, the RoBERTa model, the GPT2 model, and the ALBERT model to different existing and well-known natural language processing tasks, and analyze each model based on their performance. There are a few papers that comprehensively compare various transformer models. In our paper, we use six types of well-known tasks, such as sentiment analysis, question answering, text generation, text summarization, name entity recognition, and topic modeling tasks to compare the performance of various transformer models. In addition, using the existing models, we also propose ensemble learning models for the different natural language processing tasks. The results show that our ensemble learning models perform better than a single classifier on specific tasks.

PMID:38321999 | PMC:PMC10838835 | DOI:10.1186/s40537-023-00842-0