RESUMO
Parkinson's disease (PD) entails the progressive loss of dopaminergic (DA) neurons in the substantia nigra pars compacta (SNc), leading to movement-related impairments. Accurate assessment of DA neuron health is vital for research applications. Manual analysis, however, is laborious and subjective. To address this, we introduce TrueTH, a user-friendly and robust pipeline for unbiased quantification of DA neurons. Existing deep learning tools for tyrosine hydroxylase-positive (TH+) neuron counting often lack accessibility or require advanced programming skills. TrueTH bridges this gap by offering an open-sourced and user-friendly solution for PD research. We demonstrate TrueTH's performance across various PD rodent models, showcasing its accuracy and ease of use. TrueTH exhibits remarkable resilience to staining variations and extreme conditions, accurately identifying TH+ neurons even in lightly stained images and distinguishing brain section fragments from neurons. Furthermore, the evaluation of our pipeline's performance in segmenting fluorescence images shows strong correlation with ground truth and outperforms existing models in accuracy. In summary, TrueTH offers a user-friendly interface and is pretrained with a diverse range of images, providing a practical solution for DA neuron quantification in Parkinson's disease research.
Assuntos
Aprendizado Profundo , Neurônios Dopaminérgicos , Neurônios Dopaminérgicos/metabolismo , Animais , Tirosina 3-Mono-Oxigenase/metabolismo , Doença de Parkinson/metabolismo , Doença de Parkinson/patologia , Masculino , Camundongos , RatosRESUMO
In this paper, a highly integrated terahertz (THz) biosensor is proposed and implemented, which pioneered the preparation of low-temperature gallium arsenide (LT-GaAs) thin film photoconductive antenna (PCA) on the sensor for direct generation and detection of THz waves, simplifying complex terahertz time-domain spectroscopy (THz-TDS) systems. A latch type metasurface is deposited in the detection region to produce a resonance absorption peak at 0.6 THz that is independent of polarisation. Microfluidics is utilised and automatic injection is incorporated to mitigate the experimental effects of hydrogen bond absorption of THz waves in aqueous-based environment. Additionally, cell damage is minimised by regulating the cell flow rate. The biosensor was utilised to detect the concentration of three distinct sizes of bacteria with successful results. The assay was executed as a proof of concept to detect two distinct types of breast cancer cells. Based on the experimental findings, it has been observed that the amplitude and blueshift of the resonance absorption peaks have the ability to identify and differentiate various cancer cell types. The findings of this study introduce a novel approach for developing microfluidic THz metasurface biosensors that possess exceptional levels of integration, sensitivity, and rapid label-free detection capabilities.
Assuntos
Arsenicais , Técnicas Biossensoriais , Gálio , Espectroscopia Terahertz , Gálio/química , Arsenicais/química , Técnicas Biossensoriais/instrumentação , Espectroscopia Terahertz/instrumentação , Humanos , Desenho de Equipamento , Microfluídica/instrumentaçãoRESUMO
Although microRNA (miRNA) have important clinical prospects in the early diagnosis and treatment of PD, the functions and mechanisms of miRNAs in PD models remain poorly defined. In this study, we screened 9 miRNAs that differently expressed in PD patients and found that miR-142-3p expression was downregulated in both animal and cell models of PD. We showed that overexpression of miR-142-3p significantly alleviates the neuronal damage induced by MPP+, while knockdown of miR-142-3p exacerbates the neuronal damage caused by MPP+. We further found that miR-142-3p targets and inhibits the expression of C9orf72. Knockdown of C9orf72 mitigated neuronal autophagy dysfunction by reducing excessive activation of the AKT/mTOR pathway after MPP+ stimulation, thereby exerted neuroprotective effects. This study reveals that miR-142-3p protects neuron in PD pathogenesis via negatively regulating C9orf72 and enhancing autophagy. Our findings provides an insight into the development of potential biomarkers and therapeutic targets for PD.
Assuntos
Apoptose , Autofagia , Proteína C9orf72 , MicroRNAs , Neurônios , Doença de Parkinson , MicroRNAs/metabolismo , MicroRNAs/genética , Animais , Neurônios/metabolismo , Neurônios/patologia , Humanos , Doença de Parkinson/genética , Doença de Parkinson/metabolismo , Doença de Parkinson/patologia , Autofagia/fisiologia , Proteína C9orf72/genética , Proteína C9orf72/metabolismo , Masculino , CamundongosRESUMO
Previously, we analyzed 316 herbal extracts to evaluate their potential nematocidal properties in Caenorhabditis elegans. In this study, our attention was directed towards Torenia sp., resulting in reduced survival and heightened larval arrest/lethality, alongside a noticeable decrease in DAPI-stained bivalent structures and disrupted meiotic progression, thus disrupting developmental processes. Notably, Torenia sp. extracts activated a DNA damage checkpoint response via the ATM/ATR and CHK-1 pathways, hindering germline development. LC-MS analysis revealed 13 compounds in the Torenia sp. extracts, including flavonoids, terpenoids, tanshinones, an analog of resveratrol, iridoids, carotenoids, fatty acids, and alkaloids. Of these, 10 are known for their antitumor activity, suggesting the potential of Torenia species beyond traditional gardening, extending into pharmaceutical and therapeutic applications.
RESUMO
Objective.Depression is a common chronic mental disorder characterized by high rates of prevalence, recurrence, suicide, and disability as well as heavy disease burden. An accurate diagnosis of depression is a prerequisite for treatment. However, existing questionnaire-based diagnostic methods are limited by the innate subjectivity of medical practitioners and subjects. In the search for a more objective diagnostic methods for depression, researchers have recently started to use deep learning approaches.Approach.In this work, a deep-learning network, named adaptively multi-time-window graph convolutional network (GCN) with long-short-term memory (LSTM) (i.e. AMGCN-L), is proposed. This network can automatically categorize depressed and non-depressed people by testing for the existence of inherent brain functional connectivity and spatiotemporal features contained in electroencephalogram (EEG) signals. AMGCN-L is mainly composed of two sub-networks: the first sub-network is an adaptive multi-time-window graph generation block with which adjacency matrices that contain brain functional connectivity on different time periods are adaptively designed. The second sub-network consists of GCN and LSTM, which are used to fully extract the innate spatial and temporal features of EEG signals, respectively.Main results.Two public datasets, namely the patient repository for EEG data and computational tools, and the multi-modal open dataset for mental-disorder analysis, were used to test the performance of the proposed network; the depression recognition accuracies achieved in both datasets (using tenfold cross-validation) were 90.38% and 90.57%, respectively.Significance.This work demonstrates that GCN and LSTM have eminent effects on spatial and temporal feature extraction, respectively, suggesting that the exploration of brain connectivity and the exploitation of spatiotemporal features benefit the detection of depression. Moreover, the proposed method provides effective support and supplement for the detection of clinical depression and later treatment procedures.
Assuntos
Depressão , Transtorno Depressivo Maior , Humanos , Depressão/diagnóstico , Memória de Curto Prazo , Encéfalo , EletroencefalografiaRESUMO
ETHNOPHARMACOLOGICAL RELEVANCE: Potentilla discolor Bunge (PD) is a member of the Rosaceae family. It has been traditionally used in folk medicine for the treatment of diabetes. Additionally, people in folk also eat fresh and tender PD stems as vegetables or brew them as tea. AIM OF THE STUDY: The aim of this study was to explore the antidiabetic effects and underlying mechanisms of the water extract of Potentilla discolor (PDW) in a fruit fly model of high-sugar diet-induced type 2 diabetes. MATERIALS AND METHODS: The antidiabetic efficacy of PDW was evaluated in a fruit fly model of diabetes induced by a high-sugar diet (HSD). Various physiological parameters were tested to evaluate the anti-diabetic effect of PDW. Gene expression levels related to insulin signaling pathways, glucose metabolism, lipid metabolism, and JAK/STAT signaling pathways were primarily analyzed using RT-qPCR to investigate the therapeutic mechanisms. RESULTS: In this study, we found that the water extract of Potentilla discolor (PDW) can ameliorate type II diabetes phenotypes induced by the HSD in fruit flies. These phenotypes include growth rate, body size, hyperglycemia, glycogen metabolism, fat storage, and intestinal microflora homeostasis. PDW also improved the body size of s6k and rheb knockdown flies, suggesting its potential to activate the downstream insulin pathway and alleviate insulin resistance. Furthermore, we demonstrated that PDW reduced the expression of two target genes of the JAK/STAT signaling pathway, namely the insulin antagonist Impl2 and insulin receptor inhibitor Socs36E, which act as regulators inhibiting the activation of the insulin signaling pathway. CONCLUSIONS: This study provides evidence for the anti-diabetic activity of PDW and suggests that its underlying mechanism may involve the improvement of insulin resistance by inhibiting the JAK/STAT signaling pathway.
Assuntos
Diabetes Mellitus Tipo 2 , Resistência à Insulina , Potentilla , Animais , Diabetes Mellitus Tipo 2/tratamento farmacológico , Drosophila melanogaster , Hipoglicemiantes/farmacologia , Hipoglicemiantes/uso terapêutico , Insulina/metabolismo , Transdução de Sinais , Dieta , Açúcares/metabolismoRESUMO
Ferroelectric materials have received great attention in the field of data storage, benefiting from their exotic transport properties. Among these materials, the two-dimensional (2D) In2Se3 has been of particular interest because of its ability to exhibit both in-plane and out-of-plane ferroelectricity. In this article, we realized the molecular beam epitaxial (MBE) growth of ß-In2Se3 films on bilayer graphene (BLG) substrates with precisely controlled thickness. Combining in situ scanning tunneling microscopy (STM) and angle-resolved photoemission spectroscopy (ARPES) measurements, we found that the four-monolayer ß-In2Se3 is a semiconductor with a (9 × 1) reconstructed superlattice. In contrast, the monolayer ß-In2Se3/BLG heterostructure does not show any surface reconstruction due to the interfacial interaction and moiré superlattice, which instead results in a folding Dirac cone at the center of the Brillouin zone. In addition, we found that the band gap of In2Se3 film decreases after potassium doping on its surface, and the valence band maximum also shifts in momentum after surface potassium doping. The successful growth of high-quality ß-In2Se3 thin films would be a new platform for studying the 2D ferroelectric heterostructures and devices. The experimental results on the surface reconstruction and band structures also provide important information on the quantum confinement and interfacial effects in the epitaxial ß-In2Se3 films.
RESUMO
The itinerant ferromagnetism can be induced by a van Hove singularity (VHS) with a divergent density of states at Fermi level. Utilizing the giant magnified dielectric constant εr of SrTiO3(111) substrate with cooling, here we successfully manipulated the VHS in the epitaxial monolayer (ML) 1T-VSe2 film approaching to Fermi level via the large interfacial charge transfer, and thus induced a two-dimensional (2D) itinerant ferromagnetic state below 3.3 K. Combining the direct characterization of the VHS structure via angle-resolved photoemission spectroscopy (ARPES), together with the theoretical analysis, we ascribe the manipulation of VHS to the physical origin of the itinerant ferromagnetic state in ML 1T-VSe2. Therefore, we further demonstrated that the ferromagnetic state in the 2D system can be controlled through manipulating the VHS by engineering the film thickness or replacing the substrate. Our findings clearly evidence that the VHS can serve as an effective manipulating degree of freedom for the itinerant ferromagnetic state, expanding the application potentials of 2D magnets for the next-generation information technology.
Assuntos
Asma , Doença Pulmonar Obstrutiva Crônica , Humanos , Imãs , Temperatura BaixaRESUMO
By introducing different contents of Bi adatoms to the surface of monolayer graphene, the carrier concentration and their dynamics have been effectively modulated as probed directly by the time- and angle-resolved photoemission spectroscopy technique. The Bi adatoms are found to assist acoustic phonon scattering events mediated by supercollisions as the disorder effectively relaxes the momentum conservation constraint. A reduced carrier multiplication has been observed, which is related to the shrinking Fermi sea for scattering, as confirmed by time-dependent density functional theory simulation. This work gives insight into hot carrier dynamics in graphene, which is crucial for promoting the application of photoelectric devices.
RESUMO
The JNK pathway play a critical role in insulin resistance induced by a long-term high-sugar diet. However, the roles of up- and downstream molecules of the JNK pathway in insulin resistance are less known in vertebrates and invertebrates. As a classical organism in biological research, Drosophila melanogaster (D. melanogaster) has been widely applied to the studies of mechanism of insulin resistance. Based on previous studies, we found a novel predictive mechanism of the formation of insulin resistance in D. melanogaster. We found that JNK activated by high-sugar diet and dysregulated intestinal microbiota could mediate inflammation, and then the activated JNK released Upd3, which in turn stimulated Jak/STAT pathway to release ImpL2. ImpL2 can compete with Drosophila insulin-like peptides (Dilps) for binding with the insulin receptor and inhibit the activation of insulin pathway. In this study, we reviewed novel studies on the insulin signalling pathway based on the D. melanogaster model. The findings support our hypothesis. We, therefore, described how a long-term high-sugar diet disrupts intestinal microbiota to induce inflammation and the disruption of JNK-Jak/STAT axis. This description may offer some new clues to the formation of insulin resistance.
Assuntos
Proteínas de Drosophila , Microbioma Gastrointestinal , Resistência à Insulina , Animais , Drosophila melanogaster/metabolismo , Proteínas de Drosophila/metabolismo , Janus Quinases/metabolismo , Transdução de Sinais , Fatores de Transcrição STAT/metabolismo , Drosophila/metabolismo , Insulina/metabolismo , Inflamação , Açúcares/metabolismo , Proteínas de Ligação a Fator de Crescimento Semelhante a Insulina/metabolismoRESUMO
In recent years, solid state terahertz (THz) modulators have obtained rapid progress with the widespread use of two-dimensional (2D) materials in the field of THz; however, challenges remain in preparing flexible THz modulators. In this study, flexible ferromagnetic nematic materials were prepared by doping thermotropic nematic liquid crystals 5CB into magnetic fluids, and the influence of water was reduced by a self-made cyclic olefin copolymer (COC) microfluidic chip. THz modulation characteristics of magnetic fluid and ferromagnetic nematic liquid crystal (FNLC) under the induction of external magnetic field were compared using a THz time domain spectroscopy system. Under the action of a 91 mT magnetic field, the magnetic fluid has a maximum modulation depth (MD) of 54%. Under the same magnetic field, the maximum MD of the FNLC materials increase to 78% because of the rearrangement of Fe3O4 nanoparticles induced by the topological defect of the liquid crystal. We demonstrate that the magneto-optical effect is significantly enhanced in the ferromagnetic nematic liquid crystal hybrid system. This strategy of doping thermotropic nematic liquid crystals to enhance the magneto-optical effect has great potential for THz filtering, modulation, and sensing applications.
RESUMO
In an era of increasing interest in the potential health benefits of medicinal foods, the need to assess their safety and potential toxicity remains a critical concern. While these natural remedies have garnered substantial attention for their therapeutic potential, a comprehensive understanding of their effects on living organisms is essential. We examined 316 herbal extracts to determine their potential nematocidal attributes in Caenorhabditis elegans. Approximately 16% of these extracts exhibited the capacity to induce diminished survival rates and larval arrest, establishing a correlation between larval arrest and overall worm viability. Certain extracts led to an unexpected increase in male nematodes, accompanied by a discernible reduction in DAPI-stained bivalent structures and perturbed meiotic advancement, thereby disrupting the conventional developmental processes. Notably, Onobrychis cornuta and Veratrum lobelianum extracts activated a DNA damage checkpoint response via the ATM/ATR and CHK-1 pathways, thus hindering germline development. Our LC-MS analysis revealed jervine in V. lobelianum and nine antitumor compounds in O. cornuta. Interestingly, linoleic acid replicated phenotypes induced by O. cornuta exposure, including an increased level of pCHK-1 foci, apoptosis, and the MAPK pathway. Mutants in the MAPK pathway mitigated the decline in worm survival, underscoring its importance in promoting worm viability. This study reveals complex interactions between herbal extracts and C. elegans processes, shedding light on potential antitumor effects and mechanisms. The findings provide insights into the complex landscape of herbal medicine's impact on a model organism, offering implications for broader applications.
Assuntos
Fabaceae , Veratrum , Masculino , Animais , Caenorhabditis elegans , Antinematódeos , Células GerminativasRESUMO
Olfactory-induced emotion plays an important role in communication, decision-making, multimedia, and disorder treatment. Using electroencephalogram (EEG) technology, this paper focuses on (1) exploring the possibility of recognizing pleasantness induced by different concentrations of odors, (2) finding the EEG rhythm wave that is most suitable for the recognition of different odor concentrations, (3) analyzing recognition accuracies with concentration changes, and (4) selecting a suitable classifier for this classification task. To explore these issues, first, emotions induced by five different concentrations of rose or rotten odors are divided into five kinds of pleasantness by averaging subjective evaluation scores. Then, the power spectral density features of EEG signals and support vector machine (SVM) are used for classification tasks. Classification results on the EEG signals collected from 13 participants show that for pleasantness recognition induced by pleasant or disgusting odor concentrations, considerable average classification accuracies of 93.5% or 92.2% are obtained, respectively. The results indicate that (1) using EEG technology, pleasantness recognition induced by different odor concentrations is possible; (2) gamma frequency band outperformed other EEG rhythm-based frequency bands in terms of classification accuracy, and as the maximum frequency of the EEG spectrum increases, the pleasantness classification accuracy gradually increases; (3) for both rose and rotten odors, the highest concentration obtains the best classification accuracy, followed by the lowest concentration.
Assuntos
Eletroencefalografia , Odorantes , Humanos , Eletroencefalografia/métodos , Emoções , Olfato , Máquina de Vetores de SuporteRESUMO
Terahertz (THz) waves can cover the characteristic spectra of substances such as plasma, organisms, and biomolecules, whereas THz photons have low energy and do not damage biological tissues. Therefore, its absorption characteristics in the THz region can be used to characterize the internal structure of biomolecules. In this study, we designed a microfluidic chip and combined it with THz technology. The spectral intensity in descending order was found to be deionized water, phenylalanine, histidine, glycine and glutamic acid by observing the THz wave transmission in the range of 0.1-1.0 THz, comparing the frequency domain spectra of four amino acid solutions with volume fraction of 2% and deionized water. It is inferred that different molecular structures of amino acids resulted in different numbers of hydrogen bonds formed between them and water molecules, leading to different degrees of absorption of THz waves. In addition, magnetic fields parallel to the THz wave transmission were used to study the variation of different amino acids with magnetic field intensity. It is found that increasing the magnetic field strength decrease the transmission of THz waves. This is because under the action of the magnetic field, on the one hand, the hydrogen bonds formed by water molecules are strengthened and the absorption of THz waves is enhanced; on the other hand, amino acid molecules aggregate and the radius of molecular clusters increases, thus blocking the transmission of THz waves. Finally, we also calculated the electric conductivity of the solutions to prove the accuracy of the experimental results from a theoretical point of view.
RESUMO
Recently, with the widespread application of metamaterials in the terahertz (THz) modulation field, solid-state THz modulators have made breakthrough progress; however, there are still challenges in preparing flexible THz modulators with wide modulation bandwidths. In this study, a THz microfluidic chip was fabricated using cycloolefin copolymers with high transmission (90%) of THz waves. The THz modulation characteristics of TiO2, Ag, and Fe3O4 nanosols under the control of an optical field, electric field, and magnetic field, respectively, were investigated. Under the action of photogenerated carrier migration, colloidal electrophoresis, and magneto-optical effect, all three nanosols exhibit broadband modulation performance in the frequency range of 0.3-2.4 THz, and the maximum modulation depth is 24%, 33%, and 54%, respectively. Contrary to previous studies based on traditional solid-state materials, this study innovatively explores the possibility of modulating THz waves with liquid materials, laying the foundation for the application of flexible liquid-film THz modulators.
RESUMO
Histone methylation shapes the epigenetic configuration and adjusts multiple fundamental nuclear processes, including transcription, cell cycle control and DNA repair. The absence of histone demethylase LSD1/SPR-5 leads to progressive fertility defects as well as a reduction in brood size. Similarly, C. elegans LSD2 homolog AMX-1 has been implicated in regulating H3K4me2 and maintaining interstrand crosslinks (ICL) susceptibility. However, the mechanisms of how lack of AMX-1 induces sterility have not been addressed so far. This study investigated the histone demethylase AMX-1 in C. elegans and uncovered how amx-1 contributes to sterility in a p53/CEP-1 dependent manner. We show that while sterility in spr-5 mutants exhibited progressive over generations, amx-1 mutants displayed non-transgenerational fertility defects. Also, amx-1 mutants exhibited a reduced number of sperms and produced low brood size (LBS) or sterile worms that retain neither sperms nor germline nuclei, suggesting that fertility defects originated from germline development failure. Surprisingly, sterility exhibited in amx-1 was mediated by p53/CEP-1 function. Consistent with this result, upregulation of Piwi expression in amx-1 mutants suggested that AMX-1 is essential for germline development by regulating Piwi gene expressions. We propose that AMX-1 is required for proper Piwi expression and transposon silencing in a p53/CEP-1 dependent manner; thus, the absence of AMX-1 expression leads to defective meiotic development and sterility. This study elucidates how LSD2/AMX-1 contributes to sterility, therefore, expanding the boundaries of histone demethylase function.
RESUMO
Objective.The classification of olfactory-induced electroencephalogram (olfactory EEG) signals has potential applications in disease diagnosis, emotion regulation, multimedia, and so on. To achieve high-precision classification, numerous EEG channels are usually used, but this also brings problems such as information redundancy, overfitting and high computational load. Consequently, channel selection is necessary to find and use the most effective channels.Approach.In this study, we proposed a multi-strategy fusion binary harmony search (MFBHS) algorithm and combined it with the Riemannian geometry classification framework to select the optimal channel sets for olfactory EEG signal classification. MFBHS was designed by simultaneously integrating three strategies into the binary harmony search algorithm, including an opposition-based learning strategy for generating high-quality initial population, an adaptive parameter strategy for improving search capability, and a bitwise operation strategy for maintaining population diversity. It performed channel selection directly on the covariance matrix of EEG signals, and used the number of selected channels and the classification accuracy computed by a Riemannian classifier to evaluate the newly generated subset of channels.Main results.With five different classification protocols designed based on two public olfactory EEG datasets, the performance of MFBHS was evaluated and compared with some state-of-the-art algorithms. Experimental results reveal that our method can minimize the number of channels while achieving high classification accuracy compatible with using all the channels. In addition, cross-subject generalization tests of MFBHS channel selection show that subject-independent channels obtained through training can be directly used on untrained subjects without greatly compromising classification accuracy.Significance.The proposed MFBHS algorithm is a practical technique for effective use of EEG channels in olfactory recognition.
Assuntos
Interfaces Cérebro-Computador , Eletroencefalografia , Algoritmos , Eletroencefalografia/métodos , HumanosRESUMO
With the continuous development of terahertz (THz) detection technology, the use of terahertz spectroscopy to study chemical samples has become one of the indispensable tools in the field of biochemistry. While most biomolecules biological activity can only be expressed in aqueous solutions, water as a polar molecule has strong absorption properties for terahertz waves, making it difficult to use terahertz technology to study the activity of biological samples in aqueous solutions. In this study, a sandwich-type terahertz microfluidic chip with high terahertz wave transmission was designed and combined with a terahertz time domain spectroscopy (THz-TDS) system to test the terahertz spectra of distilled water, 0.9 mol/L NH4Cl, (NH4)2SO4, (NH4)2CO3 and CH3COONH4 solutions, respectively, and to investigate the effect of the electric field action time on the hydrogen bond in the solution under the action of an external electric field. The experimental results show that the terahertz spectra of different ammonium solutions at the same concentration differ significantly, indicating that the ion hydration process affects the intermolecular hydrogen bonding in water, while the applied electric field also affects the hydrogen bonding in water, resulting in a change in the terahertz waves water absorption.
Assuntos
Compostos de Amônio , Espectroscopia Terahertz , Ligação de Hidrogênio , Microfluídica , Espectroscopia Terahertz/métodos , Água/químicaRESUMO
CRISPR/Cas9 technology has been applied to many arthropods. However, application of this technology to crustaceans remains limited because of the unique characteristics of embryos. Our group has developed a microinjection system to introduce the CRISPR/Cas9 system into Neocaridina heteropoda embryos (one-cell stage). Using the developed method, we mutated the target gene Nh-scarlet (N. heteropoda scarlet), which functions in eye development and pigmentation. The results showed that both eye color and shape were altered in individuals in which Nh-scarlet was knocked out. Furthermore, this system was also successfully applied to another decapod crustacean, Eriocheir sinensis. DNA sequencing revealed that the zoeae with red eyes had an edited version of Es-scarlet. This study provides a stable microinjection method for freshwater crustaceans, and will contribute to functional genomics studies in various decapods.
Assuntos
Sistemas CRISPR-Cas , Decápodes , Animais , Sistemas CRISPR-Cas/genética , Crustáceos , Decápodes/genética , Humanos , Microinjeções , MutagêneseRESUMO
It is quite laborious and costly to manually label LiDAR point cloud data for training high-quality 3D object detectors. This work proposes a weakly supervised framework which allows learning 3D detection from a few weakly annotated examples. This is achieved by a two-stage architecture design. Stage-1 learns to generate cylindrical object proposals under inaccurate and inexact supervision, obtained by our proposed BEV center-click annotation strategy, where only the horizontal object centers are click-annotated in bird's view scenes. Stage-2 learns to predict cuboids and confidence scores in a coarse-to-fine, cascade manner, under incomplete supervision, i.e., only a small portion of object cuboids are precisely annotated. With KITTI dataset, using only 500 weakly annotated scenes and 534 precisely labeled vehicle instances, our method achieves 86-97 percent the performance of current top-leading, fully supervised detectors (which require 3,712 exhaustively annotated scenes with 15,654 instances). More importantly, with our elaborately designed network architecture, our trained model can be applied as a 3D object annotator, supporting both automatic and active (human-in-the-loop) working modes. The annotations generated by our model can be used to train 3D object detectors, achieving over 95 percent of their original performance (with manually labeled training data). Our experiments also show our model's potential in boosting performance when given more training data. The above designs make our approach highly practical and open-up opportunities for learning 3D detection at reduced annotation cost.