Article
Biology
Sebastian Loyola, Tycho M. Hoogland, Hugo Hoedemaker, Vincenzo Romano, Mario Negrello, Chris I. De Zeeuw
Summary: This study investigates the interaction between inhibitory and excitatory inputs to inferior olive neurons, finding that the timing between these inputs determines the output pattern of the neurons. Activating the excitatory input shortly after the inhibitory input leads to unstable phase of intrinsic oscillations and minimal output, while activating the excitatory input one cycle after the inhibitory input optimally drives spiking activity. A large-scale network model simulation highlights the extent to which synaptic interactions generate oscillatory patterns in the inferior olive.
Article
Neurosciences
Sinem Balta Beylergil, Palak Gupta, Aasef G. Shaikh
Summary: Multisensory integration is crucial for accurate perception of heading direction, but deficiency in cerebellar function can lead to impaired integration and inaccurate heading perception. Oculopalatal tremor patients show poorer heading direction perception compared to healthy controls, possibly due to abnormal noise in the cerebellar system caused by hypersynchronized inferior olive signals.
Review
Clinical Neurology
Shinji Kakei, Mario Manto, Hirokazu Tanaka, Hiroshi Mitoma
Summary: Researchers propose a novel hypothesis that lesions in the Guillain-Mollaret (G-M) triangle result in various types of tremors or tremor-like movements, with each loop contributing to physiologically distinct types of tremors.
FRONTIERS IN NEUROLOGY
(2021)
Article
Neurosciences
Kevin Dorgans, Da Guo, Kiyoto Kurima, Jeff Wickens, Marylka Yoe Uusisaari
Summary: Adeno-associated viral (AAV) vectors are a powerful tool in modern neuroscience for gene transfer into the brain, allowing identification of specific neuronal populations and monitoring their activity. Researchers have successfully created an AAV vector for strong transfection of inferior olivary (IO) neurons and demonstrated the ability to monitor their activity.
FRONTIERS IN CELLULAR NEUROSCIENCE
(2022)
Article
Neurosciences
Tom J. H. Ruigrok, Xiaolu Wang, Erika Sabel-Goedknegt, Patrice Coulon, Zhenyu Gao
Summary: Recent studies have found a previously unknown connection between subcortical basal ganglia and the inferior olive (IO), a crucial part of the olivocerebellar climbing fiber system. This connection involves GABAergic neurons in the entopeduncular nucleus, which innervate cells surrounding the fasciculus retroflexus and collectively known as the area parafascicularis prerubralis. This connection may play a role in regulating olivary excitability, influencing cerebellar learning and possibly transmitting reward properties.
FRONTIERS IN SYSTEMS NEUROSCIENCE
(2023)
Article
Statistics & Probability
Terence P. Speed, Damien G. Hicks
Summary: The paper extends the concept of ANOVA to MANOVA and introduces a spectral principal component analysis. The authors attempt to apply similar methods to arrays of random variables indexed by binary trees, but the existence of spectral PCA remains unresolved.
JOURNAL OF MULTIVARIATE ANALYSIS
(2022)
Article
Environmental Studies
Ricardo Martin, Victor Yepes
Summary: This study aimed to identify and assess the landscape values of a marina, using interviews and questionnaires to enhance stakeholder and user participation. The results showed that the marina should align with an atmosphere of tranquility and well-being, but there is a need to improve values related to nautical tourism.
Article
Chemistry, Multidisciplinary
Dariusz S. Bajkowski, Wojciech J. Cynarski
Summary: This study examined the characteristics of participants in martial arts and combat sports, including age, weight, years of training, skill level, and handgrip strength. The results showed that these characteristics, combined with gender and martial arts style, can be used to differentiate between practitioners of different martial styles and skill levels, as well as between genders.
APPLIED SCIENCES-BASEL
(2023)
Article
Environmental Sciences
Joao Lopes, Afonso Silva Pinto, Telmo Eleuterio, Maria Gabriela Meirelles, Helena Cristina Vasconcelos
Summary: This study identified the key factors influencing phytoplankton development in four lakes on the island of Sao Miguel. Multivariate analysis was used to explore relationships between biological parameters, physicochemical parameters, and meteorological data. The results showed correlations between different phytoplankton phyla and various environmental factors such as precipitation, evaporation, wind speed, air temperature, water temperature, and radiation. The study also found that the physicochemical parameters of these lakes remained stable over the past 15 years, indicating the effectiveness of monitoring and protection measures.
Review
Biochemistry & Molecular Biology
Pia C. Burboa, Mariela Puebla, Pablo S. Gaete, Walter N. Duran, Mauricio A. Lillo
Summary: Microcirculation homeostasis depends on channels permeable to ions and small molecules, and the Connexin and Pannexin large-pore channel proteins play a vital role in regulating vascular tone and intercellular communication.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Chemistry, Analytical
K. R. Sri Preethaa, Shyamala Devi Munisamy, Aruna Rajendran, Akila Muthuramalingam, Yuvaraj Natarajan, Ahmed Abdi Yusuf Ali
Summary: This study proposes a method for accurately assessing the damage grade of buildings using the ANOVA-Statistic-Reduced Deep Fully Connected Neural Network (ASR-DFCNN) model. Through feature selection and model optimization, accurate prediction of damage grades is achieved.
Article
Engineering, Multidisciplinary
Jogendra Kumar, Rajesh Kumar Verma
Summary: This study investigated the drilling behavior of polymer nanocomposites reinforced by Graphene oxide/ Carbon fiber using a hybrid method of Grey theory and Principal component analysis (GR-PCA). The results showed that feed rate was the most predominant factor, with higher feed rate and graphene oxide content leading to surface damages such as fiber pull-out and cracks.
DEFENCE TECHNOLOGY
(2021)
Article
Neurosciences
Mriga Das, Duo Cheng, Till Matzat, Vanessa J. Auld
Summary: Glia are crucial for protecting and enabling nervous system function, and the formation of the glial sheath around peripheral axons plays a key role. In this study, the role of Innexins in mediating glial function in the Drosophila periphery was investigated. It was found that Inx1 and Inx2 are important for peripheral glia development, and their loss led to defects in wrapping glia and disruption of the glia wrap. Inx2 was also found to play a role in linking subperineurial glia and wrapping glia, ensuring the integrity of the glial wrap.
JOURNAL OF NEUROSCIENCE
(2023)
Article
Environmental Sciences
Tawfik El Moussaoui
Summary: Olive mill wastewater is a severe environmental problem in Mediterranean producer countries. This study provides a comprehensive analysis of activated sludge biomass and crucial process parameters in the treatment of olive mill wastewater. The results show that increasing the mass ratio of olive mill wastewater can improve the treatment efficiency of the activated sludge system, after an acclimation step.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Chemistry, Analytical
Julieth G. Herrera, Marilia P. Ramos, Bheatriz Nunes de Lima Albuquerque, Julio Cesar Ribeiro de Oliveira Farias de Aguiar, Afonso Cordeiro Agra Neto, Patricia Maria Guedes Paiva, Daniela Maria do Amaral Ferraz Navarro, Licarion Pinto
Summary: This study evaluated the effects of temperature, pressure, extraction time, and their interactions on the constituents of essential oil extracted from Piper cor-covadensis using supercritical fluid extraction (SFE). The results showed that pressure and temperature significantly influenced the extraction of constituents, while extraction time was not within the analyzed range. ANOVA-PCA was used to assess the influence of process parameters on each constituent, and the advantages of both ANOVA and univariate ANOVA were compared. Additionally, new constituents were identified during the SFE process.
MICROCHEMICAL JOURNAL
(2022)
Review
Neurosciences
Sook-Lei Liew, Artemis Zavaliangos-Petropulu, Neda Jahanshad, Catherine E. Lang, Kathryn S. Hayward, Keith R. Lohse, Julia M. Juliano, Francesca Assogna, Lee A. Baugh, Anup K. Bhattacharya, Bavrina Bigjahan, Michael R. Borich, Lara A. Boyd, Amy Brodtmann, Cathrin M. Buetefisch, Winston D. Byblow, Jessica M. Cassidy, Adriana B. Conforto, R. Cameron Craddock, Michael A. Dimyan, Adrienne N. Dula, Elsa Ermer, Mark R. Etherton, Kelene A. Fercho, Chris M. Gregory, Shahram Hadidchi, Jess A. Holguin, Darryl H. Hwang, Simon Jung, Steven A. Kautz, Mohamed Salah Khlif, Nima Khoshab, Bokkyu Kim, Hosung Kim, Amy Kuceyeski, Martin Lotze, Bradley J. MacIntosh, John L. Margetis, Feroze B. Mohamed, Fabrizio Piras, Ander Ramos-Murguialday, Genevieve Richard, Pamela Roberts, Andrew D. Robertson, Jane M. Rondina, Natalia S. Rost, Nerses Sanossian, Nicolas Schweighofer, Na Jin Seo, Mark S. Shiroishi, Surjo R. Soekadar, Gianfranco Spalletta, Cathy M. Stinear, Anisha Suri, Wai Kwong W. Tang, Gregory T. Thielman, Daniela Vecchio, Arno Villringer, Nick S. Ward, Emilio Werden, Lars T. Westlye, Carolee Winstein, George F. Wittenberg, Kristin A. Wong, Chunshui Yu, Steven C. Cramer, Paul M. Thompson
Summary: The ENIGMA Stroke Recovery working group aims to understand the relationship between brain and behavior using meta- and mega-analytic approaches. They have developed neuroinformatics protocols and methods to manage large-scale data from over 2,100 stroke patients. The challenges and recommendations for data harmonization in stroke research are discussed.
HUMAN BRAIN MAPPING
(2022)
Article
Biochemical Research Methods
Bastien Berret, Adrien Conessa, Nicolas Schweighofer, Etienne Burdet
Summary: The study introduces a new stochastic optimal feedforward-feedback control model that can predict the timing and variability of self-paced arm reaching movements carried out with or without visual feedback. The model considers effort and variance minimization as well as the effects of motor and sensory noise on arm movement planning and execution. By elegantly combining both feedforward and feedback control aspects, the SFFC model is able to address issues where previous models may fail, providing a more comprehensive understanding of human motor control.
PLOS COMPUTATIONAL BIOLOGY
(2021)
Article
Neurosciences
Sujin Kim, Cheol E. Han, Bokkyu Kim, Carolee J. Winstein, Nicolas Schweighofer
Summary: In reaching movements following stroke, right-hemiparetic individuals show a habitual pattern of arm choice, while left-hemiparetic individuals choose their paretic left arm more optimally.
JOURNAL OF NEUROPHYSIOLOGY
(2022)
Article
Acoustics
Annemie Van Hirtum, Anne Bouvet, Isao Tokuda, Xavier Pelorson
Summary: The study found that angular asymmetry affects the decay of vocal fold vibration modes, with a stiff epithelium-like surface layer increasing the mode decay. Spatial mode patterns near the glottal aperture reflect the mode order and the imposed angular asymmetry reduces the spatial mode extent near the tilted vocal fold edge.
JOURNAL OF SOUND AND VIBRATION
(2022)
Article
Acoustics
Takuto Honda, Mayuka Kanaya, Isao T. Tokuda, Anne Bouvet, Annemie Van Hirtum, Xavier Pelorson
Summary: This study examined the quasi-steady approximation of glottal flow by measuring intraglottal pressure distributions in a scaled-up static vocal fold model under time-varying flow conditions. The results showed that the pressure profiles and air-jet separation point were indistinguishable between time-varying and steady flow conditions with matching subglottal pressure. Therefore, it suggests that time-varying glottal flow can be approximated as a series of steady flow states with a matching subglottal pressure in the range of normal vocalization frequencies.
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA
(2022)
Article
Biochemistry & Molecular Biology
Mark Greenwood, Isao T. Tokuda, James C. W. Locke
Summary: Individual plant cells possess a circadian clock that times internal processes to the day-night cycle. This clock is regulated by a genetic network and is sensitive to light. The cells communicate their timing through local or long-distance sharing of clock components, allowing for spatial coordination. Local coupling minimizes timing errors caused by noisy light-dark cycles and maintains different clock phases in different plant regions.
MOLECULAR SYSTEMS BIOLOGY
(2022)
Article
Cardiac & Cardiovascular Systems
Artemis Zavaliangos-Petropulu, Bethany Lo, Miranda R. Donnelly, Nicolas Schweighofer, Keith Lohse, Neda Jahanshad, Giuseppe Barisano, Nerisa Banaj, Michael R. Borich, Lara A. Boyd, Cathrin M. Buetefisch, Winston D. Byblow, Jessica M. Cassidy, Charalambos C. Charalambous, Adriana B. Conforto, Julie A. DiCarlo, Adrienne N. Dula, Natalia Egorova-Brumley, Mark R. Etherton, Wuwei Feng, Kelene A. Fercho, Fatemeh Geranmayeh, Colleen A. Hanlon, Kathryn S. Hayward, Brenton Hordacre, Steven A. Kautz, Mohamed Salah Khlif, Hosung Kim, Amy Kuceyeski, David J. Lin, Jingchun Liu, Martin Lotze, Bradley J. MacIntosh, John L. Margetis, Feroze B. Mohamed, Fabrizio Piras, Ander Ramos-Murguialday, Kate P. Revill, Pamela S. Roberts, Andrew D. Robertson, Heidi M. Schambra, Na Jin Seo, Mark S. Shiroishi, Cathy M. Stinear, Surjo R. Soekadar, Gianfranco Spalletta, Myriam Taga, Wai Kwong Tang, Gregory T. Thielman, Daniela Vecchio, Nick S. Ward, Lars T. Westlye, Emilio Werden, Carolee Winstein, George F. Wittenberg, Steven L. Wolf, Kristin A. Wong, Chunshui Yu, Amy Brodtmann, Steven C. Cramer, Paul M. Thompson, Sook-Lei Liew
Summary: This study identified novel associations between chronic poststroke sensorimotor impairments and ipsilesional hippocampal volume, which may be stronger in women.
JOURNAL OF THE AMERICAN HEART ASSOCIATION
(2022)
Article
Multidisciplinary Sciences
Takeshi Nishimura, Isao T. Tokuda, Shigehiro Miyachi, Jacob C. Dunn, Christian T. Herbst, Kazuyoshi Ishimura, Akihisa Kaneko, Yuki Kinoshita, Hiroki Koda, Jaap P. P. Saers, Hirohiko Imai, Tetsuya Matsuda, Ole Naesbye Larsen, Uwe Jurgens, Hideki Hirabayashi, Shozo Kojima, W. Tecumseh Fitch
Summary: Human speech production follows the same acoustic principles as vocal production in other animals but has distinctive features due to simplifications in laryngeal anatomy. The loss of vocal membranes allows human speech to avoid spontaneous nonlinear phenomena and acoustic chaos found in other primate vocalizations, leading to stable and harmonic-rich phonation.
Article
Multidisciplinary Sciences
Florian Grziwotz, Chun -Wei Chang, Vasilis Dakos, Egbert H. van Nes, Markus Schwarzlaender, Oliver Kamps, Martin Hessler, Isao T. Tokuda, Arndt Telschow, Chih-hao Hsieh
Summary: Critical transitions occur in various real-world systems and forecasting their occurrence is of great interest. This study introduces a powerful early warning signal called dynamical eigenvalue (DEV) that estimates the dominant eigenvalue of a system using bifurcation theory. The efficacy of the DEV approach is demonstrated in model systems with known bifurcation types and tested on various critical transitions in real-world systems.
Article
Biology
Rintaro Miyazaki, Tomoki Yoshitani, Mayuka Kanaya, Shigehiro Miyachi, Akihisa Kaneko, Yuki Kinoshita, Kanta Nakamura, Takeshi Nishimura, Isao T. Tokuda
Summary: We conducted ex vivo and in vivo experiments to study the role of the ventricular folds in sound production in macaques. Our results show that the ventricular folds co-oscillate with the vocal folds and significantly lower the fundamental frequency. A mathematical model suggests that this is due to the low oscillation frequency of the ventricular folds entraining the vocal folds. The findings suggest that macaques may use the ventricular folds more frequently than humans in vocalization.
JOURNAL OF EXPERIMENTAL BIOLOGY
(2023)
Article
Multidisciplinary Sciences
Alan Zigler, Stephanie Straw, Isao Tokuda, Ellen Bronson, Tobias Riede
Summary: The Panamanian golden frog, a critically endangered species, only survives and reproduces in human care. Their vocal behavior and patterns were studied to better understand their behavior and improve breeding efforts. The results showed individual and population specificity in male advertisement calls, as well as circadian and circannual periodicity in vocal activities. The findings have important implications for improving breeding success and care of the Panamanian golden frog.
Article
Neurosciences
Giordano Marcio Gatinho Bonuzzi, Flavio Henrique Bastos, Nicolas Schweighofer, Eric Wade, Carolee Joyce Winstein, Camila Torriani-Pasin
Summary: The study investigated the effects of cardiovascular exercise on implicit motor learning of stroke survivors and neurotypical adults. It found that there was no benefit to motor learning from moderate-intensity exercise, and exercise performed before practice impaired encoding in adults and attenuated retention performance in stroke survivors.
EXPERIMENTAL BRAIN RESEARCH
(2023)
Article
Physics, Fluids & Plasmas
Kota Shiozawa, Taisuke Uemura, Isao T. Tokuda
Summary: A method is proposed to detect the dynamical instability of complex time series by studying the evolution of the partitioned entropy of an initially localized region of the attractor. The growth rate of the partitioned entropy is found to correspond to the first Lyapunov exponent. A criterion is introduced to distinguish chaos from limit cycles or tori to avoid spurious detection. Numerical experiments and analysis of experimental data demonstrate the effectiveness and robustness of the method.
Article
Acoustics
Mayuka Kanaya, Takuma Matsumoto, Taisuke Uemura, Rei Kawabata, Takeshi Nishimura, Isao T. Tokuda
Summary: The vocal membrane, an extended part of the vocal fold, has been observed in various species and is predicted to enhance efficiency of vocalizations by lowering the phonation threshold pressure. A synthetic model of the vocal membrane was developed and experiments showed that it indeed lowered the phonation threshold pressure and resulted in chaotic oscillations.
JASA EXPRESS LETTERS
(2022)
Article
Mathematics, Interdisciplinary Applications
Kota Shiozawa, Takaya Miyano, Isao T. Tokuda
Summary: This paper introduces a modified version of the Kuramoto model as a new method for data synchronization, which can solve clustering problems by setting the natural frequencies of the oscillators. The proposed method outperforms existing data-clustering algorithms in handling datasets with non-convex shaped clusters, as demonstrated through three case studies.
IEICE NONLINEAR THEORY AND ITS APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.