Article
Computer Science, Artificial Intelligence
Lihao Liu, Angelica I. Aviles-Rivero, Carola-Bibiane Schonlieb
Summary: Medical image segmentation is a crucial task in medical imaging, and this paper presents a novel unsupervised segmentation technique called CLMorph. By combining registration and contrastive learning, the proposed technique achieves improved accuracy in image segmentation.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Jiaofen Nan, Junya Su, Jincan Zhang
Summary: This paper proposes a technique of human brain image registration based on tissue morphology in vivo, which aims to address the problems of previous image registration. Different feature points, including those at the boundary of different brain tissues and those of the maximum or minimum from the original image, are extracted and combined. The correct matching pairs of feature points are used to generate the model parameters of spatial transformation, and the brain image registration is completed by combining interpolation techniques. The proposed method outperforms other algorithms in terms of quantitative indicators and spatial location, size, appearance contour, and registration details.
Editorial Material
Multidisciplinary Sciences
Esther Landhuis
Summary: After years of development, researchers have successfully miniaturized two-photon microscopy technology into a device that can be attached to rodents' heads without interfering with their behavior.
Review
Physiology
Kenneth W. Dunn
Summary: Over the past 30 years, the scale and complexity of images collected in biological microscopy have grown enormously. The development of multiphoton microscopy and new methods of optical sectioning and tissue clearing have provided biologists with the ability to characterize entire organs at subcellular resolution. The Indiana O'Brien Center has been developing robust and accessible image analysis tools for biomedical researchers to utilize these advanced imaging techniques.
FRONTIERS IN PHYSIOLOGY
(2021)
Article
Computer Science, Information Systems
Anusha Achuthan, Mandava Rajeswari
Summary: Segmentation of subcortical structures like the hippocampus in brain MR images is challenging due to weak or unclear boundary definitions, especially at the head and tail. An automated segmentation approach showed promising results with an average Dice Similarity Coefficient of 0.8050 on public datasets, comparable to other state-of-the-art approaches.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2021)
Article
Chemistry, Multidisciplinary
Eric Schwenker, Venkata Surya Chaitanya Kolluru, Jinglong Guo, Rui Zhang, Xiaobing Hu, Qiucheng Li, Joshua T. Paul, Mark C. Hersam, Vinayak P. Dravid, Robert Klie, Jeffrey R. Guest, Maria K. Y. Chan
Summary: This paper introduces an open-source automation framework called ingrained, which solves the correspondence between simulation and experimental images and fuses atomic resolution image simulations into the corresponding experimental images.
Article
Optics
Mengnan Liu, Yu Han, Xiaoqi Xi, Linlin Zhu, Huijuan Fu, Siyu Tan, Xiangzhi Zhang, Lei Li, Jian Chen, Bin Yan
Summary: Nanocomputed tomography is an effective tool for observing 3D structures of nanomaterials, but it requires correction phantom to reduce artifacts. This study proposes a rough-to-refined correction framework based on global mixed evaluation for precise drift estimation.
Article
Engineering, Biomedical
Jianan Wei, Huawei Cai, Yong Pi, Zhen Zhao, Zhang Yi
Summary: The paper presents an automatic fine-grained skeleton segmentation method for whole-body bone scintigraphy, outperforming traditional registration methods with improved accuracy and performance, which could be beneficial in clinical applications.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2022)
Article
Biotechnology & Applied Microbiology
Noah F. Greenwald, Geneva Miller, Erick Moen, Alex Kong, Adam Kagel, Thomas Dougherty, Christine Camacho Fullaway, Brianna J. McIntosh, Ke Xuan Leow, Morgan Sarah Schwartz, Cole Pavelchek, Sunny Cui, Isabella Camplisson, Omer Bar-Tal, Jaiveer Singh, Mara Fong, Gautam Chaudhry, Zion Abraham, Jackson Moseley, Shiri Warshawsky, Erin Soon, Shirley Greenbaum, Tyler Risom, Travis Hollmann, Sean C. Bendall, Leeat Keren, William Graf, Michael Angelo, David Van Valen
Summary: In this study, the researchers created the TissueNet dataset and developed the Mesmer segmentation algorithm based on deep learning to address the challenge of cell segmentation. Mesmer showed improved accuracy, generalization to various tissue types and imaging platforms, and achieved human-level performance.
NATURE BIOTECHNOLOGY
(2022)
Article
Biochemical Research Methods
Fei Xu, Lingli Lin, Zihan Li, Qingqi Hong, Kunhong Liu, Qingqiang Wu, Qingde Li, Yinhuan Zheng, Jie Tian
Summary: This paper proposes an improved Deep Forest framework (MRDFF) for automatic whole heart segmentation. The framework consists of two stages, where the first stage extracts the heart region through binary classification and the second stage subdivides the results to obtain accurate cardiac substructures. Additionally, methods such as feature fusion, multi-resolution fusion, and multi-scale fusion are proposed to further improve segmentation accuracy.
Article
Engineering, Biomedical
Xiao Liang, Howard Morgan, Ti Bai, Michael Dohopolski, Dan Nguyen, Steve Jiang
Summary: CBCT-based online adaptive radiotherapy requires accurate auto-segmentation, but DL-based direct segmentation of CBCT images is challenging due to poor quality and lack of well-labelled datasets. This study proposes a method using DIR and pseudo labels derived from deformed pCT contours for initial training, influencer volumes for defining the region of interest, and fine-tuning with a smaller set of true labels. Evaluation on nine patients shows that DL-based direct segmentation with influencer volumes improves performance to reach the level of DIR-based segmentation.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
Article
Environmental Sciences
Yong Feng, Ka Lun Leung, Yingkui Li, Kwai Lam Wong
Summary: This article introduces an AI-based workflow for the registration of large point cloud data. By detecting stable objects from photos and registering only the point cloud data of these objects, the accuracy and computational speed of the registration process are improved.
Article
Biochemical Research Methods
L. Silvestri, M. C. Mullenbroich, I. Costantini, A. P. Di Giovanna, G. Mazzamuto, A. Franceschini, D. Kutra, A. Kreshuk, C. Checcucci, L. O. Toresano, P. Frasconi, L. Sacconi, F. S. Pavone
Summary: RAPID is a real-time autofocus method for widefield microscopy that removes image degradation in large, cleared samples for enhanced quantitative analyses. It enables high-resolution imaging of macroscopic biological samples and allows for 3D spatial clustering analysis of neurons and morphological analysis of microglia. Beyond light-sheet microscopy, RAPID also maintains high image quality in various settings, making it suitable for traditional automated microscopy tasks and quantitative analysis of large biological specimens.
Article
Computer Science, Interdisciplinary Applications
Dongming Wei, Sahar Ahmad, Yuyu Guo, Liyun Chen, Yunzhi Huang, Lei Ma, Zhengwang Wu, Gang Li, Li Wang, Weili Lin, Pew-Thian Yap, Dinggang Shen, Qian Wang
Summary: In this paper, a recurrently usable deep neural network is proposed for the registration of infant brain MR images. By using brain tissue segmentation maps for registration and training a single registration network that is recurrently applied in inference, the proposed method overcomes the challenge of fast brain development in infants. Experimental results show that the method achieves the highest registration accuracy while preserving the smoothness of the deformation field.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Lin Ma, Weicheng Chi, Howard E. Morgan, Mu-Han Lin, Mingli Chen, David Sher, Dominic Moon, Dat T. Vo, Vladimir Avkshtol, Weiguo Lu, Xuejun Gu
Summary: In this study, a registration-guided DL segmentation framework for online cone beam computed tomography (CBCT) image was proposed. By integrating image registration algorithms and DL segmentation models, this framework overcame the issues of low image quality and limited training data, resulting in more accurate segmentation.
Article
Pharmacology & Pharmacy
Adam L. Tyson, Stephen T. Hilton, Laura C. Andreae
INTERNATIONAL JOURNAL OF PHARMACEUTICS
(2015)
Article
Genetics & Heredity
Eleftheria Pervolaraki, Adam L. Tyson, Francesca Pibiri, Steven L. Poulter, Amy C. Reichelt, R. John Rodgers, Steven J. Clapcote, Colin Lever, Laura C. Andreae, James Dachtler
Article
Multidisciplinary Sciences
Adam L. Tyson, Ayesha M. Akhtar, Laura C. Andreae
SCIENTIFIC REPORTS
(2019)
Article
Cell Biology
Mark Jackman, Chiara Marcozzi, Martina Barbiero, Mercedes Pardo, Lu Yu, Adam L. Tyson, Jyoti S. Choudhary, Jonathon Pines
JOURNAL OF CELL BIOLOGY
(2020)
Article
Biochemistry & Molecular Biology
Nikos Koundouros, Evdoxia Karali, Aurelien Tripp, Adamo Valle, Paolo Inglese, Nicholas J. S. Perry, David J. Magee, Sara Anjomani Virmouni, George A. Elder, Adam L. Tyson, Maria Luisa Doria, Antoinette van Weverwijk, Renata F. Soares, Clare M. Isacke, Jeremy K. Nicholson, Robert C. Glen, Zoltan Takats, George Poulogiannis
Article
Neurosciences
Sepiedeh Keshavarzi, Edward F. Bracey, Richard A. Faville, Dario Campagner, Adam L. Tyson, Stephen C. Lenzi, Tiago Branco, Troy W. Margrie
Summary: Animals rely on continuously tracking their heading direction and speed to navigate their environment. This study found that vestibular inputs dominate the coding of angular head velocity in the cortical region called retrosplenial cortex (RSP) in mice. Additionally, the integration of visual inputs onto these neurons enhances their tuning during active exploration, resulting in increased perceptual accuracy of angular self-motion and fidelity of its representation by RSP ensembles.