Article
Computer Science, Artificial Intelligence
Mohamad Dhaini, Maxime Berar, Paul Honeine, Antonin Van Exem
Summary: This paper studies the problem of unsupervised domain adaptation for regression tasks and proposes a new approach based on dictionary learning. Experimental results show that the proposed method outperforms most of state-of-the-art methods on several benchmark datasets, especially when transferring knowledge from synthetic to real domains.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Abtin Riasatian, Morteza Babaie, Danial Maleki, Shivam Kalra, Mojtaba Valipour, Sobhan Hemati, Manit Zaveri, Amir Safarpoor, Sobhan Shafiei, Mehdi Afshari, Maral Rasoolijaberi, Milad Sikaroudi, Mohd Adnan, Sultaan Shah, Charles Choi, Savvas Damaskinos, Clinton Jv Campbell, Phedias Diamandis, Liron Pantanowitz, Hany Kashani, Ali Ghodsi, H. R. Tizhoosh
Summary: Pre-trained deep artificial neural networks are a dominant source for image representation and their performance in image analysis can be improved through fine-tuning. This study introduces a new network, KimiaNet, which outperforms the original DenseNet and other networks in representing histopathology images. By utilizing a large dataset and training with different configurations, KimiaNet shows superior results in image analysis.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Interdisciplinary Applications
Shidan Wang, Ruichen Rong, Zifan Gu, Junya Fujimoto, Xiaowei Zhan, Yang Xie, Guanghua Xiao
Summary: This study proposes an Instance Segmentation CycleGAN (ISC-GAN) algorithm for unsupervised domain adaptation in multiclass-instance segmentation. By combining with Mask R-CNN, it learns categorical correspondence between source and target domains through image-level domain adaptation and virtual supervision. Experiments show that ISC-GAN achieves state-of-the-art performance in instance segmentation tasks.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Medicine, General & Internal
Matthew Brendel, Vanesa Getseva, Majd Al Assaad, Michael Sigouros, Alexandros Sigaras, Troy Kane, Pegah Khosravi, Juan Miguel Mosquera, Olivier Elemento, Iman Hajirasouliha
Summary: In this study, a weakly-supervised purity (wsPurity) approach was proposed to accurately quantify tumor purity within a digitally captured histological slide. The model demonstrated high accuracy in predicting cancer type and showed promising generalizability to unseen data from an external cohort. The approach also identified high resolution tumor regions within a slide and could stratify tumors into high and low purity.
Article
Computer Science, Artificial Intelligence
Quoc Dang Vu, Kashif Rajpoot, Shan E. Ahmed Raza, Nasir Rajpoot
Summary: Diagnostic, prognostic and therapeutic decision-making of cancer in pathology clinics can now be carried out based on analysis of multi-gigapixel tissue images, also known as whole-slide images (WSIs). Deep convolutional neural networks (CNNs) have been proposed to derive unsupervised WSI representations, but a major trade-off is the lack of interpretability. To address this, a handcrafted framework called Handcrafted Histological Transformer (H2T) is presented, which offers competitive performance and is faster than Transformer models.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Artificial Intelligence
Viviane Clay, Peter Koenig, Kai-Uwe Kuehnberger, Gordon Pipa
Summary: This study investigates how humans acquire meaningful understanding of the world with little supervision or semantic labels provided by the environment, emphasizing embodiment as a key component in the process. By training a deep reinforcement learning agent with high-dimensional visual observations in a 3D environment, the study shows the agent can learn stable representations of meaningful concepts without receiving any semantic labels. The results demonstrate the agent's ability to represent action-relevant information in a wide variety of sparse activation patterns extracted from a simulated camera stream, highlighting the strength of embodied learning over fully supervised approaches.
Article
Biology
Anna Metzger, Matteo Toscani
Summary: When touching an object, its spatial structure is translated into vibrations on the skin, allowing the perceptual system to distinguish between different materials. The study demonstrates that a deep neural network trained with unsupervised learning can classify materials based on the vibratory patterns elicited by human exploration. The compressed representation shows similarities to perceptual distances, indicating a similar coding mechanism.
Article
Geochemistry & Geophysics
Behnood Rasti, Bikram Koirala
Summary: The proposed sparse unmixing technique using a convolutional neural network (SUnCNN) for hyperspectral images introduces a new deep learning-based approach that outperforms existing methods in terms of signal to reconstruction error (SRE) and visual presentation on both real and synthetic datasets.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Jinyu Cai, Shiping Wang, Wenzhong Guo
Summary: The paper proposes a deep stacked sparse embedded clustering method that considers both local structure preservation and input sparsity. The deep learning approach jointly learns clustering-oriented features and optimizes cluster label assignments by minimizing both the reconstruction and clustering loss. Comprehensive experiments validate the effectiveness of introducing sparsity and preserving local structure in the proposed method.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Wanxia Deng, Qing Liao, Lingjun Zhao, Deke Guo, Gangyao Kuang, Dewen Hu, Li Liu
Summary: The Joint Clustering and Discriminative Feature Alignment (JCDFA) approach proposed in this paper aims to simultaneously mine discriminative features of target data and align cross-domain discriminative features to enhance performance in Unsupervised Domain Adaptation (UDA). The method integrates supervised classification of labeled source data and discriminative clustering of unlabeled target data, as well as optimizing supervised contrastive learning and conditional Maximum Mean Discrepancy (MMD) for feature alignment. Experimental results on real-world benchmarks demonstrate the superiority of JCDFA over state-of-the-art domain adaptation methods.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Biology
Chenyi Zeng, Shen Zhao, Bin Chen, An Zeng, Shuo Li
Summary: Automatic recognition of vertebrae from MRI is important for disease diagnosis and surgical treatment of spinal patients. This paper proposes a framework called FORCE that extracts discriminative features and addresses the challenges of vertebra appearance and field of view variability. FORCE achieves high performance in vertebra recognition and outperforms other state-of-the-art methods.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Oncology
Deepak Anand, Kumar Yashashwi, Neeraj Kumar, Swapnil Rane, Peter H. Gann, Amit Sethi
Summary: The study utilized weakly supervised learning to train a DNN model for predicting a specific mutational status without requiring regional annotations, achieving high predictive accuracy. A visualization technique was also developed to accurately highlight the most informative regions, moving towards explainable artificial intelligence.
JOURNAL OF PATHOLOGY
(2021)
Review
Gastroenterology & Hepatology
Sung Hak Lee, Hyun-Jong Jang
Summary: Deep learning (DL) can predict molecular test results and treatment response from tissue slides. Although performance needs improvement, these studies demonstrate the feasibility of DL-based prediction of key molecular features in cancer tissues.
CLINICAL AND MOLECULAR HEPATOLOGY
(2022)
Article
Engineering, Biomedical
Feng-Ping An, Xing-min Ma, Lei Bai
Summary: This paper proposed an end-to-end unsupervised deep learning model for image fusion, which addresses the issues of supervised learning, image fusion weight map setting and noise. An optimized sparse representation method was also introduced to further improve the quality of the fusion results. The experiments demonstrated that the proposed method outperformed mainstream machine learning and deep learning image fusion methods in terms of quality evaluation.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Review
Urology & Nephrology
Frederik Wessels, Sara Kuntz, Eva Krieghoff-Henning, Max Schmitt, Volker Braun, Thomas S. Worst, Manuel Neuberger, Matthias Steeg, Timo Gaiser, Stefan Frohling, Maurice-Stephan Michel, Philipp Nuhn, Titus J. Brinker
Summary: Artificial intelligence (AI) has shown promise in automatic tumor detection and grading in histopathological image analysis in urologic oncology. This review aimed to assess the applicability of these approaches in image-based oncological outcome prediction. The included studies demonstrate the potential of AI approaches, but further well-designed studies are needed to evaluate their clinical applicability.
MINERVA UROLOGY AND NEPHROLOGY
(2022)
Article
Cell Biology
Boris Julg, Po-Ting Liu, Kshitij Wagh, William M. Fischer, Peter Abbink, Noe B. Mercado, James B. Whitney, Joseph P. Nkolola, Katherine McMahan, Lawrence J. Tartaglia, Erica N. Borducchi, Shreeya Khatiwada, Megha Kamath, Jake A. LeSuer, Michael S. Seaman, Stephen D. Schmidt, John R. Mascola, Dennis R. Burton, Bette T. Korber, Dan H. Barouch
SCIENCE TRANSLATIONAL MEDICINE
(2017)
Article
Microbiology
Gustavo H. Kijak, Eric Sanders-Buell, Agnes-Laurence Chenine, Michael A. Eller, Nilu Goonetilleke, Rasmi Thomas, Sivan Leviyang, Elizabeth A. Harbolick, Meera Bose, Phuc Pham, Celina Oropeza, Kultida Poltavee, Anne Marie O'Sullivan, Erik Billings, Melanie Merbah, Margaret C. Costanzo, Joanna A. Warren, Bonnie Slike, Hui Li, Kristina K. Peachman, Will Fischer, Feng Gao, Claudia Cicala, James Arthos, Leigh A. Eller, Robert J. O'Connell, Samuel Sinei, Lucas Maganga, Hannah Kibuuka, Sorachai Nitayaphan, Mangala Rao, Mary A. Marovich, Shelly J. Krebs, Morgane Rolland, Bette T. Korber, George M. Shaw, Nelson L. Michael, Merlin L. Robb, Sodsai Tovanabutra, Jerome H. Kim
Article
Chemistry, Multidisciplinary
Jaewoon Jung, Wataru Nishima, Marcus Daniels, Gavin Bascom, Chigusa Kobayashi, Adetokunbo Adedoyin, Michael Wall, Anna Lappala, Dominic Phillips, William Fischer, Chang-Shung Tung, Tamar Schlick, Yuji Sugita, Karissa Y. Sanbonmatsu
JOURNAL OF COMPUTATIONAL CHEMISTRY
(2019)
Article
Biotechnology & Applied Microbiology
Bette Korber, Will Fischer
HUMAN VACCINES & IMMUNOTHERAPEUTICS
(2020)
Article
Biochemistry & Molecular Biology
Bette Korber, Will M. Fischer, Sandrasegaram Gnanakaran, Hyejin Yoon, James Theiler, Werner Abfalterer, Nick Hengartner, Elena E. Giorgi, Tanmoy Bhattacharya, Brian Foley, Kathryn M. Hastie, Matthew D. Parker, David G. Partridge, Cariad M. Evans, Timothy M. Freeman, Thushan de Silva, Charlene McDanal, Lautaro G. Perez, Haili Tang, Alex Moon-Walker, Sean P. Whelan, Celia C. LaBranche, Erica O. Saphire, David C. Montefiori
Review
Immunology
Zachary R. Stromberg, Will Fischer, Steven B. Bradfute, Jessica Z. Kubicek-Sutherland, Peter Hraber
Review
Microbiology
Will Fischer, Elena E. Giorgi, Srirupa Chakraborty, Kien Nguyen, Tanmoy Bhattacharya, James Theiler, Pablo A. Goloboff, Hyejin Yoon, Werner Abfalterer, Brian T. Foley, Houriiyah Tegally, James Emmanuel San, Tulio de Oliveira, Sandrasegaram Gnanakaran, Bette Korber
Summary: Humanity is currently facing two devastating pandemics caused by two very different RNA viruses: HIV-1 and SARS-CoV-2. The evolution of both viruses is driven by the same evolutionary strategies, such as single nucleotide mutations, multi-base insertions and deletions, recombination, and surface glycan variation. Despite limited diversity in SARS-CoV-2, recent variants still carry Spike mutations that impact antibody resistance and infectivity.
CELL HOST & MICROBE
(2021)
Article
Multidisciplinary Sciences
Ryuta Uraki, Shun Iida, Peter J. Halfmann, Seiya Yamayoshi, Yuichiro Hirata, Kiyoko Iwatsuki-Horimoto, Maki Kiso, Mutsumi Ito, Yuri Furusawa, Hiroshi Ueki, Yuko Sakai-Tagawa, Makoto Kuroda, Tadashi Maemura, Taksoo Kim, Sohtaro Mine, Noriko Iwamoto, Rong Li, Yanan Liu, Deanna Larson, Shuetsu Fukushi, Shinji Watanabe, Ken Maeda, Zhongde Wang, Norio Ohmagari, James Theiler, Will Fischer, Bette Korber, Masaki Imai, Tadaki Suzuki, Yoshihiro Kawaoka
Summary: The Omicron subvariant BA.2.75 rapidly spread globally in India and Nepal during the summer of 2022. However, its virological features were largely unknown. In this study, BA.2.75 clinical isolates were evaluated in Syrian hamsters, and it was found that BA.2.75 had higher replicative ability in the lungs compared to BA.2 and BA.5. BA.2.75 also caused focal viral pneumonia in hamsters, unlike BA.5. These findings suggest that BA.2.75 may cause more severe respiratory disease and should be closely monitored.
NATURE COMMUNICATIONS
(2023)
Article
Medicine, General & Internal
Lauren J. Beesley, Kelly R. Moran, Kshitij Wagh, Lauren A. Castro, James Theiler, Hyejin Yoon, Will Fischer, Nick W. Hengartner, Bette Korber, Sara Y. Del Valle
Summary: This paper retrospectively analyzes longitudinal sequencing data to characterize differences in the speed, calendar timing, and magnitude of 16 SARS-CoV-2 variant waves/transitions for 230 countries and sub-country regions. It also identifies groups of locations exhibiting similar variant transitions through clustering. The study finds associations between the behavior of an emerging variant and the number of co-circulating variants, as well as the demographic context of the population.
Article
Immunology
Sam Turner, Arghavan Alisoltani, Debbie Bratt, Liel Cohen-Lavi, Bethany L. Dearlove, Christian Drosten, Will M. Fischer, Ron A. M. Fouchier, Ana Silvia Gonzalez-Reiche, Lukasz Jaroszewski, Zain Khalil, Eric LeGresley, Marc Johnson, Terry C. Jones, Barbara Muehlemann, David O'Connor, Mayya Sedova, Maulik Shukla, James Theiler, Zachary S. Wallace, Hyejin Yoon, Yun Zhang, Harm van Bakel, Marciela M. Degrace, Elodie Ghedin, Adam Godzik, Tomer Hertz, Bette Korber, Jacob Lemieux, Anna M. Niewiadomska, Diane J. Post, Morgane Rolland, Richard Scheuermann, Derek J. Smith
Summary: Since late 2020, SARS-CoV-2 variants with competitive and phenotypic differences have been regularly emerging, sometimes having the potential to escape immunity. The Early Detection group of the US National Institutes of Health uses bioinformatics to monitor and prioritize the most relevant variants for experimental characterization. Their success includes identifying major variants and providing updated information for phenotypic investigations.
EMERGING INFECTIOUS DISEASES
(2023)
Article
Medicine, Research & Experimental
Kristen W. Cohen, Andrew Fiore-Gartland, Stephen R. Walsh, Karina Yusim, Nicole Frahm, Marnie L. Elizaga, Janine Maenza, Hyman Scott, Kenneth H. Mayer, Paul A. Goepfert, Srilatha Edupuganti, Giuseppe Pantaleo, Julia Hutter, Daryl E. Morris, Stephen C. De Rosa, Daniel E. Geraghty, Merlin L. Robb, Nelson L. Michael, Will Fischer, Elena E. Giorgi, Harman Malhi, Michael N. Pensiero, Guido Ferrari, Georgia D. Tomaras, David C. Montefiori, Peter B. Gilbert, M. Juliana McElrath, Barton F. Haynes, Bette T. Korber, Lindsey R. Baden
Summary: This study found that vaccination with mosaic immunogens could induce more specific T cell responses and increase recognition of heterologous variants, suggesting that mosaic and consensus immunogens are promising approaches to address the global diversity of HIV-1.
JOURNAL OF CLINICAL INVESTIGATION
(2023)
Article
Medicine, Research & Experimental
Suzanne L. Campion, Elena Brenna, Elaine Thomson, Will Fischer, Kristin Ladell, James E. McLaren, David A. Price, Nicole Frahm, Juliana M. McElrath, Kristen W. Cohen, Janine R. Maenza, Stephen R. Walsh, Lindsey R. Baden, Barton F. Haynes, Bette Korber, Persephone Borrow, Andrew J. McMichael
Summary: A study found that preexisting memory CD4(+) T cells could shape the early immune response to vaccination with a previously unencountered HIV-1 antigen in HIV-1-seronegative volunteers who received an HIV-1 vaccine.
JOURNAL OF CLINICAL INVESTIGATION
(2021)
Meeting Abstract
Immunology
Kathryn Foulds, Will Fischer, Mitzi Donaldson, Shing-Fen Kao, Amy Ransier, Jianfei Hu, Brandon Keele, Daniel Douek, Mario Roederer
AIDS RESEARCH AND HUMAN RETROVIRUSES
(2018)
Article
Biochemistry & Molecular Biology
Anna Lappala, Wataru Nishima, Jacob Miner, Paul Fenimore, Will Fischer, Peter Hraber, Ming Zhang, Benjamin McMahon, Chang-Shung Tung