Article
Biology
Lei Su, Yu Liu, Minghui Wang, Ao Li
Summary: This study proposes a novel semi-supervised deep learning method called Semi-HIC for histopathological image classification. By introducing a new semi-supervised loss function and employing an efficient network architecture, the method effectively addresses the challenges of inter-class similarity and intra-class variation in histopathological images, leading to significantly improved classification performance.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Biology
Wenxue Li, Wei Lu, Jinghui Chu, Qi Tian, Fugui Fan
Summary: In this paper, a novel Confidence-Guided Mask Learning (CGML) method is proposed for semi-supervised medical image segmentation. The method introduces an auxiliary generation task with mask learning and a confidence-guided masking strategy to improve segmentation accuracy and feature representation reliability.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Krishna Chaitanya, Ertunc Erdil, Neerav Karani, Ender Konukoglu
Summary: Supervised deep learning methods require large labeled datasets for accurate medical image segmentation. This paper proposes a local contrastive loss-based approach that utilizes pseudo-labels of unlabeled images and limited annotated images to learn pixel-level features for segmentation. Experimental results on three public medical datasets demonstrate the substantial improvement achieved by the proposed method.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Artificial Intelligence
Krishna Chaitanya, Neerav Karani, Christian F. Baumgartner, Ertunc Erdil, Anton Becker, Olivio Donati, Ender Konukoglu
Summary: Supervised learning-based segmentation methods typically require a large number of annotated training data, which is challenging in medical applications. This work presents a novel task-driven data augmentation method that significantly outperforms other approaches in limited annotation settings.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Anneke Meyer, Suhita Ghosh, Daniel Schindele, Martin Schostak, Sebastian Stober, Christian Hansen, Marko Rak
Summary: The study introduces a semi-supervised learning technique named uncertainty-aware temporal self-learning (UATS) for fine-grained segmentation of the prostate, which significantly outperforms the supervised baseline in segmentation quality, especially for minimal amounts of labeled data.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Yu Hua, Xin Shu, Zizhou Wang, Lei Zhang
Summary: This paper proposes a semi-supervised method that narrows the gap between semi-supervised and fully supervised models by utilizing unlabeled data and establishing contrastive relationships between feature representation vectors through supervised contrastive learning. It overcomes data misuse and underutilization in semi-supervised frameworks, enhancing performance.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Xuanang Xu, Thomas Sanford, Baris Turkbey, Sheng Xu, Bradford J. Wood, Pingkun Yan
Summary: This paper proposes a method for prostate segmentation in transrectal ultrasound images using two novel mechanisms (Shadow-AUG and Shadow-DROP) to address the challenges of low image quality and shadow artifacts. Experimental results show that the method achieves good performance in both fully-supervised and semi-supervised settings, indicating its importance in clinical applications.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Computer Science, Artificial Intelligence
Feng Gao, Minhao Hu, Min-Er Zhong, Shixiang Feng, Xuwei Tian, Xiaochun Meng, Ma-yi-di-li Ni-jia-ti, Zeping Huang, Minyi Lv, Tao Song, Xiaofan Zhang, Xiaoguang Zou, Xiaojian Wu
Summary: This paper proposes a novel weakly- and semi-supervised framework named SOUSA, which aims to learn from a small set of sparse annotated data and a large amount of unlabeled data. Extensive experiments demonstrate the robustness and generalization ability of the proposed method on multiple datasets.
MEDICAL IMAGE ANALYSIS
(2022)
Article
Chemistry, Analytical
Bee-ing Sae-ang, Wuttipong Kumwilaisak, Pakorn Kaewtrakulpong
Summary: The study proposed a semi-supervised approach that utilized both unlabeled and labeled samples to automatically segment out defect regions through network training. Experimental results showed a 3.83% overall improvement with the help of a handful of ground-truth segmentation maps.
Article
Biology
Yongqiang Tang, Shilei Wang, Yuxun Qu, Zhihua Cui, Wensheng Zhang
Summary: This paper proposes a novel semi-supervised medical image segmentation method, which improves the existing methods' heavy reliance on a large amount of labeled data by introducing the adversarial training mechanism and collaborative consistency learning strategy. Experimental results demonstrate the superiority and effectiveness of our method in three representative medical image segmentation tasks.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Information Systems
Jiangbo Shi, Tieliang Gong, Chunbao Wang, Chen Li
Summary: Accurate tissue segmentation in histopathological images is crucial for advancing precision pathology. We propose a semi-supervised pixel contrastive learning framework (SSPCL) to mimic the pathologist's diagnosis process and model the semantic relation of the whole slide image. SSPCL includes an uncertainty-guided mutual dual consistency learning module (UMDC) and a cross image pixel-contrastive learning module (CIPC). Experimental results show that SSPCL significantly reduces labeling cost and achieves accurate quantitation of tissues, outperforming state-of-the-art methods by up to 5.0% in mDice.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Zhiyong Xiao, Yixin Su, Zhaohong Deng, Weidong Zhang
Summary: This study enhances the segmentation of MR images using a semi-supervised learning method with a dual-teacher structure, utilizing a small amount of labeled data and a large amount of unlabeled data. The method significantly improves the segmentation results of MR images with high accuracy.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Mathematics
Giovanna Maria Dimitri, Paolo Andreini, Simone Bonechi, Monica Bianchini, Alessandro Mecocci, Franco Scarselli, Alberto Zacchi, Guido Garosi, Thomas Marcuzzo, Sergio Antonio Tripodi
Summary: Deep learning techniques are applied in bioinformatics and biomedical imaging for the automatic identification and segmentation of glomeruli in kidney tissues. The results show promising performance in the segmentation task and the proposed use of the CD10 staining procedure for sclerotic glomeruli segmentation is effective.
Article
Computer Science, Artificial Intelligence
Massimo Salvi, Martino Bosco, Luca Molinaro, Alessandro Gambella, Mauro Papotti, U. Rajendra Acharya, Filippo Molinari
Summary: The RINGS algorithm presented a new image segmentation method for prostate gland segmentation, achieving a high dice score of 90.16% and outperforming other state-of-the-art techniques. The hybrid segmentation strategy based on stroma detection maintained high sensitivity even in the presence of severe glandular degeneration, making it a valuable tool for accurate diagnosis and treatment in prostate cancer detection.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Xiangli Yang, Zixing Song, Irwin King, Zenglin Xu
Summary: This paper provides a comprehensive survey on deep semi-supervised learning methods, including model design and unsupervised loss functions. It categorizes existing methods into different types and reviews 60 representative methods with a detailed comparison. The paper also discusses the shortcomings of existing methods and proposes heuristic solutions.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Yiwu Yan, Bo Zhou, Chen Qian, Alex Vasquez, Mohini Kamra, Avradip Chatterjee, Yeon-Joo Lee, Xiaopu Yuan, Leigh Ellis, Dolores Di Vizio, Edwin M. Posadas, Natasha Kyprianou, Beatrice S. Knudsen, Kavita Shah, Ramachandran Murali, Arkadiusz Gertych, Sungyong You, Michael R. Freeman, Wei Yang
Summary: RIPK2 is identified as a potential therapeutic target for inhibiting prostate cancer metastasis. It is amplified/gained in about 65% of lethal metastatic castration-resistant prostate cancer cases. RIPK2 regulates the stability and activity of c-Myc by activating MKK7, and inhibiting RIPK2 signaling effectively impairs prostate cancer metastasis.
NATURE COMMUNICATIONS
(2022)
Article
Biochemical Research Methods
Mariusz Marzec, Adam Piorkowski, Arkadiusz Gertych
Summary: In this study, a new algorithm was developed to accurately segment cell nuclei in 3D images and achieved the best results in fluorescence image evaluation.
BMC BIOINFORMATICS
(2022)
Article
Oncology
Jingni Wu, Yael Raz, Maria Sol Recouvreux, Marcio Augusto Diniz, Jenny Lester, Beth Y. Karlan, Ann E. Walts, Arkadiusz Gertych, Sandra Orsulic
Summary: This study aimed to investigate the global visual and subvisual microenvironmental differences between fallopian tubes with and without STIC lesions. The results showed differences in stromal and epithelial cells, and also a correlation between age and cell type changes.
FRONTIERS IN ONCOLOGY
(2022)
Article
Orthopedics
Angela Papalamprou, Victoria Yu, Angel Chen, Tina Stefanovic, Giselle Kaneda, Khosrowdad Salehi, Chloe M. Castaneda, Arkadiusz Gertych, Juliane D. Glaeser, Dmitriy Sheyn
Summary: This study aimed to induce tenogenesis using stable Scleraxis (Scx) overexpression in combination with uniaxial mechanical stretch of iPSC-derived mesenchymal stromal-like cells (iMSCs). The results showed that Scx overexpression alone resulted in significantly higher upregulation of tenogenic markers in iMSCs compared to BM-MSCs. Mechanical stimulation combined with Scx overexpression resulted in morphometric and cytoskeleton-related changes, upregulation of early and late tendon markers, increased extracellular matrix deposition and alignment, and tenomodulin perinuclear localization in iMSCs.
JOURNAL OF ORTHOPAEDIC RESEARCH
(2023)
Article
Engineering, Biomedical
Chao Chen, Catalina Raymond, William Speier, Xinyu Jin, Timothy F. Cloughesy, Dieter Enzmann, Benjamin M. Ellingson, Corey W. Arnold
Summary: In this study, a deep learning based approach was proposed for contrast-enhanced T1 synthesis on brain tumor patients. By utilizing a 3D high-resolution fully convolutional network, pre-contrast MRI sequences were mapped to contrast-enhanced MRI sequences, reducing the need for GBCAs. The results suggest the potential of using synthetic contrast images generated via deep learning as a substitute for GBCAs.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Karolina Nurzynska, Dalin Li, Ann E. Walts, Arkadiusz Gertych
Summary: This study developed a multilayer image classification pipeline that improves the accuracy of classifying acid-fast mycobacteria (AFB) in Ziehl-Neelsen-stained slides by acquiring and aggregating images from multiple layers.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Orthopedics
Giselle Kaneda, Julie L. L. Chan, Chloe M. M. Castaneda, Angela Papalamprou, Julia Sheyn, Oksana Shelest, Dave Huang, Nadine Kluser, Victoria Yu, Gian C. C. Ignacio, Arkadiusz Gertych, Ryu Yoshida, Melodie F. F. Metzger, Wafa Tawackoli, Andrea Vernengo, Dmitriy Sheyn
Summary: This study explores a new strategy for tendon defect repair using novel three dimensional (3D) printed scaffolds and induced pluripotent stem cell-derived mesenchymal stem cells (iMSCs) overexpressing the transcription factor Scleraxis (SCX, iMSC(SCX+)). The results show that iMSC(SCX+) seeded on microgrooved scaffolds can promote tendon marker expression and enhance the organization and alignment of cells both in vitro and in vivo. This study demonstrates the potential of 3D-printed scaffolds with cell-instructive surface topography seeded with iMSC(SCX+) as an approach to tendon defect repair.
JOURNAL OF ORTHOPAEDIC RESEARCH
(2023)
Article
Multidisciplinary Sciences
Ricky K. Taira, Anders O. Garlid, William Speier
Summary: This paper describes a framework inspired by mechanisms of human cognition to improve the performance of medical natural language processing (NLP) systems. The framework is centered around a hierarchical semantic compositional model (HSCM) as a guiding substrate for the interpretation process. The insights from four key cognitive aspects are discussed, including semantic memory, semantic composition, semantic activation, and hierarchical predictive coding. The design of a generative semantic model and associated semantic parser is presented, which transforms free-text sentences into logical representations of meaning. Supportive and antagonistic arguments for the key features of the architecture as a long-term foundational framework are discussed.
Article
Health Care Sciences & Services
Kaushal Rao, William Speier, Yiwen Meng, Jinhan Wang, Nidhi Ramesh, Fenglong Xie, Yujie Su, W. Benjamin Nowell, Jeffrey R. Curtis, Corey Arnold
Summary: This study developed machine learning models to classify and predict patient-reported outcome (PRO) scores using Fitbit data from patients with rheumatoid arthritis. The results showed that physical activity tracker data can be used to classify health status and enable scheduled clinical interventions for patients.
JMIR FORMATIVE RESEARCH
(2023)
Meeting Abstract
Biotechnology & Applied Microbiology
Giselle Kaneda, Julie Chan, Chloe Castaneda, Angela Papalamprou, Julia Sheyn, Oksana Shelest, Dave Huang, Nadine Kluser, Victoria Yu, Gian Ignacio, Arkadiusz Gertych, Ryu Yoshida, Melodie Metzger, Wafa Tawackoli, Andrea Vernengo, Dmitriy Sheyn
Proceedings Paper
Computer Science, Artificial Intelligence
Kaiyang (Victor) Cheng, Han Jie (Shawn) Liu, Brianna Sun, Selina Wu, William Speier
Summary: This paper presents a domain-knowledge end-to-end pipeline for automating the 3D localization of ECoG electrodes. By utilizing preoperative CT volumes, fluoroscopy images, and brain volume masks, the proposed method achieves a high level of localization accuracy, enabling the potential for real-time localization of ECoG electrodes in future work.
2022 IEEE INTERNATIONAL CONFERENCE ON METROLOGY FOR EXTENDED REALITY, ARTIFICIAL INTELLIGENCE AND NEURAL ENGINEERING (METROXRAINE)
(2022)
Proceedings Paper
Engineering, Biomedical
Patrick Liu, Saarang Panchavati, Mara Pleasure, Nathan Siu, Clemence Bonnet, Sophie Deng, Corey Arnold, William Speier
Summary: This study demonstrates the performance of a deep learning-based pipeline to automatically identify clinically relevant images from IVCM volume scans and classify the severity of LSCD. The classification model achieved high accuracy and good classification performance in testing, showcasing the potential of deep learning in improving diagnostic efficiency and reducing clinician variability.
2022 IEEE 22ND INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOENGINEERING (BIBE 2022)
(2022)
Meeting Abstract
Gastroenterology & Hepatology
Sourabh Tirodkar, Dalin Li, Elena E. Chang, Karolina O. Nurzynska, Dermot P. B. Mcgovern, Arkadiusz Gertych
Meeting Abstract
Medicine, Research & Experimental
Karolina Nurzynska, Ann Walts, Arkadiusz Gertych
LABORATORY INVESTIGATION
(2022)
Meeting Abstract
Pathology
Karolina Nurzynska, Ann Walts, Arkadiusz Gertych