Review
Genetics & Heredity
Khoa A. Tran, Olga Kondrashova, Andrew Bradley, Elizabeth D. Williams, John Pearson, Nicola Waddell
Summary: Deep learning, a subdiscipline of artificial intelligence, is increasingly being applied in healthcare, particularly in cancer research. While promising results have been achieved, there are still many challenges in applying deep learning to oncology, including the need for more explainable deep learning models.
Article
Computer Science, Artificial Intelligence
Kaiwen Tan, Weixian Huang, Xiaofeng Liu, Jinlong Hu, Shoubin Dong
Summary: This study presents a multi-modal fusion framework for survival analysis and cancer grade classification by integrating histopathological images and genomic data. The framework can learn better feature representations and achieve better performance.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2022)
Article
Computer Science, Interdisciplinary Applications
Yibing Fu, Lai Jiang, Sai Pan, Pu Chen, Xiaofei Wang, Ning Dai, Xiangmei Chen, Mai Xu
Summary: In this paper, a new method based on DeepMT-ND for diagnosing nephropathy on blurred immunofluorescence (IF) images is proposed. The diagnosis accuracy and generalization ability of DeepMT-ND are experimentally verified to be effective over both synthetic and real-world databases.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Baiying Lei, Nina Cheng, Alejandro F. Frangi, Yichen Wei, Bihan Yu, Lingyan Liang, Wei Mai, Gaoxiong Duan, Xiucheng Nong, Chong Li, Jiahui Su, Tianfu Wang, Lihua Zhao, Demao Deng, Zhiguo Zhang
Summary: The study introduces an auto weighted centralised multi-task learning framework for differential diagnosis of SCD and MCI. By combining information from neuroimaging functional and structural connectivity, the proposed algorithm improves diagnostic accuracy for early cognitive impairment.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Software Engineering
Sijia Li, Shiguang Liu, Dinesh Manocha
Summary: This learning-based approach generates binaural audio from mono audio by leveraging multi-task learning, extracting spatialization features, predicting left and right audio channels, and judging channel flips based on visual and audio input.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Energy & Fuels
Lei Wang, Yigang He
Summary: In recent years, wind power has become an important source of renewable energy, and accurate multi-location ultra-short-term wind power predictions are crucial for the safe, stable, and economical operation of the power system. The development of artificial intelligence technology provides new approaches for modeling spatiotemporal correlations, and multi-step forecasting is more widely applicable in reality.
Article
Computer Science, Artificial Intelligence
Han Xu, Jiteng Yuan, Jiayi Ma
Summary: This study proposes a novel method called MURF that mutually reinforces image registration and fusion. MURF consists of three modules, which progressively correct global and local offsets during the coarse-to-fine registration process and incorporate texture enhancement into image fusion. Extensive experiments validate the superiority and universality of MURF on different types of multi-modal data.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Multidisciplinary Sciences
Rania M. Ghoniem, Abeer D. Algarni, Basel Refky, Ahmed A. Ewees
Summary: This study introduces a hybrid evolutionary deep learning model using multi-modal data to predict ovarian cancer stages and subtypes more effectively. The model combines gene modality with histopathological image modality, utilizing optimization algorithms in deep feature extraction networks for improved performance.
Article
Engineering, Electrical & Electronic
Dinghao Fan, Hengjie Lu, Shugong Xu, Shan Cao
Summary: This study introduces an end-to-end multi-task learning framework that utilizes depth modality to enhance the accuracy of gesture recognition. Experimental results demonstrate that the proposed method outperforms existing gesture recognition frameworks on three public datasets, and also achieves excellent accuracy improvement when applied to other 2D CNN-based frameworks.
IEEE SENSORS JOURNAL
(2021)
Article
Biochemical Research Methods
Xingze Wang, Guoxian Yu, Jun Wang, Azlan Mohd Zain, Wei Guo
Summary: Diagnosing lung cancer subtypes accurately is crucial for precise treatment. This study introduces an interpretable and flexible solution called LungDWM, which utilizes weakly paired multiomics data to diagnose lung cancer subtypes. By extracting important diagnostic features, imputing missing data, and fusing information from different omics, LungDWM outperforms other competitive methods in terms of performance, authenticity, and interpretability.
Article
Medicine, Research & Experimental
Zihang Zeng, Jiali Li, Jianguo Zhang, Yangyi Li, Xingyu Liu, Jiarui Chen, Zhengrong Huang, Qiuji Wu, Yan Gong, Conghua Xie
Summary: The study developed a novel immune and stromal scoring system named ISTMEscore, which could reflect TME status and predict prognosis. Compared to previous TME scores, ISTMEscore was superior in predicting prognosis and immunotherapy response.
JOURNAL OF TRANSLATIONAL MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Hao Liu, Yongxin Tong, Jindong Han, Panpan Zhang, Xinjiang Lu, Hui Xiong
Summary: This paper proposes a deep learning-based multi-modal transportation recommendation system called Hydra, which considers transportation mode and situational context to provide better user experience and recommendation performance. The experimental results demonstrate significant improvement in user click ratio on Baidu Maps.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Medicine, General & Internal
Siqi Zhang, Xiaohong Liu, Lixin Zhou, Kai Wang, Jun Shao, Jianyu Shi, Xuan Wang, Jiaxing Mu, Tianrun Gao, Zeyu Jiang, Kezhong Chen, Chengdi Wang, Guangyu Wang
Summary: An intelligent prognosis evaluation system (IPES) was developed in this study to assist the traditional TNM staging system for more accurate prognosis prediction of resected NSCLC patients using pre-therapy CT images. The IPES showed promising results in predicting overall survival risk and stratifying NSCLC patients with the same TNM stage or EGFR genotype, potentially offering more personalized treatment and surveillance suggestions.
Article
Multidisciplinary Sciences
Nikhilanand Arya, Sriparna Saha, Archana Mathur, Snehanshu Saha
Summary: Early prognosis and diagnosis systems are crucial for breast cancer patients, providing oncologists with vital information for treatment plans and avoiding unnecessary therapies and their side effects.
SCIENTIFIC REPORTS
(2023)
Article
Biology
Yuan Zou, Lingkai Cai, Chunxiao Chen, Qiang Shao, Xue Fu, Jie Yu, Liang Wang, Zhiying Chen, Xiao Yang, Baorui Yuan, Peikun Liu, Qiang Lu
Summary: A deep learning approach based on T2WI images alone can accurately predict NMIBC and MIBC, providing helpful information for urologists in preoperative decision-making for BCa patients.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Oncology
Sai Huang, Zhi Huang, Ping Chen, Cong Feng
FRONTIERS IN ONCOLOGY
(2020)
Article
Multidisciplinary Sciences
Tong Wang, Yi Wu, Lan Shi, Xinhua Hu, Min Chen, Limin Wu
Summary: The authors present a hierarchically structured polymethyl methacrylate film with a micropore array combined with random nanopores for highly efficient day- and nighttime passive radiative cooling, achieving high solar reflectance and longwave infrared thermal emittance. There is still a challenge in fabricating highly efficient and low-cost radiative coolers for all-day and all-climates.
NATURE COMMUNICATIONS
(2021)
Article
Multidisciplinary Sciences
Travis S. Johnson, Shunian Xiang, Tianhan Dong, Zhi Huang, Michael Cheng, Tianfu Wang, Kai Yang, Dong Ni, Kun Huang, Jie Zhang
Summary: This study analyzed transcriptomic data from AD brains and found that the increased expression of microglia modules in AD samples was due to increased microglia proportions, while the decreased expression and perturbed co-expression within neuron modules were likely related to impaired neuronal pathways. Differentiated expression of transcription factors may account for altered gene regulation in AD. The changes in gene expression and co-expression within astrocyte modules could be attributed to both astrogliosis and astrocyte gene activation.
SCIENTIFIC REPORTS
(2021)
Article
Genetics & Heredity
Zhi Huang, Zhi Han, Tongxin Wang, Wei Shao, Shunian Xiang, Paul Salama, Maher Rizkalla, Kun Huang, Jie Zhang
Summary: TSUNAMI is an online tool package designed to help users mine GCN modules and perform downstream gene set enrichment analysis. It features a user-friendly interface, real-time co-expression network mining, direct access to NCBI Gene Expression Omnibus and TCGA databases, multiple co-expression analysis tools with parameter selection options, summarization of GCN modules to eigengenes, integrated downstream Enrichr enrichment analysis, and visualization of gene loci by Circos plot.
GENOMICS PROTEOMICS & BIOINFORMATICS
(2021)
Article
Biochemistry & Molecular Biology
Norah Alghamdi, Wennan Chang, Pengtao Dang, Xiaoyu Lu, Changlin Wan, Silpa Gampala, Zhi Huang, Jiashi Wang, Qin Ma, Yong Zang, Melissa Fishel, Sha Cao, Chi Zhang
Summary: This study developed a novel computational method, single-cell flux estimation analysis (scFEA), to infer cell-wise metabolic flux from single-cell RNA-sequencing data. Experimental validation showed the method's ability to accurately predict cellular metabolic flux, aiding in understanding metabolic heterogeneity and cooperative mechanisms within cells and tissues.
Article
Multidisciplinary Sciences
Tongxin Wang, Wei Shao, Zhi Huang, Haixu Tang, Jie Zhang, Zhengming Ding, Kun Huang
Summary: The study introduces a novel multi-omics integrative method named MOGONET, which can effectively perform biomedical classification and identify important biomarkers from different types of omics data.
NATURE COMMUNICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Wei Shao, Tongxin Wang, Zhi Huang, Zhi Han, Jie Zhang, Kun Huang
Summary: WSI is considered as the gold standard for cancer diagnosis and prognosis. However, existing prediction models do not efficiently utilize ordinal information among patients, and the large size and single label of WSIs complicate the training process.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Genetics & Heredity
Travis S. Johnson, Christina Y. Yu, Zhi Huang, Siwen Xu, Tongxin Wang, Chuanpeng Dong, Wei Shao, Mohammad Abu Zaid, Xiaoqing Huang, Yijie Wang, Christopher Bartlett, Yan Zhang, Brian A. Walker, Yunlong Liu, Kun Huang, Jie Zhang
Summary: DEGAS is a novel deep transfer learning framework that transfers disease information from patients to cells, associating individual cells with disease attributes like diagnosis, prognosis, and response to therapy.
Article
Biochemistry & Molecular Biology
Ruishan Liu, Shemra Rizzo, Sarah Waliany, Marius Rene Garmhausen, Navdeep Pal, Zhi Huang, Nayan Chaudhary, Lisa Wang, Chris Harbron, Joel Neal, Ryan Copping, James Zou
Summary: This study conducted a large-scale computational analysis on real-world data of over 40,000 US cancer patients. By studying mutation profiles, treatment sequences, and outcomes, the study identified 458 mutations that predict patient survival in specific cancer therapies, such as immunotherapies, chemotherapy agents, and targeted therapies. The study also investigated mutation-mutation interactions that affect the outcomes of targeted therapies.
Article
Oncology
Zhi Huang, Wei Shao, Zhi Han, Ahmad Mahmoud Alkashash, Carlo de la Sancha, Anil V. V. Parwani, Hiroaki Nitta, Yanjun Hou, Tongxin Wang, Paul Salama, Maher Rizkalla, Jie Zhang, Kun Huang, Zaibo Li
Summary: This study describes an automatic, accurate, comprehensive, interpretable, and reproducible whole slide image feature extraction pipeline called IMPRESS, which is used to predict the response to neoadjuvant chemotherapy in breast cancer patients. Features derived from tumor immune micro-environment and clinical data are used to train machine learning models, resulting in accurate predictions for HER2-positive and triple-negative breast cancer patients.
NPJ PRECISION ONCOLOGY
(2023)
Article
Multidisciplinary Sciences
Zhi Huang, Gennifer E. Merrihew, Eric B. Larson, Jea Park, Deanna Plubell, Edward J. Fox, Kathleen S. Montine, Caitlin S. Latimer, C. Dirk Keene, James Y. Zou, Michael J. MacCoss, Thomas J. Montine
Summary: Resilience to Alzheimer's disease is a rare combination of high disease burden without dementia, which provides valuable insights into limiting clinical impact. Lowering soluble A beta concentration may suppress severe cognitive impairment along the Alzheimer's disease continuum.
NATURE COMMUNICATIONS
(2023)
Article
Biochemistry & Molecular Biology
Zhi Huang, Federico Bianchi, Mert Yuksekgonul, Thomas J. J. Montine, James Zou
Summary: The lack of annotated publicly available medical images is a major barrier for computational research and education innovations. This study utilizes de-identified images and knowledge shared by clinicians on public forums to curate a large dataset called OpenPath, which consists of 208,414 pathology images paired with natural language descriptions. The researchers develop a multimodal artificial intelligence, PLIP, which is trained on OpenPath and achieves state-of-the-art performances for classifying pathology images. PLIP also enables users to retrieve similar cases by either image or natural language search, facilitating knowledge sharing.
Article
Neurosciences
Zhi Huang, Gennifer E. Merrihew, Eric B. Larson, Jea Park, Deanna Plubell, Edward J. Fox, Kathleen S. Montine, C. Dirk Keene, Caitlin S. Latimer, James Y. Zou, Michael J. MacCoss, Thomas J. Montine
Summary: Studying proteomics data of the human brain can provide insights into resilience to Alzheimer's disease. This study identified 6 proteins associated with resistance to Alzheimer's disease and used them to construct a decision tree classifier to differentiate between different groups.
NEUROSCIENCE INSIGHTS
(2023)
Article
Geriatrics & Gerontology
Shan Cong, Xiaohui Yao, Zhi Huang, Shannon L. Risacher, Kwangsik Nho, Andrew J. Saykin, Li Shen
NEUROBIOLOGY OF AGING
(2020)
Article
Computer Science, Artificial Intelligence
Hong Liu, Dong Wei, Donghuan Lu, Xiaoying Tang, Liansheng Wang, Yefeng Zheng
Summary: This study proposes a framework based on hybrid 2D-3D convolutional neural networks for obtaining continuous 3D retinal layer surfaces from OCT volumes. The framework works well with both full and sparse annotations and utilizes alignment displacement vectors and layer segmentation to align the B-scans and segment the layers. Experimental results show that the framework outperforms state-of-the-art 2D deep learning methods in terms of layer segmentation accuracy and cross-B-scan 3D continuity.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Simon Oxenford, Ana Sofia Rios, Barbara Hollunder, Clemens Neudorfer, Alexandre Boutet, Gavin J. B. Elias, Jurgen Germann, Aaron Loh, Wissam Deeb, Bryan Salvato, Leonardo Almeida, Kelly D. Foote, Robert Amaral, Paul B. Rosenberg, David F. Tang-Wai, David A. Wolk, Anna D. Burke, Marwan N. Sabbagh, Stephen Salloway, M. Mallar Chakravarty, Gwenn S. Smith, Constantine G. Lyketsos, Michael S. Okun, William S., Zoltan Mari, Francisco A. Ponce, Andres Lozano, Wolf-Julian Neumann, Bassam Al-Fatly, Andreas Horn
Summary: Spatial normalization is a method to map subject brain images to an average template brain, allowing comparison of brain imaging results. We introduce a novel tool called WarpDrive, which enables manual refinements of image alignment after automated registration. The tool improves accuracy of data representation and aids in understanding patient outcomes.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Ricards Marcinkevics, Patricia Reis Wolfertstetter, Ugne Klimiene, Kieran Chin-Cheong, Alyssia Paschke, Julia Zerres, Markus Denzinger, David Niederberger, Sven Wellmann, Ece Ozkan, Christian Knorr, Julia E. Vogt
Summary: This study presents interpretable machine learning models for predicting the diagnosis, management, and severity of suspected appendicitis using ultrasound images. The proposed models utilize concept bottleneck models (CBM) that facilitate interpretation and intervention by clinicians, without compromising performance or requiring time-consuming image annotation.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Jian-Qing Zheng, Ziyang Wang, Baoru Huang, Ngee Han Lim, Bartlomiej W. Papiez
Summary: This article introduces a new method for medical image registration, which utilizes a separable motion backbone and a residual aligner module to better handle the discontinuous motion of multiple neighboring objects. The proposed method achieves excellent registration results on abdominal CT scans and lung CT scans.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Xiangqiong Wu, Guanghua Tan, Hongxia Luo, Zhilun Chen, Bin Pu, Shengli Li, Kenli Li
Summary: This study develops a user-friendly framework for the automated diagnosis of thyroid nodules in ultrasound videos, simulating the diagnostic workflow of radiologists. By interpreting image characteristics and modeling temporal contextual information, the efficiency and generalizability of the diagnosis can be improved.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Riddhish Bhalodia, Shireen Elhabian, Jadie Adams, Wenzheng Tao, Ladislav Kavan, Ross Whitaker
Summary: This paper introduces DeepSSM, a deep learning-based framework for image-to-shape modeling. By learning the functional mapping from images to low-dimensional shape descriptors, DeepSSM can directly infer statistical representation of anatomy from 3D images. Compared to traditional methods, DeepSSM eliminates the need for heavy manual preprocessing and segmentation, and significantly improves computational time.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Florentin Liebmann, Marco von Atzigen, Dominik Stutz, Julian Wolf, Lukas Zingg, Daniel Suter, Nicola A. Cavalcanti, Laura Leoty, Hooman Esfandiari, Jess G. Snedeker, Martin R. Oswald, Marc Pollefeys, Mazda Farshad, Philipp Furnstahl
Summary: This study presents a marker-less approach for automatic registration and real-time navigation of lumbar spinal fusion surgery using a deep neural network, avoiding radiation exposure and surgical errors. The method was validated on an ex-vivo surgery and a public dataset.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Piyush Tiwary, Kinjawl Bhattacharyya, A. P. Prathosh
Summary: Domain shift refers to the change of distributional characteristics between training and testing datasets, leading to performance drop. For medical image tasks, domain shift can be caused by changes in imaging modalities, devices, and staining mechanisms. Existing approaches based on generative models suffer from training difficulties and lack of diversity. In this paper, the authors propose the use of energy-based models (EBMs) for unpaired image-to-image translation in medical images. The proposed method, called Cycle Consistent Twin EBMs (CCT-EBM), employs a pair of EBMs in the latent space of an Auto-Encoder to ensure translation symmetry and coupling between domains.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Yutong Xie, Jianpeng Zhang, Lingqiao Liu, Hu Wang, Yiwen Ye, Johan Verjans, Yong Xia
Summary: This paper proposes a hybrid pre-training paradigm that combines self-supervised learning and supervised learning to improve the representation quality for medical image segmentation tasks. It introduces a reference task in self-supervised learning and optimizes the model using a gradient matching method. The experimental results demonstrate the effectiveness of this approach on multiple medical image segmentation benchmarks.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Youyi Song, Jing Zou, Kup-Sze Choi, Baiying Lei, Jing Qin
Summary: Cell classification is crucial for intelligent cervical cancer screening, but the variation in cells' appearance and shape poses challenges. A new learning algorithm, worse-case boosting, is proposed to improve classification accuracy for under-represented data. Experimental results demonstrate the effectiveness of this algorithm in two publicly available datasets, achieving a 4% improvement in accuracy.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Sangjoon Park, Eun Sun Lee, Kyung Sook Shin, Jeong Eun Lee, Jong Chul Ye
Summary: The increasing demand for AI systems to monitor human errors and abnormalities in healthcare presents challenges. This study presents a model called Medical X-VL, which is tailored for the medical domain and outperformed current state-of-the-art models in two medical image datasets. The model enables various zero-shot tasks for monitoring AI in the medical domain.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Anna Klimovskaia Susmelj, Berkan Lafci, Firat Ozdemir, Neda Davoudi, Xose Luis Dean-Ben, Fernando Perez-Cruz, Daniel Razansky
Summary: Optoacoustic imaging is a technique that uses optical excitation and ultrasound detection for biological tissue imaging. The quality of the images depends on the extent of tomographic coverage provided by the ultrasound detector arrays. However, full coverage is not always possible due to experimental constraints. The proposed signal domain adaptation network aims to reduce limited-view artifacts in the images.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Srijay Deshpande, Muhammad Dawood, Fayyaz Minhas, Nasir Rajpoot
Summary: In this work, a novel framework called SynCLay is proposed for automated synthesis of histology images based on user-defined cellular layouts. The framework can generate realistic and high-quality histology images with different cellular arrangements, which is helpful for studying the role of cells in the tumor microenvironment. The framework integrates a nuclear segmentation and classification model to refine nuclear structures and generate nuclear masks. Evaluation using quantitative metrics and feedback from pathologists shows that the synthetic images generated by SynCLay have high realism scores and can accurately differentiate between benign and malignant tumors.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Ahmed H. Shahin, An Zhao, Alexander C. Whitehead, Daniel C. Alexander, Joseph Jacob, David Barber
Summary: Survival analysis is a valuable tool in healthcare for predicting the time to specific events. This paper introduces CenTime, a novel approach that directly estimates the time to event. The method performs well with censored data and can be easily integrated with deep learning models. Compared to standard methods, CenTime offers superior performance in predicting event time while maintaining comparable ranking performance.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Bingyuan Liu, Jose Dolz, Adrian Galdran, Riadh Kobbi, Ismail Ben Ayed
Summary: Most segmentation losses, such as CE and Dice, are variants of the Cross-Entropy or Dice losses. This work provides a theoretical analysis that shows a deeper connection between CE and Dice than previously thought. From a constrained-optimization perspective, both CE and Dice decompose into similar ground-truth matching terms and region-size penalty terms. The analysis uncovers hidden region-size biases: Dice has an intrinsic bias towards extremely imbalanced solutions, while CE implicitly encourages the ground-truth region proportions. Based on this analysis, a principled and simple solution is proposed to explicitly control the region-size bias.
MEDICAL IMAGE ANALYSIS
(2024)