Qin Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Qin Liu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Alejandro Federico Frangi
University of Manchester
1 shared publication - Chaoyu Chen
National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China; Medical Ultrasound Image Computing (MUSIC) Laboratory, Shenzhen University, Shenzhen, China
1 shared publication Dan Zhu
National Institute of Parasitic Diseases, Chinese Center for Disease Control and Prevention; Key Laboratory of Parasite and Vector Biology, Ministry of Health; WHO Collaborating Center for Tropical Diseases; Chinese Center for Tropical Diseases Research, Shanghai 200025, P. R. China
1 shared publication- Dong Ni
Shenzhen University
1 shared publication - Jian Wang
Department of Neurology and Neuroscience, University of Virginia, School of Medicine, Charlottesville, VA, United States
1 shared publication Jiatong Wu
National Institute of Parasitic Diseases, Chinese Center for Disease Control and Prevention; Key Laboratory of Parasite and Vector Biology, Ministry of Health; WHO Collaborating Center for Tropical Diseases; Chinese Center for Tropical Diseases Research, Shanghai 200025, P. R. China
1 shared publication
Latest Publications
- Open Access
Statistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound
Standard plane recognition plays an important role in prenatal ultrasound (US) screening. Automatically recognizing the standard plane along with the corresponding anatomical structures in US image can not only facilitate US image interpretation but also improve diagnostic efficiency. In this study, we build a novel multi-label learning (MLL) scheme to identify multiple standard planes and corresponding anatomical structures of fetus simultaneously. Our contribution is three-fold. First, we represent the class correlation by word embeddings to capture the fine-grained semantic and latent statistical concurrency. Second, we equip the MLL with a graph convolutional network to explore the inner and outer relationship among categories. Third, we propose a novel cluster relabel-based contrastive learning algorithm to encourage the divergence among ambiguous classes. Extensive validation was performed on our large in-house dataset. Our approach reports the highest accuracy as 90.25% for standard planes labeling, 85.59% for planes and structures labeling and mAP as 94.63%. The proposed MLL scheme provides a novel perspective for standard plane recognition and can be easily extended to other medical image classification tasks.
Open AccessStatistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound
Standard plane recognition plays an important role in prenatal ultrasound (US) screening. Automatically recognizing the standard plane along with the corresponding anatomical structures in US image can not only facilitate US image interpretation but also improve diagnostic efficiency. In this study, we build a novel multi-label learning (MLL) scheme to identify multiple standard planes and corresponding anatomical structures of fetus simultaneously. Our contribution is three-fold. First, we represent the class correlation by word embeddings to capture the fine-grained semantic and latent statistical concurrency. Second, we equip the MLL with a graph convolutional network to explore the inner and outer relationship among categories. Third, we propose a novel cluster relabel-based contrastive learning algorithm to encourage the divergence among ambiguous classes. Extensive validation was performed on our large in-house dataset. Our approach reports the highest accuracy as 90.25% for standard planes labeling, 85.59% for planes and structures labeling and mAP as 94.63%. The proposed MLL scheme provides a novel perspective for standard plane recognition and can be easily extended to other medical image classification tasks.
- Open Access
- 1 August 2019
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 8 (8)
A chromosomal-level genome assembly for the insect vector for Chagas disease, Triatoma rubrofasciata
Triatoma rubrofasciata is a widespread pathogen vector for Chagas disease, an illness that affects approximately 7 million people worldwide. Despite its importance to human health, its evolutionary origin has not been conclusively determined. A reference genome for T. rubrofasciata is not yet available. We have sequenced the genome of a female individual with T. rubrofasciatausing a single molecular DNA sequencing technology (i.e., PacBio Sequel platform) and have successfully reconstructed a whole-genome (680-Mb) assembly that covers 90% of the nuclear genome (757 Mb). Through Hi-C analysis, we have reconstructed full-length chromosomes of this female individual that has 13 unique chromosomes (2n = 24 = 22 + X1 + X2) with a contig N50 of 2.72 Mb and a scaffold N50 of 50.7 Mb. This genome has achieved a high base-level accuracy of 99.99%. This platinum-grade genome assembly has 12,691 annotated protein-coding genes. More than 95.1% of BUSCO genes were single-copy completed, indicating a high level of completeness of the genome. The platinum-grade genome assembly and its annotation provide valuable information for future in-depth comparative genomics studies, including sexual determination analysis in T. rubrofasciata and the pathogenesis of Chagas disease.
- 1 August 2019
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 8 (8)
Open AccessA chromosomal-level genome assembly for the insect vector for Chagas disease, Triatoma rubrofasciata
Triatoma rubrofasciata is a widespread pathogen vector for Chagas disease, an illness that affects approximately 7 million people worldwide. Despite its importance to human health, its evolutionary origin has not been conclusively determined. A reference genome for T. rubrofasciata is not yet available. We have sequenced the genome of a female individual with T. rubrofasciatausing a single molecular DNA sequencing technology (i.e., PacBio Sequel platform) and have successfully reconstructed a whole-genome (680-Mb) assembly that covers 90% of the nuclear genome (757 Mb). Through Hi-C analysis, we have reconstructed full-length chromosomes of this female individual that has 13 unique chromosomes (2n = 24 = 22 + X1 + X2) with a contig N50 of 2.72 Mb and a scaffold N50 of 50.7 Mb. This genome has achieved a high base-level accuracy of 99.99%. This platinum-grade genome assembly has 12,691 annotated protein-coding genes. More than 95.1% of BUSCO genes were single-copy completed, indicating a high level of completeness of the genome. The platinum-grade genome assembly and its annotation provide valuable information for future in-depth comparative genomics studies, including sexual determination analysis in T. rubrofasciata and the pathogenesis of Chagas disease.