Yingcheng Liu

Yingcheng Liu

Auto-generated profile, based on publicly available information

Yingcheng Liu

Computer Science and Artificial Intelligence Lab, MIT, Cambridge, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 August 2022 in Nature Medicine
Verified
Journal Article
Open access
PDF file
YYYuzhe Yang
Yuzhe Yang
YYYuan Yuan
Yuan Yuan
GZGuo Zhang
Guo Zhang
HWHao Wang
Hao Wang
YCYing-Cong Chen
Ying-Cong Chen
DKDina Katabi
Dina Katabi
There are currently no effective biomarkers for diagnosing Parkinson’s disease (PD) or tracking its progression. Here, we developed an artificial intelligence (AI) model to detect PD and track its progression from nocturnal breathing signals. The model was evaluated on a large dataset comprising 7,671 individuals, using data from several hospitals in the United States, as well as multiple public datasets. The AI model can detect PD with an area-under-the-curve of 0.90 and 0.85 on held-out and external test sets, respectively. The AI model can also estimate PD severity and progression in accordance with the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (R = 0.94,P = 3.6 × 10–25). The AI model uses an attention layer that allows for interpreting its predictions with respect to sleep and electroencephalogram. Moreover, the model can assess PD in the home setting in a touchless manner, by extracting breathing from radio waves that bounce off a person’s body during sleep. Our study demonstrates the feasibility of objective, noninvasive, at-home assessment of PD, and also provides initial evidence that this AI model may be useful for risk assessment before clinical diagnosis.

21 September 2022 in Science Translational Medicine
Verified
Journal Article
Closed access
YLYingcheng Liu
Yingcheng Liu
GZGuo Zhang
Guo Zhang
CTChristopher G. Tarolli
Christopher G. Tarolli
RHRumen Hristov
Rumen Hristov
SJStella Jensen-Roberts
Stella Jensen-Roberts
DKDina Katabi
Dina Katabi
Parkinson’s disease (PD) is the fastest-growing neurological disease in the world. A key challenge in PD is tracking disease severity, progression, and medication response. Existing methods are semisubjective and require visiting the clinic. In this work, we demonstrate an effective approach for assessing PD severity, progression, and medication response at home, in an objective manner. We used a radio device located in the background of the home. The device detected and analyzed the radio waves that bounce off people’s bodies and inferred their movements and gait speed. We continuously monitored 50 participants, with and without PD, in their homes for up to 1 year. We collected over 200,000 gait speed measurements. Cross-sectional analysis of the data shows that at-home gait speed strongly correlates with gold-standard PD assessments, as evaluated by the Movement Disorder Society-Sponsored Revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) part III subscore and total score. At-home gait speed also provides a more sensitive marker for tracking disease progression over time than the widely used MDS-UPDRS. Further, the monitored gait speed was able to capture symptom fluctuations in response to medications and their impact on patients’ daily functioning. Our study shows the feasibility of continuous, objective, sensitive, and passive assessment of PD at home and hence has the potential of improving clinical care and drug clinical trials.

19 December 2023 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Verified
Journal Article
Open access
WCWenqiang Chen
Wenqiang Chen
YHYexin Hu
Yexin Hu
WSWei Song
Wei Song
YLYingcheng Liu
Yingcheng Liu
ATAntonio Torralba
Antonio Torralba
WMWojciech Matusik
Wojciech Matusik
Human mesh reconstruction is essential for various applications, including virtual reality, motion capture, sports performance analysis, and healthcare monitoring. In healthcare contexts such as nursing homes, it is crucial to employ plausible and non-invasive methods for human mesh reconstruction that preserve privacy and dignity. Traditional vision-based techniques encounter challenges related to occlusion, viewpoint limitations, lighting conditions, and privacy concerns. In this research, we present CAvatar, a real-time human mesh reconstruction approach that innovatively utilizes pressure maps recorded by a tactile carpet as input. This advanced, non-intrusive technology obviates the need for cameras during usage, thereby safeguarding privacy. Our approach addresses several challenges, such as the limited spatial resolution of tactile sensors, extracting meaningful information from noisy pressure maps, and accommodating user variations and multiple users. We have developed an attention-based deep learning network, complemented by a discriminator network, to predict 3D human pose and shape from 2D pressure maps with notable accuracy. Our model demonstrates promising results, with a mean per joint position error (MPJPE) of 5.89 cm and a per vertex error (PVE) of 6.88 cm. To the best of our knowledge, we are the first to generate 3D mesh of human activities solely using tactile carpet signals, offering a novel approach that addresses privacy concerns and surpasses the limitations of existing vision-based and wearable solutions. The demonstration of CAvatar is shown at https://youtu.be/ZpO3LEsgV7Y.

12 October 2023
Verified
Book Chapter
Closed access
PDF file
YLYingcheng Liu
Yingcheng Liu
NKNeerav Karani
Neerav Karani
SAS. Mazdak Abulnaga
S. Mazdak Abulnaga
JXJunshen Xu
Junshen Xu
PGPatricia Ellen Grant
Patricia Ellen Grant
PGPolina Golland
Polina Golland

20 September 2025
Verified
Book Chapter
Closed access
PDF file
YLYingcheng Liu
Yingcheng Liu
PWPeiqi Wang
Peiqi Wang
SDSebastian Diaz
Sebastian Diaz
ETEsra Abaci Turk
Esra Abaci Turk
BBBenjamin Billot
Benjamin Billot
PGPolina Golland
Polina Golland

12 August 2023 in arXiv
Verified
Preprint
Open access
PDF file
PWPeiqi Wang
Peiqi Wang
YLYingcheng Liu
Yingcheng Liu
CKChing-Yun Ko
Ching-Yun Ko
WWWilliam M. Wells
William M. Wells
SBSeth Berkowitz
Seth Berkowitz
PGPolina Golland
Polina Golland
Self-supervised representation learning on image-text data facilitates crucial medical applications, such as image classification, visual grounding, and cross-modal retrieval. One common approach involves contrasting semantically similar (positive) and dissimilar (negative) pairs of data points. Drawing negative samples uniformly from the training data set introduces false negatives, i.e., samples that are treated as dissimilar but belong to the same class. In healthcare data, the underlying class distribution is nonuniform, implying that false negatives occur at a highly variable rate. To improve the quality of learned representations, we develop a novel approach that corrects for false negatives. Our method can be viewed as a variant of debiased contrastive learning that uses estimated sample-specific class probabilities. We provide theoretical analysis of the objective function and demonstrate the proposed approach on both image and paired image-text data sets. Our experiments illustrate empirical advantages of sample-specific debiasing.