Yining Zha

Yining Zha

Auto-generated profile, based on publicly available information

Yining Zha

Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
1 May 2024 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
DTDivyanshu Tak
Divyanshu Tak
ZYZezhong Ye
Zezhong Ye
AZAnna Zapaischykova
Anna Zapaischykova
YZYining Zha
Yining Zha
ABAidan Boyd
Aidan Boyd
BKBenjamin H. Kann
Benjamin H. Kann
"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop and externally test a scan-to-prediction deep-learning pipeline for noninvasive, MRI-based BRAF mutational status classification for pediatric low-grade glioma (pLGG). Materials and Methods This retrospective study included two pLGG datasets with linked genomic and diagnostic T2-weighted MRI data of patients: BCH (development dataset, n = 214 [60 (28%) BRAF-Fusion, 50 (23%) BRAF V600E, 104 (49%) wild-type), and the Children's Brain Tumor Network (external testing, n = 112 [60 (53%) with BRAF-Fusion, 17 (15%) BRAF-V600E, 35 (32%) wild-type]). A deep learning pipeline was developed to classify BRAF mutational status (V600E versus Fusion versus Wild-Type) via a two-stage process: 1) 3D tumor segmentation and extraction of axial tumor images, and 2) slice-wise, deep learning-based classification of mutational status. Knowledge-transfer and self-supervised approaches were investigated to prevent model overfitting, with a primary endpoint of the area under the receiver operating characteristic curve (AUC). To enhance model interpretability, we developed a novel metric, COMDist (Center of Mass Distance), that quantifies the model attention around the tumor. Results A combination of transfer learning from a pretrained medical imaging-specific network and self-supervised label cross-training (TransferX) coupled with consensus logic yielded the highest classification performance with AUC of 0.82 [95% CI: 0.72-0.91], 0.87 [95% CI: 0.61-0.97], and 0.85[95% CI: 0.66-0.95] for Wild-Type, BRAF-Fusion and BRAF-V600E, respectively, on internal testing. On external testing, the pipeline yielded AUC of 0.72 [95% CI: 0.64-0.86], 0.78 [95% CI: 0.61-0.89], and 0.72 [95% CI: 0.64-0.88] for Wild-Type, BRAF-Fusion and BRAF-V600E classes, respectively. Conclusion Transfer learning and self-supervised cross-training improved classification performance and generalizability for noninvasive pLGG mutational status prediction in a limited data scenario. ©RSNA, 2024.

1 July 2024 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
ABAidan Boyd
Aidan Boyd
ZYZezhong Ye
Zezhong Ye
SPSanjay P Prabhu
Sanjay P Prabhu
MTMichael C. Tjong
Michael C. Tjong
YZYining Zha
Yining Zha
BKBenjamin H. Kann
Benjamin H. Kann
"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop, externally test, and evaluate clinical acceptability of a deep learning (DL) pediatric brain tumor segmentation model using stepwise transfer learning. Materials and Methods In this retrospective study, the authors leveraged two T2-weighted MRI datasets (May 2001-December 2015) from a national brain tumor consortium (n = 184; median age, 7 years (range: 1-23 years); 94 male) and a pediatric cancer center (n = 100; median age, 8 years (range: 1-19 years); 47 male) to develop and evaluate DL neural networks for pediatric low-grade glioma segmentation using a novel stepwise transfer learning approach to maximize performance in a limited data scenario. The best model was externally-tested on an independent test set and subjected to randomized, blinded evaluation by three clinicians, wherein they assessed clinical acceptability of expert- and artificial intelligence (AI)-generated segmentations via 10-point Likert scales and Turing tests. Results The best AI model used in-domain, stepwise transfer learning (median DSC: 0.88 [IQR 0.72-0.91] versus 0.812 [0.56-0.89] for baseline model; P = .049). On external testing, AI model yielded excellent accuracy using reference standards from three clinical experts (Expert-1: 0.83 [0.75-0.90]; Expert-2: 0.81 [0.70-0.89]; Expert-3: 0.81 [0.68-0.88]; mean accuracy: 0.82)). On clinical benchmarking (n = 100 scans), experts rated AI-based segmentations higher on average compared with other experts (median Likert score: median 9 [IQR 7-9]) versus 7 [IQR 7-9]) and rated more AI segmentations as clinically acceptable (80.2% versus 65.4%). Experts correctly predicted the origin of AI segmentations in an average of 26.0% of cases. Conclusion Stepwise transfer learning enabled expert-level, automated pediatric brain tumor auto-segmentation and volumetric measurement with a high level of clinical acceptability. ©RSNA, 2024.

15 October 2024 in Journal of the American Heart Association
Verified
Journal Article
Open access
CCCancan Cui
Cancan Cui
PLPingan Li
Pingan Li
YQYitian Qi
Yitian Qi
JSJiayin Song
Jiayin Song
THTianjiao Han
Tianjiao Han
ZWZhiyuan Wu
Zhiyuan Wu
Background: The atherogenic effect of remnant cholesterol is being increasingly acknowledged. This study aimed to explore the association of discordance between remnant cholesterol and low‐density lipoprotein cholesterol with stroke onset using 2 Chinese national cohorts. Methods and Results: We studied 11 139 participants from CHARLS (China Health and Retirement Longitudinal Study) and 5993 participants from CHNS (China Health and Nutrition Survey) aged 45 years or older. The discordance between remnant cholesterol and low‐density lipoprotein cholesterol was defined using the difference in percentile units (>15 units). There were 988 (8.9%) and 128 (2.1%) stroke events reported during follow‐up in the 2 cohorts. Elevated remnant cholesterol was significantly associated with a higher risk of total stroke in 2 cohorts. After adjusting for remnant cholesterol level, the discordantly high remnant cholesterol group was significantly associated with an increased stroke risk (CHARLS: subdistribution hazard ratio [sHR], 1.31 [95 CI, 1.10–1.55]; CHNS: sHR, 1.84 [95 CI, 1.15–3.08]) compared with the discordantly low group. Consistent results were shown even among those with optimal low‐density lipoprotein cholesterol level. Conclusions: The discordance between remnant cholesterol and low‐density lipoprotein cholesterol, representing the intraindividual discrepancy, is significantly associated with stroke onset among Chinese adults.

10 February 2026 in Journal of Clinical Oncology
Verified
Journal Article
Closed access
ZYZezhong Ye
Zezhong Ye
RMReza Mojahed-Yazdi
Reza Mojahed-Yazdi
AZAnna Zapaishchykova
Anna Zapaishchykova
DTDivyanshu Tak
Divyanshu Tak
MMMaryam Mahootiha
Maryam Mahootiha
BKBenjamin H Kann
Benjamin H Kann
PURPOSE: Extranodal extension (ENE) is a biomarker in oropharyngeal carcinoma (OPC) but can only be diagnosed via surgical pathology. We applied an automated artificial intelligence (AI) imaging platform integrating lymph node autosegmentation with ENE prediction to determine the prognostic value of the number of predicted ENE nodes. MATERIALS AND METHODS: We conducted a multisite, retrospective study of 1,733 OPC patients with pretreatment computed tomography who underwent definitive radiation therapy across three institutions. Malignant lymph nodes were segmented using a validated deep learning auto-segmentation model, and segmented lymph nodes were sequentially processed with a validated ENE prediction model to calculate number of nodes with AI-predicted ENE (AI-ENE) per patient. We evaluated associations of AI-ENE with disease outcomes using site-stratified, multivariable Cox regression, adjusting for human papillomavirus (HPV) status, smoking pack-years, tumor and nodal stage, age, and sex. We evaluated risk-stratification improvement when incorporating AI-ENE into the Radiation Therapy Oncology Group (RTOG)-0129 risk groupings and derived American Joint Committee on Cancer (AJCC) 8th edition staging with Uno C-indices and decision curve analyses. RESULTS: Overall, median AI-ENE node number was 1 (range, 0-6). AI-ENE node number was independently associated with poorer distant control (DC; hazard ratio [HR], 1.44 [95% CI, 1.23 to 1.69]; P < .001) and overall survival (OS; HR, 1.30 [95% CI, 1.16 to 1.46]; P < .001). Increasing AI-ENE node number was incrementally associated with worse outcome, particularly DC ( P < .001). C-indices improved in the external data set when incorporating AI-ENE into RTOG-0129 groupings (OS: 0.70 v 0.65; DC: 0.65 v 0.57) and AJCC-8 stage (OS: 0.75 v 0.70; DC: 0.72 v 0.67; P < .001 for each). The largest improvements were observed among HPV-negative patients (C-index: +15% for OS, +14% for DC). CONCLUSION: Automated, AI-ENE node number is a novel risk factor for OPC that may better inform pretreatment risk stratification and decision-making.