Anna Zapaishchykova

Anna Zapaishchykova

Auto-generated profile, based on publicly available information

Anna Zapaishchykova

Artificial Intelligence in Medicine (AIM) Program Mass General Brigham Harvard Medical School Boston MA United States

Research Focus & Metrics

Academic Career Length

4Years (2023-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.

5 February 2026 in Nature Neuroscience
Verified
Journal Article
Open access
PDF file
DTDivyanshu Tak
Divyanshu Tak
BGBiniam A. Garomsa
Biniam A. Garomsa
AZAnna Zapaishchykova
Anna Zapaishchykova
TCTafadzwa L. Chaunzwa
Tafadzwa L. Chaunzwa
JPJuan Carlos Climent Pardo
Juan Carlos Climent Pardo
BKBenjamin H. Kann
Benjamin H. Kann
Artificial intelligence applied to brain magnetic resonance imaging (MRI) holds potential to advance diagnosis, prognosis and treatment planning for neurological diseases. The field has been constrained, thus far, by limited training data and task-specific models that do not generalize well across patient populations and medical tasks. By leveraging self-supervised learning, pretraining and targeted adaptation, foundation models present a promising paradigm to overcome these limitations. Here we present Brain Imaging Adaptive Core (BrainIAC)—a foundation model designed to learn generalized representations from unlabeled brain MRI data and serve as a core basis for diverse downstream application adaptation. Trained and validated on 48,965 brain MRIs across a broad spectrum of tasks, we demonstrate that BrainIAC outperforms localized supervised training and other pretrained models, particularly in low-data, few-shot, settings and in high-difficulty prediction tasks, allowing for application in scenarios otherwise infeasible. BrainIAC can be integrated into imaging pipelines and multimodal frameworks and may lead to improved biomarker discovery and artificial intelligence clinical translation.

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.

9 November 2023 in Nature Communications
Verified
Journal Article
Open access
PDF file
AZAnna Zapaishchykova
Anna Zapaishchykova
KLKevin X. Liu
Kevin X. Liu
ASAnurag Saraf
Anurag Saraf
ZYZezhong Ye
Zezhong Ye
PCPaul J. Catalano
Paul J. Catalano
BKBenjamin H. Kann
Benjamin H. Kann
Lean muscle mass (LMM) is an important aspect of human health. Temporalis muscle thickness is a promising LMM marker but has had limited utility due to its unknown normal growth trajectory and reference ranges and lack of standardized measurement. Here, we develop an automated deep learning pipeline to accurately measure temporalis muscle thickness (iTMT) from routine brain magnetic resonance imaging (MRI). We apply iTMT to 23,876 MRIs of healthy subjects, ages 4 through 35, and generate sex-specific iTMT normal growth charts with percentiles. We find that iTMT was associated with specific physiologic traits, including caloric intake, physical activity, sex hormone levels, and presence of malignancy. We validate iTMT across multiple demographic groups and in children with brain tumors and demonstrate feasibility for individualized longitudinal monitoring. The iTMT pipeline provides unprecedented insights into temporalis muscle growth during human development and enables the use of LMM tracking to inform clinical decision-making.

30 June 2023 in medRxiv
Verified
Preprint
Open access
PDF file
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
Purpose: Artificial intelligence (AI)-automated tumor delineation for pediatric gliomas would enable real-time volumetric evaluation to support diagnosis, treatment response assessment, and clinical decision-making. Auto-segmentation algorithms for pediatric tumors are rare, due to limited data availability, and algorithms have yet to demonstrate clinical translation. Methods: We leveraged two datasets from a national brain tumor consortium (n=184) and a pediatric cancer center (n=100) to develop, externally validate, and clinically benchmark deep learning neural networks for pediatric low-grade glioma (pLGG) segmentation using a novel in-domain, stepwise transfer learning approach. The best model [via Dice similarity coefficient (DSC)] was externally validated and subject to randomized, blinded evaluation by three expert clinicians wherein clinicians assessed clinical acceptability of expert- and AI-generated segmentations via 10-point Likert scales and Turing tests. Results: The best AI model utilized in-domain, stepwise transfer learning (median DSC: 0.877 [IQR 0.715-0.914]) versus baseline model (median DSC 0.812 [IQR 0.559-0.888]; p <0.05). On external testing (n=60), the AI model yielded accuracy comparable to inter-expert agreement (median DSC: 0.834 [IQR 0.726-0.901] vs. 0.861 [IQR 0.795-0.905], p =0.13). On clinical benchmarking (n=100 scans, 300 segmentations from 3 experts), the experts rated the AI model higher on average compared to other experts (median Likert rating: 9 [IQR 7-9]) vs. 7 [IQR 7-9], p <0.05 for each). Additionally, the AI segmentations had significantly higher ( p <0.05) overall acceptability compared to experts on average (80.2% vs. 65.4%). Experts correctly predicted the origins of AI segmentations in an average of 26.0% of cases. Conclusions: Stepwise transfer learning enabled expert-level, automated pediatric brain tumor auto-segmentation and volumetric measurement with a high level of clinical acceptability. This approach may enable development and translation of AI imaging segmentation algorithms in limited data scenarios. Summary: Authors proposed and utilized a novel stepwise transfer learning approach to develop and externally validate a deep learning auto-segmentation model for pediatric low-grade glioma whose performance and clinical acceptability were on par with pediatric neuroradiologists and radiation oncologists. Key Points: There are limited imaging data available to train deep learning tumor segmentation for pediatric brain tumors, and adult-centric models generalize poorly in the pediatric setting. Stepwise transfer learning demonstrated gains in deep learning segmentation performance (Dice score: 0.877 [IQR 0.715-0.914]) compared to other methodologies and yielded segmentation accuracy comparable to human experts on external validation. On blinded clinical acceptability testing, the model received higher average Likert score rating and clinical acceptability compared to other experts ( Transfer-Encoder model vs. average expert: 80.2% vs. 65.4%) Turing tests showed uniformly low ability of experts’ ability to correctly identify the origins of Transfer-Encoder model segmentations as AI-generated versus human-generated (mean accuracy: 26%).

3 December 2024 in medRxiv
Verified
Preprint
Open access
PDF file
DTDivyanshu Tak
Divyanshu Tak
BGBiniam A. Garomsa
Biniam A. Garomsa
TCTafadzwa L. Chaunzwa
Tafadzwa L. Chaunzwa
AZAnna Zapaishchykova
Anna Zapaishchykova
JPJuan Carlos Climent Pardo
Juan Carlos Climent Pardo
BKBenjamin Harris Kann
Benjamin Harris Kann
Artificial intelligence (AI) applied to brain magnetic resonance imaging (MRI) has the potential to improve disease diagnosis and management but requires algorithms with generalizable knowledge that can perform well in a variety of clinical scenarios. The field has been constrained, thus far, by limited training data and task-specific models that do not generalize well across patient populations and medical tasks. Foundation models, by leveraging self-supervised learning, pretraining, and targeted adaptation, present a promising paradigm to overcome these limitations. Here, we present Brain Imaging Adaptive Core (BrainIAC), a novel foundation model designed to learn generalized representations from unlabeled brain MRI data and serve as a core basis for diverse downstream application adaptation. Trained and validated on 48,519 brain MRIs across a broad spectrum of tasks, we demonstrate that BrainIAC outperforms localized supervised training and other pretrained models, particularly in low-data settings and high-difficulty tasks, allowing for application in scenarios otherwise infeasible. BrainIAC can be integrated into imaging pipelines and multimodal frameworks and may lead to improved biomarker discovery and AI clinical translation.