Mechanosensitive TRPV4 immunohistochemistry improves deep learning‐based classification of ductal carcinoma in situ beyond H&E morphology
The Journal of Pathology: Clinical Research · 2026-07 · 12 (4)
DOI: 10.1002/2056-4538.70106 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift The Journal of Pathology: Clinical Research, online erschienen am 08.07.2026. Verfasst von Janghyun Yoo und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics and Astronomy, College of Natural Sciences, Seoul National University, Seoul, South Korea. Hauptthemen laut MEDLINE: TRPV Cation Channels, Carcinoma, Intraductal, Noninfiltrating, Deep Learning, Breast Neoplasms. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, Elsa U. Pardee Foundation, Technology Maturation Award from the George Washington University Technology Commercialization Office.
Abstract (Originalsprache)
Ductal carcinoma in situ (DCIS) spans a biologic continuum from atypical ductal hyperplasia (ADH) to high‐grade lesions with variable risk of progression to invasive ductal carcinoma (IDC), yet morphologic assessment by hematoxylin and eosin (H&E) remains diagnostically limited, particularly at the benign versus ADH/low‐grade DCIS boundary. TRPV4, a mechanosensitive ion channel with pathology‐dependent subcellular localization in DCIS, offers a biologically motivated immunohistochemical (IHC) marker that may refine classification beyond routine H&E assessment. We tested whether deep learning models trained on TRPV4 IHC outperform H&E‐based models across the DCIS progression spectrum. We assembled a multi‐institutional cohort of H&E and TRPV4 IHC whole‐slide images from 108 patients, comprising an internal development cohort ( n = 69), an external test cohort ( n = 39), yielding 24,248 annotated tiles. Histopathological tiles from annotated regions were grouped into four ordered classes: normal/benign, ADH/low‐grade DCIS, high‐grade DCIS, and IDC. Xception and EfficientNet‐B0 convolutional neural networks were trained with patient‐level three‐fold cross‐validation on the development cohort and evaluated as ensembles on the external test cohort. On external patient‐level testing, H&E ensembles achieved macro‐F1 values of 0.43–0.44 and macro‐AUC values of 0.73–0.80, whereas TRPV4 IHC ensembles improved performance to macro‐F1 values of 0.68–0.72 and macro‐AUC values of 0.91–0.92, corresponding to a 54.5–67.4% relative improvement in patient‐level macro‐F1. Patient‐level per‐class analyses showed the largest AUC gains with TRPV4 IHC versus H&E for ADH/low‐grade DCIS (0.94–0.95 versus 0.61–0.70) and IDC (0.77–0.85 versus 0.61–0.69). Per‐class analyses showed the largest gains with TRPV4 IHC versus H&E for ADH/low‐grade DCIS (AUC, 0.83–0.84 versus 0.70–0.81) and IDC (AUC, 0.74–0.79 versus 0.65–0.66). These findings support TRPV4 IHC as a mechanistically grounded complement to H&E that improves patient‐level discrimination across the DCIS progression spectrum, with the strongest gains for ADH/low‐grade DCIS and IDC, in a pilot multi‐institutional setting.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Physics and Astronomy, College of Natural Sciences, Seoul National University, Seoul, South Korea.
- Department of Anatomy and Cell Biology, School of Medicine and Health Sciences, George Washington University, Washington, DC, USA.
- Thomas Jefferson Science and Technology High School, Alexandria, VA, USA.
- Department of Pathology, School of Medicine and Health Sciences, George Washington University, Washington, DC, USA.
- Department of Biomedical Engineering, School of Engineering and Applied Science, George Washington University, Washington, DC, USA.
ORCID-Profile: Inhee Chung
Förderung
- NCI NIH HHS
- Elsa U. Pardee Foundation
- Technology Maturation Award from the George Washington University Technology Commercialization Office
- GW Cancer Center Katzen Research Program
- National Cancer Institute
Zitieren
APA
Yoo, J., Karthikeyan, R., Kamat, K., Chan, C., Samankan, S., Arbzadeh, E., Schwartz, A., Latham, P. S., & Chung, I. (2026). Mechanosensitive TRPV4 immunohistochemistry improves deep learning‐based classification of ductal carcinoma in situ beyond H&E morphology. The Journal of Pathology: Clinical Research, 12(4). https://doi.org/10.1002/2056-4538.70106
Vancouver
Yoo J, Karthikeyan R, Kamat K, Chan C, Samankan S, Arbzadeh E, et al. Mechanosensitive TRPV4 immunohistochemistry improves deep learning‐based classification of ductal carcinoma in situ beyond H&E morphology. The Journal of Pathology: Clinical Research. 2026;12(4). doi:10.1002/2056-4538.70106
BibTeX
@article{Yoo2026,
author = {Yoo, Janghyun and Karthikeyan, Raghav and Kamat, Kashi and Chan, Christopher and Samankan, Shabnam and Arbzadeh, Elham and Schwartz, Arnold and Latham, Patricia S and Chung, Inhee},
title = {Mechanosensitive TRPV4 immunohistochemistry improves deep learning‐based classification of ductal carcinoma in situ beyond H&E morphology},
journal = {The Journal of Pathology: Clinical Research},
year = {2026},
volume = {12},
number = {4},
doi = {10.1002/2056-4538.70106}
}
EUVIMED