Ms. Elena Baraznenok Profile

Elena Baraznenok

at Univ of Washington

SPIE Involvement:

Author

Publications (2)

Proceedings Article | 13 March 2024 Poster

A comprehensive workflow to generate 3D pathology datasets for large-scale clinical studies

Kevin Bishop, Lindsey Erion Barner, Qinghua Han, Elena Baraznenok, Lydia Lan, Gan Gao, Robert Serafin, Sarah S. Chow, Jonathan T. Liu

Proceedings Volume PC12827, PC128270T (2024) https://doi.org/10.1117/12.3003339

KEYWORDS: Pathology, Tissues, Biological research, Quality control, Prostate cancer, Nondestructive evaluation, Image processing, Gold, Diseases and disorders, Decision making

Read Abstract +

SPIE Journal Paper | 1 March 2024 Open Access

Direct three-dimensional segmentation of prostate glands with nnU-Net

Rui Wang, Sarah S. Chow, Robert Serafin, Weisi Xie, Qinghua Han, Elena Baraznenok, Lydia Lan, Kevin Bishop, Jonathan T. Liu

JBO, Vol. 29, Issue 03, 036001, (March 2024) https://doi.org/10.1117/12.10.1117/1.JBO.29.3.036001

KEYWORDS: Image segmentation, 3D modeling, Education and training, 3D image processing, Prostate, Data modeling, Biopsy, Pathology, Prostate cancer, Performance modeling

Read Abstract +

SignificanceIn recent years, we and others have developed non-destructive methods to obtain three-dimensional (3D) pathology datasets of clinical biopsies and surgical specimens. For prostate cancer risk stratification (prognostication), standard-of-care Gleason grading is based on examining the morphology of prostate glands in thin 2D sections. This motivates us to perform 3D segmentation of prostate glands in our 3D pathology datasets for the purposes of computational analysis of 3D glandular features that could offer improved prognostic performance.AimTo facilitate prostate cancer risk assessment, we developed a computationally efficient and accurate deep learning model for 3D gland segmentation based on open-top light-sheet microscopy datasets of human prostate biopsies stained with a fluorescent analog of hematoxylin and eosin (H&E).ApproachFor 3D gland segmentation based on our H&E-analog 3D pathology datasets, we previously developed a hybrid deep learning and computer vision-based pipeline, called image translation-assisted segmentation in 3D (ITAS3D), which required a complex two-stage procedure and tedious manual optimization of parameters. To simplify this procedure, we use the 3D gland-segmentation masks previously generated by ITAS3D as training datasets for a direct end-to-end deep learning-based segmentation model, nnU-Net. The inputs to this model are 3D pathology datasets of prostate biopsies rapidly stained with an inexpensive fluorescent analog of H&E and the outputs are 3D semantic segmentation masks of the gland epithelium, gland lumen, and surrounding stromal compartments within the tissue.ResultsnnU-Net demonstrates remarkable accuracy in 3D gland segmentations even with limited training data. Moreover, compared with the previous ITAS3D pipeline, nnU-Net operation is simpler and faster, and it can maintain good accuracy even with lower-resolution inputs.ConclusionsOur trained DL-based 3D segmentation model will facilitate future studies to demonstrate the value of computational 3D pathology for guiding critical treatment decisions for patients with prostate cancer.

DOWNLOAD PAPER

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years