98%
921
2 minutes
20
Recent developments in the registration of histology and micro-computed tomography (µCT) have broadened the perspective of pathological applications such as virtual histology based on µCT. This topic remains challenging because of the low image quality of soft tissue CT. Additionally, soft tissue samples usually deform during the histology slide preparation, making it difficult to correlate the structures between the histology slide and µCT. In this work, we propose a novel 2D-3D multi-modal deformable image registration method. The method utilizes an initial global 2D-3D registration using an ML-based differentiable similarity measure. The registration is then finalized by an analytical out-of-plane deformation refinement. The method is evaluated on datasets acquired from tonsil and tumor tissues. µCTs of both phase-contrast and conventional absorption modalities are investigated. The registration results from the proposed method are compared with those from intensity- and keypoint-based methods. The comparison is conducted using both visual and fiducial-based evaluations. The proposed method demonstrates superior performance compared to the other two methods.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12271352 | PMC |
http://dx.doi.org/10.1038/s41598-025-11583-w | DOI Listing |
Foundation models have recently emerged as powerful feature extractors in computational pathology, yet they typically omit mechanisms for leveraging the global spatial structure of tissues and the local contextual relationships among diagnostically relevant regions - key elements for understanding the tumor microenvironment. Multiple instance learning (MIL) remains an essential next step following foundation model, designing a framework to aggregate patch-level features into slide-level predictions. We present EAGLE-Net, a structure-preserving, attention-guided MIL architecture designed to augment prediction and interpretability.
View Article and Find Full Text PDFJCO Precis Oncol
September 2025
Center for Immuno-Oncology, Dana-Farber Cancer Institute, Boston, MA.
Purpose: Retrospective studies have found associations between the number of intratumoral immune cells and patient outcomes for specific cancers treated with targeted therapies. However, the clinical value of routinely quantifying intratumoral immune biomarkers using a digital pathology platform in the pan-cancer setting within an active clinical laboratory has not been established.
Methods: We developed ImmunoProfile, a daily clinical workflow that integrates automated multiplex immunofluorescence tissue staining, digital slide imaging, and machine learning-assisted scoring to quantify intratumoral CD8, PD-1, CD8PD-1, and FOXP3 immune cells and PD-L1 expression in formalin-fixed, paraffin-embedded tissue samples in a standardized and reproducible manner.
Interdiscip Sci
September 2025
School of Big Data and Software Engineering, Chongqing University, Chongqing, 400044, China.
Recent advancements in spatial transcriptomics (ST) have revolutionized our ability to simultaneously profile gene expression, spatial location, and tissue morphology, enabling the precise mapping of cell types and signaling pathways within their native tissue context. However, the high cost of sequencing remains a significant barrier to its widespread adoption. Although existing methods often leverage histopathological images to predict transcriptomic profiles and identify cellular heterogeneity, few approaches directly estimate cell-type abundance from these images.
View Article and Find Full Text PDFJ Allergy Clin Immunol
September 2025
Department of Otolaryngology, the Seventh Affiliated Hospital of Sun Yat-sen University, Shenzhen 518107, China. Electronic address:
Background: Chronic Rhinosinusitis with Nasal Polyps (CRSwNP) is a heterogeneous disorder characterized by diverse inflammatory signatures and endotypes.
Objective: To develop a histology-based deep learning network for predicting inflammatory gene signatures and spatial patterns in CRSwNP.
Methods: We developed HE2Signature, a deep learning model, using 70 H&E-stained whole-slide images (WSIs) of nasal polyps paired with corresponding endotypic signature gene expression profiles derived from transcriptomic data.
PLoS One
September 2025
Department of Electrical Engineering and Mechatronics, Faculty of Engineering, University of Debrecen, Debrecen, Hungary.
Breast cancer is highlighted in recent research as one of the most prevalent types of cancer. Timely identification is essential for enhancing patient results and decreasing fatality rates. Utilizing computer-assisted detection and diagnosis early on may greatly improve the chances of recovery by accurately predicting outcomes and developing suitable treatment plans.
View Article and Find Full Text PDF