Histopathological image analysis of stained tissue slides is routinely used in tumor detection and classification. However, diagnosis requires a highly trained pathologist and can thus be time-consuming, labor-intensive, and potentially risk bias. Here, we demonstrate a potential complementary approach for diagnosis. We show that multiphoton microscopy images from unstained, reproductive tissues can be robustly classified using deep learning techniques. We fine-train four pretrained convolutional neural networks using over 200 murine tissue images based on combined second-harmonic generation and two-photon excitation fluorescence contrast, to classify the tissues either as healthy or associated with high-grade serous carcinoma with over 95% sensitivity and 97% specificity. Our approach shows promise for applications involving automated disease diagnosis. It could also be readily applied to other tissues, diseases, and related classification problems.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1117/1.JBO.23.6.066002 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Endothelialization of coronary stents after intra-luminal adenoviral VEGF-A gene transfer in a preclinical porcine restenosis model - Studies with optical coherence tomography, angioscopy, multiphoton and scanning electron microscopy.
J Mol Cell Cardiol
December 2024
A.I.Virtanen Institute for Molecular Sciences, University of Eastern Finland, Kuopio, Finland; Heart Centre and Gene Therapy Unit, Kuopio University Hospital, Kuopio, Finland. Electronic address:
Background: Coronary stenting operations have become the main option for the treatment of coronary heart disease. Vessel recovery after stenting has emerged as a critical factor in reducing possible complications. In this study, we evaluated the feasibility, safety and efficacy of locally administered intraluminal gene therapy delivered using a specialized infusion balloon catheter.
View Article and Find Full Text PDFMultiphoton and Harmonic Imaging of Microarchitected Materials.
ACS Appl Mater Interfaces
January 2025
Laser Thermal Laboratory, Department of Mechanical Engineering, University of California, Berkeley, California 94720, United States.
Article Synopsis
- Microadditive manufacturing enables the creation of intricate nano- and microscale components, leading to advancements in various industries.
- This research explores two-photon and three-photon fluorescence imaging, along with third-harmonic generation microscopy, to analyze complex lattice structures produced by multiphoton lithography.
- The study reveals that multiphoton fluorescence imaging provides better depth penetration and nondestructive identification of internal modifications and defects, improving quality control in microadditively manufactured products.
Deep learning-based aberration compensation improves contrast and resolution in fluorescence microscopy.
Nat Commun
January 2025
Laboratory of High Resolution Optical Imaging, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, Bethesda, Maryland, USA.
Optical aberrations hinder fluorescence microscopy of thick samples, reducing image signal, contrast, and resolution. Here we introduce a deep learning-based strategy for aberration compensation, improving image quality without slowing image acquisition, applying additional dose, or introducing more optics. Our method (i) introduces synthetic aberrations to images acquired on the shallow side of image stacks, making them resemble those acquired deeper into the volume and (ii) trains neural networks to reverse the effect of these aberrations.
View Article and Find Full Text PDFQuantitative Histopathology Analysis Based on Label-free Multiphoton Imaging for Breast Cancer Diagnosis and Neoadjuvant Immunotherapy Response Assessment.
Int J Biol Sci
January 2025
Department of Medical Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China.
Accurate diagnosis and assessment of breast cancer treatment responses are critical challenges in clinical practice, influencing patient treatment strategies and ultimately long-term prognosis. Currently, diagnosing breast cancer and evaluating the efficacy of neoadjuvant immunotherapy (NAIT) primarily rely on pathological identification of tumor cell morphology, count, and arrangement. However, when tumors are small, the tumors and tumor beds are difficult to detect; relying solely on tumor cell identification may lead to false negatives.
View Article and Find Full Text PDFA domed window chamber for multi-modality optical imaging.
Biotechniques
January 2025
Biomedical Engineering, The University of Arizona, Tucson, AZ, USA.
Current dorsal skin flap window chambers with flat glass windows are compatible with optical coherence tomography (OCT) and multiphoton microscopy (MPM) imaging. However, light sheet fluorescence microscopy (LSFM) performs best with a cylindrical or spherical sample located between its two 90° objectives and when all sample materials have the same index of refraction (). A modified window chamber with a domed viewing window made from fluorinated ethylene propylene (FEP), with n similar to water and tissue, was designed.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!