We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us
LGC Clinical Diagnostics

Download Mobile App




AI Integrated With Optical Imaging Technology Enables Rapid Intraoperative Diagnosis

By LabMedica International staff writers
Posted on 17 May 2024
Print article
Image: Images of invasive ductal carcinoma, mucinous carcinoma, and papillary carcinoma (Photo courtesy of Science China Press)
Image: Images of invasive ductal carcinoma, mucinous carcinoma, and papillary carcinoma (Photo courtesy of Science China Press)

Rapid and accurate intraoperative diagnosis is essential for tumor surgery as it guides surgical decisions with precision. Traditional intraoperative assessments, such as frozen sections based on H&E histology, are demanding in terms of time, resources, and labor and also raise concerns about specimen consumption. D-FFOCT, a high-resolution optical imaging technology, allows for the quick generation of virtual histology. Researchers have now developed an intraoperative diagnostic workflow that uses deep learning algorithms to classify tumors from D-FFOCT images, offering rapid and automated diagnosis for surgical decision-making.

A prospective cohort study conducted by researchers from Peking University People’s Hospital (Beijing, China) included 224 breast samples imaged using D-FFOCT. This imaging technique is non-destructive and requires no tissue preparation or staining. The D-FFOCT images were segmented into patches, and slides were allocated into a training set (182 slides, 10,357 patches) and an external testing set (42 slides, 3,140 patches) based on the order in which they were collected. A five-fold cross-validation method was employed to train and fine-tune the model. A machine learning model aggregated the patch prediction results to the slide level after feature extraction.

The testing set showed the model performed well at the patch level, identifying breast tissue types with an AUC of 0.926 (95% CI: 0.907–0.943). At the slide level, the diagnostic accuracy reached 97.62%, with a sensitivity of 96.88% and a specificity of 100%. Accuracy did not significantly differ across various molecular subtypes and histologic tumor types of breast cancer. Visualization heatmaps demonstrated that the deep learning models could identify features corresponding to metabolically active cell clusters in D-FFOCT images, aligning with expert assessments. This image analysis approach could potentially extend to various tumor types, given the conserved features detected in the model. In a margin simulation experiment, the diagnosis process took about three minutes, with the deep learning model achieving a high accuracy of 95.24%.

Based on the results, the study has proposed an intraoperative cancer diagnosis workflow integrating D-FFOCT with a deep learning model. In simulated intraoperative margin diagnosis, the workflow substantially reduced diagnosis time by about tenfold compared to traditional methods and proved to be highly cost-effective in terms of labor. No tissue was destroyed during optical imaging and analysis. Overall, this workflow offers a transparent solution for rapid and accurate intraoperative diagnosis, potentially guiding surgical decisions effectively.

Related Links:
Peking University People’s Hospital 

Gold Member
Chagas Disease Test
CHAGAS Cassette
Verification Panels for Assay Development & QC
Seroconversion Panels
New
Silver Member
Total Hemoglobin Monitoring System
GREENCARE Hb
New
H.pylori Test
Humasis H.pylori Card

Print article

Channels

Molecular Diagnostics

view channel
Image: The experimental blood test accurately indicates severity and predicts potential recovery from spinal cord injury (Photo courtesy of 123RF)

Blood Test Identifies Multiple Biomarkers for Rapid Diagnosis of Spinal Cord Injury

The National Institutes of Health estimates that 18,000 individuals in the United States sustain spinal cord injuries (SCIs) annually, resulting in a staggering financial burden of over USD 9.... Read more

Immunology

view channel
Image: The findings were based on patients from the ADAURA clinical trial of the targeted therapy osimertinib for patients with NSCLC with EGFR-activated mutations (Photo courtesy of YSM Multimedia Team)

Post-Treatment Blood Test Could Inform Future Cancer Therapy Decisions

In the ongoing advancement of personalized medicine, a new study has provided evidence supporting the use of a tool that detects cancer-derived molecules in the blood of lung cancer patients years after... Read more

Microbiology

view channel
Image: Schematic representation illustrating the key findings of the study (Photo courtesy of UNIST)

Breakthrough Diagnostic Technology Identifies Bacterial Infections with Almost 100% Accuracy within Three Hours

Rapid and precise identification of pathogenic microbes in patient samples is essential for the effective treatment of acute infectious diseases, such as sepsis. The fluorescence in situ hybridization... Read more

Industry

view channel
Image: Tumor-associated macrophages visualized using the Multiomic LS Assay (Photo courtesy of ACD)

Leica Biosystems and Bio-Techne Expand Spatial Multiomic Collaboration

Bio-Techne Corporation (Minneapolis, MN, USA) has expanded the longstanding partnership between its spatial biology brand, Advanced Cell Diagnostics (ACD, Newark, CA, USA), and Leica Biosystems (Nussloch,... Read more
Copyright © 2000-2025 Globetech Media. All rights reserved.