Aims: Increasing the sectioning rate for breast sentinel lymph nodes can increase the likelihood of detecting micrometastases. To make serial sectioning feasible, we have developed an algorithm for computer-assisted detection (CAD) with digitized lymph node sections.
Methods And Results: K-means clustering assigned image pixels to one of four areas in a colourspace (representing tumour, unstained background, counterstained background and microtomy artefacts). Four filters then removed 'false-positive' pixels from the tumour cluster. A set of 43 sections containing tumour (a total of 259 foci) and 59 sections negative for malignancy was defined by two pathologists, using light microscopy, and CAD was applied. For the clinically relevant task of identifying the largest focus in each section (micrometastasis in 22/43 sections), the sensitivity and specificity were 100%. Isolated tumour cells (ITCs) were identified in one slide initially considered to be negative. Identification of all 259 foci yielded sensitivities of 57.5% for ITCs (<0.200 mm), 89.5% for micrometastases, and 100% for larger metastases, with one false-positive. Reduced sensitivity was ascribed to variable staining. Nine additional metastases (<0.01-0.3 mm) that were not initially identified were detected by CAD.
Conclusions: This algorithm is well suited to the task of sentinel lymph node evaluation and may enhance the detection of occult micrometastases.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1111/j.1365-2559.2011.03896.x | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Validation of a novel tool for automated tooth modelling by fusion of CBCT-derived roots with the respective IOS-derived crowns.
J Dent
December 2024
OMFS-IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven, Leuven, Belgium; Department of Dental Medicine, Karolinska Institute, Stockholm, Sweden. Electronic address:
Objectives: To validate a novel artificial intelligence (AI)-based tool for automated tooth modelling by fusing cone beam computed tomography (CBCT)-derived roots with corresponding intraoral scanner (IOS)-derived crowns.
Methods: A retrospective dataset of 30 patients, comprising 30 CBCT scans and 55 IOS dental arches, was used to evaluate the fusion model at full arch and single tooth levels. AI-fused models were compared with CBCT tooth segmentation using point-to-point surface distances-reported as median surface distance (MSD), root mean square distance (RMSD), and Hausdorff distance (HD)- alongside visual assessments.
Deep learning-enabled filter-free fluorescence microscope.
Sci Adv
January 2025
Engineering Research Center of Optical Instrument and System, the Ministry of Education, Shanghai Key Laboratory of Modern Optical System, University of Shanghai for Science and Technology, Shanghai 200093, China.
Optical filtering is an indispensable part of fluorescence microscopy for selectively highlighting molecules labeled with a specific fluorophore and suppressing background noise. However, the utilization of optical filtering sets increases the complexity, size, and cost of microscopic systems, making them less suitable for multifluorescence channel, high-speed imaging. Here, we present filter-free fluorescence microscopic imaging enabled with deep learning-based digital spectral filtering.
View Article and Find Full Text PDFAdaptive deep feature representation learning for cross-subject EEG decoding.
BMC Bioinformatics
December 2024
College of Computer and Information Engineering/College of Artificial Intelligence, Nanjing Tech University, Nanjing, 210093, China.
Background: The collection of substantial amounts of electroencephalogram (EEG) data is typically time-consuming and labor-intensive, which adversely impacts the development of decoding models with strong generalizability, particularly when the available data is limited. Utilizing sufficient EEG data from other subjects to aid in modeling the target subject presents a potential solution, commonly referred to as domain adaptation. Most current domain adaptation techniques for EEG decoding primarily focus on learning shared feature representations through domain alignment strategies.
View Article and Find Full Text PDFEnhanced heart sound classification using Mel frequency cepstral coefficients and comparative analysis of single vs. ensemble classifier strategies.
PLoS One
December 2024
Future Technology Research Center, National Yunlin University of Science and Technology, Yunlin, Taiwan.
This paper seeks to enhance the performance of Mel Frequency Cepstral Coefficients (MFCCs) for detecting abnormal heart sounds. Heart sounds are first pre-processed to remove noise and then segmented into S1, systole, S2, and diastole intervals, with thirteen MFCCs estimated from each segment, yielding 52 MFCCs per beat. Finally, MFCCs are used for heart sound classification.
View Article and Find Full Text PDFA data-driven approach to establishing cell motility patterns as predictors of macrophage subtypes and their relation to cell morphology.
PLoS One
December 2024
Department of Applied Mathematics, University of California, Santa Cruz, Santa Cruz, CA, United States of America.
The motility of macrophages in response to microenvironment stimuli is a hallmark of innate immunity, where macrophages play pro-inflammatory or pro-reparatory roles depending on their activation status during wound healing. Cell size and shape have been informative in defining macrophage subtypes. Studies show pro and anti-inflammatory macrophages exhibit distinct migratory behaviors, in vitro, in 3D and in vivo but this link has not been rigorously studied.
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!