Label-free colorectal cancer screening using deep learning and spatial light interference microscopy (SLIM).

@article{Zhang2020LabelfreeCC,
  title={Label-free colorectal cancer screening using deep learning and spatial light interference microscopy (SLIM).},
  author={Jingfang K. Zhang and Yuchen R. He and Nahil Atef Sobh and Gabriel Alexandru Popescu},
  journal={APL photonics},
  year={2020},
  volume={5 4}
}
Current pathology workflow involves staining of thin tissue slices, which otherwise would be transparent, followed by manual investigation under the microscope by a trained pathologist. While the hematoxylin and eosin (H&E) stain is well-established and a cost-effective method for visualizing histology slides, its color variability across preparations and subjectivity across clinicians remain unaddressed challenges. To mitigate these challenges, recently we have demonstrated that spatial light… 

Figures from this paper

Automatic Colorectal Cancer Screening Using Deep Learning in Spatial Light Interference Microscopy Data
TLDR
A mask R-CNN deep learning algorithm is applied to the SLIM data to achieve an automated colorectal cancer screening procedure, i.e., classifying normal vs. cancerous specimens, resulting in results that reduce human bias and make imaging data comparable across instruments and clinics.
Automatic colorectal cancer screening using deep-learning on spatial light interference microscopy data
TLDR
This work applied spatial light interference microscopy (SLIM), a label-free method that generates contrast based on the intrinsic tissue refractive index signatures to achieve an automated colorectal cancer screening procedure, i.e., classifying normal vs. cancer specimens.
Label-free imaging of collagen fibers in tissue slices using phase imaging with computational specificity
TLDR
A multimodal imaging instrument that yields both Spatial light Inference Microscopy (SLIM) and polarized light microscopy (PLM) images from the same field of view and results indicate that the distributions of collagen fiber orientation, length, and straightness reported by PICS closely match the ones from ground truth as defined by KL-divergence.
Stain-free nucleus identification in holographic learning flow cyto-tomography
TLDR
A novel computational segmentation method based on statistical inference that bridges the gap between the specificity of Fluorescence Microscopy and the label-free property of QPI techniques to identify the cell nucleus and it is demonstrated that the nucleus-like regions can be accurately distinguished within the stain-free tomograms.
Label-Free White Blood Cell Classification Using Refractive Index Tomography and Deep Learning
TLDR
A rapid and accurate blood cell identification method exploiting deep learning and label-free refractive index (RI) tomography is proposed, providing cost-effective and rapid diagnosis for hematologic malignancy.
Deep learning virtual Zernike phase contrast imaging for singlet microscopy
Singlet microscopy is very attractive for the development of cost-effective and portable microscopes. In contrast to conventional microscope objectives, which consist of multiple lenses, the
Label-free screening of brain tissue myelin content using phase imaging with computational specificity (PICS)
TLDR
This work used spatial light interference microcopy (SLIM), a highly sensitive quantitative phase imaging technique, to correlate the dry mass content of myelin in piglet brain tissue with dietary changes and gestational size, and combined SLIM micrographs with an AI classifying model that allows us to discern subtle disparities in myelin distributions with high accuracy.
Single-cell cytometry via multiplexed fluorescence prediction by label-free reflectance microscopy
TLDR
A label-free technique that alleviates the physical staining and provides highly multiplexed readouts via a deep learning-augmented digital labeling method that can dramatically improve the throughput for imaging cytometry toward applications for phenotyping, pathology, and high-content screening.
Label-free bone marrow white blood cell classification using refractive index tomograms and deep learning
TLDR
A label-free bone marrow white blood cell classification framework that captures the three-dimensional (3D) refractive index (RI) distributions of individual cells and analyzes with deep learning, thereby providing cost-effective and rapid diagnosis of hematologic malignancy.
Label-free screening of brain tissue myelin content using phase imaging with computational specificity (PICS)
TLDR
This work used spatial light interference microcopy (SLIM), a highly sensitive quantitative phase imaging technique, to correlate the dry mass content of myelin in piglet brain tissue with dietary changes and gestational size, and combined SLIM micrographs with an artificial intelligence (AI) classifying model that allows us to discern subtle disparities in myelin distributions with high accuracy.
...
1
2
3
...

References

SHOWING 1-10 OF 37 REFERENCES
Label-free tissue scanner for colorectal cancer screening
TLDR
A label-free tissue scanner based on “quantitative phase imaging,” which maps out optical path length at each point in the field of view and yields images that are sensitive to the “nanoscale” tissue architecture is developed, which provides unique capabilities for quantitative diagnosis and automation.
Label-free quantitative evaluation of breast tissue using Spatial Light Interference Microscopy (SLIM)
TLDR
By extracting tissue markers of malignancy based on the nanostructure revealed by the optical path-length, the method provides an objective, label-free and potentially automatable method for breast histopathology.
PhaseStain: the digital staining of label-free quantitative phase microscopy images using deep learning
TLDR
Using a deep neural network, a digital staining technique is demonstrated to transform the quantitative phase images (QPI) of label-free tissue sections into images that are equivalent to the brightfield microscopy images of the same samples that are histologically stained.
Virtual histological staining of unlabelled tissue-autofluorescence images via deep learning
TLDR
It is shown that a convolutional neural network trained using a generative adversarial-network model can transform wide-field autofluorescence images of unlabelled tissue sections into images that are equivalent to the bright-field images of histologically stained versions of the same samples.
Quantitative Histopathology of Stained Tissues using Color Spatial Light Interference Microscopy (cSLIM)
TLDR
The results on 196 breast cancer patients indicate that cSLIM can provide stain-independent prognostic information from the alignment of collagen fibers in the tumor microenvironment, and these characteristics are likely to reduce barriers to clinical translation for the new c SLIM technology.
Quantitative phase imaging for medical diagnosis
TLDR
This paper focuses on the areas of hematological diagnosis and cancer pathology, which are the areas where most significant advances have been made to date by QPI techniques.
Tissue refractive index as marker of disease.
TLDR
The results show that the tissue refractive index reports on the nanoscale tissue architecture and, in principle, can be used as an intrinsic marker for cancer diagnosis.
Quantifying collagen fiber orientation in breast cancer using quantitative phase imaging
TLDR
It is shown that spatial light interference microscopy (SLIM), a label-free quantitative phase imaging technique, is able to provide information on collagen-fiber orientation that is comparable to that provided by SHGM.
Automatic Gleason grading of prostate cancer using quantitative phase imaging and machine learning
TLDR
This approach will provide a clinically objective and quantitative metric for Gleason grading, allowing us to corroborate results across instruments and laboratories and feed the computer algorithms for improved accuracy.
Early Prediction of Cancer Progression by Depth-Resolved Nanoscale Mapping of Nuclear Architecture from Unstained Tissue Specimens.
TLDR
The findings demonstrate great potential for nanoNAM in predicting cancer progression risk and suggest that further validation in a multicenter study with larger cohorts may eventually advance this method to become a routine clinical test.
...
1
2
3
4
...