Automatic detection of head and neck squamous cell carcinoma on pathologic slides using polarized hyperspectral imaging and machine learning

Zhou, Ximing; Ma, Ling; Brown, William; Little, James V.; Chen, Amy Y.; Myers, Larry L.; Sumer, Baran D.; Fei, Baowei

doi:10.1117/12.2582330

Cited by 23 publications

(28 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…45,46 We will look into these components and investigate how HSI can facilitate their pathology analysis. Moreover, by combining HSI with other imaging modalities such as autofluorescence 45 and polarized light imaging, 47,48 more features that the human eye cannot directly see in the H&E stained slides, might be revealed.…”

Section: Discussionmentioning

confidence: 99%

Automatic detection of head and neck squamous cell carcinoma on histologic slides using hyperspectral microscopic imaging

Little

Chen

et al. 2022

J. Biomed. Opt.

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Automatic detection of head and neck squamous cell carcinoma on histologic slides using hyperspectral microscopic imaging

Little

Chen

et al. 2022

J. Biomed. Opt.

View full text Add to dashboard Cite

“…Studies have proven the usefulness of HSI in microscopy applications. 3 – 15 One of the promising applications for this technology is employing HSI for whole-slide imaging (WSI) to aid the histopathological cancer detection of tissue samples because HSI not only provides a reproducible and quantitative diagnosis of the slides but also improves the classification results compared with RGB. 3 , 5 Although various steps such as fixation and embedding during the preparation of the histological samples may alter a few tissue features, such as the texture and the water content, lots of important molecules such as proteins are preserved in the tissue slides.…”

Section: Introductionmentioning

confidence: 99%

“… 3 , 5 Although various steps such as fixation and embedding during the preparation of the histological samples may alter a few tissue features, such as the texture and the water content, lots of important molecules such as proteins are preserved in the tissue slides. The light absorption, scattering, and autofluorescence of these molecular components all contribute to the spectral characteristics in hyperspectral histologic images, 6 , 16 which provide a different perspective from the traditional gross-level reflectance HSI. Even for the dyes, HSI can expand the three-channel color information into a much wider spectral dimension, which might increase the discriminability.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised super-resolution reconstruction of hyperspectral histology images for whole-slide imaging

Rathgeb

Mubarak

et al. 2022

J. Biomed. Opt.

Self Cite

View full text Add to dashboard Cite

. Significance: Hyperspectral imaging (HSI) provides rich spectral information for improved histopathological cancer detection. However, acquiring high-resolution HSI data for whole-slide imaging (WSI) can be time-consuming and requires a huge amount of storage space. Aim: WSI using a color camera can be achieved with fast speed, high image resolution, and excellent image quality due to the established techniques. We aim to develop an RGB-guided unsupervised hyperspectral super-resolution reconstruction method that is hypothesized to improve image quality while maintaining the spectral characteristics. Approach: High-resolution hyperspectral images of 32 histologic slides were obtained via automated WSI. High-resolution RGB histology images were registered to the hyperspectral images for RGB guidance. An unsupervised super-resolution network was trained to take the downsampled low-resolution hyperspectral patches (LR-HSI) and high-resolution RGB patches (HR-RGB) as inputs to reconstruct high-resolution hyperspectral patches (HR-HSI). Then, an Inception-based network was trained with the HR-RGB, original HR-HSI, and generated HR-HSI, respectively, for whole-slide histopathological cancer detection. Results: Our super-resolution reconstruction network generated high-resolution hyperspectral images with well-maintained spectral characteristics and improved image quality. Image classification using the original hyperspectral data outperformed RGB because of the extra spectral information. The generated hyperspectral image patches further improved the results. Conclusions: The proposed method potentially reduces image acquisition time, saves storage space without compromising image quality, and improves the image classification performance.

show abstract

“…The highest accuracy was reached using SVM. 22 In the study by He et al, a method for diagnosing laryngeal SCC was tested. A pool of 3458 pathological images were taken from 1228 patients underwent AI-aided endoscopy of the upper aerodigestive tract to look for suspicious laryngeal lesions that were biopsied and histologically examined.…”

Section: Resultsmentioning

confidence: 99%

Artificial intelligence in head and neck cancer diagnosis

Bassani

Nicola

Eccher³

et al. 2022

Journal of Pathology Informatics

View full text Add to dashboard Cite

Automatic detection of head and neck squamous cell carcinoma on pathologic slides using polarized hyperspectral imaging and machine learning

Cited by 23 publications

References 0 publications

Automatic detection of head and neck squamous cell carcinoma on histologic slides using hyperspectral microscopic imaging

Automatic detection of head and neck squamous cell carcinoma on histologic slides using hyperspectral microscopic imaging

Unsupervised super-resolution reconstruction of hyperspectral histology images for whole-slide imaging

Artificial intelligence in head and neck cancer diagnosis

Contact Info

Product

Resources

About