H&amp;E-like staining of OCT images of human skin via generative adversarial network

Tsai, Sheng-Ting; Liu, Chih-Hao; Chan, Chin-Cheng; Li, Yi-Hsin; Huang, Sheng‐Lung; Chen, Homer H.

doi:10.1063/5.0122965

Cited by 9 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, future studies are warranted using a large sample size (including benign lesions) and performing a multi-reader diagnostic accuracy study. Furthermore, deep learning algorithms can be integrated to convert grayscale images into digitally colored purple and pink images 27 , similar to the images created by an ex vivo confocal microscope. This would improve visualization of the OCT images and reduce the learning curve .…”

Section: Discussionmentioning

confidence: 99%

High‐resolution full‐field optical coherence tomography microscope for the evaluation of freshly excised skin specimens during Mohs surgery: A feasibility study

Jain,

Chang,

Singh

et al. 2023

Journal of Biophotonics

Self Cite

View full text Add to dashboard Cite

Histopathology for tumor margin assessment is time‐consuming and expensive. High‐resolution full‐field optical coherence tomography (FF‐OCT) images fresh tissues rapidly at cellular resolution and potentially facilitates evaluation. Here, we define FF‐OCT features of normal and neoplastic skin lesions in fresh ex vivo tissues and assess its diagnostic accuracy for malignancies. For this, normal and neoplastic tissues were obtained from Mohs surgery, imaged using FF‐OCT, and their features were described. Two expert OCT readers conducted a blinded analysis to evaluate their diagnostic accuracies, using histopathology as the ground truth. A convolutional neural network was built to distinguish and outline normal structures and tumors. Of the 113 tissues imaged, 95 (84%) had a tumor (75 basal cell carcinomas [BCCs] and 17 squamous cell carcinomas [SCCs]). The average reader diagnostic accuracy was 88.1%, with a sensitivity of 93.7%, and a specificity of 58.3%. The artificial intelligence (AI) model achieved a diagnostic accuracy of 87.6 ± 5.9%, sensitivity of 93.2 ± 2.1%, and specificity of 81.2 ± 9.2%. A mean intersection‐over‐union of 60.3 ± 10.1% was achieved when delineating the nodular BCC from normal structures. Limitation of the study was the small sample size for all tumors, especially SCCs. However, based on our preliminary results, we envision FF‐OCT to rapidly image fresh tissues, facilitating surgical margin assessment. AI algorithms can aid in automated tumor detection, enabling widespread adoption of this technique.

show abstract

Section: Discussionmentioning

confidence: 99%

High‐resolution full‐field optical coherence tomography microscope for the evaluation of freshly excised skin specimens during Mohs surgery: A feasibility study

Jain,

Chang,

Singh

et al. 2023

Journal of Biophotonics

Self Cite

View full text Add to dashboard Cite

show abstract

“…It can't enhance the hardware resolution. In these years, many groups have leveraged the power of deep learning in OCT image processing, such as layer segmentation of the retina [9], classification of lesions [10], image-to-image translation [11], and high-resolution (HR) image reconstruction [12,13]. They have all presented promising results.…”

Section: Introductionmentioning

confidence: 99%

Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks

Chueh,

Chen,

et al. 2023

Optical Coherence Imaging Techniques and Imaging in Scattering Media V

View full text Add to dashboard Cite

Optical coherence tomography (OCT) has been widely used in many clinical apartments. The trade-off between field-ofview (FOV) and transverse resolution has always become critical. High-resolution (HR) image reconstruction of OCT has the potential to increase the resolution without reducing the FOV. Although it has been widely explored in these years, it is hard to find one-to-one paired high-resolution for reference. The SR methods are used to improve the cross-sectional OCT image only. Therefore, we build a custom-design, wide field-of-view (FOV), multi-scale optical coherence tomography that can allow us to produce excellent high-and low-resolution one-to-one mapping volumetric data set. With the SR methods, we can reduce the acquisition of synthetic high-resolution volumetric images by up to four times.

show abstract

“…CycleGAN is an unsupervised training model which, unlike the other supervised methods, can convert images from the FCM domain into H&E without requiring paired data [27]. This unsupervised method has the potential to restructure the clinical work ow in histopathology and can bene t from various imaging modalities, such as nonlinear microscopy [8], holographic microscopy [28], and optical coherence tomography [29]. It has the potential to provide a computational alternative to the standard practice of histological preparation and staining of tissue samples.…”

mentioning

confidence: 99%

Cycle-consistent Generative Adversarial Network for computational hematoxylin-and-eosin staining of fluorescence confocal microscopic images of basal cell carcinoma tissue

Bagheri

Ghanadan

Daneshpazhooh

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Histopathology based on Hematoxylin-and-Eosin (H&E) staining is the gold standard for basal cell carcinoma (BCC) diagnosis but requires lengthy and laborious tissue preparation. Fluorescence confocal microscopy (FCM) enables fluorescence detection and high-resolution imaging in less time and with minimal tissue preparation. This work proposes a deep learning model for the computational staining of FCM images based on an unsupervised approach, which correlates color with H&E images. Methods In this study, we investigated the utility of FCM on BCC tissue sections stained with Acridine Orange (AO) and computationally colored to simulate H&E dyes. We adopted Cycle-consistent Generative Adversarial Network (CycleGAN), an unsupervised framework, for computational staining. The dataset consists of unpaired and unannotated thousands of FCM and H&E patches from whole slide images of BCC tissue sections. CycleGAN includes two forward and backward GANs that are coupled together and complete a cycle to ensure a reliable transformation between the two domains. In addition to the adversarial and cycle consistency constraints, a saliency constraint was employed to enhance the correct mapping direction between FCM and H&E images and avoid appearance distortions of the image content. Results The generated H&E-like images from FCM through this CycleGAN model were visually and quantitatively similar to real H&E images. Computationally stained images had skin tissue characteristics. The trained models showed a high performance in the structure preservation of the original image when comparing the source and reconstructed images. Quantitative metrics (by Fréchet Inception Distance) showed that CycleGAN could improve the similarity of training images by up to 63% after mapping images from a source domain to a target domain. Conclusion FCM could expand the application and usefulness of rapid tissue analysis. Thus, using the CycleGAN model for computational staining is beneficial for diagnostic applications while simplifying laboratory staining procedures. The proposed approach has significant potential in clinical computational staining and advanced computer-aided histology image analysis.

show abstract

H&E-like staining of OCT images of human skin via generative adversarial network

Cited by 9 publications

References 29 publications

High‐resolution full‐field optical coherence tomography microscope for the evaluation of freshly excised skin specimens during Mohs surgery: A feasibility study

High‐resolution full‐field optical coherence tomography microscope for the evaluation of freshly excised skin specimens during Mohs surgery: A feasibility study

Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks

Cycle-consistent Generative Adversarial Network for computational hematoxylin-and-eosin staining of fluorescence confocal microscopic images of basal cell carcinoma tissue

Contact Info

Product

Resources

About