SignificanceLabel-free, two-photon excited fluorescence (TPEF) imaging captures morphological and functional metabolic tissue changes and enables enhanced understanding of numerous diseases. However, noise and other artifacts present in these images severely complicate the extraction of biologically useful information.AimWe aim to employ deep neural architectures in the synthesis of a multiscale denoising algorithm optimized for restoring metrics of metabolic activity from low-signal-to-noise ratio (SNR), TPEF images.ApproachTPEF images of reduced nicotinamide adenine dinucleotide (phosphate) (NAD(P)H) and flavoproteins (FAD) from freshly excised human cervical tissues are used to assess the impact of various denoising models, preprocessing methods, and data on metrics of image quality and the recovery of six metrics of metabolic function from the images relative to ground truth images.ResultsOptimized recovery of the redox ratio and mitochondrial organization is achieved using a novel algorithm based on deep denoising in the wavelet transform domain. This algorithm also leads to significant improvements in peak-SNR (PSNR) and structural similarity index measure (SSIM) for all images. Interestingly, other models yield even higher PSNR and SSIM improvements, but they are not optimal for recovery of metabolic function metrics.ConclusionsDenoising algorithms can recover diagnostically useful information from low SNR label-free TPEF images and will be useful for the clinical translation of such imaging.
Multi-photon excited intensity and lifetime fluorescence images relying on endogenous contrast can be analyzed to quantify contributions from key metabolic co-enzymes and associated metabolic function and mitochondrial organization metrics. The high spatio-temporal resolution and context of these non-destructive measurements can be used to provide important insights related to a wide range of samples, conditions and disease models. Corresponding images are acquired from mitochondria, engineered tissues, excised and in vivo human tissues. Recent studies highlight the value of multi-parametric, label-free, metabolic assessments to improve our understanding of traumatic brain injury, (pre)cancer development, and vitiligo lesions.
The potential to differentiate between diseased and healthy tissue has been demonstrated through the extraction of morphological and functional metrics from label-free, two-photon images. Acquiring such images as fast as possible without compromising their diagnostic and functional content is critical for clinical translation of two-photon imaging. Computational restoration methods have demonstrated impressive recovery of image quality and important biological information. However, access to large clinical datasets has hampered advancement of denoising algorithms. Here, we seek to demonstrate the application of denoising algorithms on depth-resolved two-photon excited fluorescence (TPEF) images with specific focus on recovery of functional metabolic metrics. Datasets were generated through the collection of images of reduced nicotinamide adenine dinucleotide (phosphate) (NAD(P)H) and flavoproteins from freshly excised rat cheek epithelium. Image datasets were patched across depth, generating 1012, 256-by-256 patches. A well-known U-net architecture was trained on 6628 low-signal-to-noise-ratio (SNR) patches from a previously collected large dataset and later retrained on a smaller 620 low-SNR patches dataset before being validated and evaluated on 88 and 304 low-SNR patches, respectively, using a structural similarity index measure (SSIM) loss function. We demonstrate models trained on larger datasets of human cervical tissue could be used to successfully restore metabolic metrics with an improvement in image quality when applied to rat cheek epithelium images. These results motivate further exploration of weight transfer for denoising of small clinical two-photon microscopy datasets.
Fiber endoscopes capable of making two-photon (2P) autofluorescence measurements, time-resolved fluorescence decay measurements, and collagen second harmonic generation (SHG) measurements have been applied to animal models. Clinical translation of such devices to internal human organs has the potential to overhaul conventional methods of disease diagnosis and monitoring. Previous work by our lab has established the potential to diagnose high-grade cervical precancers using 2P autofluorescence measurements. Other groups have demonstrated that 2P-based fluorescence lifetime imaging microscopy (FLIM) measurements of nicotinamide adenine dinucleotide (phosphate) (NAD(P)H) and collagen SHG measurements have the potential to discriminate between cancerous and benign tissues. In this work, we demonstrate the potential to discern high-grade cervical precancerous lesions (HSILs) from benign tissues using fluorescence intensity measurements of NAD(P)H and oxidized flavoproteins, FLIM NAD(P)H measurements, and collagen SHG measurements. Consistent with previous results, benign tissues demonstrated increased depth-dependent heterogeneity in mitochondrial clustering, and increased overall and intrafield heterogeneity of oxido-reductive state relative to HSILs. FLIM phasor analysis demonstrated a relative decrease in NAD(P)H short and long lifetime, and a relative increase in NAD(P)H bound fraction for benign tissues compared to HSILs. Collagen SHG intensity in benign tissues was greater than that of HSIL tissues, along with overall intrafield variations in collagen fiber orientation. This work motivates the functionalization of a clinical 2P fiber endoscope capable of making SHG, autofluorescence intensity and lifetime measurements of metabolic coenzymes in the human cervix.
The World Health Organization (WHO) called for a global fight against cervical cancer. There are an estimated 569,000 new cases and 310,000 deaths annually. Searching for practical approaches to deal with cervical cancer screening and treatment has been an urgent research subject. One solution could be to use label-free two-photon excited fluorescence (TPEF) imaging to address this need. The colposcopy-guided biopsy method is being used for cervical precancer detection relying primarily on morphological and organization cell and tissue feature changes. However, the overall performance of colposcopy and biopsy remains unsatisfactory. Label-free TPEF provides images with high morphological and functional (metabolic) content and could lead to enhanced detection of cervical pre-cancers. This paper uses the cell texture and morphology features to classify stacks of such TPEF images acquired from freshly excised healthy and pre-cancerous human cervical tissues. Herein, an automated denoising algorithm and a parametrized edge enhancement method is used for pre-processing the images in the stack. The computer simulations performed on the privately available dataset of 10 healthy stacks, 53 precancer stacks, and the recall and specificity of 100 %, respectively, were observed for both texture and morphology features. However, the dataset used to acquire these results is small. The presented model can be used as a base model for further research and analysis of a larger data set to identify early cervical cancerous changes and potentially significantly improve diagnosis and treatment.
KEYWORDS: Image restoration, Tissues, Signal to noise ratio, In vivo imaging, Biopsy, Two photon imaging, Microscopy, Luminescence, Imaging systems, Image quality
High signal-to-noise ratio (SNR) images are necessary for analyzing sub-cellular features in biomedical images. Acquisition of such images may be limited by temporal or photon-budget-based imaging constraints. This study aims to use deep-learning-based image restoration methods to extract morpho-functional information from low-SNR, depth-resolved, label-free, two-photon images of human cervical tissue. A deep convolutional autoencoder model was trained using single-frame image inputs and multiple-frame averaged ground-truth image pairs. Automated analysis of restored reduced nicotinamide adenine dinucleotide (NADH) and flavin adenine dinucleotide (FAD) two-photon excitation fluorescence (TPEF) images extracts depth-dependent, morpho-functional information otherwise lost in single-frame images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.