Deep learning-enabled detection of rare circulating tumor cell clusters in whole blood using label-free, flow cytometry.

Metastatic tumors have poor prognoses for progression-free and overall survival for all cancer patients. Rare circulating tumor cells (CTCs) and rarer circulating tumor cell clusters (CTCCs) are potential biomarkers of metastatic growth, with CTCCs representing an increased risk factor for metastasis. Current detection platforms are optimized for ex vivo detection of CTCs only. Microfluidic chips and size exclusion methods have been proposed for CTCC detection; however, they lack in vivo utility and real-time monitoring capability. Confocal backscatter and fluorescence flow cytometry (BSFC) has been used for label-free detection of CTCCs in whole blood based on machine learning (ML) enabled peak classification. Here, we expand to a deep-learning (DL)-based, peak detection and classification model to detect CTCCs in whole blood data. We demonstrate that DL-based BSFC has a low false alarm rate of 0.78 events per min with a high Pearson correlation coefficient of 0.943 between detected events and expected events. DL-based BSFC of whole blood maintains a detection purity of 72% and a sensitivity of 35.3% for both homotypic and heterotypic CTCCs starting at a minimum size of two cells. We also demonstrate through artificial spiking studies that DL-based BSFC is sensitive to changes in the number of CTCCs present in the samples and does not add variability in detection beyond the expected variability from Poisson statistics. The performance established by DL-based BSFC motivates its use for in vivo detection of CTCCs. Using transfer learning, we additionally validate DL-based BSFC on blood samples from different species and cancer cell types. Further developments of label-free BSFC to enhance throughput could lead to critical applications in the clinical detection of CTCCs and ex vivo isolation of CTCC from whole blood with minimal disruption and processing steps.

Rapid, high-resolution, non-destructive assessments of metabolic and morphological homogeneity uniquely identify high-grade cervical precancerous lesions.

Purpose: Two-photon microscopy (2PM) is an emerging clinical imaging modality with the potential to non-invasively assess tissue metabolism and morphology in high-resolution. This study aimed to assess the translational potential of 2PM for improved detection of high-grade cervical precancerous lesions. Experimental Design: 2P images attributed to reduced nicotinamide adenine dinucleotide (phosphate) (NAD(P)H) and oxidized flavoproteins (FP) were acquired from the full epithelial thickness of freshly excised human cervical tissue biopsies (N = 62). Fifteen biopsies harbored high-grade squamous intraepithelial lesions (HSILs), 14 biopsies harbored low-grade SILs (LSILs), and 33 biopsies were benign. Quadratic discriminant analysis (QDA) leveraged morphological and metabolic functional metrics extracted from these images to predict the presence of HSILs. We performed gene set enrichment analysis (GSEA) using datasets available on the Gene Expression Omnibus (GEO) to validate the presence of metabolic reprogramming in HSILs. Results: Integrating metabolic and morphological 2P-derived metrics from finely sampled, full-thickness epithelia achieved a high 90.8 ± 6.1% sensitivity and 72.3 ± 11.3% specificity of HSIL detection. Notably, sensitivity (91.4 ± 12.0%) and specificity (77.5 ± 12.6%) were maintained when utilizing metrics from only two images at 12- and 72-µm from the tissue surface. Upregulation of glycolysis, fatty acid metabolism, and oxidative phosphorylation in HSIL tissues validated the metabolic reprogramming captured by 2P biomarkers. Conclusion: Label-free 2P images from as few as two epithelial depths enable rapid and robust HSIL detection through the quantitative characterization of metabolic and morphological reprogramming, underscoring the potential of this tool for clinical evaluation of cervical precancers.

Deep Learning-Enabled, Detection of Rare Circulating Tumor Cell Clusters in Whole Blood Using Label-free, Flow Cytometry.

Metastatic tumors have poor prognoses for progression-free and overall survival for all cancer patients. Rare circulating tumor cells (CTCs) and rarer circulating tumor cell clusters (CTCCs) are potential biomarkers of metastatic growth, with CTCCs representing an increased risk factor for metastasis. Current detection platforms are optimized for ex vivo detection of CTCs only. Microfluidic chips and size exclusion methods have been proposed for CTCC detection; however, they lack in vivo utility and real-time monitoring capability. Confocal backscatter and fluorescence flow cytometry (BSFC) has been used for label-free detection of CTCCs in whole blood based on machine learning (ML) enabled peak classification. Here, we expand to a deep-learning (DL) -based, peak detection and classification model to detect CTCCs in whole blood data. We demonstrate that DL-based BSFC has a low false alarm rate of 0.78 events/min with a high Pearson correlation coefficient of 0.943 between detected events and expected events. DL-based BSFC of whole blood maintains a detection purity of 72% and a sensitivity of 35.3% for both homotypic and heterotypic CTCCs starting at a minimum size of two cells. We also demonstrate through artificial spiking studies that DL-based BSFC is sensitive to changes in the number of CTCCs present in the samples and does not add variability in detection beyond the expected variability from Poisson statistics. The performance established by DL-based BSFC motivates its use for in vivo detection of CTCCs. Further developments of label-free BSFC to enhance throughput could lead to critical applications in the clinical detection of CTCCs and ex vivo isolation of CTCC from whole blood with minimal disruption and processing steps.

Restoration of metabolic functional metrics from label-free, two-photon cervical tissue images using multiscale deep-learning-based denoising algorithms.

Label-free, two-photon imaging captures morphological and functional metabolic tissue changes and enables enhanced understanding of numerous diseases. However, this modality suffers from low signal arising from limitations imposed by the maximum permissible dose of illumination and the need for rapid image acquisition to avoid motion artifacts. Recently, deep learning methods have been developed to facilitate the extraction of quantitative information from such images. Here, we employ deep neural architectures in the synthesis of a multiscale denoising algorithm optimized for restoring metrics of metabolic activity from low-SNR, two-photon images. Two-photon excited fluorescence (TPEF) images of reduced nicotinamide adenine dinucleotide (phosphate) (NAD(P)H) and flavoproteins (FAD) from freshly excised human cervical tissues are used. We assess the impact of the specific denoising model, loss function, data transformation, and training dataset on established metrics of image restoration when comparing denoised single frame images with corresponding six frame averages, considered as the ground truth. We further assess the restoration accuracy of six metrics of metabolic function from the denoised images relative to ground truth images. Using a novel algorithm based on deep denoising in the wavelet transform domain, we demonstrate optimal recovery of metabolic function metrics. Our results highlight the promise of denoising algorithms to recover diagnostically useful information from low SNR label-free two-photon images and their potential importance in the clinical translation of such imaging.

Restoration of metabolic functional metrics from label-free, two-photon human tissue images using multiscale deep-learning-based denoising algorithms.

Significance: Label-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. Aim: We 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. Approach: TPEF 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. Results: Optimized 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. Conclusions: Denoising algorithms can recover diagnostically useful information from low SNR label-free TPEF images and will be useful for the clinical translation of such imaging.

Label-free flow cytometry of rare circulating tumor cell clusters in whole blood.

Circulating tumor cell clusters (CTCCs) are rare cellular events found in the blood stream of metastatic tumor patients. Despite their scarcity, they represent an increased risk for metastasis. Label-free detection methods of these events remain primarily limited to in vitro microfluidic platforms. Here, we expand on the use of confocal backscatter and fluorescence flow cytometry (BSFC) for label-free detection of CTCCs in whole blood using machine learning for peak detection/classification. BSFC uses a custom-built flow cytometer with three excitation wavelengths (405 nm, 488 nm, and 633 nm) and five detectors to detect CTCCs in whole blood based on corresponding scattering and fluorescence signals. In this study, detection of CTCC-associated GFP fluorescence is used as the ground truth to assess the accuracy of endogenous back-scattered light-based CTCC detection in whole blood. Using a machine learning model for peak detection/classification, we demonstrated that the combined use of backscattered signals at the three wavelengths enable detection of ~ 93% of all CTCCs larger than two cells with a purity of > 82% and an overall accuracy of > 95%. The high level of performance established through BSFC and machine learning demonstrates the potential for label-free detection and monitoring of CTCCs in whole blood. Further developments of label-free BSFC to enhance throughput could lead to important applications in the isolation of CTCCs in whole blood with minimal disruption and ultimately their detection in vivo.

Data analysis of the unsteadily accelerating GPS and seismic records at Campi Flegrei caldera from 2000 to 2020.

Ongoing resurgence affects Campi Flegrei caldera (Italy) via bradyseism, i.e. a series of ground deformation episodes accompanied by increases in shallow seismicity. In this study, we perform a mathematical analysis of the GPS and seismic data in the instrumental catalogs from 2000 to 2020, and a comparison of them to the preceding data from 1983 to 1999. We clearly identify and characterize two overlying trends, i.e. a decennial-like acceleration and cyclic oscillations with various periods. In particular, we show that all the signals have been accelerating since 2005, and 90-97% of their increase has occurred since 2011, 40-80% since 2018. Nevertheless, the seismic and ground deformation signals evolved differently-the seismic count increased faster than the GPS data since 2011, and even more so since 2015, growing faster than an exponential function The ground deformation has a linearized rate slope, i.e. acceleration, of 0.6 cm/yr2 and 0.3 cm/yr2 from 2000 to 2020, respectively for the vertical (RITE GPS) and the horizontal (ACAE GPS) components. In addition, all annual rates show alternating speed-ups and slow-downs, consistent between the signals. We find seven major rate maxima since 2000, one every 2.8-3.5 years, with secondary maxima at fractions of the intervals. A cycle with longer period of 6.5-9 years is also identified. Finally, we apply the probabilistic failure forecast method, a nonlinear regression that calculates the theoretical time limit of the signals going to infinity (interpreted here as a critical state potentially reached by the volcano), conditional on the continuation of the observed nonlinear accelerations. Since 2000, we perform a retrospective analysis of the temporal evolution of these forecasts which highlight the periods of more intense acceleration. The failure forecast method applied on the seismic count from 2001 to 2020 produces upper time limits of [0, 3, 11] years (corresponding to the 5th, 50th and 95th percentiles, respectively), significantly shorter than those based on the GPS data, e.g. [0, 6, 21] years. Such estimates, only valid under the model assumption of continuation of the ongoing decennial-like acceleration, warn to keep the guard up on the future evolution of Campi Flegrei caldera.

An assessment of stress analyses in the theory of abfraction.

Wedged-shaped lesions at the cemento-enamel junction of teeth have been attributed primarily to biomechanical loading forces that cause flexure and failure of enamel and dentin. This theory, termed abfraction, remains controversial. This review examined studies on mechanical properties of enamel and dentin and studies on bite forces and mastication as background information. Abfraction is based principally on a few early finite element analysis and photoelastic models showing stress concentration at the dental cervical area without actually showing enamel and dentin fracture. However, a review of more recent dental stress analyses has been contradictory. Particularly, analyses of the periodontal ligament and alveolar bone, not modeled in previous studies, have shown that those structures may dissipate occlusal loading forces from the cervical areas. In addition, some models may not fully represent intricate dental anatomy and complex occlusal function. Therefore, the key basis of the abfraction theory may be flawed.

Proximal femoral physis shear in slipped capital femoral epiphysis--a finite element study.

The following finite element study was conducted to determine whether increased body weight, femoral retroversion, and varus hip loading could sufficiently raise physeal shear strains and stresses above the yield point and predispose an adolescent hip to a slip. A computer tomography scan of a 13-year-old child with slipped capital femoral epiphysis was used to generate a solid model of the proximal femur and physis. The model was parameterized using 3-dimensional software to generate three difference angles of femoral neck version-neutral, 15 degrees retroversion, and 15 degrees anteversion. Loads of 2.7 times body weight in a 46- and 86-kg child were applied to the proximal femur to model stance on one leg. In addition, the loading vector was reoriented at various degrees of varus to study the effect of varus loading on physis shear. The results demonstrated that physis stress, strain, and displacement increased with greater body weight, retroversion, and varus displacement of the loading vector. Physis shear strain in hips with a combination of varus loading and femoral neck retroversion exceeded the reported ultimate strain values for cartilaginous soft tissues. The finite element models suggest that in an overweight child, the combination of retroversion and varus hip load may be sufficient to increase physeal strains above the yield point and result in a slip.