Deep learning-based correction of cataract-induced influence on macular pigment optical density measurement by autofluorescence spectroscopy.

PURPOSE: Measurements of macular pigment optical density (MPOD) using the autofluorescence spectroscopy yield underestimations of actual values in eyes with cataracts. Previously, we proposed a correction method for this error using deep learning (DL); however, the correction performance was validated through internal cross-validation. This cross-sectional study aimed to validate this approach using an external validation dataset. METHODS: MPODs at 0.25°, 0.5°, 1°, and 2° eccentricities and macular pigment optical volume (MPOV) within 9° eccentricity were measured using SPECTRALIS (Heidelberg Engineering, Heidelberg, Germany) in 197 (training dataset inherited from our previous study) and 157 eyes (validating dataset) before and after cataract surgery. A DL model was trained to predict the corrected value from the pre-operative value using the training dataset, and we measured the discrepancy between the corrected value and the actual postoperative value. Subsequently, the prediction performance was validated using a validation dataset. RESULTS: Using the validation dataset, the mean absolute values of errors for MPOD and MPOV corrected using DL ranged from 8.2 to 12.4%, which were lower than values with no correction (P < 0.001, linear mixed model with Tukey's test). The error depended on the autofluorescence image quality used to calculate MPOD. The mean errors in high and moderate quality images ranged from 6.0 to 11.4%, which were lower than those of poor quality images. CONCLUSION: The usefulness of the DL correction method was validated. Deep learning reduced the error for a relatively good autofluorescence image quality. Poor-quality images were not corrected.

Artificial intelligence-based classification of peripheral blood nucleated cells using label-free imaging flow cytometry.

Label-free image identification of circulating rare cells, such as circulating tumor cells within peripheral blood nucleated cells (PBNCs), the vast majority of which are white blood cells (WBCs), remains challenging. We previously described developing label-free image cytometry for classifying live cells using computer vision technology for pattern recognition, based on the subcellular structure of the quantitative phase microscopy images. We applied our image recognition methods to cells flowing in a flow cytometer microfluidic channel, and differentiated WBCs from cancer cell lines (area under receiver operating characteristic curve = 0.957). We then applied this method to healthy volunteers' and advanced cancer patients' blood samples and found that the non-WBC fraction rates (NWBC-FRs), defined as the percentage of cells classified as non-WBCs of the total PBNCs, were significantly higher in cancer patients than in healthy volunteers. Furthermore, we monitored NWBC-FRs over the therapeutic courses in cancer patients, which revealed the potential ability in monitoring the clinical status during therapy. Our image recognition system has the potential to provide a morphological diagnostic tool for circulating rare cells as non-WBC fractions.

Multiple-scattering suppressive refractive index tomography for the label-free quantitative assessment of multicellular spheroids.

Refractive index (RI) tomography is a quantitative tomographic technique used to visualize the intrinsic contrast of unlabeled biological samples. Conventional RI reconstruction algorithms are based on weak-scattering approximation, such as the Born or Rytov approximation. Although these linear algorithms are computationally efficient, they are invalid when the fields are strongly distorted by multiple scattering (MS) of specimens. Herein, we propose an approach to reconstruct the RI distributions of MS objects even under weak-scattering approximation using an MS-suppressive operation. The operation converts the distorted fields into MS-suppressed fields, where weak-scattering approximation is applicable. Using this approach, we reconstructed a whole multicellular spheroid and successfully visualized its internal subcellular structures. Our work facilitates the realization of RI tomography of MS specimens and label-free quantitative analysis of 3D multicellular specimens.

Single-shot quantitative phase imaging as an extension of differential interference contrast microscopy.

Various studies have been conducted to obtain quantitative phase information based on differential interference contrast (DIC) microscopy. As one such attempt, we propose in this study a single-shot quantitative phase imaging (QPI) method by combining two developments. First, an add-on optical system to a commercialized DIC microscope was developed to perform quantitative phase gradient imaging (QPGI) with single image acquisition using a polarization camera. Second, an algorithm was formulated to reconstitute QPI from the obtained QPGI by reducing linear artifacts, which arise in simply integrated QPGI images. To demonstrate the applicability of the developed system in cell biology, the system was used to measure various cell lines and compared with fluorescence microscopy images of the same field of view. Consistent with previous studies, nucleoli and lipid droplets can be imaged by the system with greater optical path lengths (OPL). The results also implied that combining fluorescence microscopy and the developed system might be more informative for cell biology research than using these methods individually. Exploiting the single-shot performance of the developed system, time-lapse imaging was also conducted to visualize the dynamics of intracellular granules in monocyte-/macrophage-like cells. Our proposed approach may accelerate the implementation of QPI in standard biomedical laboratories.

Correction for the Influence of Cataract on Macular Pigment Measurement by Autofluorescence Technique Using Deep Learning.

Purpose: Measurements of macular pigment optical density (MPOD) by the autofluorescence technique yield underestimations of actual values in eyes with cataract. We applied deep learning (DL) to correct this error. Subjects and Methods: MPOD was measured by SPECTRALIS (Heidelberg Engineering, Heidelberg, Germany) in 197 eyes before and after cataract surgery. The nominal MPOD values (= preoperative value) were corrected by three methods: the regression equation (RE) method, subjective classification (SC) method (described in our previous study), and DL method. The errors between the corrected and true values (= postoperative value) were calculated for local MPODs at 0.25°, 0.5°, 1°, and 2° eccentricities and macular pigment optical volume (MPOV) within 9° eccentricity. Results: The mean error for MPODs at four eccentricities was 32% without any correction, 15% with correction by RE, 16% with correction by SC, and 14% with correction by DL. The mean error for MPOV was 21% without correction and 14%, 10%, and 10%, respectively, with correction by the same methods. The errors with any correction were significantly lower than those without correction (P < 0.001, linear mixed model with Tukey's test). The errors with DL correction were significantly lower than those with RE correction in MPOD at 1° eccentricity and MPOV (P < 0.001) and were equivalent to those with SC correction. Conclusions: The objective method using DL was useful to correct MPOD values measured in aged people. Translational Relevance: MPOD can be obtained with small errors in eyes with cataract using DL.

Label-free imaging flow cytometer for analyzing large cell populations by line-field quantitative phase microscopy with digital refocusing.

We propose a line-field quantitative phase-imaging flow cytometer for analyzing large populations of label-free cells. Hydrodynamical focusing brings cells into the focus plane of an optical system while diluting the cell suspension, resulting in decreased throughput rate. To overcome the trade-off between throughput rate and in-focus imaging, our cytometer involves digitally extending the depth-of-focus on loosely hydrodynamically focusing cell suspensions. The cells outside the depth-of-focus range in the 70-µm diameter of the core flow were automatically digitally refocused after image acquisition. We verified that refocusing was successful with our cytometer through statistical analysis of image quality before and after digital refocusing.

Label-free classification of cells based on supervised machine learning of subcellular structures.

It is demonstrated that cells can be classified by pattern recognition of the subcellular structure of non-stained live cells, and the pattern recognition was performed by machine learning. Human white blood cells and five types of cancer cell lines were imaged by quantitative phase microscopy, which provides morphological information without staining quantitatively in terms of optical thickness of cells. Subcellular features were then extracted from the obtained images as training data sets for the machine learning. The built classifier successfully classified WBCs from cell lines (area under ROC curve = 0.996). This label-free, non-cytotoxic cell classification based on the subcellular structure of QPM images has the potential to serve as an automated diagnosis of single cells.