Artificial intelligence-enabled quantitative phase imaging methods for life sciences.

Quantitative phase imaging, integrated with artificial intelligence, allows for the rapid and label-free investigation of the physiology and pathology of biological systems. This review presents the principles of various two-dimensional and three-dimensional label-free phase imaging techniques that exploit refractive index as an intrinsic optical imaging contrast. In particular, we discuss artificial intelligence-based analysis methodologies for biomedical studies including image enhancement, segmentation of cellular or subcellular structures, classification of types of biological samples and image translation to furnish subcellular and histochemical information from label-free phase images. We also discuss the advantages and challenges of artificial intelligence-enabled quantitative phase imaging analyses, summarize recent notable applications in the life sciences, and cover the potential of this field for basic and industrial research in the life sciences.

Deep learning-based label-free hematology analysis framework using optical diffraction tomography.

Hematology analysis, a common clinical test for screening various diseases, has conventionally required a chemical staining process that is time-consuming and labor-intensive. To reduce the costs of chemical staining, label-free imaging can be utilized in hematology analysis. In this work, we exploit optical diffraction tomography and the fully convolutional one-stage object detector or FCOS, a deep learning architecture for object detection, to develop a label-free hematology analysis framework. Detected cells are classified into four groups: red blood cell, abnormal red blood cell, platelet, and white blood cell. In the results, the trained object detection model showed superior detection performance for blood cells in refractive index tomograms (0.977 mAP) and also showed high accuracy in the four-class classification of blood cells (0.9708 weighted F1 score, 0.9712 total accuracy). For further verification, mean corpuscular volume (MCV) and mean corpuscular hemoglobin (MCH) were compared with values obtained from reference hematology equipment, with our results showing reasonable correlation in both MCV (0.905) and MCH (0.889). This study provides a successful demonstration of the proposed framework in detecting and classifying blood cells using optical diffraction tomography for label-free hematology analysis.

Machine-learning-based diagnosis of thyroid fine-needle aspiration biopsy synergistically by Papanicolaou staining and refractive index distribution.

We developed a machine learning algorithm (MLA) that can classify human thyroid cell clusters by exploiting both Papanicolaou staining and intrinsic refractive index (RI) as correlative imaging contrasts and evaluated the effects of this combination on diagnostic performance. Thyroid fine-needle aspiration biopsy (FNAB) specimens were analyzed using correlative optical diffraction tomography, which can simultaneously measure both, the color brightfield of Papanicolaou staining and three-dimensional RI distribution. The MLA was designed to classify benign and malignant cell clusters using color images, RI images, or both. We included 1535 thyroid cell clusters (benign: malignancy = 1128:407) from 124 patients. Accuracies of MLA classifiers using color images, RI images, and both were 98.0%, 98.0%, and 100%, respectively. As information for classification, the nucleus size was mainly used in the color image; however, detailed morphological information of the nucleus was also used in the RI image. We demonstrate that the present MLA and correlative FNAB imaging approach has the potential for diagnosing thyroid cancer, and complementary information from color and RI images can improve the performance of the MLA.

DeepRegularizer: Rapid Resolution Enhancement of Tomographic Imaging Using Deep Learning.

Optical diffraction tomography measures the three-dimensional refractive index map of a specimen and visualizes biochemical phenomena at the nanoscale in a non-destructive manner. One major drawback of optical diffraction tomography is poor axial resolution due to limited access to the three-dimensional optical transfer function. This missing cone problem has been addressed through regularization algorithms that use a priori information, such as non-negativity and sample smoothness. However, the iterative nature of these algorithms and their parameter dependency make real-time visualization impossible. In this article, we propose and experimentally demonstrate a deep neural network, which we term DeepRegularizer, that rapidly improves the resolution of a three-dimensional refractive index map. Trained with pairs of datasets (a raw refractive index tomogram and a resolution-enhanced refractive index tomogram via the iterative total variation algorithm), the three-dimensional U-net-based convolutional neural network learns a transformation between the two tomogram domains. The feasibility and generalizability of our network are demonstrated using bacterial cells and a human leukaemic cell line, and by validating the model across different samples. DeepRegularizer offers more than an order of magnitude faster regularization performance compared to the conventional iterative method. We envision that the proposed data-driven approach can bypass the high time complexity of various image reconstructions in other imaging modalities.

Prediction of Coronary Stent Underexpansion by Pre-Procedural Intravascular Ultrasound-Based Deep Learning.

OBJECTIVES: The aim of this study was to develop pre-procedural intravascular ultrasound (IVUS)-based models for predicting the occurrence of stent underexpansion. BACKGROUND: Although post-stenting IVUS has been used to optimize percutaneous coronary intervention, there are no pre-procedural guidelines to estimate the degree of stent expansion and provide preemptive management before stent deployment. METHODS: A total of 618 coronary lesions in 618 patients undergoing percutaneous coronary intervention were randomized into training and test sets in a 5:1 ratio. Following the coregistration of pre- and post-stenting IVUS images, the pre-procedural images and clinical information (stent diameter, length, and inflation pressure; balloon diameter; and maximal balloon pressure) were used to develop a regression model using a convolutional neural network to predict post-stenting stent area. To separate the frames with from those without the occurrence of underexpansion (stent area <5.5 mm2), binary classification models (XGBoost) were developed. RESULTS: Overall, the frequency of stent underexpansion was 15% (5,209 of 34,736 frames). At the frame level, stent areas predicted by the pre-procedural IVUS-based regression model significantly correlated with those measured on post-stenting IVUS (r = 0.802). To predict stent underexpansion, maximal accuracy of 94% (area under the curve = 0.94) was achieved when the convolutional neural network- and mask image-derived features were used for the classification model. At the lesion level, there were significant correlations between predicted and measured minimal stent area (r = 0.832) and between predicted and measured total stent volume (r = 0.958). CONCLUSIONS: Deep-learning algorithms accurately predicted incomplete stent expansion. A data-driven approach may assist clinicians in making treatment decisions to avoid stent underexpansion as a preventable cause of stent failure.

Remote afterloading patient-specific brachytherapy with liquid radioisotope for irradiation of extensive scalp lesions: A Monte Carlo study.

PURPOSE: The aim of this study is to propose a remote afterloading patient-specific brachytherapy technique for total scalp irradiation by utilizing liquid radioisotope as well as a three-dimensional (3D) printer and to find an optimal radioisotope for the suggested technique. METHODS: We designed a brachytherapy device composed of liquid radioisotope tank, tube, patient-specific applicator, and a thin flexible pouch. The liquid radioisotope tank, tube, and the flexible pouch are interconnected one another to constitute a closed loop system. The pouch is located inside the solid patient-specific applicator; therefore, when the liquid radioisotope is injected into the pouch, the pouch is inflated and fills the space inside the applicator. The 3D-printed patient-specific applicator keeps the uniform thickness of the liquid radioisotope conforming patient's contour. To investigate an optimum condition for the suggested system, we performed Monte Carlo simulation with the GEANT4 simulation toolkit. To find the optimal radioisotope, percent depth doses (PDDs) of P-32, Sr-89, Y-90, and I-125 solutions were acquired in a rectangular parallelepiped phantom. For the selected radiation source, PDDs as well as dose rates in spherical phantoms with radii of 7.7 cm (infant head size) and 9.1 cm (adult head size) were acquired. RESULTS: To deliver prescription doses at 4-mm depth regions (scalp region), 1-mm-thick Y-90 and 5-mm-thick I-125 in liquid form were found to be feasible for the suggested technique. For both spherical phantoms with radii of 7.7 and 9.1 cm, when delivering 2 Gy at the 4-mm depth region with the 1-mm-thick Y-90 and 5-mm-thick I-125 sources, 53.3 and 3.8 Gy were delivered at the surface regions, respectively (delivery time = 111.1 and 3.5 min with 1 GBq/ml solutions). The PDDs of Y-90 and I-125 became less than 1% at depths greater than 8 and 50 mm, respectively. CONCLUSIONS: The remote afterloading patient-patient specific brachytherapy with I-125 or Y-90 in liquid form seems feasible for total scalp irradiation.

Fano cavity test for electron Monte Carlo transport algorithms in magnetic fields: comparison between EGSnrc, PENELOPE, MCNP6 and Geant4.

A Fano cavity test was performed for four general-purpose Monte Carlo codes, EGSnrc, PENELOPE, MCNP6 and Geant4 to evaluate the accuracy of their electron transport algorithms in magnetic fields. In the simulations, a plane-parallel ionization chamber was modelled as a circular gas disk sandwiched between two circular solid wall disks. It was assumed that an isotropic and uniform line source per unit mass along the central axis of the gas and solid emits mono-energetic electrons with energies 0.01, 0.1, 1.0 and 3.0 MeV at different magnetic field strengths 0, 0.35, 1.0, 1.5 and 3.0 T in the electron transport mode (no Bremsstrahlung). The relative difference between the calculated dose to the gas region and the initial total energy of emitted electrons per unit mass was defined as the accuracy of Monte Carlo codes. In all results, EGSnrc with the enhanced electric and magnetic field (EEMF) macros was not considerably sensitive to the step size parameters and showed accuracy less than 0.18% ± 0.06% with a coverage factor k = 2. The other codes could not achieve competent accuracy with their default settings of step size parameters, compared to EGSnrc with the EEMF macros. With the step size parameters carefully selected, the accuracy of PENELOPE and MCNP6 was within 1.0% and 0.4%, respectively. However, Geant4 showed accuracy within 1.7% except in 3.0 T. EGSnrc with the EEMF macros achieved the best accuracy for the Fano test at the electron energies and the magnetic field strengths investigated in this study and thus, would be recommended to simulate dose responses of ionization chambers in the presence of magnetic fields.