RESUMEN
Ovarian cancer detection has traditionally relied on a multi-step process that includes biopsy, tissue staining, and morphological analysis by experienced pathologists. While widely practiced, this conventional approach suffers from several drawbacks: it is qualitative, time-intensive, and heavily dependent on the quality of staining. Mid-infrared (MIR) hyperspectral photothermal imaging is a label-free, biochemically quantitative technology that, when combined with machine learning algorithms, can eliminate the need for staining and provide quantitative results comparable to traditional histology. However, this technology is slow. This work presents a novel approach to MIR photothermal imaging that enhances its speed by an order of magnitude. Our method significantly accelerates data collection by capturing a combination of highresolution and interleaved, lower-resolution infrared band images and applying computational techniques for data interpolation. We effectively minimize data collection requirements by leveraging sparse data acquisition and employing curvelet-based reconstruction algorithms. This approach enhances imaging speed without compromising image quality and ensures robust tissue segmentation. This method resolves the longstanding trade-off between imaging resolution and data collection speed, enabling the reconstruction of high-quality, high-resolution images from undersampled datasets and achieving a 10X improvement in data acquisition time. We assessed the performance of our sparse imaging methodology using a variety of quantitative metrics, including mean squared error (MSE), structural similarity index (SSIM), and tissue subtype classification accuracies, employing both random forest and convolutional neural network (CNN) models, accompanied by Receiver Operating Characteristic (ROC) curves. Our statistically robust analysis, based on data from 100 ovarian cancer patient samples and over 65 million data points, demonstrates the method's capability to produce superior image quality and accurately distinguish between different gynecological tissue types with segmentation accuracy exceeding 95%. Our work demonstrates the feasibility of integrating rapid MIR hyperspectral photothermal imaging with machine learning in enhancing ovarian cancer tissue characterization, paving the way for quantitative, label-free, automated histopathology. It represents a significant leap forward from traditional histopathological methods, offering profound implications for cancer diagnostics and treatment decision-making.
RESUMEN
Mid-infrared spectroscopic imaging (MIRSI) is an emerging class of label-free techniques being leveraged for digital histopathology. Modern histopathologic identification of ovarian cancer involves tissue staining followed by morphological pattern recognition. This process is time-consuming and subjective and requires extensive expertise. This paper presents the first label-free, quantitative, and automated histological recognition of ovarian tissue subtypes using a new MIRSI technique. This optical photothermal infrared (O-PTIR) imaging technique provides a 10× enhancement in spatial resolution relative to prior instruments. It enables sub-cellular spectroscopic investigation of tissue at biochemically important fingerprint wavelengths. We demonstrate that the enhanced resolution of sub-cellular features, combined with spectroscopic information, enables reliable classification of ovarian cell subtypes achieving a classification accuracy of 0.98. Moreover, we present a statistically robust analysis from 78 patient samples with over 60 million data points. We show that sub-cellular resolution from five wavenumbers is sufficient to outperform state-of-the-art diffraction-limited techniques with up to 235 wavenumbers. We also propose two quantitative biomarkers based on the relative quantities of epithelia and stroma that exhibit efficacy in early cancer diagnosis. This paper demonstrates that combining deep learning with intrinsic biochemical MIRSI measurements enables quantitative evaluation of cancerous tissue, improving the rigor and reproducibility of histopathology.
Asunto(s)
Aprendizaje Profundo , Neoplasias Ováricas , Humanos , Femenino , Reproducibilidad de los Resultados , Espectrofotometría Infrarroja , Diagnóstico por Imagen , Neoplasias Ováricas/diagnósticoRESUMEN
BACKGROUND: Segmented cine cardiac MRI combines data from multiple heartbeats to achieve high spatiotemporal resolution cardiac images, yet predefined k-space segmentation trajectories can lead to suboptimal k-space sampling. In this work, we developed and evaluated an autonomous and closed-loop control system for radial k-space sampling (ARKS) to increase sampling uniformity. METHODS: The closed-loop system autonomously selects radial k-space sampling trajectory during live segmented cine MRI and attempts to optimize angular sampling uniformity by selecting views in regions of k-space that were not previously well-sampled. Sampling uniformity and the ability to detect cardiac phase in vivo was assessed using ECG data acquired from 10 normal subjects in an MRI scanner. The approach was then implemented with a fast gradient echo sequence on a whole-body clinical MRI scanner and imaging was performed in 4 healthy volunteers. The closed-loop k-space trajectory was compared to random, uniformly distributed and golden angle view trajectories via measurement of k-space uniformity and the point spread function. Lastly, an arrhythmic dataset was used to evaluate a potential application of the approach. RESULTS: The autonomous trajectory increased k-space sampling uniformity by 15±7%, main lobe point spread function (PSF) signal intensity by 6±4%, and reduced ringing relative to golden angle sampling. When implemented, the autonomous pulse sequence prescribed radial view angles faster than the scan TR (0.98 ± 0.01 ms, maximum = 1.38 ms) and increased k-space sampling mean uniformity by 10±11%, decreased uniformity variability by 44±12%, and increased PSF signal ratio by 6±6% relative to golden angle sampling. CONCLUSION: The closed-loop approach enables near-uniform radial sampling in a segmented acquisition approach which was higher than predetermined golden-angle radial sampling. This can be utilized to increase the sampling or decrease the temporal footprint of an acquisition and the closed-loop framework has the potential to be applied to patients with complex heart rhythms.
Asunto(s)
Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Cinemagnética/métodos , Adulto , Algoritmos , Femenino , Voluntarios Sanos , Corazón/fisiología , Humanos , Aumento de la Imagen/métodos , Interpretación de Imagen Asistida por Computador/métodos , Imagen por Resonancia Magnética/métodos , MasculinoRESUMEN
Osteosclerosis and myefibrosis are complications of myeloproliferative neoplasms. These disorders result in excess growth of trabecular bone and collagen fibers that replace hematopoietic cells, resulting in abnormal bone marrow function. Treatments using imatinib and JAK2 pathway inhibitors can be effective on osteosclerosis and fibrosis; therefore, accurate grading is critical for tracking treatment effectiveness. Current grading standards use a four-class system based on analysis of biopsies stained with three histological stains: hematoxylin and eosin (H&E), Masson's trichrome, and reticulin. However, conventional grading can be subjective and imprecise, impacting the effectiveness of treatment. In this Article, we demonstrate that mid-infrared spectroscopic imaging may serve as a quantitative diagnostic tool for quantitatively tracking disease progression and response to treatment. The proposed approach is label-free and provides automated quantitative analysis of osteosclerosis and collagen fibrosis.
Asunto(s)
Osteosclerosis/diagnóstico , Espectroscopía Infrarroja por Transformada de Fourier/métodos , Biopsia , Huesos/química , Huesos/patología , Colágeno/análisis , Progresión de la Enfermedad , Fibrosis , Humanos , Osteosclerosis/patologíaRESUMEN
Cell segmentation in microscopy is a challenging problem, since cells are often asymmetric and densely packed. Successful cell segmentation algorithms rely identifying seed points, and are highly sensitive to variablility in cell size. In this paper, we present an efficient and highly parallel formulation for symmetric three-dimensional contour evolution that extends previous work on fast two-dimensional snakes. We provide a formulation for optimization on 3D images, as well as a strategy for accelerating computation on consumer graphics hardware. The proposed software takes advantage of Monte-Carlo sampling schemes in order to speed up convergence and reduce thread divergence. Experimental results show that this method provides superior performance for large 2D and 3D cell localization tasks when compared to existing methods on large 3D brain images.
Asunto(s)
Encéfalo/diagnóstico por imagen , Imagenología Tridimensional/métodos , Algoritmos , Encéfalo/citología , Tamaño de la Célula , Método de Montecarlo , Programas InformáticosRESUMEN
Current methods for cancer detection rely on tissue biopsy, chemical labeling/staining, and examination of the tissue by a pathologist. Though these methods continue to remain the gold standard, they are non-quantitative and susceptible to human error. Fourier transform infrared (FTIR) spectroscopic imaging has shown potential as a quantitative alternative to traditional histology. However, identification of histological components requires reliable classification based on molecular spectra, which are susceptible to artifacts introduced by noise and scattering. Several tissue types, particularly in heterogeneous tissue regions, tend to confound traditional classification methods. Convolutional neural networks (CNNs) are the current state-of-the-art in image classification, providing the ability to learn spatial characteristics of images. In this paper, we demonstrate that CNNs with architectures designed to process both spectral and spatial information can significantly improve classifier performance over per-pixel spectral classification. We report classification results after applying CNNs to data from tissue microarrays (TMAs) to identify six major cellular and acellular constituents of tissue, namely adipocytes, blood, collagen, epithelium, necrosis, and myofibroblasts. Experimental results show that the use of spatial information in addition to the spectral information brings significant improvements in the classifier performance and allows classification of cellular subtypes, such as adipocytes, that exhibit minimal chemical information but have distinct spatial characteristics. This work demonstrates the application and efficiency of deep learning algorithms in improving the diagnostic techniques in clinical and research activities related to cancer.
RESUMEN
Histological stains, such as hematoxylin and eosin (H&E), are routinely used in clinical diagnosis and research. While these labels offer a high degree of specificity, throughput is limited by the need for multiple samples. Traditional histology stains, such as immunohistochemical labels, also rely only on protein expression and cannot quantify small molecules and metabolites that may aid in diagnosis. Finally, chemical stains and dyes permanently alter the tissue, making downstream analysis impossible. Fourier transform infrared (FT-IR) spectroscopic imaging has shown promise for label-free characterization of important tissue phenotypes and can bypass the need for many chemical labels. Fourier transform infrared classification commonly leverages supervised learning, requiring human annotation that is tedious and prone to errors. One alternative is digital staining, which leverages machine learning to map IR spectra to a corresponding chemical stain. This replaces human annotation with computer-aided alignment. Previous work relies on alignment of adjacent serial tissue sections. Since the tissue samples are not identical at the cellular level, this technique cannot be applied to high-definition FT-IR images. In this paper, we demonstrate that cellular-level mapping can be accomplished using identical samples for both FT-IR and chemical labels. In addition, higher-resolution results can be achieved using a deep convolutional neural network that integrates spatial and spectral features.
RESUMEN
Infrared (IR) spectroscopic microscopes provide the potential for label-free quantitative molecular imaging of biological samples, which can be used to aid in histology, forensics, and pharmaceutical analysis. Most IR imaging systems use broadband illumination combined with a spectrometer to separate the signal into spectral components. This technique is currently too slow for many biomedical applications such as clinical diagnosis, primarily due to the availability of bright mid-infrared sources and sensitive MCT detectors. There has been a recent push to increase throughput using coherent light sources, such as synchrotron radiation and quantum cascade lasers. While these sources provide a significant increase in intensity, the coherence introduces fringing artifacts in the final image. We demonstrate that applying time-delayed integration in one dimension can dramatically reduce fringing artifacts with minimal alterations to the standard infrared imaging pipeline. The proposed technique also offers the potential for less expensive focal plane array detectors, since linear arrays can be more readily incorporated into the proposed framework.
RESUMEN
Understanding the structure of a scattered electromagnetic (EM) field is critical to improving the imaging process. Mechanisms such as diffraction, scattering, and interference affect an image, limiting the resolution, and potentially introducing artifacts. Simulation and visualization of scattered fields thus plays an important role in imaging science. However, EM fields are high-dimensional, making them time-consuming to simulate, and difficult to visualize. In this paper, we present a framework for interactively computing and visualizing EM fields scattered by micro and nano-particles. Our software uses graphics hardware for evaluating the field both inside and outside of these particles. We then use Monte-Carlo sampling to reconstruct and visualize the three-dimensional structure of the field, spectral profiles at individual points, the structure of the field at the surface of the particle, and the resulting image produced by an optical system.
RESUMEN
There has recently been significant interest within the vibrational spectroscopy community to apply quantitative spectroscopic imaging techniques to histology and clinical diagnosis. However, many of the proposed methods require collecting spectroscopic images that have a similar region size and resolution to the corresponding histological images. Since spectroscopic images contain significantly more spectral samples than traditional histology, the resulting data sets can approach hundreds of gigabytes to terabytes in size. This makes them difficult to store and process, and the tools available to researchers for handling large spectroscopic data sets are limited. Fundamental mathematical tools, such as MATLAB, Octave, and SciPy, are extremely powerful but require that the data be stored in fast memory. This memory limitation becomes impractical for even modestly sized histological images, which can be hundreds of gigabytes in size. In this paper, we propose an open-source toolkit designed to perform out-of-core processing of hyperspectral images. By taking advantage of graphical processing unit (GPU) computing combined with adaptive data streaming, our software alleviates common workstation memory limitations while achieving better performance than existing applications.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Programas Informáticos , Análisis Espectral , AlgoritmosRESUMEN
PURPOSE: To develop a robust T1ρ magnetic resonance imaging (MRI) sequence for assessment of myocardial disease in humans. MATERIALS AND METHODS: We developed a breath-held T1ρ mapping method using a single-shot, T1ρ-prepared balanced steady-state free-precession (bSSFP) sequence. The magnetization trajectory was simulated to identify sources of T1ρ error. To limit motion artifacts, an optical flow-based image registration method was used to align T1ρ images. The reproducibility and accuracy of these methods was assessed in phantoms and 10 healthy subjects. Results are shown in 1 patient with pre-ventricular contractions (PVCs), 1 patient with chronic myocardial infarction (MI) and 2 patients with hypertrophic cardiomyopathy (HCM). RESULTS: In phantoms, the mean bias was 1.0 ± 2.7 msec (100 msec phantom) and 0.9 ± 0.9 msec (60 msec phantom) at 60 bpm and 2.2 ± 3.2 msec (100 msec) and 1.4 ± 0.9 msec (60 msec) at 80 bpm. The coefficient of variation (COV) was 2.2 (100 msec) and 1.3 (60 msec) at 60 bpm and 2.6 (100 msec) and 1.4 (60 msec) at 80 bpm. Motion correction improved the alignment of T1ρ images in subjects, as determined by the increase in Dice Score Coefficient (DSC) from 0.76 to 0.88. T1ρ reproducibility was high (COV < 0.05, intra-class correlation coefficient (ICC) = 0.85-0.97). Mean myocardial T1ρ value in healthy subjects was 63.5 ± 4.6 msec. There was good correspondence between late-gadolinium enhanced (LGE) MRI and increased T1ρ relaxation times in patients. CONCLUSION: Single-shot, motion corrected, spin echo, spin lock MRI permits 2D T1ρ mapping in a breath-hold with good accuracy and precision.