Lung cancer lesion detection in histopathology images using graph-based sparse PCA network.

Early detection of lung cancer is critical for improvement of patient survival. To address the clinical need for efficacious treatments, genetically engineered mouse models (GEMM) have become integral in identifying and evaluating the molecular underpinnings of this complex disease that may be exploited as therapeutic targets. Assessment of GEMM tumor burden on histopathological sections performed by manual inspection is both time consuming and prone to subjective bias. Therefore, an interplay of needs and challenges exists for computer-aided diagnostic tools, for accurate and efficient analysis of these histopathology images. In this paper, we propose a simple machine learning approach called the graph-based sparse principal component analysis (GS-PCA) network, for automated detection of cancerous lesions on histological lung slides stained by hematoxylin and eosin (H&E). Our method comprises four steps: 1) cascaded graph-based sparse PCA, 2) PCA binary hashing, 3) block-wise histograms, and 4) support vector machine (SVM) classification. In our proposed architecture, graph-based sparse PCA is employed to learn the filter banks of the multiple stages of a convolutional network. This is followed by PCA hashing and block histograms for indexing and pooling. The meaningful features extracted from this GS-PCA are then fed to an SVM classifier. We evaluate the performance of the proposed algorithm on H&E slides obtained from an inducible K-rasG12D lung cancer mouse model using precision/recall rates, Fß-score, Tanimoto coefficient, and area under the curve (AUC) of the receiver operator characteristic (ROC) and show that our algorithm is efficient and provides improved detection accuracy compared to existing algorithms.

Automated thalamic nuclei segmentation using multi-planar cascaded convolutional neural networks.

PURPOSE: To develop a fast and accurate convolutional neural network based method for segmentation of thalamic nuclei. METHODS: A cascaded multi-planar scheme with a modified residual U-Net architecture was used to segment thalamic nuclei on conventional and white-matter-nulled (WMn) magnetization prepared rapid gradient echo (MPRAGE) data. A single network was optimized to work with images from healthy controls and patients with multiple sclerosis (MS) and essential tremor (ET), acquired at both 3 T and 7 T field strengths. WMn-MPRAGE images were manually delineated by a trained neuroradiologist using the Morel histological atlas as a guide to generate reference ground truth labels. Dice similarity coefficient and volume similarity index (VSI) were used to evaluate performance. Clinical utility was demonstrated by applying this method to study the effect of MS on thalamic nuclei atrophy. RESULTS: Segmentation of each thalamus into twelve nuclei was achieved in under a minute. For 7 T WMn-MPRAGE, the proposed method outperforms current state-of-the-art on patients with ET with statistically significant improvements in Dice for five nuclei (increase in the range of 0.05-0.18) and VSI for four nuclei (increase in the range of 0.05-0.19), while performing comparably for healthy and MS subjects. Dice and VSI achieved using 7 T WMn-MPRAGE data are comparable to those using 3 T WMn-MPRAGE data. For conventional MPRAGE, the proposed method shows a statistically significant Dice improvement in the range of 0.14-0.63 over FreeSurfer for all nuclei and disease types. Effect of noise on network performance shows robustness to images with SNR as low as half the baseline SNR. Atrophy of four thalamic nuclei and whole thalamus was observed for MS patients compared to healthy control subjects, after controlling for the effect of parallel imaging, intracranial volume, gender, and age (p < 0.004). CONCLUSION: The proposed segmentation method is fast, accurate, performs well across disease types and field strengths, and shows great potential for improving our understanding of thalamic nuclei involvement in neurological diseases.

Racioethnic differences in the biomechanical response of the lamina cribrosa.

Glaucoma is the second leading cause of irreversible blindness in the world with a higher prevalence in those of African Descent (AD) and Hispanic Ethnicity (HE) than in those of European Descent (ED). The objective of this study was to investigate the pressure dependent biomechanical response of the lamina cribrosa (LC) in normal human donor tissues from these racioethnic backgrounds. Pressure inflation tests were performed on 24 human LCs (n = 9 AD, n = 6 ED, and n = 9 HE) capturing the second harmonic generation (SHG) signal of collagen at 5, 15, 30, and 45 mmHg from an anterior view. A non-rigid image registration technique was utilized to determine the 3D displacement field in each LC from which 3D Green strains were calculated. The peak shear strain in the superior quadrant of the LC in those of ED was significantly higher than in those of AD and HE (p-value = 0.005 & 0.034, respectively) where ED = 0.017 [IQR = 0.012-0.027], AD = 0.0002 [IQR = -0.001-0.007], HE = 0.0016 [IQR = -0.002-0.012]). There were also significant differences in the regional strain heterogeneity in those of AD and HE that were absent in those of ED. This work represents, to our knowledge, the first ex-vivo study identifying significant differences in the biomechanical response of the LC in populations at increased risk of glaucoma. Future work will be necessary to assess if and how these differences play a role in predisposing those of Hispanic Ethnicity and African Descent to the onset and/or progression of primary open angle glaucoma. STATEMENT OF SIGNIFICANCE: Glaucoma is the second leading cause of irreversible blindness in the world and occurs more frequently in those of African Descent and Hispanic Ethnicity than in those of European Descent. To date, there has been no ex-vivo study quantifying differences in the biomechanical response of the non-glaucomatous lamina cribrosa (LC) across these racioethnic backgrounds. In this work we report, for the first time, differences in the pressure dependent biomechanical response of LC across different racioethnic groups as quantified using nonlinear optical microscopy. This study lays the foundation for future work investigating if and how these differences may play a role in predisposing those at increased risk to the onset and/or progression of primary open angle glaucoma.

Image Inpainting Using Nonlocal Texture Matching and Nonlinear Filtering.

Nonlocal texture similarity and local intensity smoothness are both essential for solving most image inpainting problems. In this paper, we propose a novel image inpainting algorithm that is capable of reproducing the underlying textural details using a nonlocal texture measure and also smoothing pixel intensity seamlessly in order to achieve natural-looking inpainted images. For matching texture, we propose a Gaussian-weighted nonlocal texture similarity measure to obtain multiple candidate patches for each target patch. To compute the pixel intensity, we apply the -trimmed mean filter to the candidate patches to inpaint the target patch pixel-by-pixel. The proposed algorithm is compared with four current image inpainting algorithms under different scenarios, including object removal, texture synthesis, and error concealment. Experimental results show that the proposed algorithm outperforms the existing algorithms when inpainting large missing regions in images with texture and geometric structures.

Automatic classification of dual-modalilty, smartphone-based oral dysplasia and malignancy images using deep learning.

With the goal to screen high-risk populations for oral cancer in low- and middle-income countries (LMICs), we have developed a low-cost, portable, easy to use smartphone-based intraoral dual-modality imaging platform. In this paper we present an image classification approach based on autofluorescence and white light images using deep learning methods. The information from the autofluorescence and white light image pair is extracted, calculated, and fused to feed the deep learning neural networks. We have investigated and compared the performance of different convolutional neural networks, transfer learning, and several regularization techniques for oral cancer classification. Our experimental results demonstrate the effectiveness of deep learning methods in classifying dual-modal images for oral cancer detection.

Automated High-Throughput Damage Scoring of Zebrafish Lateral Line Hair Cells After Ototoxin Exposure.

Zebrafish have emerged as a powerful biological system for drug development against hearing loss. Zebrafish hair cells, contained within neuromasts along the lateral line, can be damaged with exposure to ototoxins, and therefore, pre-exposure to potentially otoprotective compounds can be a means of identifying promising new drug candidates. Unfortunately, anatomical assays of hair cell damage are typically low-throughput and labor intensive, requiring trained experts to manually score hair cell damage in fluorescence or confocal images. To enhance throughput and consistency, our group has developed an automated damage-scoring algorithm based on machine-learning techniques that produce accurate damage scores, eliminate potential operator bias, provide more fidelity in determining damage scores that are between two levels, and deliver consistent results in a fraction of the time required for manual analysis. The system has been validated against trained experts using linear regression, hypothesis testing, and the Pearson's correlation coefficient. Furthermore, performance has been quantified by measuring mean absolute error for each image and the time taken to automatically compute damage scores. Coupling automated analysis of zebrafish hair cell damage to behavioral assays for ototoxicity produces a novel drug discovery platform for rapid translation of candidate drugs into preclinical mammalian models of hearing loss.

Three-Dimensional Segmentation of the Ex-Vivo Anterior Lamina Cribrosa From Second-Harmonic Imaging Microscopy.

The lamina cribrosa (LC) is a connective tissue in the posterior eye with a complex mesh-like trabecular microstructure, through which all the retinal ganglion cell axons and central retinal vessels pass. Recent studies have demonstrated that changes in the structure of the LC correlate with glaucomatous damage. Thus, accurate segmentation and reconstruction of the LC is of utmost importance. This paper presents a new automated method for segmenting the microstructure of the anterior LC in the images obtained via multiphoton microscopy using a combination of ideas. In order to reduce noise, we first smooth the input image using a 4-D collaborative filtering scheme. Next, we enhance the beam-like trabecular microstructure of the LC using wavelet multiresolution analysis. The enhanced LC microstructure is then automatically extracted using a combination of histogram thresholding and graph-cut binarization. Finally, we use morphological area opening as a postprocessing step to remove the small and unconnected 3-D regions in the binarized images. The performance of the proposed method is evaluated using mutual overlap accuracy, Tanimoto index, F-score, and Rand index. Quantitative and qualitative results show that the proposed algorithm provides improved segmentation accuracy and computational efficiency compared to the other recent algorithms.

Segmentation of the right ventricle in four chamber cine cardiac MR images using polar dynamic programming.

The four chamber plane is currently underutilized in the right ventricular segmentation community. Four chamber information can be useful to determine ventricular short axis stacks and provide a rough estimate of the right ventricle in short axis stacks. In this study, we develop and test a semi-automated technique for segmenting the right ventricle in four chamber cine cardiac magnetic resonance images. The three techniques that use minimum cost path algorithms were used. The algorithms are: Dijkstra's shortest path algorithm (Dijkstra), an A* algorithm that uses length, curvature and torsion into an active contour model (ALCT), and a variation of polar dynamic programming (PDP). The techniques are evaluated against the expert traces using 175 cardiac images from 7 patients. The evaluation first looks at mutual overlap metrics and then focuses on clinical measures such as fractional area change (FAC). The mean mutual overlap between the physician's traces ranged from 0.85 to 0.88. Using as reference physician 1's landmarks and traces (i.e., comparing the traces from physician 1 to the semi-automated segmentation using physician 1's landmarks), the PDP algorithm has a mean mutual overlap of 0.8970 compared to 0.8912 for ALCT and 0.8879 for Dijkstra. The mean mutual overlap between the BP regions generated by physician 1 and physician 2 landmarks are 0.9674, 0.9605 and 0.9531 for PDP, ALCT and Dijkstra, respectively. The FAC correlation coefficient between the physician's traces ranged from 0.73 to 0.93.

A Fully Automated High-Throughput Zebrafish Behavioral Ototoxicity Assay.

Zebrafish animal models lend themselves to behavioral assays that can facilitate rapid screening of ototoxic, otoprotective, and otoregenerative drugs. Structurally similar to human inner ear hair cells, the mechanosensory hair cells on their lateral line allow the zebrafish to sense water flow and orient head-to-current in a behavior called rheotaxis. This rheotaxis behavior deteriorates in a dose-dependent manner with increased exposure to the ototoxin cisplatin, thereby establishing itself as an excellent biomarker for anatomic damage to lateral line hair cells. Building on work by our group and others, we have built a new, fully automated high-throughput behavioral assay system that uses automated image analysis techniques to quantify rheotaxis behavior. This novel system consists of a custom-designed swimming apparatus and imaging system consisting of network-controlled Raspberry Pi microcomputers capturing infrared video. Automated analysis techniques detect individual zebrafish, compute their orientation, and quantify the rheotaxis behavior of a zebrafish test population, producing a powerful, high-throughput behavioral assay. Using our fully automated biological assay to test a standardized ototoxic dose of cisplatin against varying doses of compounds that protect or regenerate hair cells may facilitate rapid translation of candidate drugs into preclinical mammalian models of hearing loss.

Dynamic Programming Using Polar Variance for Image Segmentation.

When using polar dynamic programming (PDP) for image segmentation, the object size is one of the main features used. This is because if size is left unconstrained the final segmentation may include high-gradient regions that are not associated with the object. In this paper, we propose a new feature, polar variance, which allows the algorithm to segment the objects of different sizes without the need for training data. The polar variance is the variance in a polar region between a user-selected origin and a pixel we want to analyze. We also incorporate a new technique that allows PDP to segment complex shapes by finding low-gradient regions and growing them. The experimental analysis consisted on comparing our technique with different active contour segmentation techniques on a series of tests. The tests consisted on robustness to additive Gaussian noise, segmentation accuracy with different grayscale images and finally robustness to algorithm-specific parameters. Experimental results show that our technique performs favorably when compared with other segmentation techniques.

Size-Invariant Detection of Cell Nuclei in Microscopy Images.

Accurate detection of individual cell nuclei in microscopy images is an essential and fundamental task for many biological studies. In particular, multivariate fluorescence microscopy is used to observe different aspects of cells in cultures. Manual detection of individual cell nuclei by visual inspection is time consuming, and prone to induce subjective bias. This makes automatic detection of cell nuclei essential for large-scale, objective studies of cell cultures. Blur, clutter, bleed-through, imaging noise and touching and partially overlapping nuclei with varying sizes and shapes make automated detection of individual cell nuclei a challenging task using image analysis. In this paper we propose a new automated method for fast and robust detection of individual cell nuclei based on their radial symmetric nature in fluorescence in-situ hybridization (FISH) images obtained via confocal microscopy. The main contributions are two-fold. 1) This work presents a more accurate cell nucleus detection system using the fast radial symmetry transform (FRST). 2) The proposed cell nucleus detection system is robust against most occlusions and variations in size and moderate shape deformations. We evaluate the performance of the proposed algorithm using precision/recall rates, Fß-score and root-mean-squared distance (RMSD) and show that our algorithm provides improved detection accuracy compared to existing algorithms.

A maximum-likelihood method to estimate a single ADC value of lesions using diffusion MRI.

PURPOSE: Design a statistically rigorous procedure to estimate a single apparent diffusion coefficient (ADC) of lesion from the mean lesion signal intensity in diffusion MRI. THEORY AND METHODS: A rigorous maximum-likelihood technique that incorporated the statistics of the mean lesion intensity and accounted for lesion heterogeneity was derived to estimate the ADC value. Performance evaluation included comparison with the conventionally used linear-regression and a statistically rigorous state-of-the-art ADC-map technique using realistic and clinically relevant simulation studies conducted with assistance of patient data for homogeneous and heterogeneous lesion models. RESULTS: The proposed technique outperformed the linear-regression and ADC-map approaches over a large spectrum of signal-to-noise ratio, ADC, lesion size, image-misalignment parameters, including at no image misalignment, and different amounts of lesion heterogeneity. The method was also superior at different sets of b values and in studies from specific patient-image-derived data. The technique took less than a second to execute. CONCLUSIONS: A rigorous, computationally fast, easy-to-implement, and convenient-to-use maximum-likelihood technique was proposed to estimate a single ADC value of the lesion. Results provide strong evidence in support of the method. Magn Reson Med 76:1919-1931, 2016. © 2016 International Society for Magnetic Resonance in Medicine.

Transfer function analysis in epi-illumination Fourier ptychography.

This Letter explores Fourier ptychography (FP) using epi-illumination. The approach effectively modifies the FP transfer function to be coherent-like out to the incoherent limit of twice the numerical aperture over the wavelength 2NA/λ. Images reconstructed using this approach are shown to have higher contrast at finer details compared with images using incoherent illumination, indicating that the FP transfer function is superior in high spatial frequency regions.

Direct superresolution for realistic image reconstruction.

Traditional superresolution techniques employ optimizers, priors, and regularizers to deliver stable, appealing restorations even though deviating from the real, ground-truth scene. We have developed a non-regularized superresolution algorithm that directly solves a fully-characterized multi-shift imaging reconstruction problem to achieve realistic restorations without being penalized by improper assumptions made in the inverse problem. An adaptive frequency-based filtering scheme is introduced to upper bound the reconstruction errors while still producing more fine details as compared with previous methods when inaccurate shift estimation, noise, and blurring scenarios are considered.

Diffusion MRI with Semi-Automated Segmentation Can Serve as a Restricted Predictive Biomarker of the Therapeutic Response of Liver Metastasis.

PURPOSE: To assess the value of semi-automated segmentation applied to diffusion MRI for predicting the therapeutic response of liver metastasis. METHODS: Conventional diffusion weighted magnetic resonance imaging (MRI) was performed using b-values of 0, 150, 300 and 450s/mm(2) at baseline and days 4, 11 and 39 following initiation of a new chemotherapy regimen in a pilot study with 18 women with 37 liver metastases from primary breast cancer. A semi-automated segmentation approach was used to identify liver metastases. Linear regression analysis was used to assess the relationship between baseline values of the apparent diffusion coefficient (ADC) and change in tumor size by day 39. RESULTS: A semi-automated segmentation scheme was critical for obtaining the most reliable ADC measurements. A statistically significant relationship between baseline ADC values and change in tumor size at day 39 was observed for minimally treated patients with metastatic liver lesions measuring 2-5cm in size (p=0.002), but not for heavily treated patients with the same tumor size range (p=0.29), or for tumors of smaller or larger sizes. ROC analysis identified a baseline threshold ADC value of 1.33µm(2)/ms as 75% sensitive and 83% specific for identifying non-responding metastases in minimally treated patients with 2-5cm liver lesions. CONCLUSION: Quantitative imaging can substantially benefit from a semi-automated segmentation scheme. Quantitative diffusion MRI results can be predictive of therapeutic outcome in selected patients with liver metastases, but not for all liver metastases, and therefore should be considered to be a restricted biomarker.

Automated breast segmentation of fat and water MR images using dynamic programming.

RATIONALE AND OBJECTIVES: To develop and test an algorithm that outlines the breast boundaries using information from fat and water magnetic resonance images. MATERIALS AND METHODS: Three algorithms were implemented and tested using registered fat and water magnetic resonance images. Two of the segmentation algorithms are simple extensions of the techniques used for contrast-enhanced images: one algorithm uses clustering and local gradient (CLG) analysis and the other algorithm uses a Hessian-based sheetness filter (HSF). The third segmentation algorithm uses k-means++ and dynamic programming (KDP) for finding the breast pixels. All three algorithms separate the left and right breasts using either a fixed region or a morphological method. The performance is quantified using a mutual overlap (Dice) metric and a pectoral muscle boundary error. The algorithms are evaluated against three manual tracers using 266 breast images from 14 female subjects. RESULTS: The KDP algorithm has a mean overlap percentage improvement that is statistically significant relative to the HSF and CLG algorithms. When using a fixed region to remove the tissue between breasts with tracer 1 as a reference, the KDP algorithm has a mean overlap of 0.922 compared to 0.864 (P < .01) for HSF and 0.843 (P < .01) for CLG. The performance of KDP is very similar to tracers 2 (0.926 overlap) and 3 (0.929 overlap). The performance analysis in terms of pectoral muscle boundary error showed that the fraction of the muscle boundary within three pixels of reference tracer 1 is 0.87 using KDP compared to 0.578 for HSF and 0.617 for CLG. Our results show that the performance of the KDP algorithm is independent of breast density. CONCLUSIONS: We developed a new automated segmentation algorithm (KDP) to isolate breast tissue from magnetic resonance fat and water images. KDP outperforms the other techniques that focus on local analysis (CLG and HSF) and yields a performance similar to human tracers.

Multi-polarization fringe projection imaging for high dynamic range objects.

Traditional fringe-projection three-dimensional (3D) imaging techniques struggle to estimate the shape of high dynamic range (HDR) objects where detected fringes are of limited visibility. Moreover, saturated regions of specular reflections can completely block any fringe patterns, leading to lost depth information. We propose a multi-polarization fringe projection (MPFP) imaging technique that eliminates saturated points and enhances the fringe contrast by selecting the proper polarized channel measurements. The developed technique can be easily extended to include measurements captured under different exposure times to obtain more accurate shape rendering for very HDR objects.

Analysis of second-harmonic-generation microscopy in a mouse model of ovarian carcinoma.

Second-harmonic-generation (SHG) imaging of mouse ovaries ex vivo was used to detect collagen structure changes accompanying ovarian cancer development. Dosing with 4-vinylcyclohexene diepoxide and 7,12-dimethylbenz[a]anthracene resulted in histologically confirmed cases of normal, benign abnormality, dysplasia, and carcinoma. Parameters for each SHG image were calculated using the Fourier transform matrix and gray-level co-occurrence matrix (GLCM). Cancer versus normal and cancer versus all other diagnoses showed the greatest separation using the parameters derived from power in the highest-frequency region and GLCM energy. Mixed effects models showed that these parameters were significantly different between cancer and normal (P<0.008). Images were classified with a support vector machine, using 25% of the data for training and 75% for testing. Utilizing all images with signal greater than the noise level, cancer versus not-cancer specimens were classified with 81.2% sensitivity and 80.0% specificity, and cancer versus normal specimens were classified with 77.8% sensitivity and 79.3% specificity. Utilizing only images with greater than of 75% of the field of view containing signal improved sensitivity and specificity for cancer versus normal to 81.5% and 81.1%. These results suggest that using SHG to visualize collagen structure in ovaries could help with early cancer detection.

Task-based evaluation of segmentation algorithms for diffusion-weighted MRI without using a gold standard.

In many studies, the estimation of the apparent diffusion coefficient (ADC) of lesions in visceral organs in diffusion-weighted (DW) magnetic resonance images requires an accurate lesion-segmentation algorithm. To evaluate these lesion-segmentation algorithms, region-overlap measures are used currently. However, the end task from the DW images is accurate ADC estimation, and the region-overlap measures do not evaluate the segmentation algorithms on this task. Moreover, these measures rely on the existence of gold-standard segmentation of the lesion, which is typically unavailable. In this paper, we study the problem of task-based evaluation of segmentation algorithms in DW imaging in the absence of a gold standard. We first show that using manual segmentations instead of gold-standard segmentations for this task-based evaluation is unreliable. We then propose a method to compare the segmentation algorithms that does not require gold-standard or manual segmentation results. The no-gold-standard method estimates the bias and the variance of the error between the true ADC values and the ADC values estimated using the automated segmentation algorithm. The method can be used to rank the segmentation algorithms on the basis of both the ensemble mean square error and precision. We also propose consistency checks for this evaluation technique.