Shahid A. Haider

Apparent Ultra-High

A promising, recently explored, alternative to ultra-high b-value diffusion weighted imaging (UHB-DWI) is apparent ultra-high b-value diffusion-weighted image reconstruction (AUHB-DWR), where a computational model is used to assist in the reconstruction of apparent DW images at ultra-high b-values. Firstly, we present a novel approach to AUHB-DWR that aims to improve image quality. We formulate the reconstruction of an apparent DW image as a hidden conditional random field (HCRF) in which tissue model diffusion parameters act as hidden states in this random field. The second contribution of this paper is a new generation of fully connected conditional random fields, called the hidden stochastically fully connected conditional random fields (HSFCRF) that allows for efficient inference with significantly reduced computational complexity via stochastic clique structures. The proposed AUHB-DWR algorithms, HCRF and HSFCRF, are evaluated quantitatively in nine different patient cases using Fishers criteria, probability of error, and coefficient of variation metrics to validate its effectiveness for the purpose of improving intensity delineation between expert identified suspected cancerous and healthy tissue within the prostate gland. The proposed methods are also examined using a prostate phantom, where the apparent ultra-high b-value DW images reconstructed using the tested AUHB-DWR methods are compared with real captured UHB-DWI. The results illustrate that the proposed AUHB-DWR methods has improved reconstruction quality and improved intensity delineation compared with existing AUHB-DWR approaches.

b

Traditional methods for early detection of melanoma rely upon a dermatologist to visually assess a skin lesion using the ABCDE (Asymmetry, Border irregularity, Color variegation, Diameter, Evolution) criteria before confirmation can be done through biopsy by a pathologist. However, this visual assessment strategy taken by dermatologists is hampered by clinician subjectivity and suffers from low sensitivity. Computer-aided diagnostic methods based on dermatological photographs are being developed to aid in the melanoma diagnosis process, but most of these methods rely only on superficial, topographic features that can be limiting in characterizing melanoma. In this work, a hybrid feature model is introduced for characterizing skin lesions that combines low-level and high-level features, and augments them with a set of physiological features extracted from dermatological photographs using a nearest-neighbor nonlinear model to improve classification performance. The physiological features extracted from the lesion for the proposed hybrid feature model include those based on: i) eumelanin concentrations, ii) pheomelanin concentrations, and iii) blood oxygen saturation. The proposed hybrid feature model was evaluated on 206 dermatological photographs of skin lesions (119 confirmed melanoma cases, 87 confirmed non-melanoma cases) using a cross validation scheme. The experimental results show that the proposed hybrid feature model, with integrated physiological features, provided improved sensitivity, specificity, precision and accuracy for the purpose of melanoma classification.

-Value Diffusion-Weighted Image Reconstruction via Hidden Conditional Random Fields

Fluorescence microscopy is an essential part of a biologist’s toolkit, allowing assaying of many parameters like subcellular localization of proteins, changes in cytoskeletal dynamics, protein-protein interactions, and the concentration of specific cellular ions. A fundamental challenge with using fluorescence microscopy is the presence of noise. This study introduces a novel approach to reducing noise in fluorescence microscopy images. The noise reduction problem is posed as a Maximum A Posteriori estimation problem, and solved using a novel random field model called stochastically-connected random field (SRF), which combines random graph and field theory. Experimental results using synthetic and real fluorescence microscopy data show the proposed approach achieving strong noise reduction performance when compared to several other noise reduction algorithms, using quantitative metrics. The proposed SRF approach was able to achieve strong performance in terms of signal-to-noise ratio in the synthetic results, high signal to noise ratio and contrast to noise ratio in the real fluorescence microscopy data results, and was able to maintain cell structure and subtle details while reducing background and intra-cellular noise.

Enhanced classification of malignant melanoma lesions via the integration of physiological features from dermatological photographs.

The current diagnostic technique for melanoma solely relies on the surface level of skin and under-skin information is neglected. Since physiological features of skin such as melanin are closely related to development of melanoma, the non-linear physiological feature extraction model based on random forest regression is proposed. The proposed model characterizes the concentration of eumelanin and pheomelanin from standard camera images or dermoscopic images, which are conventionally used for diagnosis of melanoma. For the validation, the phantom study and the separability test using clinical images were conducted and compared against the state-of-the art non-linear and linear feature extraction models. The results showed that the proposed model outperformed other comparing models in phantom and clinical experiments. Promising results show that the quantitative characterization of skin features, which is provided by the proposed method, can allow dermatologists and clinicians to make a more accurate and improved diagnosis of melanoma.

Fluorescence microscopy image noise reduction using a stochastically-connected random field model.

The current computer-aided melanoma diagnostic technique employs the features that extracted from the surface level of skin, and any under-skin information is ignored. Since the colour formation of lesion is vastly influenced by the concentration of melanin, the quantitative features of spatial heterogeneity of melanin concentration was proposed. To quantify the spatial heterogeneity of eumelanin and pheomelanin concentrations, the concentration maps were divided into two and the Earth movers distance between the concentration clusters on both sides was measured. The proposed features were evaluated on 206 dermatological images (119 melanoma cases, 87 benign cases) using a cross-validation scheme. The results show that adopting spatial heterogeneity of melanin concentrations improved the sensitivity, specificity, and accuracy of diagnosing melanoma.

Physiological characterization of skin lesion using non-linear random forest regression model

Mobile robots that rely on vision, for navigation and object detection, use saliency approaches to identify a set of potential candidates to recognize. The state of the art in saliency detection for mobile robotics often rely upon visible light imaging, using conventional camera setups, to distinguish an object against its surroundings based on factors such as feature compactness, heterogeneity and/or homogeneity. We are demonstrating a novel multi- polarimetric saliency detection approach which uses multiple measured polarization states of a scene. We leverage the light-material interaction known as Fresnel reflections to extract rotationally invariant multi-polarimetric textural representations to then train a high dimensional sparse texture model. The multi-polarimetric textural distinctiveness is characterized using a conditional probability framework based on the sparse texture model which is then used to determine the saliency at each pixel of the scene. It was observed that through the inclusion of additional polarized states into the saliency analysis, we were able to compute noticeably improved saliency maps in scenes where objects are difficult to distinguish from their background due to color intensity similarities between the object and its surroundings.

Quantitative features for computer-aided melanoma classification using spatial heterogeneity of eumelanin and pheomelanin concentrations

Observing the circular dichroism (CD) caused by organic molecules in biological fluids can provide powerful indicators of patient health and provide diagnostic clues for treatment. Methods for this kind of analysis involve tabletop devices that weigh tens of kilograms with costs on the order of tens of thousands of dollars, making them prohibitive in point-of-care diagnostic applications. In an e ort to reduce the size, cost, and complexity of CD estimation systems for point-of-care diagnostics, we propose a novel method for CD estimation that leverages a vortex half-wave retarder in between two linear polarizers and a two-dimensional photodetector array to provide an overall complexity reduction in the system. This enables the measurement of polarization variations across multiple polarizations after they interact with a biological sample, simultaneously, without the need for mechanical actuation. We further discuss design considerations of this methodology in the context of practical applications to point-of-care diagnostics.

Multi-polarimetric textural distinctiveness for outdoor robotic saliency detection

An ideal laser is a useful tool for the analysis of biological systems. In particular, the polarization property of lasers can allow for the concentration of important organic molecules in the human body, such as proteins, amino acids, lipids, and carbohydrates, to be estimated. However, lasers do not always work as intended and there can be effects such as mode hopping and thermal drift that can cause time-varying intensity fluctuations. The causes of these effects can be from the surrounding environment, where either an unstable current source is used or the temperature of the surrounding environment is not temporally stable. This intensity fluctuation can cause bias and error in typical organic molecule concentration estimation techniques. In a low-resource setting where cost must be limited and where environmental factors, like unregulated power supplies and temperature, cannot be controlled, the hardware required to correct for these intensity fluctuations can be prohibitive. We propose a method for computational laser intensity stabilisation that uses Bayesian state estimation to correct for the time-varying intensity fluctuations from electrical and thermal instabilities without the use of additional hardware. This method will allow for consistent intensities across all polarization measurements for accurate estimates of organic molecule concentrations.

Computational circular dichroism estimation for point-of-care diagnostics via vortex half-wave retarders

A novel approach to spatio-temporal saliency detection in video is proposed. Saliency computation is considered as an optimization problem that maximizes the energy of a fully-connected graphical model based on spatio-temporal feature distinctiveness. Each pixel in a video is modeled by a node, and the spatio-temporal feature distinctiveness between pixels by edges connecting the nodes in the graph. The computational complexity is addressed by compressing the fully-connected graph into an abstracted, fully-connected graph with far fewer nodes, where each node in the new graph characterizes nodal groups. The saliency value of each pixel is then computed based on spatio-temporal feature distinctiveness and the energy representation of its nodal group given the constructed graphical model. Experimental results show that our approach outperforms existing approaches to spatio-temporal salient region detection.

Computational laser intensity stabilisation for organic molecule concentration estimation in low-resource settings

Lung cancer is the second most common cancer in the United States, regardless of gender. Lung cancer staging is a critical process for diagnosis and prognosis that is commonly done through the analysis of computed tomography of the chest. Analysis can be done by extracting quantitative metrics from clinician defined contours; however, defining contours manually can be a time consuming process which, in an environment where fast staging is necessary, is undesirable. Semi-automatic methods are desirable for minimizing user input while achieving similar contouring results. However, they can be hampered by image noise and complex shapes. In this paper, we present a single-click, semi-automatic contouring method for lung nodules that formulates the problem as a texture-based hierarchical conditional random field, making it robust to noise and capable of contouring complex shapes. Comparing against other semi-automatic contouring methods using clinician contours as ground truth, the proposed method achieves higher results in the sensitivity, Dice, and Jaccard metrics while achieving comparable results with the specificity and accuracy metrics.