Andrew Cameron

MAPS: A Quantitative Radiomics Approach for Prostate Cancer Detection

This paper presents a quantitative radiomics feature model for performing prostate cancer detection using multiparametric MRI (mpMRI). It incorporates a novel tumor candidate identification algorithm to efficiently and thoroughly identify the regions of concern and constructs a comprehensive radiomics feature model to detect tumorous regions. In contrast to conventional automated classification schemes, this radiomics-based feature model aims to ground its decisions in a way that can be interpreted and understood by the diagnostician. This is done by grouping features into high-level feature categories which are already used by radiologists to diagnose prostate cancer: Morphology, Asymmetry, Physiology, and Size (MAPS), using biomarkers inspired by the PI-RADS guidelines for performing structured reporting on prostate MRI. Clinical mpMRI data were collected from 13 men with histology-confirmed prostate cancer and labeled by an experienced radiologist. These annotated data were used to train classifiers using the proposed radiomics-driven feature model in order to evaluate the classification performance. The preliminary experimental results indicated that the proposed model outperformed each of its constituent feature groups as well as a comparable conventional mpMRI feature model. A further validation of the proposed algorithm will be conducted using a larger dataset as future work.

Correlated diffusion imaging

BackgroundProstate cancer is one of the leading causes of cancer death in the male population. Fortunately, the prognosis is excellent if detected at an early stage. Hence, the detection and localization of prostate cancer is crucial for diagnosis, as well as treatment via targeted focal therapy. New imaging techniques can potentially be invaluable tools for improving prostate cancer detection and localization.MethodsIn this study, we introduce a new form of diffusion magnetic resonance imaging called correlated diffusion imaging, where the tissue being imaged is characterized by the joint correlation of diffusion signal attenuation across multiple gradient pulse strengths and timings. By taking into account signal attenuation at different water diffusion motion sensitivities, correlated diffusion imaging can provide improved delineation between cancerous tissue and healthy tissue when compared to existing diffusion imaging modalities.ResultsQuantitative evaluation using receiver operating characteristic (ROC) curve analysis, tissue class separability analysis, and visual assessment by an expert radiologist were performed to study correlated diffusion imaging for the task of prostate cancer diagnosis. These results are compared with that obtained using T2-weighted imaging and standard diffusion imaging (via the apparent diffusion coefficient (ADC)). Experimental results suggest that correlated diffusion imaging provide improved delineation between healthy and cancerous tissue and may have potential as a diagnostic tool for cancer detection and localization in the prostate gland.ConclusionsA new form of diffusion magnetic resonance imaging called correlated diffusion imaging (CDI) was developed for the purpose of aiding radiologists in cancer detection and localization in the prostate gland. Preliminary results show CDI shows considerable promise as a diagnostic aid for radiologists in the detection and localization of prostate cancer.

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

In this work, we present a new multi-parametric magnetic resonance imaging (MP-MRI) texture feature model for automatic detection of prostate cancer. In addition to commonly used imaging sequences in conventional MP-MRI, namely T2-weighted MRI (T2w) and diffusion-weighted imaging (DWI), our proposed MP-MRI texture feature model uses computed high-b DWI (CHB-DWI) and a new diffusion imaging sequence called correlated diffusion imaging (CDI). A set of texture features was calculated for both the conventional MP-MRI and new MP-MRI texture feature model. We evaluated the performance of the proposed MP-MRI texture feature model via leave-one-patient-out cross-validation using a Bayesian classifier trained on cancerous and healthy tissue samples obtained from real clinical MP-MRI datasets. The proposed MP-MRI texture feature model outperformed the conventional model (i.e., T2w+DWI) with regard to cancer detection accuracy.

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

High b-value diffusion-weighted imaging is a promising approach for diagnosing and localizing cancer in the prostate gland. However, ultra-high b-value imaging is difficult to achieve at a high signal-to-noise ratio due to hardware limitations. An alternative approach being recently discussed is computed diffusion-weighted imaging, which allows for estimation of ultra-high b-value images from a set of diffusion-weighted acquisitions with different magnetic gradient strengths. This paper presents a quantitative investigative analysis of the improvement in tumour separability in the prostate gland from using ultra-high b-value computed diffusion-weighted imaging. The analysis computes ultra-high b-value images for six patient cases and investigates the separability of the tumour from the normal prostate gland. Based on quantitative metrics such as expected probability of classification error and the Receiver Operating Characteristic (ROC), it was found that the use of ultra-high computed diffusion-weighted imaging may significantly improve tumour separability, with a b-value around 3000 providing optimal separability.

A Multi-Parametric Diffusion Magnetic Resonance Imaging Texture Feature Model for Prostate Cancer Analysis

Optical coherence tomography (OCT) allows for non-invasive 3D visualization of biological tissue at cellular level resolution. Often hindered by speckle noise, the visualization of important biological tissue details in OCT that can aid disease diagnosis can be improved by speckle noise compensation. A challenge with handling speckle noise is its inherent non-stationary nature, where the underlying noise characteristics vary with the spatial location. In this study, an innovative speckle noise compensation method is presented for handling the non-stationary traits of speckle noise in OCT imagery. The proposed approach centers on a non-stationary spline-based speckle noise modeling strategy to characterize the speckle noise. The novel method was applied to ultra high-resolution OCT (UHROCT) images of the human retina and corneo-scleral limbus acquired in-vivo that vary in tissue structure and optical properties. Test results showed improved performance of the proposed novel algorithm compared to a number of previously published speckle noise compensation approaches in terms of higher signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and better overall visual assessment.

Quantitative investigative analysis of tumour separability in the prostate gland using ultra-high b-value computed diffusion imaging

Multiparametric MRI has shown considerable promise as a diagnostic tool for prostate cancer grading. Diffusion-weighted MRI (DWI) has shown particularly strong potential for improving the delineation between cancerous and healthy tissue in the prostate gland. Current automated diagnostic methods using multiparametric MRI, however, tend to either use low-level features, which are difficult to interpret by radiologists and clinicians, or use highly subjective heuristic methods. We propose a novel strategy comprising a tumor candidate identification scheme and a hybrid textural-morphological feature model for delineating between cancerous and non-cancerous tumor candidates in the prostate gland via multiparametric MRI. Experimental results using clinical multiparametric MRI datasets show that the proposed strategy has strong potential as a diagnostic tool to aid radiologists and clinicians identify and detect prostate cancer more efficiently and effectively.

Stochastic speckle noise compensation in optical coherence tomography using non-stationary spline-based speckle noise modelling.

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.

Multiparametric MRI prostate cancer analysis via a hybrid morphological-textural model.

Low-dose computed tomography (CT) reduces radiation exposure but decreases signal-to-noise ratio (SNR) and diagnostic capabilities. Noise compensation can improve SNR so low-dose CT can provide valuable information for diagnosis without risking patient radiation exposure. In this study, a novel noise-compensated CT reconstruction method that uses spatially adaptive Monte-Carlo sampling to produce noise-compensated reconstructions is investigated. By adapting to local noise statistics, a non-parametric estimation of the noise-free image is computed that successfully handles non-stationary noise found in low-dose CT images. Using phantom and real low-dose CT images, effective noise suppression is shown to be accomplished while maintaining structures and details.

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

A promising approach to prostate cancer diagnosis is multi-parametric MRI. One of the key modalities used in multi-parametric MRI is diffusion weighted MRI. Using multiple diffusion weighted MR acquisitions taken with different magnetic gradient strengths, the apparent diffusion coefficient (ADC) is calculated and can be used to identify tumors in the prostate. Current algorithms used to calculate ADC assume a parametric measurement model, but this assumption is not true due to the presence of additional phenomena during the acquisition process. A novel Non-parametric Estimated ADC (NEstA) algorithm is proposed which uses a Monte Carlo strategy to learn the inherent measurement distribution model based on the underlying statistical behavior of the DWI measurements to estimate the ADC values. The proposed algorithm is compared to the results of the commonly used least-squares (LS) estimation algorithm for computing ADC values. Nine test patient cases with visible tumors in the prostate gland were processed using both algorithms and compared visually. It was found that NEstA produced ADC data with reduced artifacts while preserving structure. Quantitatively, Fishers criterion measuring the separability of the healthy prostate and tumor tissues was computed for the nine patient cases, comparing the NEstA and LS methods. It was found that Fishers criterion increased with the NEstA method, meaning the separation of classes was more pronounced.