Browsing by Subject "Image analysis"

Diagnosis, prognosis, and treatment of many ocular and neurodegenerative diseases, including achromatopsia (ACHM), require the visualization of microscopic structures in the eye. The development of adaptive optics ophthalmic imaging systems has made high resolution visualization of ocular microstructures possible. These systems include the confocal and split detector adaptive optics scanning light ophthalmoscope (AOSLO), which can visualize human cone and rod photoreceptors in vivo. However, the avalanche of data generated by such imaging systems is often too large, costly, and time consuming to be evaluated manually, making automation necessary. The few currently available automated cone photoreceptor identification methods are unable to reliably identify rods and cones in low-quality images of diseased eyes, which are common in clinical practice.

This dissertation describes the development of automated methods for the analysis of AOSLO images, specifically focusing on cone and rod photoreceptors which are the most commonly studied biomarker using these systems. A traditional image processing approach, which requires little training data and takes advantage of intuitive image features, is presented for detecting cone photoreceptors in split detector AOSLO images. The focus is then shifted to deep learning using convolutional neural networks (CNNs), which have been shown in other image processing tasks to be more adaptable and produce better results than classical image processing approaches, at the cost of requiring more training data and acting as a “black box”. A CNN based method for detecting cones is presented and validated against state-of-the-art cone detections methods for confocal and split detector images. The CNN based method is then modified to take advantage of multimodal AOSLO information in order to detect cones in images of subjects with ACHM. Finally, a significantly faster CNN based approach is developed for the classification and detection of cones and rods, and is validated on images from both healthy and pathological subjects. Additionally, several image processing and analysis works on optical coherence tomography images that were carried out during the completion of this dissertation are presented.

The completion of this dissertation led to fast and accurate image analysis tools for the quantification of biomarkers in AOSLO images pertinent to an array of retinal diseases, lessening the reliance on subjective and time-consuming manual analysis. For the first time, automatic methods have comparable accuracy to humans for quantifying photoreceptors in diseased eyes. This is an important step in the long-term goal to facilitate early diagnosis, accurate prognosis, and personalized treatment of ocular and neurodegenerative diseases through optimal visualization and quantification of microscopic structures in the eye.

Purpose: RECA (Radiotherapy Enhanced by Cherenkov photo-Activation) is a novel treatment with potential to add an anti-cancer immunogenic component through Cherenkov activation of a photo-chemotherapeutic agent (psoralen). This work investigates RECA in a novel tissue-representative in-vitro model consisting of 4T1 murine cancer cells grown on thin slices of viable rat-brain tissue.Methods: Accurate estimation of viable tumor burden is of foundational importance to this work. A CellProfiler pipeline was created and optimized and validated on realistic simulated data/images where the ground truth of number of colonies and integrated intensity was known. Simulated data sets mimicked key features of real experimental data including colony spatial and size distributions, contaminant and stray light signals, colony overlap, and noise. The optimized CellProfiler pipeline was then applied to the original 4T1 tumor cell images to determine colony growth over five days. Several experiments were conducted prior to the RECA experiment to determine the best protocol. The first tested the optimal concentration of psoralen, loading technique, and type of psoralen by co-incubating 4T1 cells with psoralen for differing times and concentrations and subsequently exposing them to 365nm radiation at variable energy fluences. The plates were tested for 4T1 cell viability using Celltiter-glo and luciferase assay 48-72 hours later depending on confluence of the control plate. Another experiment tested the output of the CellProfiler image analysis for relative growth over time measuring 4T1 mCherry cells plated on rat brain slices at 10k,20k,30k,40k,50k cells per hemisphere. For the RECA experiment, six 12-well plates, each containing 1cm of agarose supporting a 400 µm thick coronal slice of viable rat brain tissue were created. Each plate represented one arm of an experiment incorporating the psoralen derivative 4’-aminomethyl trioxsalen (AMT): MV control, MV+AMT, kV control, kV+AMT, no irradiation control, and AMT alone control. 20,000 4T1 cells expressing both mCherry-flourescent and firefly luciferase-luminescent reporter proteins plated on each rat brain slice hemisphere. For the AMT arms, the cells were co-incubated with 1 µM AMT for 1 hour prior to plating. The MV arms received 4 Gy from a 15 MV linear accelerator beam, and the kV arms received 4 Gy from 160 keV photons. Images were taken of the plates each day for 5 days with a Zeiss Lumar microscope with rhodamine filter for the mCherry protein signal. Results: The CellProfiler pipeline measured integrated intensity of the 10 simulated images that best approximated the images from the experiment with an accuracy of 99.23% ± 0.75%. Further analysis on images with increasing colonies, background, and noise showed the pipeline was accurate on images with variable features. These results gave confidence that the same pipeline could be used on images from this experiment. AMT was found to be a more effective psoralen (0.43 ± 0.22% cell survival after 48hr) relative to 8-MOP (31.3% ± 3.7% cell survival after 72hr). The psoralen cell loading was found to be optimal at 1µM for 1 hr prior to plating. The analysis of the cell titration images showed a significant increase in signal for each increase in cells plated on day one and for all subsequent days except for the 20k cell arm. Additionally, the growth in signal for the plates was consistent between the arms except for the 20k arm due to extra signal on the periphery of the slice likely from displaced cells. Integrated intensity analysis of the 4T1 mCherry cells revealed a significant decrease in tumor proliferation by day 5 between the MV control (5.65±0.78-fold growth) and MV AMT (3.49±-0.52-fold growth) arms. This result is consistent with the hypothesis that psoralen is being activated, causing the decreased proliferation seen in MV AMT arm. The kV control and kV AMT arms had a smaller decrease in proliferation when compared to their MV counterparts (6.73±1.24 and 5.26±0.59-fold growth respectively). The growth observed in the Dark control arm was consistent with the 13.6 ± 1.5 hour doubling time for 4T1 cells. In the MV AMT arm, there were punctuated regions of increased signal in 7/12 wells not corresponding to colonies, making segmentation for this arm challenging. The viability of the brain slice was assessed each day and found to be stable over the 5 days. Conclusions: The technique of testing image analytic software on simulated images proved to be an effective tool to verify the software’s accuracy. A similar technique can be applied to images with new and challenging features. The rat brain slice model gives the opportunity to both generate Cherenkov in real tissue while providing a 3D matrix for the colonies to grow, which is an improvement to the 2D well plate culture for this experiment. This new model adds challenges of proper image analysis with cell autofluorescence as well as cell clumping. The preliminary results are consistent with psoralen activated in RECA treated cells causing decreased proliferation for the MV arm. Further work is needed to confirm and quantify the effect.

Cell division and growth are complex processes fundamental to all living organisms. In the budding yeast, Saccharomyces cerevisiae, these two processes are known to be coordinated with one another as a cell's mass must roughly double before division. Moreover, cell-cycle progression is dependent on cell size with smaller cells at birth generally taking more time in the cell cycle. This dependence is a signature of size control. Systems biology is an emerging field that emphasizes connections or dependencies between biological entities and processes over the characteristics of individual entities. Statistical models provide a quantitative framework for describing and analyzing these dependencies. In this dissertation, I take a statistical systems biology approach to study cell division and growth and the dependencies within and between these two processes, drawing on observations from richly informative microscope images and time-lapse movies. I review the current state of knowledge on these processes, highlighting key results and open questions from the biological literature. I then discuss my development of machine learning and statistical approaches to extract cell-cycle information from microscope images and to better characterize the cell-cycle progression of populations of cells. In addition, I analyze single cells to uncover correlation in cell-cycle progression, evaluate potential models of dependence between growth and division, and revisit classical assertions about budding yeast size control. This dissertation presents a unique perspective and approach towards comprehensive characterization of the coordination between growth and division.

Retinal and corneal diseases are the leading causes of global vision impairment. The advent of high‐resolution ophthalmic imaging technology enables the visualization of internal and external structures of the eye, thereby aiding clinicians in the assessment of these diseases. However, there are high costs and constraints associated with manual image analysis by clinicians. Therefore, the development of automatic algorithms with suitable performance for clinical practice is crucial to alleviate the burden on clinicians and improve the efficiency of the clinical workflow. This dissertation describes the development of a deep learning‐based image analysis framework consisting of computational algorithms for accurate automatic medical image analysis applied to ophthalmology for the clinical assessment of retinal and corneal diseases.

In Chapter 2, we developed longitudinal algorithms for the assessment of 3‐D medical images with applications for optical coherence tomography (OCT). For clinical application, we used the algorithms for the assessment of macular telangiectasia type 2 and USH2A‐related retinitis pigmentosa in large‐scale clinical trials. We also introduced the concept of longitudinal transfer learning to develop personalized algorithms and introduced a new paradigm for validating automatic algorithms for clinical applications beyond performance metrics.

In Chapter 3, we developed region‐based algorithms for the assessment of 2‐D medical images with applications for slit lamp photography (SLP). For clinical application, we used the algorithms for the assessment of microbial keratitis in clinical studies from the USA and India. We also demonstrated the potential of automatic SLP-based measurements for assessing ocular function and paved the way for the development of objective and standardized strategies for the assessment of corneal diseases.

In Chapter 4, we developed hybrid algorithms for the joint assessment of spatially-registered 2‐D and 3‐D medical images with applications for indocyanine green angiography and OCT. For clinical application, we used the algorithms for the assessment of polypoidal choroidal vasculopathy, a sub‐type of age‐related macular degeneration. We introduced hybrid network architectures with fusion attention modules that effectively processed co‐registered images of different dimensionalities to enable sharing of learned features between the different imaging modalities. We also derived quantitative definitions of important imaging biomarkers of the disease.

In conclusion, this dissertation provides an image analysis framework for clinical management of retinal and corneal diseases. Our deep learning‐based computational algorithms can accurately identify and quantify important disease biomarkers automatically and have been validated for several aspects of clinical applicability. These algorithms can be used by clinicians to improve the efficiency of the clinical workflow, leading to timely and precise medical decisions, ultimately improving patient outcomes.

Purpose: Radiotherapy Enhanced by Cherenkov photo-Activation (RECA) is a novel radiation treatment method that seeks an anti-cancer effect with the introduction of a psoralen compound administered for treatment. The goal of the RECA method is to enhance standard radiation therapy treatments with the addition of psoralen being photo-activated by Cherenkov radiation that is generated during radiotherapy. The purpose of this work is to investigate the effectiveness of RECA on 4T1 mCherry FLuc breast cancer cells seeded on a psoralen-baked-agarose-based rat brain slice.Methods: A previously established CellProfiler pipeline, developed in our lab by Holden et al., was used to assess tumor burden on rat brain slices used for a tissue-equivalent medium for cell culturing. The CellProfiler pipeline was implemented on images of 4T1 breast cancer cells growing over the course of four to five days post-treatment to measure the average intensity of fluorescing cells. Prior to the RECA experiment, multiple preparatory experiments were conducted to refine and optimize experimental techniques. The first preparatory experiment tested the possibility of a plate reader bias effect, i.e., signal from nearby wells contributing to signal of other wells, seen during measurements of cell luminescence within individual wells of a clear-bottom 96-well plate. A CellTiter-Glo endpoint readout was taken 48-hours post-treatment for an endpoint measure to assess the if there was any added signal from nearby wells in the clear-bottom plates. The next experiment tested whether fractionation of dose was feasible and preferrable to single dose treatment by irradiating 4T1 mCherry Fluc cells with 2 Gy and 4 Gy of kV radiation with and without fractionation. An endpoint CellTiter-Glo readout was conducted 72 hours post-treatment to assess cell viability between the treatment plans. Additional preparatory experiments investigated whether psoralen-doped agarose was an effective method for cell loading. A 30 µM AMT-baked agar base was placed in half of the wells in plates with 4T1 mCherry Fluc cells seeded on brain slices on top of the agar. One plate received no treatment and one plate received treatment of 365 nm UVA, and an endpoint Firefly Luciferase reporter assay was conducted 48 hours post-treatment to assess cell viability between the conditions. For the RECA experiment, five 12-well plates, each containing 1 cm of agar with a 400 µm thick coronal slice of rat brain tissue, were given one of five conditions of treatment: no treatment, 4.95 Gy of fractionated kV or MV treatment, or 4.95 Gy of whole kV of MV treatment. Each plate condition consisted of six wells containing AMT-baked agar and six wells containing a standard agar base. After irradiation, images were taken of each of the plates for each day over the course of five days five days with a Zeiss Lumar microscope. The microscope was equipped with a rhodamine filter to analyze the luminescence readings from each well for assessment of cell viability. Results: The preparatory experiments all yielded results that allowed for development of the RECA experiment procedure. Investigation of the plate reader effect showed that background signal from nearby wells was not leaking into well signal readout, with all wells having nearly consistent signal throughout all the wells. Fractionating the dose was found to be preferable because it decreased cell viability less than delivering all dose at once, which floored cell viability. Testing psoralen-doped agar demonstrated that this is an effective delivery method for psoralen to intercalate with cells. The RECA experiment utilizing kV and MV whole dose conditions allowed comparison between irradiations with and without a fractionation scheme. The Firefly Luciferase reporter assay signal for the MV treatment conditions showed less cell viability than the Dark control conditions for both AMT and DMSO. Additionally, the whole dose MV conditions demonstrated a more pronounced decrease in cell viability than the fractionated MV conditions, as expected. The CellProfiler analysis demonstrated the same trends with the whole dose MV AMT condition (8.54 ± 0.99-fold increase) and whole dose MV DMSO condition (11.80 ± 0.70-fold increase) demonstrating less cell viability than the Dark AMT (13.41 ± 0.83-fold increase) and Dark DMSO (14.11 ± 0.62-fold increase). Interestingly, there was not a significant difference in cell viability seen between the fractionated and whole dose conditions. Conclusions: The procedural techniques developed for the analysis of the RECA effect during the preparatory experiments ruled out a plate reader effect and demonstrated that introducing fractionation and psoralen-baked agar is effective. The testing of the fractionation scheme used for kV irradiations proved to be sufficient for decreasing cell viability without killing all the cells. Additionally, the testing of the psoralen-baked agarose slabs proved to be an adequate psoralen delivery method when compared to methods that used cells suspended in psoralen treated media in prior studies. When these changes to the procedure were introduced together during MV irradiations, the RECA effect did not clearly replicate the results demonstrated during kV irradiations in the preparatory experiments. Further investigation is required to confirm and validate the RECA effect generated during radiotherapy.

Quantitative imaging is important in medical imaging. Physical phantoms are used. There is reason to believe that anthropomorphic physical phatoms are better than uniform phantoms. To investigate this question, we develop a novel imaging metrology with a phatient-based phantom and apply its use to several digital breast tomosytneshis machines. At the same time, we use the traditional means of assessing image quality. Our results show a strong dependence on image performance with the type of phantom used. Furthermore, we demonstrate the feasibility of this metrology in real, clinical applications.

Tree-like structures are fundamental in nature. A wide variety of two-dimensional imaging techniques allow us to image trees. However, an image of a tree typically includes spurious branch crossings and the original relationships of ancestry among edges may be lost. We present a methodology for estimating the most likely topology of a rooted, directed, three-dimensional tree given a single two-dimensional image of it. We regularize this inverse problem via a prior parametric tree-growth model that realistically captures the morphology of a wide variety of trees. We show that the problem of estimating the optimal tree has linear complexity if ancestry is known, but is NP-hard if it is lost. For the latter case, we present both a greedy approximation algorithm and a heuristic search algorithm that effectively explore the space of possible trees. Experimental results on retinal vessel, plant root, and synthetic tree datasets show that our methodology is both accurate and efficient.