Image Analysis Methods for Sugar Beet Phenotyping

In un mondo che richiede sempre maggiormente un'automazione delle attività della catena produttiva industriale, la computer vision rappresenta uno strumento fondamentale perciò che viene già riconosciuta internazionalmente come la Quarta Rivoluzione Industriale o Industry 4.0. Avvalendomi di questo strumento ho intrapreso presso l'azienda Syngenta lo studio della problematica della conta automatica del numero di foglie di una pianta. Il problema è stato affrontato utilizzando due differenti approcci, ispirandosi alla letteratura. All'interno dell'elaborato è presente anche la descrizione progettuale di un ulteriore metodo, ad oggi non presente in letteratura. Le metodologie saranno spiegate in dettaglio ed i risultati ottenuti saranno confrontati utilizzando i primi due approcci. Nel capitolo finale si trarranno le conclusioni sulle basi dei risultati ottenuti e dall'analisi degli stessi.

Single fluoroscopic image based 2D/3D reconstruction of a scaled, patient-specific vertebral model

Purpose Accurate three-dimensional (3D) models of lumbar vertebrae can enable image-based 3D kinematic analysis. The common approach to derive 3D models is by direct segmentation of CT or MRI datasets. However, these have the disadvantages that they are expensive, timeconsuming and/or induce high-radiation doses to the patient. In this study, we present a technique to automatically reconstruct a scaled 3D lumbar vertebral model from a single two-dimensional (2D) lateral fluoroscopic image. Methods Our technique is based on a hybrid 2D/3D deformable registration strategy combining a landmark-to-ray registration with a statistical shape model-based 2D/3D reconstruction scheme. Fig. 1 shows different stages of the reconstruction process. Four cadaveric lumbar spine segments (total twelve lumbar vertebrae) were used to validate the technique. To evaluate the reconstruction accuracy, the surface models reconstructed from the lateral fluoroscopic images were compared to the associated ground truth data derived from a 3D CT-scan reconstruction technique. For each case, a surface-based matching was first used to recover the scale and the rigid transformation between the reconstructed surface model Results Our technique could successfully reconstruct 3D surface models of all twelve vertebrae. After recovering the scale and the rigid transformation between the reconstructed surface models and the ground truth models, the average error of the 2D/3D surface model reconstruction over the twelve lumbar vertebrae was found to be 1.0 mm. The errors of reconstructing surface models of all twelve vertebrae are shown in Fig. 2. It was found that the mean errors of the reconstructed surface models in comparison to their associated ground truths after iterative scaled rigid registrations ranged from 0.7 mm to 1.3 mm and the rootmean squared (RMS) errors ranged from 1.0 mm to 1.7 mm. The average mean reconstruction error was found to be 1.0 mm. Conclusion An accurate, scaled 3D reconstruction of the lumbar vertebra can be obtained from a single lateral fluoroscopic image using a statistical shape model based 2D/3D reconstruction technique. Future work will focus on applying the reconstructed model for 3D kinematic analysis of lumbar vertebrae, an extension of our previously-reported imagebased kinematic analysis. The developed method also has potential applications in surgical planning and navigation.

Fully Automatic Segmentation of Brain Tumor Images using Support Vector Machine Classiffication in Combination with Hierarchical Conditional Random Field Regularization

Delineating brain tumor boundaries from magnetic resonance images is an essential task for the analysis of brain cancer. We propose a fully automatic method for brain tissue segmentation, which combines Support Vector Machine classification using multispectral intensities and textures with subsequent hierarchical regularization based on Conditional Random Fields. The CRF regularization introduces spatial constraints to the powerful SVM classification, which assumes voxels to be independent from their neighbors. The approach first separates healthy and tumor tissue before both regions are subclassified into cerebrospinal fluid, white matter, gray matter and necrotic, active, edema region respectively in a novel hierarchical way. The hierarchical approach adds robustness and speed by allowing to apply different levels of regularization at different stages. The method is fast and tailored to standard clinical acquisition protocols. It was assessed on 10 multispectral patient datasets with results outperforming previous methods in terms of segmentation detail and computation times.

Multi-Scale Modeling for Image Analysis of Brain Tumor Studies

Image-based modeling of tumor growth combines methods from cancer simulation and medical imaging. In this context, we present a novel approach to adapt a healthy brain atlas to MR images of tumor patients. In order to establish correspondence between a healthy atlas and a pathologic patient image, tumor growth modeling in combination with registration algorithms is employed. In a first step, the tumor is grown in the atlas based on a new multi-scale, multi-physics model including growth simulation from the cellular level up to the biomechanical level, accounting for cell proliferation and tissue deformations. Large-scale deformations are handled with an Eulerian approach for finite element computations, which can operate directly on the image voxel mesh. Subsequently, dense correspondence between the modified atlas and patient image is established using nonrigid registration. The method offers opportunities in atlasbased segmentation of tumor-bearing brain images as well as for improved patient-specific simulation and prognosis of tumor progression.

Feature-invariant image registration method for quantification of surgical outcomes in patients with craniosynostosis: a preliminary study

Craniosynostosis consists of a premature fusion of the sutures in an infant skull that restricts skull and brain growth. During the last decades, there has been a rapid increase of fundamentally diverse surgical treatment methods. At present, the surgical outcome has been assessed using global variables such as cephalic index, head circumference, and intracranial volume. However, these variables have failed in describing the local deformations and morphological changes that may have a role in the neurologic disorders observed in the patients. This report describes a rigid image registration-based method to evaluate outcomes of craniosynostosis surgical treatments, local quantification of head growth, and indirect intracranial volume change measurements. The developed semiautomatic analysis method was applied to computed tomography data sets of a 5-month-old boy with sagittal craniosynostosis who underwent expansion of the posterior skull with cranioplasty. Quantification of the local changes between pre- and postoperative images was quantified by mapping the minimum distance of individual points from the preoperative to the postoperative surface meshes, and indirect intracranial volume changes were estimated. The proposed methodology can provide the surgeon a tool for the quantitative evaluation of surgical procedures and detection of abnormalities of the infant skull and its development.

How valuable are multiple treatment comparison methods in evidence-based health-care evaluation?

Objectives To compare the use of pair-wise meta-analysis methods to multiple treatment comparison (MTC) methods for evidence-based health-care evaluation to estimate the effectiveness and cost-effectiveness of alternative health-care interventions based on the available evidence. Methods Pair-wise meta-analysis and more complex evidence syntheses, incorporating an MTC component, are applied to three examples: 1) clinical effectiveness of interventions for preventing strokes in people with atrial fibrillation; 2) clinical and cost-effectiveness of using drug-eluting stents in percutaneous coronary intervention in patients with coronary artery disease; and 3) clinical and cost-effectiveness of using neuraminidase inhibitors in the treatment of influenza. We compare the two synthesis approaches with respect to the assumptions made, empirical estimates produced, and conclusions drawn. Results The difference between point estimates of effectiveness produced by the pair-wise and MTC approaches was generally unpredictable—sometimes agreeing closely whereas in other instances differing considerably. In all three examples, the MTC approach allowed the inclusion of randomized controlled trial evidence ignored in the pair-wise meta-analysis approach. This generally increased the precision of the effectiveness estimates from the MTC model. Conclusions The MTC approach to synthesis allows the evidence base on clinical effectiveness to be treated as a coherent whole, include more data, and sometimes relax the assumptions made in the pair-wise approaches. However, MTC models are necessarily more complex than those developed for pair-wise meta-analysis and thus could be seen as less transparent. Therefore, it is important that model details and the assumptions made are carefully reported alongside the results.

Evaluation of a portable image overlay projector for the visualisation of surgical navigation data: phantom studies

Presenting visual feedback for image-guided surgery on a monitor requires the surgeon to perform time-consuming comparisons and diversion of sight and attention away from the patient. Deficiencies in previously developed augmented reality systems for image-guided surgery have, however, prevented the general acceptance of any one technique as a viable alternative to monitor displays. This work presents an evaluation of the feasibility and versatility of a novel augmented reality approach for the visualisation of surgical planning and navigation data. The approach, which utilises a portable image overlay device, was evaluated during integration into existing surgical navigation systems and during application within simulated navigated surgery scenarios.

Pathology hinting as the combination of automatic segmentation with a statistical shape model

With improvements in acquisition speed and quality, the amount of medical image data to be screened by clinicians is starting to become challenging in the daily clinical practice. To quickly visualize and find abnormalities in medical images, we propose a new method combining segmentation algorithms with statistical shape models. A statistical shape model built from a healthy population will have a close fit in healthy regions. The model will however not fit to morphological abnormalities often present in the areas of pathologies. Using the residual fitting error of the statistical shape model, pathologies can be visualized very quickly. This idea is applied to finding drusen in the retinal pigment epithelium (RPE) of optical coherence tomography (OCT) volumes. A segmentation technique able to accurately segment drusen in patients with age-related macular degeneration (AMD) is applied. The segmentation is then analyzed with a statistical shape model to visualize potentially pathological areas. An extensive evaluation is performed to validate the segmentation algorithm, as well as the quality and sensitivity of the hinting system. Most of the drusen with a height of 85.5 microm were detected, and all drusen at least 93.6 microm high were detected.

Graph-Based Multi-Surface Segmentation of OCT Data Using Trained Hard and Soft Constraints

Optical coherence tomography (OCT) is a well-established image modality in ophthalmology and used daily in the clinic. Automatic evaluation of such datasets requires an accurate segmentation of the retinal cell layers. However, due to the naturally low signal to noise ratio and the resulting bad image quality, this task remains challenging. We propose an automatic graph-based multi-surface segmentation algorithm that internally uses soft constraints to add prior information from a learned model. This improves the accuracy of the segmentation and increase the robustness to noise. Furthermore, we show that the graph size can be greatly reduced by applying a smart segmentation scheme. This allows the segmentation to be computed in seconds instead of minutes, without deteriorating the segmentation accuracy, making it ideal for a clinical setup. An extensive evaluation on 20 OCT datasets of healthy eyes was performed and showed a mean unsigned segmentation error of 3.05 ±0.54 μm over all datasets when compared to the average observer, which is lower than the inter-observer variability. Similar performance was measured for the task of drusen segmentation, demonstrating the usefulness of using soft constraints as a tool to deal with pathologies.

Registry for the Evaluation of the Prognostik value of a novel integrated imaging approach combining Single Photon Emission Computed Tomography with coronary calcification imaging (REPROSPECT)

AIMS: Although an added diagnostic and prognostic value of the global coronary artery calcification (CAC) score as an adjunct to single-photon emission computed tomography (SPECT)-myocardial perfusion image (MPI) has been repeatedly documented, none of the previous studies took advantage of the anatomic information provided by the unenhanced cardiac CT. Therefore, no co-registration has so far been used to match a myocardial perfusion defect with calcifications in the subtending coronary artery. To evaluate the prognostic value of integrating SPECT-MPI with CAC images were obtained from non-enhanced cardiac computed tomography (CT) for attenuation correction to predict major adverse cardiac events (MACE). METHODS AND RESULTS: Follow-up was obtained in 462 patients undergoing a 1-day stress/rest (99m)Tc-teterofosmin SPECT and non-enhanced cardiac CT for attenuation correction. Survival free of MACE was determined using the Kaplan-Meier method. After integrating MPI and CT findings, patients were divided into three groups (i) MPI defect matched by calcification (CAC ≥ 1) in the subtending coronary artery (ii) unmatched MPI and CT finding (iii) normal finding by MPI and CT. At a mean follow-up of 34.5 ± 13 months, a MACE was observed in 80 patients (33 death, 6 non-fatal myocardial infarction, 9 hospitalizations due to unstable angina, and 32 revascularizations). Survival analysis revealed the most unfavourable outcome (P < 0.001 log-rank test) for patients with a matched finding. CONCLUSION: In the present study, a novel approach using a combined integration of cardiac SPECT-CAC imaging allows for refined risk stratification, as a matched defect emerged as an independent predictor of MACE.

Cardiac image fusion from stand-alone SPECT and CT: clinical experience

Myocardial perfusion imaging with SPECT (SPECT-MPI) and 64-slice CT angiography (CTA) are both established techniques for the noninvasive evaluation of coronary artery disease (CAD). Three-dimensional (3D) SPECT/CT image fusion may offer an incremental diagnostic value by integrating both sets of information. We report our first clinical experiences with fused 3D SPECT/CT in CAD patients. METHODS: Thirty-eight consecutive patients with at least 1 perfusion defect on SPECT-MPI (1-d adenosine stress/rest SPECT with (99m)Tc-tetrofosmin) and 64-slice CTA were included. 3D volume-rendered fused SPECT/CT images were generated and compared with the findings from the side-by-side analysis with regard to coronary lesion interpretation by assigning the perfusion defects to their corresponding coronary lesion. RESULTS: The fused SPECT/CT images added information on pathophysiologic lesion severity in 27 coronary stenoses (22%) of 12 patients (29%) (P<0.001). Among 40 equivocal lesions on side-by-side analysis, the fused interpretation confirmed hemodynamic significance in 14 lesions and excluded functional relevance in 10 lesions. In 3 lesions, assignment of perfusion defect and coronary lesion appeared to be reliable on side-by-side analysis but proved to be inaccurate on fused interpretation. Added diagnostic information by SPECT/CT was more commonly found in patients with stenoses of small vessels (P=0.004) and involvement of diagonal branches (P=0.01). CONCLUSION: In addition to being intuitively convincing, 3D SPECT/CT fusion images in CAD may provide added diagnostic information on the functional relevance of coronary artery lesions.

Semi-automatic segmentation of fetal cardiac cavities: progress towards an automated fetal echocardiogram

OBJECTIVE: To develop a novel application of a tool for semi-automatic volume segmentation and adapt it for analysis of fetal cardiac cavities and vessels from heart volume datasets. METHODS: We studied retrospectively virtual cardiac volume cycles obtained with spatiotemporal image correlation (STIC) from six fetuses with postnatally confirmed diagnoses: four with normal hearts between 19 and 29 completed gestational weeks, one with d-transposition of the great arteries and one with hypoplastic left heart syndrome. The volumes were analyzed offline using a commercially available segmentation algorithm designed for ovarian folliculometry. Using this software, individual 'cavities' in a static volume are selected and assigned individual colors in cross-sections and in 3D-rendered views, and their dimensions (diameters and volumes) can be calculated. RESULTS: Individual segments of fetal cardiac cavities could be separated, adjacent segments merged and the resulting electronic casts studied in their spatial context. Volume measurements could also be performed. Exemplary images and interactive videoclips showing the segmented digital casts were generated. CONCLUSION: The approach presented here is an important step towards an automated fetal volume echocardiogram. It has the potential both to help in obtaining a correct structural diagnosis, and to generate exemplary visual displays of cardiac anatomy in normal and structurally abnormal cases for consultation and teaching.

Infrared Thermography Enhancements for Concrete Bridge Evaluation

Infrared thermography is a well-recognized non-destructive testing technique for evaluating concrete bridge elements such as bridge decks and piers. However, overcoming some obstacles and limitations are necessary to be able to add this invaluable technique to the bridge inspector's tool box. Infrared thermography is based on collecting radiant temperature and presenting the results as a thermal infrared image. Two methods considered in conducting an infrared thermography test include passive and active. The source of heat is the main difference between these two approaches of infrared thermography testing. Solar energy and ambient temperature change are the main heat sources in conducting a passive infrared thermography test, while active infrared thermography involves generating a temperature gradient using an external source of heat other than sun. Passive infrared thermography testing was conducted on three concrete bridge decks in Michigan. Ground truth information was gathered through coring several locations on each bridge deck to validate the results obtained from the passive infrared thermography test. Challenges associated with data collection and processing using passive infrared thermography are discussed and provide additional evidence to confirm that passive infrared thermography is a promising remote sensing tool for bridge inspections. To improve the capabilities of the infrared thermography technique for evaluation of the underside of bridge decks and bridge girders, an active infrared thermography technique using the surface heating method was developed in the laboratory on five concrete slabs with simulated delaminations. Results from this study demonstrated that active infrared thermography not only eliminates some limitations associated with passive infrared thermography, but also provides information regarding the depth of the delaminations. Active infrared thermography was conducted on a segment of an out-of-service prestressed box beam and cores were extracted from several locations on the beam to validate the results. This study confirms the feasibility of the application of active infrared thermography on concrete bridges and of estimating the size and depth of delaminations. From the results gathered in this dissertation, it was established that applying both passive and active thermography can provide transportation agencies with qualitative and quantitative measures for efficient maintenance and repair decision-making.