Superpixel-based roughness measure for multispectral satellite image segmentation

The new generation of artificial satellites is providing a huge amount of Earth observation images whose exploitation can report invaluable benefits, both economical and environmental. However, only a small fraction of this data volume has been analyzed, mainly due to the large human resources needed for that task. In this sense, the development of unsupervised methodologies for the analysis of these images is a priority. In this work, a new unsupervised segmentation algorithm for satellite images is proposed. This algorithm is based on the rough-set theory, and it is inspired by a previous segmentation algorithm defined in the RGB color domain. The main contributions of the new algorithm are: (i) extending the original algorithm to four spectral bands; (ii) the concept of the superpixel is used in order to define the neighborhood similarity of a pixel adapted to the local characteristics of each image; (iii) and two new region merged strategies are proposed and evaluated in order to establish the final number of regions in the segmented image. The experimental results show that the proposed approach improves the results provided by the original method when both are applied to satellite images with different spectral and spatial resolutions.

Application of active and transfer learning to wound image segmentation

Wound management is a fundamental task in standard clinical practice. Automated solutions already exist for humans, but there is a lack of applications on wound management for pets. The importance of a precise and efficient wound assessment is helpful to improve diagnosis and to increase the effectiveness of treatment plans for the chronic wounds. The goal of the research was to propose an automated pipeline capable of segmenting natural light-reflected wound images of animals. Two datasets composed by light-reflected images were used in this work: Deepskin dataset, 1564 human wound images obtained during routine dermatological exams, with 145 manual annotated images; Petwound dataset, a set of 290 wound photos of dogs and cats with 0 annotated images. Two implementations of U-Net Convolutioal Neural Network model were proposed for the automated segmentation. Active Semi-Supervised Learning techniques were applied for human-wound images to perform segmentation from 10% of annotated images. Then the same models were trained, via Transfer Learning, adopting an Active Semi- upervised Learning to unlabelled animal-wound images. The combination of the two training strategies proved their effectiveness in generating large amounts of annotated samples (94% of Deepskin, 80% of PetWound) with the minimal human intervention. The correctness of automated segmentation were evaluated by clinical experts at each round of training thus we can assert that the results obtained in this thesis stands as a reliable solution to perform a correct wound image segmentation. The use of Transfer Learning and Active Semi-Supervied Learning allows to minimize labelling effort from clinicians, even requiring no starting manual annotation at all. Moreover the performances of the model with limited number of parameters suggest the implementation of smartphone-based application to this topic, helping the future standardization of light-reflected images as acknowledge medical images.

Optimisation of paediatrics computed radiography for full spine curvature measurements using a phantom: a pilot study

Aim: Optimise a set of exposure factors, with the lowest effective dose, to delineate spinal curvature with the modified Cobb method in a full spine using computed radiography (CR) for a 5-year-old paediatric anthropomorphic phantom. Methods: Images were acquired by varying a set of parameters: positions (antero-posterior (AP), posteroanterior (PA) and lateral), kilo-voltage peak (kVp) (66-90), source-to-image distance (SID) (150 to 200cm), broad focus and the use of a grid (grid in/out) to analyse the impact on E and image quality (IQ). IQ was analysed applying two approaches: objective [contrast-to-noise-ratio/(CNR] and perceptual, using 5 observers. Monte-Carlo modelling was used for dose estimation. Cohen’s Kappa coefficient was used to calculate inter-observer-variability. The angle was measured using Cobb’s method on lateral projections under different imaging conditions. Results: PA promoted the lowest effective dose (0.013 mSv) compared to AP (0.048 mSv) and lateral (0.025 mSv). The exposure parameters that allowed lower dose were 200cm SID, 90 kVp, broad focus and grid out for paediatrics using an Agfa CR system. Thirty-seven images were assessed for IQ and thirty-two were classified adequate. Cobb angle measurements varied between 16°±2.9 and 19.9°±0.9. Conclusion: Cobb angle measurements can be performed using the lowest dose with a low contrast-tonoise ratio. The variation on measurements for this was ±2.9° and this is within the range of acceptable clinical error without impact on clinical diagnosis. Further work is recommended on improvement to the sample size and a more robust perceptual IQ assessment protocol for observers.

Cervical soft tissue imaging using a mobile CBCT scanner with a flat panel detector in comparison with corresponding CT and MRI data sets

OBJECTIVE: The aim of this study was to evaluate soft tissue image quality of a mobile cone-beam computed tomography (CBCT) scanner with an integrated flat-panel detector. STUDY DESIGN: Eight fresh human cadavers were used in this study. For evaluation of soft tissue visualization, CBCT data sets and corresponding computed tomography (CT) and magnetic resonance imaging (MRI) data sets were acquired. Evaluation was performed with the help of 10 defined cervical anatomical structures. RESULTS: The statistical analysis of the scoring results of 3 examiners revealed the CBCT images to be of inferior quality regarding the visualization of most of the predefined structures. Visualization without a significant difference was found regarding the demarcation of the vertebral bodies and the pyramidal cartilages, the arteriosclerosis of the carotids (compared with CT), and the laryngeal skeleton (compared with MRI). Regarding arteriosclerosis of the carotids compared with MRI, CBCT proved to be superior. CONCLUSIONS: The integration of a flat-panel detector improves soft tissue visualization using a mobile CBCT scanner.

Comparison of organ doses and image quality between CT and flat panel XperCT scans in wrist and inner ear examinations.

The aim of this study was to evaluate and compare organ doses delivered to patients in wrist and petrous bone examinations using a multislice spiral computed tomography (CT) and a C-arm cone-beam CT equipped with a flat-panel detector (XperCT). For this purpose, doses to the target organ, i.e. wrist or petrous bone, together with those to the most radiosensitive nearby organs, i.e. thyroid and eye lens, were measured and compared. Furthermore, image quality was compared for both imaging systems and different acquisition modes using a Catphan phantom. Results show that both systems guarantee adequate accuracy for diagnostic purposes for wrist and petrous bone examinations. Compared with the CT scanner, the XperCT system slightly reduces the dose to target organs and shortens the overall duration of the wrist examination. In addition, using the XperCT enables a reduction of the dose to the eye lens during head scans (skull base and ear examinations).

Subcutaneous Tissue Thickness is an Independent Predictor of Image Noise in Cardiac CT

Background: Few data on the definition of simple robust parameters to predict image noise in cardiac computed tomography (CT) exist. Objectives: To evaluate the value of a simple measure of subcutaneous tissue as a predictor of image noise in cardiac CT. Methods: 86 patients underwent prospective ECG-gated coronary computed tomographic angiography (CTA) and coronary calcium scoring (CAC) with 120 kV and 150 mA. The image quality was objectively measured by the image noise in the aorta in the cardiac CTA, and low noise was defined as noise < 30HU. The chest anteroposterior diameter and lateral width, the image noise in the aorta and the skin-sternum (SS) thickness were measured as predictors of cardiac CTA noise. The association of the predictors and image noise was performed by using Pearson correlation. Results: The mean radiation dose was 3.5 ± 1.5 mSv. The mean image noise in CT was 36.3 ± 8.5 HU, and the mean image noise in non-contrast scan was 17.7 ± 4.4 HU. All predictors were independently associated with cardiac CTA noise. The best predictors were SS thickness, with a correlation of 0.70 (p < 0.001), and noise in the non-contrast images, with a correlation of 0.73 (p < 0.001). When evaluating the ability to predict low image noise, the areas under the ROC curve for the non-contrast noise and for the SS thickness were 0.837 and 0.864, respectively. Conclusion: Both SS thickness and CAC noise are simple accurate predictors of cardiac CTA image noise. Those parameters can be incorporated in standard CT protocols to adequately adjust radiation exposure.

Prospective Estimation of Radiation Dose and Image Quality for Optimized CT Performance

X-ray computed tomography (CT) is a non-invasive medical imaging technique that generates cross-sectional images by acquiring attenuation-based projection measurements at multiple angles. Since its first introduction in the 1970s, substantial technical improvements have led to the expanding use of CT in clinical examinations. CT has become an indispensable imaging modality for the diagnosis of a wide array of diseases in both pediatric and adult populations [1, 2]. Currently, approximately 272 million CT examinations are performed annually worldwide, with nearly 85 million of these in the United States alone [3]. Although this trend has decelerated in recent years, CT usage is still expected to increase mainly due to advanced technologies such as multi-energy [4], photon counting [5], and cone-beam CT [6].

Despite the significant clinical benefits, concerns have been raised regarding the population-based radiation dose associated with CT examinations [7]. From 1980 to 2006, the effective dose from medical diagnostic procedures rose six-fold, with CT contributing to almost half of the total dose from medical exposure [8]. For each patient, the risk associated with a single CT examination is likely to be minimal. However, the relatively large population-based radiation level has led to enormous efforts among the community to manage and optimize the CT dose.

As promoted by the international campaigns Image Gently and Image Wisely, exposure to CT radiation should be appropriate and safe [9, 10]. It is thus a responsibility to optimize the amount of radiation dose for CT examinations. The key for dose optimization is to determine the minimum amount of radiation dose that achieves the targeted image quality [11]. Based on such principle, dose optimization would significantly benefit from effective metrics to characterize radiation dose and image quality for a CT exam. Moreover, if accurate predictions of the radiation dose and image quality were possible before the initiation of the exam, it would be feasible to personalize it by adjusting the scanning parameters to achieve a desired level of image quality. The purpose of this thesis is to design and validate models to quantify patient-specific radiation dose prospectively and task-based image quality. The dual aim of the study is to implement the theoretical models into clinical practice by developing an organ-based dose monitoring system and an image-based noise addition software for protocol optimization.

More specifically, Chapter 3 aims to develop an organ dose-prediction method for CT examinations of the body under constant tube current condition. The study effectively modeled the anatomical diversity and complexity using a large number of patient models with representative age, size, and gender distribution. The dependence of organ dose coefficients on patient size and scanner models was further evaluated. Distinct from prior work, these studies use the largest number of patient models to date with representative age, weight percentile, and body mass index (BMI) range.

With effective quantification of organ dose under constant tube current condition, Chapter 4 aims to extend the organ dose prediction system to tube current modulated (TCM) CT examinations. The prediction, applied to chest and abdominopelvic exams, was achieved by combining a convolution-based estimation technique that quantifies the radiation field, a TCM scheme that emulates modulation profiles from major CT vendors, and a library of computational phantoms with representative sizes, ages, and genders. The prospective quantification model is validated by comparing the predicted organ dose with the dose estimated based on Monte Carlo simulations with TCM function explicitly modeled.

Chapter 5 aims to implement the organ dose-estimation framework in clinical practice to develop an organ dose-monitoring program based on a commercial software (Dose Watch, GE Healthcare, Waukesha, WI). In the first phase of the study we focused on body CT examinations, and so the patient’s major body landmark information was extracted from the patient scout image in order to match clinical patients against a computational phantom in the library. The organ dose coefficients were estimated based on CT protocol and patient size as reported in Chapter 3. The exam CTDIvol, DLP, and TCM profiles were extracted and used to quantify the radiation field using the convolution technique proposed in Chapter 4.

With effective methods to predict and monitor organ dose, Chapters 6 aims to develop and validate improved measurement techniques for image quality assessment. Chapter 6 outlines the method that was developed to assess and predict quantum noise in clinical body CT images. Compared with previous phantom-based studies, this study accurately assessed the quantum noise in clinical images and further validated the correspondence between phantom-based measurements and the expected clinical image quality as a function of patient size and scanner attributes.

Chapter 7 aims to develop a practical strategy to generate hybrid CT images and assess the impact of dose reduction on diagnostic confidence for the diagnosis of acute pancreatitis. The general strategy is (1) to simulate synthetic CT images at multiple reduced-dose levels from clinical datasets using an image-based noise addition technique; (2) to develop quantitative and observer-based methods to validate the realism of simulated low-dose images; (3) to perform multi-reader observer studies on the low-dose image series to assess the impact of dose reduction on the diagnostic confidence for multiple diagnostic tasks; and (4) to determine the dose operating point for clinical CT examinations based on the minimum diagnostic performance to achieve protocol optimization.

Chapter 8 concludes the thesis with a summary of accomplished work and a discussion about future research.

CT Image Electron Density Quantification in Regions with Metal Implants: Implications for Radiotherapy Treatment Planning

In radiotherapy planning, computed tomography (CT) images are used to quantify the electron density of tissues and provide spatial anatomical information. Treatment planning systems use these data to calculate the expected spatial distribution of absorbed dose in a patient. CT imaging is complicated by the presence of metal implants which cause increased image noise, produce artifacts throughout the image and can exceed the available range of CT number values within the implant, perturbing electron density estimates in the image. Furthermore, current dose calculation algorithms do not accurately model radiation transport at metal-tissue interfaces. Combined, these issues adversely affect the accuracy of dose calculations in the vicinity of metal implants. As the number of patients with orthopedic and dental implants grows, so does the need to deliver safe and effective radiotherapy treatments in the presence of implants. The Medical Physics group at the Cancer Centre of Southeastern Ontario and Queen's University has developed a Cobalt-60 CT system that is relatively insensitive to metal artifacts due to the high energy, nearly monoenergetic Cobalt-60 photon beam. Kilovoltage CT (kVCT) images, including images corrected using a commercial metal artifact reduction tool, were compared to Cobalt-60 CT images throughout the treatment planning process, from initial imaging through to dose calculation. An effective metal artifact reduction algorithm was also implemented for the Cobalt-60 CT system. Electron density maps derived from the same kVCT and Cobalt-60 CT images indicated the impact of image artifacts on estimates of photon attenuation for treatment planning applications. Measurements showed that truncation of CT number data in kVCT images produced significant mischaracterization of the electron density of metals. Dose measurements downstream of metal inserts in a water phantom were compared to dose data calculated using CT images from kVCT and Cobalt-60 systems with and without artifact correction. The superior accuracy of electron density data derived from Cobalt-60 images compared to kVCT images produced calculated dose with far better agreement with measured results. These results indicated that dose calculation errors from metal image artifacts are primarily due to misrepresentation of electron density within metals rather than artifacts surrounding the implants.

How Low Can We Go in Contrast-Enhanced CT Imaging of the Chest?: A Dose-Finding Cadaver Study Using the Model-based Iterative Image Reconstruction Approach.

RATIONALE AND OBJECTIVES: Dose reduction may compromise patients because of a decrease of image quality. Therefore, the amount of dose savings in new dose-reduction techniques needs to be thoroughly assessed. To avoid repeated studies in one patient, chest computed tomography (CT) scans with different dose levels were performed in corpses comparing model-based iterative reconstruction (MBIR) as a tool to enhance image quality with current standard full-dose imaging. MATERIALS AND METHODS: Twenty-five human cadavers were scanned (CT HD750) after contrast medium injection at different, decreasing dose levels D0-D5 and respectively reconstructed with MBIR. The data at full-dose level, D0, have been additionally reconstructed with standard adaptive statistical iterative reconstruction (ASIR), which represented the full-dose baseline reference (FDBR). Two radiologists independently compared image quality (IQ) in 3-mm multiplanar reformations for soft-tissue evaluation of D0-D5 to FDBR (-2, diagnostically inferior; -1, inferior; 0, equal; +1, superior; and +2, diagnostically superior). For statistical analysis, the intraclass correlation coefficient (ICC) and the Wilcoxon test were used. RESULTS: Mean CT dose index values (mGy) were as follows: D0/FDBR = 10.1 ± 1.7, D1 = 6.2 ± 2.8, D2 = 5.7 ± 2.7, D3 = 3.5 ± 1.9, D4 = 1.8 ± 1.0, and D5 = 0.9 ± 0.5. Mean IQ ratings were as follows: D0 = +1.8 ± 0.2, D1 = +1.5 ± 0.3, D2 = +1.1 ± 0.3, D3 = +0.7 ± 0.5, D4 = +0.1 ± 0.5, and D5 = -1.2 ± 0.5. All values demonstrated a significant difference to baseline (P < .05), except mean IQ for D4 (P = .61). ICC was 0.91. CONCLUSIONS: Compared to ASIR, MBIR allowed for a significant dose reduction of 82% without impairment of IQ. This resulted in a calculated mean effective dose below 1 mSv.

CT study of the performance of reciprocating and oscillatory motions in flattened root canal areas

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Abdominal multislice CT for obese patients: effect on image quality and radiation dose in a phantom study

RATIONALE AND OBJECTIVES: To evaluate the effect of a modified abdominal multislice computed tomography (CT) protocol for obese patients on image quality and radiation dose. MATERIALS AND METHODS: An adult female anthropomorphic phantom was used to simulate obese patients by adding one or two 4-cm circumferential layers of fat-equivalent material to the abdominal portion. The phantom was scanned with a subcutaneous fat thickness of 0, 4, and 8 cm using the following parameters (detector configuration/beam pitch/table feed per rotation/gantry rotation time/kV/mA): standard protocol A: 16 x 0.625 mm/1.75/17.5 mm/0.5 seconds/140/380, and modified protocol B: 16 x 1.25 mm/1.375/27.5 mm/1.0 seconds/140/380. Radiation doses to six abdominal organs and the skin, image noise values, and contrast-to-noise ratios (CNRs) were analyzed. Statistical analysis included analysis of variance, Wilcoxon rank sum, and Student's t-test (P < .05). RESULTS: Applying the modified protocol B with one or two fat rings, the image noise decreased significantly (P < .05), and simultaneously, the CNR increased significantly compared with protocol A (P < .05). Organ doses significantly increased, up to 54.7%, comparing modified protocol B with one fat ring to the routine protocol A with no fat rings (P < .05). However, no significant change in organ dose was seen for protocol B with two fat rings compared with protocol A without fat rings (range -2.1% to 8.1%) (P > .05). CONCLUSIONS: Using a modified abdominal multislice CT protocol for obese patients with 8 cm or more of subcutaneous fat, image quality can be substantially improved without a significant increase in radiation dose to the abdominal organs.

Measurement of structural anisotropy in femoral trabecular bone using clinical-resolution CT images

Discrepancies in finite-element model predictions of bone strength may be attributed to the simplified modeling of bone as an isotropic structure due to the resolution limitations of clinical-level Computed Tomography (CT) data. The aim of this study is to calculate the preferential orientations of bone (the principal directions) and the extent to which bone is deposited more in one direction compared to another (degree of anisotropy). Using 100 femoral trabecular samples, the principal directions and degree of anisotropy were calculated with a Gradient Structure Tensor (GST) and a Sobel Structure Tensor (SST) using clinical-level CT. The results were compared against those calculated with the gold standard Mean-Intercept-Length (MIL) fabric tensor using micro-CT. There was no significant difference between the GST and SST in the calculation of the main principal direction (median error=28°), and the error was inversely correlated to the degree of transverse isotropy (r=−0.34, p<0.01). The degree of anisotropy measured using the structure tensors was weakly correlated with the MIL-based measurements (r=0.2, p<0.001). Combining the principal directions with the degree of anisotropy resulted in a significant increase in the correlation of the tensor distributions (r=0.79, p<0.001). Both structure tensors were robust against simulated noise, kernel sizes, and bone volume fraction. We recommend the use of the GST because of its computational efficiency and ease of implementation. This methodology has the promise to predict the structural anisotropy of bone in areas with a high degree of anisotropy, and may improve the in vivo characterization of bone.

Reducing CT radiation dose with iterative reconstruction algorithms: the influence of scan and reconstruction parameters on image quality and CTDIvol

OBJECTIVES In this phantom CT study, we investigated whether images reconstructed using filtered back projection (FBP) and iterative reconstruction (IR) with reduced tube voltage and current have equivalent quality. We evaluated the effects of different acquisition and reconstruction parameter settings on image quality and radiation doses. Additionally, patient CT studies were evaluated to confirm our phantom results. METHODS Helical and axial 256 multi-slice computed tomography scans of the phantom (Catphan(®)) were performed with varying tube voltages (80-140kV) and currents (30-200mAs). 198 phantom data sets were reconstructed applying FBP and IR with increasing iterations, and soft and sharp kernels. Further, 25 chest and abdomen CT scans, performed with high and low exposure per patient, were reconstructed with IR and FBP. Two independent observers evaluated image quality and radiation doses of both phantom and patient scans. RESULTS In phantom scans, noise reduction was significantly improved using IR with increasing iterations, independent from tissue, scan-mode, tube-voltage, current, and kernel. IR did not affect high-contrast resolution. Low-contrast resolution was also not negatively affected, but improved in scans with doses <5mGy, although object detectability generally decreased with the lowering of exposure. At comparable image quality levels, CTDIvol was reduced by 26-50% using IR. In patients, applying IR vs. FBP resulted in good to excellent image quality, while tube voltage and current settings could be significantly decreased. CONCLUSIONS Our phantom experiments demonstrate that image quality levels of FBP reconstructions can also be achieved at lower tube voltages and tube currents when applying IR. Our findings could be confirmed in patients revealing the potential of IR to significantly reduce CT radiation doses.