A review on segmentation of positron emission tomography images

Spectral Clustering Predicts Tumor Tissue Heterogeneity Using Dynamic 18F-FDG PET: A Complement to the Standard Compartmental Modeling Approach

In this study, we described and validated an unsupervised segmentation algorithm for the assessment of tumor heterogeneity using dynamic ¹⁸F-FDG PET. The aim of our study was to objectively evaluate the proposed method and make comparisons with compartmental modeling parametric maps and SUV segmentations using simulations of clinically relevant tumor tissue types. Methods: An irreversible 2-tissue-compartmental model was implemented to simulate clinical and preclinical ¹⁸F-FDG PET time-activity curves using population-based arterial input functions (80 clinical and 12 preclinical) and the kinetic parameter values of 3 tumor tissue types. The simulated time-activity curves were corrupted with different levels of noise and used to calculate the tissue-type misclassification errors of spectral clustering (SC), parametric maps, and SUV segmentation. The utility of the inverse noise variance- and Laplacian score-derived frame weighting schemes before SC was also investigated. Finally, the SC scheme with the best results was tested on a dynamic ¹⁸F-FDG measurement of a mouse bearing subcutaneous colon cancer and validated using histology. Results: In the preclinical setup, the inverse noise variance-weighted SC exhibited the lowest misclassification errors (8.09%-28.53%) at all noise levels in contrast to the Laplacian score-weighted SC (16.12%-31.23%), unweighted SC (25.73%-40.03%), parametric maps (28.02%-61.45%), and SUV (45.49%-45.63%) segmentation. The classification efficacy of both weighted SC schemes in the clinical case was comparable to the unweighted SC. When applied to the dynamic ¹⁸F-FDG measurement of colon cancer, the proposed algorithm accurately identified densely vascularized regions from the rest of the tumor. In addition, the segmented regions and clusterwise average time-activity curves showed excellent correlation with the tumor histology. Conclusion: The promising results of SC mark its position as a robust tool for quantification of tumor heterogeneity using dynamic PET studies. Because SC tumor segmentation is based on the intrinsic structure of the underlying data, it can be easily applied to other cancer types as well.

Combined fuzzy logic and random walker algorithm for PET image tumor delineation

PURPOSE

The random walk (RW) technique serves as a powerful tool for PET tumor delineation, which typically involves significant noise and/or blurring. One challenging step is hard decision-making in pixel labeling. Fuzzy logic techniques have achieved increasing application in edge detection. We aimed to combine the advantages of fuzzy edge detection with the RW technique to improve PET tumor delineation.

METHODS

A fuzzy inference system was designed for tumor edge detection from RW probabilities. Three clinical PET/computed tomography datasets containing 12 liver, 13 lung, and 18 abdomen tumors were analyzed, with manual expert tumor contouring as ground truth. The standard RW and proposed combined method were compared quantitatively using the dice similarity coefficient, the Hausdorff distance, and the mean standard uptake value.

RESULTS

The dice similarity coefficient of the proposed method versus standard RW showed significant mean improvements of 21.0±7.2, 12.3±5.8, and 18.4%±6.1% for liver, lung, and abdominal tumors, respectively, whereas the mean improvements in the Hausdorff distance were 3.6±1.4, 1.3±0.4, 1.8±0.8 mm, and the mean improvements in SUVmean error were 15.5±6.3, 11.7±8.6, and 14.1±6.8% (all P's<0.001). For all tumor sizes, the proposed method outperformed the RW algorithm. Furthermore, tumor edge analysis demonstrated further enhancement of the performance of the algorithm, relative to the RW method, with decreasing edge gradients.

CONCLUSION

The proposed technique improves PET lesion delineation at different tumor sites. It depicts greater effectiveness in tumors with smaller size and/or low edge gradients, wherein most PET segmentation algorithms encounter serious challenges. Favorable execution time and accurate performance of the algorithm make it a great tool for clinical applications.

Detection of Aβ plaque deposition in MR images based on pixel feature selection and class information in image level

Background

Amyloid β-protein (Aβ) plaque deposition is an important prevention and treatment target for Alzheimer’s disease (AD). As a noninvasive, nonradioactive and highly cost-effective clinical imaging method, magnetic resonance imaging (MRI) is the perfect imaging technology for the clinical diagnosis of AD, but it cannot display the plaque deposition directly. This paper resolves this problem based on pixel feature selection algorithms at the image level.

Methods and results

Firstly, the brain region was segmented from mouse model brain MR images. Secondly, the pixels in the segmented brain region were extracted as a feature vector (features). Thirdly, feature selection was conducted on the extracted features, and the optimal feature subset was obtained. Fourthly, the various optimal feature subsets were obtained by repeating the same processing above. Fifthly, based on the optimal feature subsets, the final optimal feature subset was obtained by voting mechanism. Finally, using the final optimal selected features, the corresponding pixels on the MR images could be found and marked to show the information about Aβ plaque deposition. The MR images and brain histological image slices of twenty-two model mice were used in the experiments. Four feature selection algorithms were used on the MR images and six kinds of classification experiments are conducted, thereby choosing a pixel feature selection algorithm for further study. The experimental results showed that by using the pixel features selected by the algorithms in this paper, the best classification accuracy between early AD and control slides could be as high as 80 %. The selected and marked MR pixels could show information of Aβ plaque deposition without missing most of the Aβ plaque deposition compared with brain histological slice images. The hit rate is over than 90 %.

Conclusions

According to the experimental results, the proposed detection algorithm of the Aβ plaque deposition based on MR pixel feature selection algorithm is effective. The proposed algorithm can detect the information of the Aβ plaque deposition on MR images and the information can be useful for improving the classification accuracy as assistant MR biomarker. Besides, these findings firstly show the feasibility of detection of the Aβ plaque deposition on MR images and provide reference method for interested relevant researchers in public.

Imaging and analysis of thin structures using positron emission tomography: Thin phantoms and in vivo tobacco leaves study

In this work, a novel approach utilizing the designed phantoms imitating the plant tissues was applied for the evaluation of the relationships between the parameters of the prepared phantoms and/or quantitative variables obtained within the PET analysis. The microPET system developed for animal objects and approaches used made it possible to obtain the quantitative data in the form of (18)F radioactivity as well as the glucose (in µg) accumulated in leaf tissues within the dynamic in vivo study.

Generic and robust method for automatic segmentation of PET images using an active contour model

PURPOSE

Although positron emission tomography (PET) images have shown potential to improve the accuracy of targeting in radiation therapy planning and assessment of response to treatment, the boundaries of tumors are not easily distinguishable from surrounding normal tissue owing to the low spatial resolution and inherent noisy characteristics of PET images. The objective of this study is to develop a generic and robust method for automatic delineation of tumor volumes using an active contour model and to evaluate its performance using phantom and clinical studies.

METHODS

MASAC, a method for automatic segmentation using an active contour model, incorporates the histogram fuzzy C-means clustering, and localized and textural information to constrain the active contour to detect boundaries in an accurate and robust manner. Moreover, the lattice Boltzmann method is used as an alternative approach for solving the level set equation to make it faster and suitable for parallel programming. Twenty simulated phantom studies and 16 clinical studies, including six cases of pharyngolaryngeal squamous cell carcinoma and ten cases of nonsmall cell lung cancer, were included to evaluate its performance. Besides, the proposed method was also compared with the contourlet-based active contour algorithm (CAC) and Schaefer's thresholding method (ST). The relative volume error (RE), Dice similarity coefficient (DSC), and classification error (CE) metrics were used to analyze the results quantitatively.

RESULTS

For the simulated phantom studies (PSs), MASAC and CAC provide similar segmentations of the different lesions, while ST fails to achieve reliable results. For the clinical datasets (2 cases with connected high-uptake regions excluded) (CSs), CAC provides for the lowest mean RE (-8.38% ± 27.49%), while MASAC achieves the best mean DSC (0.71 ± 0.09) and mean CE (53.92% ± 12.65%), respectively. MASAC could reliably quantify different types of lesions assessed in this work with good accuracy, resulting in a mean RE of -13.35% ± 11.87% and -11.15% ± 23.66%, a mean DSC of 0.89 ± 0.05 and 0.71 ± 0.09, and a mean CE of 19.19% ± 7.89% and 53.92% ± 12.65%, for PSs and CSs, respectively.

CONCLUSIONS

The authors' results demonstrate that the developed novel PET segmentation algorithm is applicable to various types of lesions in the authors' study and is capable of producing accurate and consistent target volume delineations, potentially resulting in reduced intraobserver and interobserver variabilities observed when using manual delineation and improved accuracy in treatment planning and outcome evaluation.

SPEQTACLE: An automated generalized fuzzy C-means algorithm for tumor delineation in PET

PURPOSE

Accurate tumor delineation in positron emission tomography (PET) images is crucial in oncology. Although recent methods achieved good results, there is still room for improvement regarding tumors with complex shapes, low signal-to-noise ratio, and high levels of uptake heterogeneity.

METHODS

The authors developed and evaluated an original clustering-based method called spatial positron emission quantification of tumor-Automatic Lp-norm estimation (SPEQTACLE), based on the fuzzy C-means (FCM) algorithm with a generalization exploiting a Hilbertian norm to more accurately account for the fuzzy and non-Gaussian distributions of PET images. An automatic and reproducible estimation scheme of the norm on an image-by-image basis was developed. Robustness was assessed by studying the consistency of results obtained on multiple acquisitions of the NEMA phantom on three different scanners with varying acquisition parameters. Accuracy was evaluated using classification errors (CEs) on simulated and clinical images. SPEQTACLE was compared to another FCM implementation, fuzzy local information C-means (FLICM) and fuzzy locally adaptive Bayesian (FLAB).

RESULTS

SPEQTACLE demonstrated a level of robustness similar to FLAB (variability of 14% ± 9% vs 14% ± 7%, p = 0.15) and higher than FLICM (45% ± 18%, p < 0.0001), and improved accuracy with lower CE (14% ± 11%) over both FLICM (29% ± 29%) and FLAB (22% ± 20%) on simulated images. Improvement was significant for the more challenging cases with CE of 17% ± 11% for SPEQTACLE vs 28% ± 22% for FLAB (p = 0.009) and 40% ± 35% for FLICM (p < 0.0001). For the clinical cases, SPEQTACLE outperformed FLAB and FLICM (15% ± 6% vs 37% ± 14% and 30% ± 17%, p < 0.004).

CONCLUSIONS

SPEQTACLE benefitted from the fully automatic estimation of the norm on a case-by-case basis. This promising approach will be extended to multimodal images and multiclass estimation in future developments.

Detection of bladder metabolic artifacts in (18)F-FDG PET imaging

Positron emission tomography using (18)F-fluorodeoxyglucose ((18)F-FDG-PET) is a widely used imaging modality in oncology. It enables significant functional information to be included in analyses of anatomical data provided by other image modalities. Although PET offers high sensitivity in detecting suspected malignant metabolism, (18)F-FDG uptake is not tumor-specific and can also be fixed in surrounding healthy tissue, which may consequently be mistaken as cancerous. PET analyses may be particularly hampered in pelvic-located cancers by the bladder׳s physiological uptake potentially obliterating the tumor uptake. In this paper, we propose a novel method for detecting (18)F-FDG bladder artifacts based on a multi-feature double-step classification approach. Using two manually defined seeds (tumor and bladder), the method consists of a semi-automated double-step clustering strategy that simultaneously takes into consideration standard uptake values (SUV) on PET, Hounsfield values on computed tomography (CT), and the distance to the seeds. This method was performed on 52 PET/CT images from patients treated for locally advanced cervical cancer. Manual delineations of the bladder on CT images were used in order to evaluate bladder uptake detection capability. Tumor preservation was evaluated using a manual segmentation of the tumor, with a threshold of 42% of the maximal uptake within the tumor. Robustness was assessed by randomly selecting different initial seeds. The classification averages were 0.94±0.09 for sensitivity, 0.98±0.01 specificity, and 0.98±0.01 accuracy. These results suggest that this method is able to detect most (18)F-FDG bladder metabolism artifacts while preserving tumor uptake, and could thus be used as a pre-processing step for further non-parasitized PET analyses.

Functional segmentation of dynamic PET studies: Open source implementation and validation of a leader-follower-based algorithm

We present a novel segmentation algorithm for dynamic PET studies that groups pixels according to the similarity of their time-activity curves.

METHODS

Sixteen mice bearing a human tumor cell line xenograft (CH-157MN) were imaged with three different (68)Ga-DOTA-peptides (DOTANOC, DOTATATE, DOTATOC) using a small animal PET-CT scanner. Regional activities (input function and tumor) were obtained after manual delineation of regions of interest over the image. The algorithm was implemented under the jClustering framework and used to extract the same regional activities as in the manual approach. The volume of distribution in the tumor was computed using the Logan linear method. A Kruskal-Wallis test was used to investigate significant differences between the manually and automatically obtained volumes of distribution.

RESULTS

The algorithm successfully segmented all the studies. No significant differences were found for the same tracer across different segmentation methods. Manual delineation revealed significant differences between DOTANOC and the other two tracers (DOTANOC - DOTATATE, p=0.020; DOTANOC - DOTATOC, p=0.033). Similar differences were found using the leader-follower algorithm.

CONCLUSION

An open implementation of a novel segmentation method for dynamic PET studies is presented and validated in rodent studies. It successfully replicated the manual results obtained in small-animal studies, thus making it a reliable substitute for this task and, potentially, for other dynamic segmentation procedures.

[Prognostic value of the metabolically active tumour volume]

PURPOSE

The purpose of this study was to assess the prognostic value of different parameters on pretreatment fluorodeoxyglucose [((18)F)-FDG] positron emission tomography-computed tomography (PET-CT) in patients with localized oesophageal cancer.

PATIENTS AND METHOD

We retrospectively reviewed 83 cases of localised oesophageal cancer treated in our institution. Patients were treated with curative intent and have received chemoradiotherapy alone or followed by surgery. Different prognostic parameters were correlated to survival: cancer-related factors, patient-related factors and parameters derived from PET-CT (maximum standardized uptake value [SUV max], metabolically active tumor volume either measured with an automatic segmentation software ["fuzzy locally adaptive bayesian": MATVFLAB] or with an adaptive threshold method [MATVseuil] and total lesion glycolysis [TLGFLAB and TLGseuil]).

RESULTS

The median follow-up was 21.8 months (range: 0.16-104). The median overall survival was 22 months (95% confidence interval [95%CI]: 15.2-28.9). There were 67 deaths: 49 associated with cancer and 18 from intercurrent causes. None of the tested factors was significant on overall survival. In univariate analysis, the following three factors affected the specific survival: MATVFLAB (P=0.025), TLGFLAB (P=0.04) and TLGseuil (P=0.04). In multivariate analysis, only MATVFLAB had a significant impact on specific survival (P=0.049): MATVFLAB<18 cm(3): 31.2 months (95%CI: 21.7-not reached) and MATVFLAB>18 cm(3): 20 months (95%CI: 11.1-228.9).

CONCLUSION

The metabolically active tumour volume measured with the automatic segmentation software FLAB on baseline PET-CT was a significant prognostic factor, which should be tested on a larger cohort.

A statistical method for lung tumor segmentation uncertainty in PET images based on user inference

PET has been widely accepted as an effective imaging modality for lung tumor diagnosis and treatment. However, standard criteria for delineating tumor boundary from PET are yet to develop largely due to relatively low quality of PET images, uncertain tumor boundary definition, and variety of tumor characteristics. In this paper, we propose a statistical solution to segmentation uncertainty on the basis of user inference. We firstly define the uncertainty segmentation band on the basis of segmentation probability map constructed from Random Walks (RW) algorithm; and then based on the extracted features of the user inference, we use Principle Component Analysis (PCA) to formulate the statistical model for labeling the uncertainty band. We validated our method on 10 lung PET-CT phantom studies from the public RIDER collections [1] and 16 clinical PET studies where tumors were manually delineated by two experienced radiologists. The methods were validated using Dice similarity coefficient (DSC) to measure the spatial volume overlap. Our method achieved an average DSC of 0.878 ± 0.078 on phantom studies and 0.835 ± 0.039 on clinical studies.

Variability of Image Features Computed from Conventional and Respiratory-Gated PET/CT Images of Lung Cancer

Radiomics is being explored for potential applications in radiation therapy. How various imaging protocols affect quantitative image features is currently a highly active area of research. To assess the variability of image features derived from conventional [three-dimensional (3D)] and respiratory-gated (RG) positron emission tomography (PET)/computed tomography (CT) images of lung cancer patients, image features were computed from 23 lung cancer patients. Both protocols for each patient were acquired during the same imaging session. PET tumor volumes were segmented using an adaptive technique which accounted for background. CT tumor volumes were delineated with a commercial segmentation tool. Using RG PET images, the tumor center of mass motion, length, and rotation were calculated. Fifty-six image features were extracted from all images consisting of shape descriptors, first-order features, and second-order texture features. Overall, 26.6% and 26.2% of total features demonstrated less than 5% difference between 3D and RG protocols for CT and PET, respectively. Between 10 RG phases in PET, 53.4% of features demonstrated percent differences less than 5%. The features with least variability for PET were sphericity, spherical disproportion, entropy (first and second order), sum entropy, information measure of correlation 2, Short Run Emphasis (SRE), Long Run Emphasis (LRE), and Run Percentage (RPC); and those for CT were minimum intensity, mean intensity, Root Mean Square (RMS), Short Run Emphasis (SRE), and RPC. Quantitative analysis using a 3D acquisition versus RG acquisition (to reduce the effects of motion) provided notably different image feature values. This study suggests that the variability between 3D and RG features is mainly due to the impact of respiratory motion.

Diffusion-weighted magnetic resonance imaging during radiotherapy of locally advanced cervical cancer--treatment response assessment using different segmentation methods

BACKGROUND

Diffusion-weighted magnetic resonance imaging (DW-MRI) and the derived apparent diffusion coefficient (ADC) value has potential for monitoring tumor response to radiotherapy (RT). Method used for segmentation of volumes with reduced diffusion will influence both volume size and observed distribution of ADC values. This study evaluates: 1) different segmentation methods; and 2) how they affect assessment of tumor ADC value during RT.

MATERIAL AND METHODS

Eleven patients with locally advanced cervical cancer underwent MRI three times during their RT: prior to start of RT (PRERT), two weeks into external beam RT (WK2RT) and one week prior to brachytherapy (PREBT). Volumes on DW-MRI were segmented using three semi-automatic segmentation methods: "cluster analysis", "relative signal intensity (SD4)" and "region growing". Segmented volumes were compared to the gross tumor volume (GTV) identified on T2-weighted MR images using the Jaccard similarity index (JSI). ADC values from segmented volumes were compared and changes of ADC values during therapy were evaluated.

RESULTS

Significant difference between the four volumes (GTV, DWIcluster, DWISD4 and DWIregion) was found (p < 0.01), and the volumes changed significantly during treatment (p < 0.01). There was a significant difference in JSI among segmentation methods at time of PRERT (p < 0.016) with region growing having the lowest JSIGTV (mean± sd: 0.35 ± 0.1), followed by the SD4 method (mean± sd: 0.50 ± 0.1) and clustering (mean± sd: 0.52 ± 0.3). There was no significant difference in mean ADC value compared at same treatment time. Mean tumor ADC value increased significantly (p < 0.01) for all methods across treatment time.

CONCLUSION

Among the three semi-automatic segmentations of hyper-intense intensities on DW-MR images implemented, cluster analysis and relative signal thresholding had the greatest similarity to the clinical tumor volume. Evaluation of mean ADC value did not depend on segmentation method.

A Segmentation Algorithm for Quantitative Analysis of Heterogeneous Tumors of the Cervix With ¹⁸F-FDG PET/CT

As positron-emission tomography (PET) images have low spatial resolution and much noise, accurate image segmentation is one of the most challenging issues in tumor quantification. Tumors of the uterine cervix present a particular challenge because of urine activity in the adjacent bladder. Here, we propose and validate an automatic segmentation method adapted to cervical tumors. Our proposed methodology combined the gradient field information of both the filtered PET image and the level set function into a level set framework by constructing a new evolution equation. Furthermore, we also constructed a new hyperimage to recognize a rough tumor region using the fuzzy c-means algorithm according to the tissue specificity as defined by both PET (uptake) and computed tomography (attenuation) to provide the initial zero level set, which could make the segmentation process fully automatic. The proposed method was verified based on simulation and clinical studies. For simulation studies, seven different phantoms, representing tumors with homogenous/heterogeneous-low/high uptake patterns and different volumes, were simulated with five different noise levels. Twenty-seven cervical cancer patients at different stages were enrolled for clinical evaluation of the method. Dice similarity coefficients (DSC) and Hausdorff distance (HD) were used to evaluate the accuracy of the segmentation method, while a Bland-Altman analysis of the mean standardized uptake value (SUVmean) and metabolic tumor volume (MTV) was used to evaluate the accuracy of the quantification. Using this method, the DSCs and HDs of the homogenous and heterogeneous phantoms under clinical noise level were 93.39 ±1.09% and 6.02 ±1.09 mm, 93.59 ±1.63% and 8.92 ±2.57 mm, respectively. The DSCs and HDs in patients measured 91.80 ±2.46% and 7.79 ±2.18 mm. Through Bland-Altman analysis, the SUVmean and the MTV using our method showed high correlation with the clinical gold standard. The results of both simulation and clinical studies demonstrated the accuracy, effectiveness, and robustness of the proposed method. Further assessment of the quantitative indices indicates the feasibility of this algorithm in accurate quantitative analysis of cervical tumors in clinical practice.

Electroacupuncture Treatment Improves Learning-Memory Ability and Brain Glucose Metabolism in a Mouse Model of Alzheimer's Disease: Using Morris Water Maze and Micro-PET

Introduction. Alzheimer's disease (AD) causes progressive hippocampus dysfunctions leading to the impairment of learning and memory ability and low level of uptake rate of glucose in hippocampus. What is more, there is no effective treatment for AD. In this study, we evaluated the beneficial and protective effects of electroacupuncture in senescence-accelerated mouse prone 8 (SAMP8). Method. In the electroacupuncture paradigm, electroacupuncture treatment was performed once a day for 15 days on 7.5-month-old SAMP8 male mice. In the normal control paradigm and AD control group, 7.5-month-old SAMR1 male mice and SAMP8 male mice were grabbed and bandaged while electroacupuncture group therapy, in order to ensure the same treatment conditions, once a day, 15 days. Results. From the Morris water maze (MWM) test, we found that the treatment of electroacupuncture can improve the spatial learning and memory ability of SAMP8 mouse, and from the micro-PET test, we proved that after the electroacupuncture treatment the level of uptake rate of glucose in hippocampus was higher than normal control group. Conclusion. These results suggest that the treatment of electroacupuncture may provide a viable treatment option for AD.

A statistical modeling approach to computer-aided quantification of dental biofilm

Biofilm is a formation of microbial material on tooth substrata. Several methods to quantify dental biofilm coverage have recently been reported in the literature, but at best they provide a semiautomated approach to quantification with significant input from a human grader that comes with the grader's bias of what is foreground, background, biofilm, and tooth. Additionally,human assessment indices limit the resolution of the quantification scale; most commercial scales use five levels of quantification for biofilm coverage (0%, 25%, 50%, 75%, and 100%). On the other hand, current state-of-the-art techniques in automatic plaque quantification fail to make their way into practical applications owing to their inability to incorporate human input to handle misclassifications. This paper proposes a new interactive method for biofilm quantification in Quantitative light-induced fluorescence(QLF) images of canine teeth that is independent of the perceptual bias of the grader. The method partitions a QLF image into segments of uniform texture and intensity called superpixels; every superpixel is statistically modeled as a realization of a single 2-D Gaussian Markov random field (GMRF) whose parameters are estimated; the superpixel is then assigned to one of three classes (background, biofilm, tooth substratum) based on the training set of data. The quantification results show a high degree of consistency and precision. At the same time, the proposed method gives pathologists full control to postprocess the automatic quantification by flipping misclassified superpixels to a different state (background,tooth, biofilm) with a single click, providing greater usability than simply marking the boundaries of biofilm and tooth as done by current state-of-the-art methods.

Optimally stabilized PET image denoising using trilateral filtering

Low-resolution and signal-dependent noise distribution in positron emission tomography (PET) images makes denoising process an inevitable step prior to qualitative and quantitative image analysis tasks. Conventional PET denoising methods either over-smooth small-sized structures due to resolution limitation or make incorrect assumptions about the noise characteristics. Therefore, clinically important quantitative information may be corrupted. To address these challenges, we introduced a novel approach to remove signal-dependent noise in the PET images where the noise distribution was considered as Poisson-Gaussian mixed. Meanwhile, the generalized Anscombe's transformation (GAT) was used to stabilize varying nature of the PET noise. Other than noise stabilization, it is also desirable for the noise removal filter to preserve the boundaries of the structures while smoothing the noisy regions. Indeed, it is important to avoid significant loss of quantitative information such as standard uptake value (SUV)-based metrics as well as metabolic lesion volume. To satisfy all these properties, we extended bilateral filtering method into trilateral filtering through multiscaling and optimal Gaussianization process. The proposed method was tested on more than 50 PET-CT images from various patients having different cancers and achieved the superior performance compared to the widely used denoising techniques in the literature.

BiofilmQuant: a computer-assisted tool for dental biofilm quantification

Dental biofilm is the deposition of microbial material over a tooth substratum. Several methods have recently been reported in the literature for biofilm quantification; however, at best they provide a barely automated solution requiring significant input needed from the human expert. On the contrary, state-of-the-art automatic biofilm methods fail to make their way into clinical practice because of the lack of effective mechanism to incorporate human input to handle praxis or misclassified regions. Manual delineation, the current gold standard, is time consuming and subject to expert bias. In this paper, we introduce a new semi-automated software tool, BiofilmQuant, for dental biofilm quantification in quantitative light-induced fluorescence (QLF) images. The software uses a robust statistical modeling approach to automatically segment the QLF image into three classes (background, biofilm, and tooth substratum) based on the training data. This initial segmentation has shown a high degree of consistency and precision on more than 200 test QLF dental scans. Further, the proposed software provides the clinicians full control to fix any misclassified areas using a single click. In addition, BiofilmQuant also provides a complete solution for the longitudinal quantitative analysis of biofilm of the full set of teeth, providing greater ease of usability.