Bayesian segmentation of chest tumors in pet scans using a Poisson-Gamma mixture model

Irace, Zacharie; Pereyra, Marcelo; Dobigeon, Nicolas; Batatia, Hadj

doi:10.1109/ssp.2011.5967828

Cited by 4 publications

(3 citation statements)

References 18 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike SC, mixture models (such as PMMs) assume a single latent per data point for data generation, i.e., data is modeled in terms of a single compositional feature rather than a combination of multiple features. PMMs assume the observable data to be subject to Poisson distributed noise, and they have been applied in the context of image and audio signal processing applications before (e.g., [81][82][83]). The here used PMM-based denoising approach is described in more detail in S1 Text.…”

Section: Algorithmsmentioning

confidence: 99%

Zero-shot denoising of microscopy images recorded at high-resolution limits

Salwig,

Drefs,

Lücke

2024

PLoS Comput Biol

View full text Add to dashboard Cite

Conventional and electron microscopy visualize structures in the micrometer to nanometer range, and such visualizations contribute decisively to our understanding of biological processes. Due to different factors in recording processes, microscopy images are subject to noise. Especially at their respective resolution limits, a high degree of noise can negatively effect both image interpretation by experts and further automated processing. However, the deteriorating effects of strong noise can be alleviated to a large extend by image enhancement algorithms. Because of the inherent high noise, a requirement for such algorithms is their applicability directly to noisy images or, in the extreme case, to just a single noisy image without a priori noise level information (referred to as blind zero-shot setting). This work investigates blind zero-shot algorithms for microscopy image denoising. The strategies for denoising applied by the investigated approaches include: filtering methods, recent feed-forward neural networks which were amended to be trainable on noisy images, and recent probabilistic generative models. As datasets we consider transmission electron microscopy images including images of SARS-CoV-2 viruses and fluorescence microscopy images. A natural goal of denoising algorithms is to simultaneously reduce noise while preserving the original image features, e.g., the sharpness of structures. However, in practice, a tradeoff between both aspects often has to be found. Our performance evaluations, therefore, focus not only on noise removal but set noise removal in relation to a metric which is instructive about sharpness. For all considered approaches, we numerically investigate their performance, report their denoising/sharpness tradeoff on different images, and discuss future developments. We observe that, depending on the data, the different algorithms can provide significant advantages or disadvantages in terms of their noise removal vs. sharpness preservation capabilities, which may be very relevant for different virological applications, e.g., virological analysis or image segmentation.

show abstract

Section: Algorithmsmentioning

confidence: 99%

Zero-shot denoising of microscopy images recorded at high-resolution limits

Salwig,

Drefs,

Lücke

2024

PLoS Comput Biol

View full text Add to dashboard Cite

show abstract

“…Considering the difficulties in characterizing the noise properties in PET images, many works have assumed the data to be corrupted by a Gaussian noise [12], [13], [14]. Hybrid distributions, such as Poisson-Gaussian [15] and Poisson-Gamma [16], have been also proposed in an attempt to take into account various phenomena occurring in the data. The work of Teymurazyan et al [17] tried to determine the statistical properties of data reconstructed by filtered-back projection (FBP) and iterative expectation maximization (EM) algorithms.…”

Section: Introductionmentioning

confidence: 99%

Factor Analysis of Dynamic PET Images: Beyond Gaussian Noise

Cavalcanti

Oberlin

Dobigeon

et al. 2019

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

Factor analysis has proven to be a relevant tool for extracting tissue time-activity curves (TACs) in dynamic PET images, since it allows for an unsupervised analysis of the data. Reliable and interpretable results are possible only if considered with respect to suitable noise statistics. However, the noise in reconstructed dynamic PET images is very difficult to characterize, despite the Poissonian nature of the count-rates. Rather than explicitly modeling the noise distribution, this work proposes to study the relevance of several divergence measures to be used within a factor analysis framework. To this end, the β-divergence, widely used in other applicative domains, is considered to design the data-fitting term involved in three different factor models. The performances of the resulting algorithms are evaluated for different values of β, in a range covering Gaussian, Poissonian and Gamma-distributed noises. The results obtained on two different types of synthetic images and one real image show the interest of applying non-standard values of β to improve factor analysis.

show abstract

“…However, depending on the acquisition setup, the reconstruction algorithm and its parameter values (e.g., the number of reconstruction iterations), the nature of the noise can be significantly altered [6]. To allow for a more flexible modeling of the noise, hybrid distributions, such as Poisson-Gaussian [7] and Poisson-Gamma [8], have been also used to improve different steps of the PET imaging pipeline. Teymurazyan et al investigated the statistics of images reconstructed with different algorithms [9].…”

Section: Introductionmentioning

confidence: 99%

Unmixing Dynamic Pet Images: Combining Spatial Heterogeneity and Non-gaussian Noise

Cavalcant

Oberlin

Dobigeo

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

An important task when processing dynamic PET images is to identify the time-activity curves (TACs) of the pure tissues, along with their corresponding spatial proportions. This step, often referred to as unmixing or factor analysis, is based on a loss function which measures the discrepancy between the observed data and the model. This loss function should be chosen according to the statistical properties of the noise, which is in this case hard to characterize. Indeed, while dynamic PET images results from a decay process that can be statistically described by a Poisson distribution, acquisition and post-filtering reconstruction drastically change the nature of the noise. In the literature dedicated to factor analysis of dynamic PET images, a common and underlying assumption consists in assuming that the dynamic PET images are corrupted by an additive Gaussian or by a Poisson noise. These assumptions lead to the choice of the squared Euclidian distance and the Kullback-Leibler divergence. We propose here to consider the β-divergence, which is able to encompass a wide family of divergence measures corresponding to various noise distributions. This loss function is incorporated into three different factor models and evaluated using four sets of synthetic data.

show abstract

Bayesian segmentation of chest tumors in pet scans using a Poisson-Gamma mixture model

Cited by 4 publications

References 18 publications

Zero-shot denoising of microscopy images recorded at high-resolution limits

Zero-shot denoising of microscopy images recorded at high-resolution limits

Factor Analysis of Dynamic PET Images: Beyond Gaussian Noise

Unmixing Dynamic Pet Images: Combining Spatial Heterogeneity and Non-gaussian Noise

Contact Info

Product

Resources

About