TorchMetrics - Measuring Reproducibility in PyTorch

Detlefsen, Nicki Skafte; Borovec, Jiří; Schock, Justus; Jha, Ananya; Koker, Teddy; Liello, Luca Di; Stancl, Daniel; Quan, Changsheng; Grechkin, Maxim; Falcon, William

doi:10.21105/joss.04101

Cited by 77 publications

(29 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SSIM and MS-SSIM are in the range [0, 1] and a higher value indicates a better synthetization. Both metrics are implemented using the TorchMetrics 0.10.3 library [6].…”

Section: Experiments and Resultsmentioning

confidence: 99%

fRegGAN with K-space Loss Regularization for Medical Image Translation

Baltruschat¹,

Kreis²,

Hoelscher³

et al. 2023

Preprint

View full text Add to dashboard Cite

Generative adversarial networks (GANs) have shown remarkable success in generating realistic images and are increasingly used in medical imaging for image-to-image translation tasks. However, GANs tend to suffer from a frequency bias towards low frequencies, which can lead to the removal of important structures in the generated images. To address this issue, we propose a novel frequency-aware image-to-image translation framework based on the supervised RegGAN approach, which we call fRegGAN. The framework employs a K-space loss to regularize the frequency content of the generated images and incorporates wellknown properties of MRI K-space geometry to guide the network training process. By combine our method with the RegGAN approach, we can mitigate the effect of training with misaligned data and frequency bias at the same time. We evaluate our method on the public BraTS dataset and outperform the baseline methods in terms of both quantitative and qualitative metrics when synthesizing T2-weighted from T1-weighted MR images. Detailed ablation studies are provided to understand the effect of each modification on the final performance. The proposed method is a step towards improving the performance of image-to-image translation and synthesis in the medical domain and shows promise for other applications in the field of image processing and generation.

show abstract

“…The SSIM and MS-SSIM are in the range [0, 1] and a higher value indicates a better synthetization. Both metrics are implemented using the TorchMetrics 0.10.3 library [6].…”

Section: Experiments and Resultsmentioning

confidence: 99%

fRegGAN with K-space Loss Regularization for Medical Image Translation

Baltruschat¹,

Kreis²,

Hoelscher³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…For quantitative evaluation, we compared our metric library with other widely used frameworks for machine learning and image analysis. As it can be seen in Table 1, MISeval provides currently 28 metrics, which is the highest number of segmentation metrics compared to other analyzed frameworks: scikit-learn [6] with 18, EvaluateSegmentation from VISCERAL [7] with 13, PyMIA [8] with 12, Tensorflow [9] with 16 and TorchMetrics [10] with 12.…”

Section: Resultsmentioning

confidence: 99%

MISeval: A Metric Library for Medical Image Segmentation Evaluation

Müller

Hartmann

Meyer

et al. 2022

Studies in Health Technology and Informatics

View full text Add to dashboard Cite

Correct performance assessment is crucial for evaluating modern artificial intelligence algorithms in medicine like deep-learning based medical image segmentation models. However, there is no universal metric library in Python for standardized and reproducible evaluation. Thus, we propose our open-source publicly available Python package MISeval: a metric library for Medical Image Segmentation Evaluation. The implemented metrics can be intuitively used and easily integrated into any performance assessment pipeline. The package utilizes modern DevOps strategies to ensure functionality and stability. MISeval is available from PyPI (miseval) and GitHub: https://github.com/frankkramer-lab/miseval.

show abstract

“…DICE is a similarity coefficient that measures the overlap over the union of two binary masks, and Hausdorff distance measures the average distance error between ground truth and predicted masks. To compute the metrics we used Evaluate Segmentation tool [33] and TorchMetrics package [34] Figure 2 shows a 2D sagittal slice of the T1w and T2w images and their corresponding low and high-resolution brainmasks. We can see that the low-resolution mask has very coarse boundaries and mistakes, such as missed part of the cerebellum indicated by the red arrow.…”

Section: Deep-learning Model Accuracymentioning

confidence: 99%

PigSNIPE: Scalable Neuroimaging Processing Engine for Minipig MRI

Brzus¹,

Knoernschild²,

Sieren³

et al. 2023

Preprint

View full text Add to dashboard Cite

Translation of basic animal research to find effective methods of diagnosing and treating human neurological disorders requires parallel analysis infrastructures. Small animals such as mice provide exploratory animal disease models. However, many interventions developed using small animal models fail to translate to human use due to physical or biological differences. Recently, large-animal minipigs have emerged in neuroscience due to both brain similarity and economic advantages. Medical image processing is a crucial part of research as it allows researchers to monitor their experiments and understand disease development. However, although many algorithms are created and optimized for MR analysis of human data, those tools are not directly applicable or sufficiently sensitive to measure minipig data. In this work, we propose PigSNIPE - a pipeline for the automated handling, processing, and analyzing of large-scale data sets of minipig MR images. The pipeline allows for image registration, AC-PC alignment, landmark detection, skull stripping, brainmasks and intracranial volume segmentation (DICE 0.98), tissue segmentation (DICE 0.82), and caudate-putamen brain segmentation (DICE 0.8) in under two minutes. To the best of our knowledge, this is the first automated pipeline tool aimed at large animal images.

show abstract

TorchMetrics - Measuring Reproducibility in PyTorch

Cited by 77 publications

References 1 publication

fRegGAN with K-space Loss Regularization for Medical Image Translation

fRegGAN with K-space Loss Regularization for Medical Image Translation

MISeval: A Metric Library for Medical Image Segmentation Evaluation

PigSNIPE: Scalable Neuroimaging Processing Engine for Minipig MRI

Contact Info

Product

Resources

About