TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning

Pérez‐García, Fernando; Sparks, Rachel; Ourselin, Sébastien

doi:10.1016/j.cmpb.2021.106236

Cited by 381 publications

(186 citation statements)

References 25 publications

Supporting

Mentioning

185

Contrasting

Unclassified

Order By: Relevance

“…In a similar fashion, the second model (RAN) utilizes Ranger (Wright, 2019 ) to make use of Gradient Centralization (Yong et al, 2020 ). Our third model (AUG) adds an augmentation pipeline powered by batchgenerators (Isensee et al, 2020 ), torchio (Pérez-García et al, 2020 ), and native MONAI augmentations. In addition we switch the optimizer to stochastic gradient descent ( SGD ) with momentum (momentum = 0.95).…”

Section: Methodsmentioning

confidence: 99%

Robust, Primitive, and Unsupervised Quality Estimation for Segmentation Ensembles

et al. 2021

View full text Add to dashboard Cite

A multitude of image-based machine learning segmentation and classification algorithms has recently been proposed, offering diagnostic decision support for the identification and characterization of glioma, Covid-19 and many other diseases. Even though these algorithms often outperform human experts in segmentation tasks, their limited reliability, and in particular the inability to detect failure cases, has hindered translation into clinical practice. To address this major shortcoming, we propose an unsupervised quality estimation method for segmentation ensembles. Our primitive solution examines discord in binary segmentation maps to automatically flag segmentation results that are particularly error-prone and therefore require special assessment by human readers. We validate our method both on segmentation of brain glioma in multi-modal magnetic resonance - and of lung lesions in computer tomography images. Additionally, our method provides an adaptive prioritization mechanism to maximize efficacy in use of human expert time by enabling radiologists to focus on the most difficult, yet important cases while maintaining full diagnostic autonomy. Our method offers an intuitive and reliable uncertainty estimation from segmentation ensembles and thereby closes an important gap toward successful translation of automatic segmentation into clinical routine.

show abstract

Section: Methodsmentioning

confidence: 99%

Robust, Primitive, and Unsupervised Quality Estimation for Segmentation Ensembles

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The set of image augmentations included in the search space consists of transformations from PIL, imgaug, and TorchIO [2,19,20]. The transforms were selected to mimic real variability in medical datasets produced by anatomical differences or artefacts, as well as to improve robustness to image property variability such as brightness and contrast values.…”

Section: Augmentation Policiesmentioning

confidence: 99%

“…DL has become a popular subdivision of artificial intelligence and has shown great success in many medical image analysis tasks [1][2][3]. DL algorithms have become more cost effective and accurate, making them an ideal candidate for improving clinical workflows [3].…”

Section: Introductionmentioning

confidence: 99%

“…DL networks need diverse and extensive datasets to develop robust and flexible networks [1]. Particularly in medical studies, datasets are limited due to privacy and legal concerns, disease frequency, cost of data acquisition, and the timeconsuming labelling process [1][2][3]. Despite these constraints, the success of DL networks in medicine has motivated work to adapt these networks to function well under low-data circumstances [1].…”

Section: Introductionmentioning

confidence: 99%

“…We adopt the basic design proposed in AutoAugment and BO-Aug by treating the accuracy of the neural network as a function of the DA policies applied to the training set. Many of the algorithms use only basic transformations which cannot mimic the unique variations within medical images [2]. To combat this issue, we consider an extended set of transformations, including MRI kspace based transformations, to accommodate the variations that occur in real medical MRI datasets.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Medical Augmentation (Med-Aug) for Optimal Data Augmentation in Medical Deep Learning Networks

Cardinell

Costanzo

et al. 2021

Sensors

View full text Add to dashboard Cite

Deep learning (DL) algorithms have become an increasingly popular choice for image classification and segmentation tasks; however, their range of applications can be limited. Their limitation stems from them requiring ample data to achieve high performance and adequate generalizability. In the case of clinical imaging data, images are not always available in large quantities. This issue can be alleviated by using data augmentation (DA) techniques. The choice of DA is important because poor selection can possibly hinder the performance of a DL algorithm. We propose a DA policy search algorithm that offers an extended set of transformations that accommodate the variations in biomedical imaging datasets. The algorithm makes use of the efficient and high-dimensional optimizer Bi-Population Covariance Matrix Adaptation Evolution Strategy (BIPOP-CMA-ES) and returns an optimal DA policy based on any input imaging dataset and a DL algorithm. Our proposed algorithm, Medical Augmentation (Med-Aug), can be implemented by other researchers in related medical DL applications to improve their model’s performance. Furthermore, we present our found optimal DA policies for a variety of medical datasets and popular segmentation networks for other researchers to use in related tasks.

show abstract

Patient‐specific geometrical distortion corrections of MRI images improve dosimetric planning accuracy of vestibular schwannoma treated with gamma knife stereotactic radiosurgery

Safari,

Fatemi,

Afkham

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

PurposeTo investigate the impact of MRI patient‐specific geometrical distortion (PSD) on the quality of Gamma Knife stereotactic radiosurgery (GK‐SRS) plans of the vestibular schwannoma (VS) tumors.Methods and materialsThree open access datasets including the MPI‐Leipzig Mind‐Brain‐Body (318 patients), the slow event‐related fMRI designs dataset (62 patients), and the VS dataset (242 patients) were used. We used first two datasets to train a 3D convolution network to predict the distortion map of third dataset that were then used to calculate and correct the PSD. GK‐SRS plans of VS dataset were used to evaluate dose distribution of PSD‐corrected MRI images. GK‐SRS prescription dose of VS cases was 12 Gy. Geometric and dosimetric discrepancies were assessed between the dose distributions and contours before and after the PSD corrections. Geometry indices were center of the contours, Dice coefficient (DC), Hausdorff distance (HD), and dosimetric indices were , , , and doses, target coverage (TC), Paddick's conformity index (PCI), Paddick's gradient index (GI), and homogeneity index (HI).ResultsGeometric distortions of about 1.2 mm were observed at the air‐tissue interfaces at the air canal and nasal cavity borders. Average center of the targets was significantly distorted along the frequency encoding direction after the PSD‐correction. Average DC and HD metrics were 0.90 and 2.13 mm. Average , and in Gy significantly increased after PSD correction from 16.85 to 17.25, 12.30 to 12.77, and from 8.98 to 9.92. did not significantly change after the correction. Average TC and PCI significantly increased from 0.97 to 0.98, and 0.94 to 0.96. Average GI decreased significantly from 2.24 to 2.15 after PSD correction. However, HI did not significantly change after the correction.ConclusionThe proposed method could predict and correct the PSD that indicates the importance of PSD correction before GK‐SRS plans of the VS patients.

show abstract

TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning

Cited by 381 publications

References 25 publications

Robust, Primitive, and Unsupervised Quality Estimation for Segmentation Ensembles

Robust, Primitive, and Unsupervised Quality Estimation for Segmentation Ensembles

Medical Augmentation (Med-Aug) for Optimal Data Augmentation in Medical Deep Learning Networks

Patient‐specific geometrical distortion corrections of MRI images improve dosimetric planning accuracy of vestibular schwannoma treated with gamma knife stereotactic radiosurgery

Contact Info

Product

Resources

About