Deep learning method for segmentation of rotator cuff muscles on MR images

Medina, Giovanna; Buckless, Colleen; Thomasson, Eamon; Oh, Luke S.; Torriani, Martin

doi:10.1007/s00256-020-03599-2

Cited by 40 publications

(27 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If an image has one or more contours associated with it, the same transformation is applied to the contours. Geometric transformations are so common that they were utilised by 92 of the 93 basic augmentation studies 15–106 …”

Section: Methodsmentioning

confidence: 99%

“…Patches are generated from the under‐represented class to even the balance. 30 articles made use of cropping 15–17,19,23,32,33,35,41,43,48,50,58,59,66,68,69,71,74,78,80,82,84,85,90,97,98,102,104,105 …”

Section: Methodsmentioning

confidence: 99%

“…30 articles made use of cropping. [15][16][17]19,23,32,33,35,41,43,48,50,58,59,66,68,69,71,74,78,80,82,84,85,90,97,98,102,104,105…”

Section: Croppingmentioning

confidence: 99%

See 2 more Smart Citations

A review of medical image data augmentation techniques for deep learning applications

et al. 2021

View full text Add to dashboard Cite

Summary Research in artificial intelligence for radiology and radiotherapy has recently become increasingly reliant on the use of deep learning‐based algorithms. While the performance of the models which these algorithms produce can significantly outperform more traditional machine learning methods, they do rely on larger datasets being available for training. To address this issue, data augmentation has become a popular method for increasing the size of a training dataset, particularly in fields where large datasets aren’t typically available, which is often the case when working with medical images. Data augmentation aims to generate additional data which is used to train the model and has been shown to improve performance when validated on a separate unseen dataset. This approach has become commonplace so to help understand the types of data augmentation techniques used in state‐of‐the‐art deep learning models, we conducted a systematic review of the literature where data augmentation was utilised on medical images (limited to CT and MRI) to train a deep learning model. Articles were categorised into basic, deformable, deep learning or other data augmentation techniques. As artificial intelligence models trained using augmented data make their way into the clinic, this review aims to give an insight to these techniques and confidence in the validity of the models produced.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A review of medical image data augmentation techniques for deep learning applications

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Furthermore, the progression of rotator cuff muscle atrophy and fatty infiltration after surgical repair correlates with poor functional outcomes [45]. As the commonly used Goutallier classification agreements vary between studies and measurements are time-consuming to obtain [46][47][48][49], automated deep learning-based quantification could add clinical value through improved reproducibility and efficiency gains.…”

Section: Rotator Cuff Muscle Segmentationmentioning

confidence: 99%

“…In a 2021 study, two serial deep learning algorithms successfully identify the most suitable sagittal T1-weighted MR images resembling Y-views and subsequently segmented the subscapularis, supraspinatus, and infraspinatus/teres minor muscles (Fig. 5) [49]. The fully automated algorithms performed the tasks with greater than 98% accuracy to select an appropriate Y-view, and there was a high similarity with human manual segmentation on internal (Dice score greater than 0.96) and external (Dice score greater than 0.93) data sets, which build the foundation for future AI-based MRI quantification of muscle atrophy and classification of fatty infiltration.…”

Section: Rotator Cuff Muscle Segmentationmentioning

confidence: 99%

Artificial intelligence for MRI diagnosis of joints: a scoping review of the current state-of-the-art of deep learning-based approaches

Fritz

2021

Skeletal Radiol

View full text Add to dashboard Cite

Deep learning-based MRI diagnosis of internal joint derangement is an emerging field of artificial intelligence, which offers many exciting possibilities for musculoskeletal radiology. A variety of investigational deep learning algorithms have been developed to detect anterior cruciate ligament tears, meniscus tears, and rotator cuff disorders. Additional deep learning-based MRI algorithms have been investigated to detect Achilles tendon tears, recurrence prediction of musculoskeletal neoplasms, and complex segmentation of nerves, bones, and muscles. Proof-of-concept studies suggest that deep learning algorithms may achieve similar diagnostic performances when compared to human readers in meta-analyses; however, musculoskeletal radiologists outperformed most deep learning algorithms in studies including a direct comparison. Earlier investigations and developments of deep learning algorithms focused on the binary classification of the presence or absence of an abnormality, whereas more advanced deep learning algorithms start to include features for characterization and severity grading. While many studies have focused on comparing deep learning algorithms against human readers, there is a paucity of data on the performance differences of radiologists interpreting musculoskeletal MRI studies without and with artificial intelligence support. Similarly, studies demonstrating the generalizability and clinical applicability of deep learning algorithms using realistic clinical settings with workflow-integrated deep learning algorithms are sparse. Contingent upon future studies showing the clinical utility of deep learning algorithms, artificial intelligence may eventually translate into clinical practice to assist detection and characterization of various conditions on musculoskeletal MRI exams.

show abstract

Body composition predictors of mortality in patients undergoing surgery for long bone metastases

Groot

Bongers

Buckless

et al. 2022

Journal of Surgical Oncology

Self Cite

View full text Add to dashboard Cite

Background and Objectives Body composition measurements using computed tomography (CT) may serve as imaging biomarkers of survival in patients with and without cancer. This study assesses whether body composition measurements obtained on abdominal CTs are independently associated with 90‐day and 1‐year mortality in patients with long‐bone metastases undergoing surgery. Methods This single institutional retrospective study included 212 patients who had undergone surgery for long‐bone metastases and had a CT of the abdomen within 90 days before surgery. Quantification of cross‐sectional areas (CSA) and CT attenuation of abdominal subcutaneous adipose tissue, visceral adipose tissue, and paraspinous and abdominal muscles were performed at L4. Multivariate Cox proportional‐hazards analyses were performed. Results Sarcopenia was independently associated with 90‐day mortality (hazard ratio [HR] = 1.87; 95% confidence interval [CI] = 1.11–3.16; p = 0.019) and 1‐year mortality (HR = 1.50; 95% CI = 1.02–2.19; p = 0.038) in multivariate analysis while controlling for clinical variables such as primary tumors, comorbidities, and chemotherapy. Abdominal fat CSAs and muscle attenuation were not associated with mortality. Conclusions The presence of sarcopenia assessed by CT is predictive of 90‐day and 1‐year mortality in patients undergoing surgery for long‐bone metastases. This body composition measurement can be used as novel imaging biomarker supplementing existing prognostic tools to optimize patient selection for surgery and improve shared decision making.

show abstract

Deep learning method for segmentation of rotator cuff muscles on MR images

Cited by 40 publications

References 25 publications

A review of medical image data augmentation techniques for deep learning applications

A review of medical image data augmentation techniques for deep learning applications

Artificial intelligence for MRI diagnosis of joints: a scoping review of the current state-of-the-art of deep learning-based approaches

Body composition predictors of mortality in patients undergoing surgery for long bone metastases

Contact Info

Product

Resources

About