CemrgApp: An interactive medical imaging application with image processing, computer vision, and machine learning toolkits for cardiovascular research

Razeghi, Orod; Solís-Lemus, José Alonso; Lee, Angela W.C.; Karim, Rashed; Corrado, Cesare; Roney, Caroline; Vecchi, Adelaide de; Niederer, Steven

doi:10.1016/j.softx.2020.100570

Cited by 48 publications

(44 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, 86 scans were obtained from the 2018 STACOM segmentation challenge ( Xiong et al, 2021 ), with resolution of 0.625×0.625×0.625mm 3 , and corresponding segmentations of the LA, and the second dataset was acquired from St Thomas’ Hospital ( Chubb et al, 2018 ) from 18 AF patients, comprising of an additional 36 LGE-MRI images with a resolution of 1.3×1.3×4.0mm 3 , reconstructed to 0.94×0.94×2.0mm 3 . The patient images were processed in CemrgApp ( Razeghi et al, 2020 ) using the scar quantification pipeline to first produce patient-specific 3D LA geometries with raw LGE intensity distributions. Then, the image intensity ratio thresholding technique was applied to clearly differentiate between fibrotic regions and healthy tissue ( Roy et al, 2018 ).…”

Section: Methodsmentioning

confidence: 99%

Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation

et al. 2021

View full text Add to dashboard Cite

Atrial fibrillation (AF) is the most common cardiac arrhythmia and currently affects more than 650,000 people in the United Kingdom alone. Catheter ablation (CA) is the only AF treatment with a long-term curative effect as it involves destroying arrhythmogenic tissue in the atria. However, its success rate is suboptimal, approximately 50% after a 2-year follow-up, and this high AF recurrence rate warrants significant improvements. Image-guidance of CA procedures have shown clinical promise, enabling the identification of key patient anatomical and pathological (such as fibrosis) features of atrial tissue, which require ablation. However, the latter approach still suffers from a lack of functional information and the need to interpret structures in the images by a clinician. Deep learning plays an increasingly important role in biomedicine, facilitating efficient diagnosis and treatment of clinical problems. This study applies deep reinforcement learning in combination with patient imaging (to provide structural information of the atria) and image-based modelling (to provide functional information) to design patient-specific CA strategies to guide clinicians and improve treatment success rates. To achieve this, patient-specific 2D left atrial (LA) models were derived from late-gadolinium enhancement (LGE) MRI scans of AF patients and were used to simulate patient-specific AF scenarios. Then a reinforcement Q-learning algorithm was created, where an ablating agent moved around the 2D LA, applying CA lesions to terminate AF and learning through feedback imposed by a reward policy. The agent achieved 84% success rate in terminating AF during training and 72% success rate in testing. Finally, AF recurrence rate was measured by attempting to re-initiate AF in the 2D atrial models after CA with 11% recurrence showing a great improvement on the existing therapies. Thus, reinforcement Q-learning algorithms can predict successful CA strategies from patient MRI data and help to improve the patient-specific guidance of CA therapy.

show abstract

Section: Methodsmentioning

confidence: 99%

Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The Cardio Electro-Mechanics Research Group Application (CemrgApp) [6] is an open source software platform providing an integrated custom environment for developing computer vision tools. CemrgApp was used as a platform to develop the tools and to process the input data.…”

Section: Methodsmentioning

confidence: 99%

“…Scans from six patients were assessed, as a proof of concept, where patients had undergone pre-and postablation scans. The procedure for acquiring each patient's scans is thoroughly documented in [5], and [6]. The volumes generated are loaded into CemrgApp and resampled to be isometric [6].…”

Section: Input Data and Scar Map Generationmentioning

confidence: 99%

Software Framework to Quantify Pulmonary Vein Isolation Atrium Scar Tissue

Solís-Lemus

Razeghi

Roney

et al. 2020

2020 Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

Pulmonary vein isolation (PVI) is a recommended treatment for drug refractory atrial fibrillation (AF). The ablation causes non-conductive scar tissue that separates the body of the atrium from regions around the pulmonary veins that trigger AF. This scar tissue can be seen in the atrium using cardiac MR. We aim to develop a systematic workflow to quantify the location and size of scar tissue due to PVI from CMR images to evaluate ablation procedures. Input meshes were created from segmented late-gadolineum-enhanced (LGE) cardiac magnetic resonance (CMR) scans with scalar values at each node representing the signal intensity of the scar. The software has three features: (i) Calculating the area of the scar tissue, (ii) assessing ablation lesions to identify the percentage of the pulmonary vein encircled by scar and the number of gaps in it, and (iii) comparing pre-and postablation scar tissues qualitatively. Six patients were assessed as a proof of concept, where patients had undergone pre-and post-ablation scans. In all tests, an increase in fibrotic tissue was found, from averages of 2+1.9% and 36+18%. Post-ablation lesions were assessed showing an average of 75+12% pulmonary vein encirclement, with gaps ranging from 2 to 4. The software presented is a semi-automated, user friendly framework where users are able to assess an ablation procedure.

show abstract

“…For example, [8] proposed a CNN-based double-branched model wherein one branch was utilized for feature extraction, the other for segmentation for multiple abnormality detection from medical images. [9] proposed the CemrgApp, a CNN model, to classify cardiovascular properties from cardiovascular magnetic imaging (CMRI) scans of different cardiac patients, for e cient diagnosis and treatment. A multi-label CNN was used to segment out the atria and atrial structures from the CMRI scans.…”

Section: Literature Reviewmentioning

confidence: 99%

Identifying Malignant Lymph Nodes of Prostate Cancer Patients Using A Combination of Pre-Trained Deep Models and Traditional Machine Learning Classifiers

Sarkar

Harwood

et al. 2021

Preprint

View full text Add to dashboard Cite

Prostate cancer is the second most common new cancer diagnosis in the United States. The prostate gland sits beneath the urinary bladder and surrounds the first part of the urethra. Usually, prostate cancer is slow-growing; stays confined to the prostate gland; and can be treated conservatively (active surveillance) or with surgery. However, if the cancer has spread beyond the prostate, such as to the lymph nodes, then that suggests the cancer is more aggressive and surgery is not adequate. In those cases, radiation and/or systemic therapies (e.g., chemotherapy, immunotherapy) are required. The challenge is that it is often difficult for radiologists to differentiate malignant lymph nodes from non-malignant ones with current medical imaging technology. In this study, we design a scalable hybrid approach utilizing a deep learning model to extract features into a machine learning classifier to automatically identify malignant lymph nodes in patients with prostate cancer.

show abstract

CemrgApp: An interactive medical imaging application with image processing, computer vision, and machine learning toolkits for cardiovascular research

Cited by 48 publications

References 13 publications

Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation

Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation

Software Framework to Quantify Pulmonary Vein Isolation Atrium Scar Tissue

Identifying Malignant Lymph Nodes of Prostate Cancer Patients Using A Combination of Pre-Trained Deep Models and Traditional Machine Learning Classifiers

Contact Info

Product

Resources

About