Magnetic Resonance Image-Guided Neurosurgery

Jólesz, Ferenc A.

doi:10.1007/978-1-4614-7657-3_32

Cited by 9 publications

(12 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Higher-field magnets offer the ability to achieve spatial resolutions that can visualize in detail the exquisite brain anatomy. 52 In addition, the availability of intraoperative MRI has influenced neurosurgical therapy of BCBM. Intraoperative image updates can be obtained in short-time and the resection progress can be readily monitored.…”

Section: Discussionmentioning

confidence: 99%

“…Intraoperative image updates can be obtained in short-time and the resection progress can be readily monitored. 52 Furthermore, new functional MRI sequences have been widely useful in determining the Grade, heterogeneity, and extent of BCBM. Some have even suggested that DTI might be used to aid in neurosurgical planning, radiotherapy preparation, and monitoring of tumor recurrence and response to therapy.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Diagnostic Clinical Trials in Breast Cancer Brain Metastases: Barriers and Innovations

Fares

Kanojia

Rashidi

et al. 2019

Clinical Breast Cancer

View full text Add to dashboard Cite

Optimal treatment of breast cancer brain metastases (BCBM) is often hampered by limitations in diagnostic abilities. Developing innovative tools for BCBM diagnosis is vital for early detection and effective treatment. In this study we explored the advances in trial for the diagnosis of BCBM, with review of the literature. On May 8, 2019, we searched ClinicalTrials.gov for interventional and diagnostic clinical trials involving BCBM, without limiting for date or location. Information on trial characteristics, experimental interventions, results, and publications were collected and analyzed. In addition, a systematic review of the literature was conducted to explore published studies related to BCBM diagnosis. Only 9 diagnostic trials explored BCBM. Of these, 1 trial was withdrawn because of low accrual numbers. Three trials were completed; however, none had published results. Modalities in trial for BCBM diagnosis entailed magnetic resonance imaging (MRI), computed tomography (CT), positron emission tomography (PET), PET-CT, nanobodies, and circulating tumor cells (CTCs), along with a collection of novel tracers and imaging biomarkers. MRI continues to be the diagnostic modality of choice, whereas CT is best suited for acute settings. Advances in PET and PET-CT allow the collection of metabolic and functional information related to BCBM. CTC characterization can help reflect on the molecular foundations of BCBM, whereas cell-free DNA offers new genetic material for further exploration in trials. The integration of machine learning in BCBM diagnosis seems inevitable as we continue to aim for rapid and accurate detection and better patient outcomes.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Diagnostic Clinical Trials in Breast Cancer Brain Metastases: Barriers and Innovations

Fares

Kanojia

Rashidi

et al. 2019

Clinical Breast Cancer

View full text Add to dashboard Cite

show abstract

“…Although soft tissue resolution and contrast offered by MRI are superior to other modalities, allowing improved tumour localization and margin definition, scan times can be long. In addition, the strong magnetic field used in MRI can adversely affect electronic systems and cause attractive forces on metallic objects implanted in patients [2,12]. Tools used in the interventional suite must be MRI safe and not cause image artefacts, or at least have minimal effects on image quality.…”

Section: Magnetic Resonance Imagingmentioning

confidence: 99%

“…An important prognostic indicator of success is the extent of resection of the tumour. IGN has improved the extent of resection and patient outcomes by identifying residual tumour mass and allowing the sparing of critical tissues [1,2].…”

Section: Tumour Resectionmentioning

confidence: 99%

“…Imaging is critical to neurosurgery for three main reasons. First, the object of the surgical procedure is often difficult to reach because it is typically located within the cranium and is surrounded by tissue critical to normal thought processes [1,2]. Locating the region of interest as precisely as possible using diagnostic imaging reduces the amount of bone that needs to be removed and minimizes the damage to the eloquent cortex or vascular system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image-Guided Neurosurgery

Miner

2017

Journal of Medical Imaging and Radiation Sciences

View full text Add to dashboard Cite

Active multitask learning with uncertainty‐weighted loss for coronary calcium scoring

et al. 2022

View full text Add to dashboard Cite

Purpose The coronary artery calcification (CAC) score is an independent marker for the risk of cardiovascular events. Automatic methods for quantifying CAC could reduce workload and assist radiologists in clinical decision‐making. However, large annotated datasets are needed for training to achieve very good model performance, which is an expensive process and requires expert knowledge. The number of training data required can be reduced in an active learning scenario, which requires only the most informative samples to be labeled. Multitask learning techniques can improve model performance by joint learning of multiple related tasks and extraction of shared informative features. Methods We propose an uncertainty‐weighted multitask learning model for coronary calcium scoring in electrocardiogram‐gated (ECG‐gated), noncontrast‐enhanced cardiac calcium scoring CT. The model was trained to solve the two tasks of coronary artery region segmentation (weak labels) and coronary artery calcification segmentation (strong labels) simultaneously in an active learning scenario to improve model performance and reduce the number of samples needed for training. We compared our model with a single‐task U‐Net and a sequential‐task model as well as other state‐of‐the‐art methods. The model was evaluated on 1275 individual patients in three different datasets (DISCHARGE, CADMAN, orCaScore), and the relationship between model performance and various influencing factors (image noise, metal artifacts, motion artifacts, image quality) was analyzed. Results Joint learning of multiclass coronary artery region segmentation and binary coronary calcium segmentation improved calcium scoring performance. Since shared information can be learned from both tasks for complementary purposes, the model reached optimal performance with only 12% of the training data and one‐third of the labeling time in an active learning scenario. We identified image noise as one of the most important factors influencing model performance along with anatomical abnormalities and metal artifacts. Conclusions Our multitask learning approach with uncertainty‐weighted loss improves calcium scoring performance by joint learning of shared features and reduces labeling costs when trained in an active learning scenario.

show abstract

Magnetic Resonance Image-Guided Neurosurgery

Cited by 9 publications

References 67 publications

Diagnostic Clinical Trials in Breast Cancer Brain Metastases: Barriers and Innovations

Diagnostic Clinical Trials in Breast Cancer Brain Metastases: Barriers and Innovations

Image-Guided Neurosurgery

Active multitask learning with uncertainty‐weighted loss for coronary calcium scoring

Contact Info

Product

Resources

About