Inter-rater agreement in glioma segmentations on longitudinal MRI

Visser, Maarten R.; Müller, Domenique M J; Duijn, R.J.M. van; Smits, Marion; Verburg, Niels; Hendriks, Eef J.; Nabuurs, Rob J.A.; Bot, Joseph C.J.; Eijgelaar, Roelant S; Witte, Marnix G.; Herk, Marcel van; Barkhof, Frederik; Hamer, Philip C. De Witt; Munck, Jan C. de

doi:10.1016/j.nicl.2019.101727

Cited by 89 publications

(86 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fifth, we did not calculate Jaccard/Dice overlap scores between the two observers (EH and PW). The interrater agreement for tumor segmentation before surgery in general is known to be non-trivial [49].…”

Section: Discussionmentioning

confidence: 99%

Association between tumor location and neurocognitive functioning using tumor localization maps

et al. 2019

View full text Add to dashboard Cite

Introduction: Patients with diffuse glioma often experience neurocognitive impairment already prior to surgery. Pertinent information on whether damage to a specific brain region due to tumor activity results in neurocognitive impairment or not, is relevant in clinical decision-making, and at the same time renders unique information on brain lesion location and functioning relationships. To examine the impact of tumor location on preoperative neurocognitive functioning (NCF), we performed MRI based lesion-symptom mapping. Methods: Seventy-two patients (mean age 40 years) with a radiologically suspected glioma were recruited preoperatively. For each of the six cognitive domains tested, we used tumor localization maps and voxel-based lesion-symptom mapping analyses to identify cortical and subcortical regions associated with NCF impairment. Results: Compared to healthy controls, preoperative NCF was significantly impaired in all cognitive domains. Most frequently affected were attention (30% of patients) and working memory (20% of patients). Deficits in attention were significantly associated with regions in the left frontal and parietal cortex, including the precentral and parietal-opercular cortex, and in left-sided subcortical fiber tracts, including the arcuate fasciculus and corticospinal tract. Surprisingly, no regions could be related to working memory capacity. For the other neurocognitive domains, impairments were mainly associated with regions in the left hemisphere. Conclusions: Prior to treatment, patients with diffuse glioma in the left hemisphere run the highest risk to have NCF deficits. Identification of a left frontoparietal network involved in NCF not only may optimize surgical procedures but may also be integrated in counseling and cognitive rehabilitation for these patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Association between tumor location and neurocognitive functioning using tumor localization maps

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Finally, it is worth mentioning that this experiment sheds only some light on the effectiveness of applying the deep models (or other data-driven techniques) trained over BraTS for analyzing different MRI brain images. The manual delineation protocols were different, and the lack of inter-rater agreement may play pivotal role in quantifying automated segmentation algorithms over such differently acquired and analyzed image sets-it is unclear if the differences result from the inter-rater disagreement of the incorrect segmentation (Hollingworth et al, 2006;Fyllingen et al, 2016;Visser et al, 2019).…”

Section: Datamentioning

confidence: 99%

Data Augmentation for Brain-Tumor Segmentation: A Review

Nalepa

Marcinkiewicz²,

Kawulok

2019

Front. Comput. Neurosci.

228

118

View full text Add to dashboard Cite

Data augmentation is a popular technique which helps improve generalization capabilities of deep neural networks, and can be perceived as implicit regularization. It plays a pivotal role in scenarios in which the amount of high-quality ground-truth data is limited, and acquiring new examples is costly and time-consuming. This is a very common problem in medical image analysis, especially tumor delineation. In this paper, we review the current advances in data-augmentation techniques applied to magnetic resonance images of brain tumors. To better understand the practical aspects of such algorithms, we investigate the papers submitted to the Multimodal Brain Tumor Segmentation Challenge (BraTS 2018 edition), as the BraTS dataset became a standard benchmark for validating existent and emerging brain-tumor detection and segmentation techniques. We verify which data augmentation approaches were exploited and what was their impact on the abilities of underlying supervised learners. Finally, we highlight the most promising research directions to follow in order to synthesize high-quality artificial brain-tumor examples which can boost the generalization abilities of deep models.

show abstract

“…All patients with at least a preoperative postcontrast T1-weighted scan were included, and no patients were excluded. These data were collected as part of the PICTURE project (https://www.pictureproject.nl) (7,9,(21)(22)(23). The histopathologic diagnosis was determined according to the World Health Organization 2007 criteria (24).…”

Section: Clinical Patient Datasetmentioning

confidence: 99%

“…Each model is described by the abbreviation of the included data, preceded with a "c" if only patients with complete imaging were included, and followed by "st" if sparsified training was enabled. The 20 test patients from hospital 1 were previously studied in Visser et al (9). hospital 6.…”

Section: Experimental Designmentioning

confidence: 99%

Robust Deep Learning–based Segmentation of Glioblastoma on Routine Clinical MRI Scans Using Sparsified Training

Eijgelaar¹,

Visser²,

Müller³

et al. 2020

Radiology: Artificial Intelligence

View full text Add to dashboard Cite

G lioblastoma is the most common form of primary brain tumor in adults (1,2). Radiologic tumor evaluation is typically performed using CT or MRI with two-dimensional measures (3), but with advances in imaging and the need for more detailed tumor quantification, three-dimensional volumetric segmentation in MRI is recommended and is becoming more commonplace (4,5). Preoperative glioma segmentation at MRI can aid localized treatment planning and assessment of quality of care (6,7). Several MRI sequences are acquired to assess tumor location, composition, and extent (8); however, manual tumor segmentation is a timeconsuming process and subject to interrater variability (9). Automated tumor segmentation is an active field of research. The 2017 Multimodal Brain Tumor Segmentation (BraTS) (10) challenge showed promising results with Dice scores of approximately 0.85 for the preoperative tumor core mostly using deep learning-based approaches (11). The NiftyNet (12) project offers standardized tools for deep

show abstract

Inter-rater agreement in glioma segmentations on longitudinal MRI

Cited by 89 publications

References 57 publications

Association between tumor location and neurocognitive functioning using tumor localization maps

Association between tumor location and neurocognitive functioning using tumor localization maps

Data Augmentation for Brain-Tumor Segmentation: A Review

Robust Deep Learning–based Segmentation of Glioblastoma on Routine Clinical MRI Scans Using Sparsified Training

Contact Info

Product

Resources

About