2022
DOI: 10.1088/1361-6560/ac4667
|View full text |Cite
|
Sign up to set email alerts
|

Deep-learning and radiomics ensemble classifier for false positive reduction in brain metastases segmentation

Abstract: Stereotactic radiosurgery (SRS) is now the standard of care for brain metastases (BMs) patients. The SRS treatment planning process requires precise target delineation, which in clinical workflow for patients with multiple (>4) BMs (mBMs) could become a pronounced time bottleneck. Our group has developed an automated BMs segmentation platform to assist in this process. The accuracy of the auto-segmentation, however, is influenced by the presence of false-positive segmentations, mainly caused by the injected… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
8
0

Year Published

2022
2022
2025
2025

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 13 publications
(8 citation statements)
references
References 43 publications
0
8
0
Order By: Relevance
“…31 The extent of inclusion is also usually determined via clinical oncologic guidelines, which determine the negative tumor margin resected during surgical sessions (such as the 2 mm margin in breast cancer). 31 However, in this study, we used a rather simple alternative and created rectangular masks with incrementally increasing sizes, which were all centered on the gravity center of the radiologist contour. Our approach harbors certain benefits to that currently being used.…”
Section: Discussionmentioning
confidence: 99%
See 2 more Smart Citations
“…31 The extent of inclusion is also usually determined via clinical oncologic guidelines, which determine the negative tumor margin resected during surgical sessions (such as the 2 mm margin in breast cancer). 31 However, in this study, we used a rather simple alternative and created rectangular masks with incrementally increasing sizes, which were all centered on the gravity center of the radiologist contour. Our approach harbors certain benefits to that currently being used.…”
Section: Discussionmentioning
confidence: 99%
“…Another important methodologic distinction of our study is how the tumor periphery is included in the segmentation and secondary analysis. Previous studies have utilized well‐known mask‐making operations such as closing, erosion, and dilation of the radiologist contour to obtain a secondary mask 31 . The extent of inclusion is also usually determined via clinical oncologic guidelines, which determine the negative tumor margin resected during surgical sessions (such as the 2 mm margin in breast cancer) 31 .…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Artificial intelligence (AI) has demonstrated promise in addressing these issues. With the goal of improving efficiency and standardization, machine learning models have recently been developed for automated detection and segmentation of metastatic brain tumors [2,[5][6][7][8][9][10][11][12]. However, the published literature thus far is comprised of technical proof-of-concepts in which the model is tested on small, limited sample sizes, and/or it is not readily deployable to the clinic.…”
Section: Introductionmentioning
confidence: 99%
“…For example, the spatial resolution of clinical MRI can be increased by predicting a higher resolution image 10,11 and applying contrast can be avoided with synthetic contrast MRI. 12 Radiomics represents an eclectic body of works but can be divided into studies which classify structures in an MRI image 13 or prognostic models which use MR images to predict treatment outcomes such as tumor recurrence or adverse effects. 14,15 Deep learning methods in real-time and 4D MRI overcome MRI's long acquisition time and the low field strengths of the MRI-LINAC by reconstructing images from undersampled k-space, 16 synthesizing additional MRI slices, 17 and exploiting periodic motion to improve image quality.…”
Section: Introductionmentioning
confidence: 99%