Automated MRI based pipeline for segmentation and prediction of grade, IDH mutation and 1p19q co-deletion in glioma

Decuyper, Milan; Bonte, Stijn; Deblaere, Karel; Holen, Roel Van

doi:10.1016/j.compmedimag.2020.101831

Cited by 54 publications

(60 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, the expression level of NUP37 was positively correlated with the grade of glioma, which also supports that NUP37 is a malignant molecule. Second, IDH mutations and 1p19q codeletion are protective factors for the prognosis of glioma patients, 25 but the expression of NUP37 is negatively correlated with them. Finally, we next compare the relationship between NUP37 and known biomarkers in gliomas.…”

Section: Discussionmentioning

confidence: 99%

Significantly high expression of NUP37 leads to poor prognosis of glioma patients by promoting the proliferation of glioma cells

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Significantly high expression of NUP37 leads to poor prognosis of glioma patients by promoting the proliferation of glioma cells

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Some previous studies also used multi-task networks to predict the genetic and histological features of glioma [23,24,25]. Tang et al [23] used a multi-task network that predicts multiple genetic features, as well as the overall survival of glioblastoma.…”

Section: Discussionmentioning

confidence: 99%

“…However, they do not predict the 1p/19q co-deletion status needed for the WHO 2016 categorization. Lastly, Decuyper et al [25] used a multi-task network that predicts the IDH mutation and 1p/19q co-deletion status, and the tumor grade (LGG or HGG). Their method requires a tumor segmentation as input, which they obtain from a U-Net that is applied earlier in their pipeline; thus, their method requires two networks instead of the single network we use in our method.…”

Section: Discussionmentioning

confidence: 99%

WHO 2016 subtyping and automated segmentation of glioma using multi-task deep learning

Voort¹,

Incekara²,

Wijnenga³

et al. 2020

Preprint

View full text Add to dashboard Cite

Accurate characterization of glioma is crucial for clinical decision making. A delineation of the tumor is also desirable in the initial decision stages but is a time-consuming task. Leveraging the latest GPU capabilities, we developed a single multi-task convolutional neural network that uses the full 3D, structural, pre-operative MRI scans to can predict the IDH mutation status, the 1p/19q co-deletion status, and the grade of a tumor, while simultaneously segmenting the tumor. We trained our method using the largest, most diverse patient cohort to date containing 1508 glioma patients from 16 institutes. We tested our method on an independent dataset of 240 patients from 13 different institutes, and achieved an IDH-AUC of 0.90, 1p/19q-AUC of 0.85, grade-AUC of 0.81, and a mean whole tumor DICE score of 0.84. Thus, our method non-invasively predicts multiple, clinically relevant parameters and generalizes well to the broader clinical population.

show abstract

“…Most of these approaches are based on analysing radiomics in terms of high-dimensional quantitative features extracted from a large number of medical images. Several approaches initially perform segmentation, followed by the classification based on the detected bounding box of the region of interest [5]. The performance of these approaches is affected by the detection and segmentation outcome.…”

Section: Radiological Phase Analysismentioning

confidence: 99%

Glioma Classification Using Multimodal Radiology and Histology Data

Hamidinekoo

Pieciak

Afzali

et al. 2021

Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries

View full text Add to dashboard Cite

Gliomas are brain tumours with a high mortality rate. There are various grades and sub-types of this tumour, and the treatment procedure varies accordingly. Clinicians and oncologists diagnose and categorise these tumours based on visual inspection of radiology and histology data. However, this process can be time-consuming and subjective. The computer-assisted methods can help clinicians to make better and faster decisions. In this paper, we propose a pipeline for automatic classification of gliomas into three sub-types: oligodendroglioma, astrocytoma, and glioblastoma, using both radiology and histopathology images. The proposed approach implements distinct classification models for radiographic and histologic modalities and combines them through an ensemble method. The classification algorithm initially carries out tile-level (for histology) and slice-level (for radiology) classification via a deep learning method, then tile/slice-level latent features are combined for a wholeslide and whole-volume sub-type prediction. The classification algorithm was evaluated using the data set provided in the CPM-RadPath 2020 challenge. The proposed pipeline achieved the F1-Score of 0.886, Cohen's Kappa score of 0.811 and Balance accuracy of 0.860. The ability of the proposed model for end-to-end learning of diverse features enables it to give a comparable prediction of glioma tumour sub-types.

show abstract

Automated MRI based pipeline for segmentation and prediction of grade, IDH mutation and 1p19q co-deletion in glioma

Cited by 54 publications

References 35 publications

Significantly high expression of NUP37 leads to poor prognosis of glioma patients by promoting the proliferation of glioma cells

Significantly high expression of NUP37 leads to poor prognosis of glioma patients by promoting the proliferation of glioma cells

WHO 2016 subtyping and automated segmentation of glioma using multi-task deep learning

Glioma Classification Using Multimodal Radiology and Histology Data

Contact Info

Product

Resources

About