2020
DOI: 10.1007/978-3-030-46643-5_34
|View full text |Cite
|
Sign up to set email alerts
|

Brain Tumor Classification with Multimodal MR and Pathology Images

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
14
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 17 publications
(14 citation statements)
references
References 5 publications
0
14
0
Order By: Relevance
“…In Equations 2–6, Num is the number of samples, TP the true positives, TN the true negatives, FP the false positives, FN the false negatives, and n the number of sample categories. In Equation 7, p 0 denotes the sum of the number of samples for each correct classification divided by the total number of samples, and p e the expected agreement when both annotators assign labels randomly ( 6 ). According to the accuracy metric, the best classifier was chosen as our predictive model for the task of glioma subtype classification.…”
Section: Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…In Equations 2–6, Num is the number of samples, TP the true positives, TN the true negatives, FP the false positives, FN the false negatives, and n the number of sample categories. In Equation 7, p 0 denotes the sum of the number of samples for each correct classification divided by the total number of samples, and p e the expected agreement when both annotators assign labels randomly ( 6 ). According to the accuracy metric, the best classifier was chosen as our predictive model for the task of glioma subtype classification.…”
Section: Methodsmentioning
confidence: 99%
“…Age being the only available clinical factor in the CPM-RadPath challenge dataset ( 6 ), we converted it from days to years for simplicity before analysis. The differences in age and glioma subtypes between the training and testing sets were assessed using the Mann–Whitney rank-sum test.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…In this section, we summarise the work submitted by the participants for the previous similar challenge in CPM-RadPath 2019 (https://www.med.upenn.edu/ cbica/cpm-rad-path-2019). Ma et al [13], as the first ranked group, proposed two convolutional neural networks to predict the grade of gliomas from both radiology and pathology data: (i) a 2D ResNet-based model for pathology patch based image classification and (ii) a 3D DenseNet-based model for classifying the detected regions (using a detection model) on multi-parametric MRI (mp-MRI) images. To extract the pathology patches (512 × 512) they used mean and standard deviation with predefined thresholds to consider patches including cells and excluding patches with background contents.…”
Section: Related Workmentioning
confidence: 99%
“…For skin legion classification, [113] combined CNN generated features with tabular clinical data and performed classification with a three layer DNN. In [67], MRI and pathology images were used to predict the cancer stage of brain tumors. Both modalities were classified with CNNs and their final layers were concatenated and classified using a LR classifier.…”
Section: Late Fusionmentioning
confidence: 99%