Prediction of glioma-subtypes: comparison of performance on a DL classifier using bounding box areas versus annotated tumors

Ali, Muhaddisa Barat; Gu, Irene Yu‐Hua; Lidemar, Alice; Berger, Mitchel S.; Widhalm, Georg; Jakola, Asgeir Store

doi:10.1186/s42490-022-00061-3

Cited by 6 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To identify these subtypes, tissue diagnosis is performed through invasive methods (e.g., biopsy, resection), which comes with inherent risks. Recently, non-invasive methods have been proposed for identifying such information from Magnetic Resonance Images (MRIs) without using biopsy (Buda et al, 2019 ; Ali et al, 2022 ; de Dios et al, 2022 ; Hsu et al, 2022 ). Though many challenges remain, including, among others, the lack of large amount of annotated training datasets, and data privacy and security issues related to sharing training datasets from different hospitals in different countries.…”

Section: Introductionmentioning

confidence: 99%

A novel federated deep learning scheme for glioma and its subtype classification

Ali

Berger

et al. 2023

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

BackgroundDeep learning (DL) has shown promising results in molecular-based classification of glioma subtypes from MR images. DL requires a large number of training data for achieving good generalization performance. Since brain tumor datasets are usually small in size, combination of such datasets from different hospitals are needed. Data privacy issue from hospitals often poses a constraint on such a practice. Federated learning (FL) has gained much attention lately as it trains a central DL model without requiring data sharing from different hospitals.MethodWe propose a novel 3D FL scheme for glioma and its molecular subtype classification. In the scheme, a slice-based DL classifier, EtFedDyn, is exploited which is an extension of FedDyn, with the key differences on using focal loss cost function to tackle severe class imbalances in the datasets, and on multi-stream network to exploit MRIs in different modalities. By combining EtFedDyn with domain mapping as the pre-processing and 3D scan-based post-processing, the proposed scheme makes 3D brain scan-based classification on datasets from different dataset owners. To examine whether the FL scheme could replace the central learning (CL) one, we then compare the classification performance between the proposed FL and the corresponding CL schemes. Furthermore, detailed empirical-based analysis were also conducted to exam the effect of using domain mapping, 3D scan-based post-processing, different cost functions and different FL schemes.ResultsExperiments were done on two case studies: classification of glioma subtypes (IDH mutation and wild-type on TCGA and US datasets in case A) and glioma grades (high/low grade glioma HGG and LGG on MICCAI dataset in case B). The proposed FL scheme has obtained good performance on the test sets (85.46%, 75.56%) for IDH subtypes and (89.28%, 90.72%) for glioma LGG/HGG all averaged on five runs. Comparing with the corresponding CL scheme, the drop in test accuracy from the proposed FL scheme is small (−1.17%, −0.83%), indicating its good potential to replace the CL scheme. Furthermore, the empirically tests have shown that an increased classification test accuracy by applying: domain mapping (0.4%, 1.85%) in case A; focal loss function (1.66%, 3.25%) in case A and (1.19%, 1.85%) in case B; 3D post-processing (2.11%, 2.23%) in case A and (1.81%, 2.39%) in case B and EtFedDyn over FedAvg classifier (1.05%, 1.55%) in case A and (1.23%, 1.81%) in case B with fast convergence, which all contributed to the improvement of overall performance in the proposed FL scheme.ConclusionThe proposed FL scheme is shown to be effective in predicting glioma and its subtypes by using MR images from test sets, with great potential of replacing the conventional CL approaches for training deep networks. This could help hospitals to maintain their data privacy, while using a federated trained classifier with nearly similar performance as that from a centrally trained one. Further detailed experiments have shown that different parts in the proposed 3D FL scheme, such as domain mapping (make datasets more uniform) and post-processing (scan-based classification), are essential.

show abstract

Section: Introductionmentioning

confidence: 99%

A novel federated deep learning scheme for glioma and its subtype classification

Ali

Berger

et al. 2023

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Zhang et al [ 24 ] proposed a semi-supervised method that exploits information from unlabeled data by estimating segmentation uncertainty in predictions, and Luo et al [ 25 ] used a dual-task deep network to predict a segmentation map and geometry-aware level set labels. Ali et al proposed the use of rectangular shape [ 26 ] and ellipse shape [ 27 ] bounding box tumor regions for tumor classification. Pavlov et al [ 28 ] used ResNet50 for segmentation with both tumor ground truth and image-level annotation.…”

Section: Introductionmentioning

confidence: 99%

A Feasibility Study on Deep Learning Based Brain Tumor Segmentation Using 2D Ellipse Box Areas

Ali

Bai

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

In most deep learning-based brain tumor segmentation methods, training the deep network requires annotated tumor areas. However, accurate tumor annotation puts high demands on medical personnel. The aim of this study is to train a deep network for segmentation by using ellipse box areas surrounding the tumors. In the proposed method, the deep network is trained by using a large number of unannotated tumor images with foreground (FG) and background (BG) ellipse box areas surrounding the tumor and background, and a small number of patients (<20) with annotated tumors. The training is conducted by initial training on two ellipse boxes on unannotated MRIs, followed by refined training on a small number of annotated MRIs. We use a multi-stream U-Net for conducting our experiments, which is an extension of the conventional U-Net. This enables the use of complementary information from multi-modality (e.g., T1, T1ce, T2, and FLAIR) MRIs. To test the feasibility of the proposed approach, experiments and evaluation were conducted on two datasets for glioma segmentation. Segmentation performance on the test sets is then compared with those used on the same network but trained entirely by annotated MRIs. Our experiments show that the proposed method has obtained good tumor segmentation results on the test sets, wherein the dice score on tumor areas is (0.8407, 0.9104), and segmentation accuracy on tumor areas is (83.88%, 88.47%) for the MICCAI BraTS’17 and US datasets, respectively. Comparing the segmented results by using the network trained by all annotated tumors, the drop in the segmentation performance from the proposed approach is (0.0594, 0.0159) in the dice score, and (8.78%, 2.61%) in segmented tumor accuracy for MICCAI and US test sets, which is relatively small. Our case studies have demonstrated that training the network for segmentation by using ellipse box areas in place of all annotated tumors is feasible, and can be considered as an alternative, which is a trade-off between saving medical experts’ time annotating tumors and a small drop in segmentation performance.

show abstract

A Novel Mixed Convolution Transformer Model for the Fast and Accurate Diagnosis of Glioma Subtypes

Nobel,

Swapno,

Islam

et al. 2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

Glioblastoma is the most common adult brain tumor, significantly impacts disability and mortality. Early and accurate diagnosis of glioma subtypes is essential, but manual categorization is challenging due to their complexity, prompting the need for automated solutions. We developed an innovative mixed convolution‐transformer model to classify glioma subtypes, including astrocytoma, glioblastoma, oligodendroglioma, and normal brain tissue, using whole slide images. The novelty of this model lies in its remarkable efficiency and precise results. Multiple advanced and complex layers are incorporated during its development to enhance its performance, ensuring that it delivers fast and accurate classification results for glioma. This proposed model obtains an overall training accuracy of 97.41%, peaking at 98.12% for validation and 97.35% for testing. Next, our model architecture is independently evaluated by comparing its training performances on the CIFAR‐10 and CIFAR‐100 datasets with the vision transformer and compact convolutional transformer models. Results across various datasets demonstrate that the model consistently outperforms existing models. This performance underscores the effectiveness of our proposed approach in classifying glioma subtypes accurately and efficiently, highlighting its potential impact on healthcare and disability. This system enhances the classification of glioma subtypes and facilitates swift identification, ensuring appropriate and timely treatment.

show abstract

Prediction of glioma-subtypes: comparison of performance on a DL classifier using bounding box areas versus annotated tumors

Cited by 6 publications

References 44 publications

A novel federated deep learning scheme for glioma and its subtype classification

A novel federated deep learning scheme for glioma and its subtype classification

A Feasibility Study on Deep Learning Based Brain Tumor Segmentation Using 2D Ellipse Box Areas

A Novel Mixed Convolution Transformer Model for the Fast and Accurate Diagnosis of Glioma Subtypes

Contact Info

Product

Resources

About