Fully Automated MR Based Virtual Biopsy of Cerebral Gliomas

Haubold, Johannes; Hosch, René; Parmar, Vicky; Glas, Martin; Guberina, Nika; Catalano, Onofrio A.; Pierscianek, Daniela; Wrede, Karsten H.; Deuschl, Cornelius; Forsting, Michael; Nensa, Felix; Flaschel, Nils; Umutlu, Lale

doi:10.3390/cancers13246186

Cited by 14 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…reported that the predictive accuracy of MGMT status was 0.67, while Johannes Haubold et al . reported that the AUCs of predicting MGMT status were 0.854 and 0.742 in validation and test sets, respectively [ 27 , 28 ]. In addition, Yibin Xi et al .…”

Section: Discussionmentioning

confidence: 99%

Radiomics for predicting MGMT status in cerebral glioblastoma: comparison of different MRI sequences

Zheng,

Zhang,

Chen

et al. 2024

Journal of Radiation Research

View full text Add to dashboard Cite

Using radiomics to predict O6-methylguanine-DNA methyltransferase promoter methylation status in patients with newly diagnosed glioblastoma and compare the performances of different MRI sequences. Preoperative MRI scans from 215 patients were included in this retrospective study. After image preprocessing and feature extraction, two kinds of machine-learning models were established and compared for their performances. One kind was established using all MRI sequences (T1-weighted image, T2-weighted image, contrast enhancement, fluid-attenuated inversion recovery, DWI_b_high, DWI_b_low and apparent diffusion coefficient), and the other kind was based on single MRI sequence as listed above. For the machine-learning model based on all sequences, a total of seven radiomic features were selected with the Maximum Relevance and Minimum Redundancy algorithm. The predictive accuracy was 0.993 and 0.750 in the training and validation sets, respectively, and the area under curves were 1.000 and 0.754 in the two sets, respectively. For the machine-learning model based on single sequence, the numbers of selected features were 8, 10, 10, 13, 9, 7 and 6 for T1-weighted image, T2-weighted image, contrast enhancement, fluid-attenuated inversion recovery, DWI_b_high, DWI_b_low and apparent diffusion coefficient, respectively, with predictive accuracies of 0.797–1.000 and 0.583–0.694 in the training and validation sets, respectively, and the area under curves of 0.874–1.000 and 0.538–0.697 in the two sets, respectively. Specifically, T1-weighted image-based model performed best, while contrast enhancement-based model performed worst in the independent validation set. The machine-learning models based on seven different single MRI sequences performed differently in predicting O6-methylguanine-DNA methyltransferase status in glioblastoma, while the machine-learning model based on the combination of all sequences performed best.

show abstract

Section: Discussionmentioning

confidence: 99%

Radiomics for predicting MGMT status in cerebral glioblastoma: comparison of different MRI sequences

Zheng,

Zhang,

Chen

et al. 2024

Journal of Radiation Research

View full text Add to dashboard Cite

show abstract

“…The system provided an AUC (validation/test) of 0.981 ± 0.015/0.885 ± 0.02 for the grading task. The prediction of the ATRX (−) condition had the best results, with an AUC of 0.979 ± 0.028/0.923 ± 0.045, followed by the prediction of IDH1/2(+), with an AUC of 0.929 ± 0.042/0.861 ± 0.023, while they showed only moderate results for the prediction of 1p19q and MGMT status [ 82 ].…”

Section: Tumor Characterizationmentioning

confidence: 99%

Artificial Intelligence in Brain Tumor Imaging: A Step toward Personalized Medicine

et al. 2023

View full text Add to dashboard Cite

The application of artificial intelligence (AI) is accelerating the paradigm shift towards patient-tailored brain tumor management, achieving optimal onco-functional balance for each individual. AI-based models can positively impact different stages of the diagnostic and therapeutic process. Although the histological investigation will remain difficult to replace, in the near future the radiomic approach will allow a complementary, repeatable and non-invasive characterization of the lesion, assisting oncologists and neurosurgeons in selecting the best therapeutic option and the correct molecular target in chemotherapy. AI-driven tools are already playing an important role in surgical planning, delimiting the extent of the lesion (segmentation) and its relationships with the brain structures, thus allowing precision brain surgery as radical as reasonably acceptable to preserve the quality of life. Finally, AI-assisted models allow the prediction of complications, recurrences and therapeutic response, suggesting the most appropriate follow-up. Looking to the future, AI-powered models promise to integrate biochemical and clinical data to stratify risk and direct patients to personalized screening protocols.

show abstract

“…Therefore, the scientific effort has increasingly focused on improving and streamlining the imaging of meningiomas prior to therapy. A variety of publications are dedicated to novel methods in imaging of intracranial neoplasms, such as the implementation of radiomics [8][9][10] or advanced multiparametric MRI [4,11,12]. Here, especially diffusion-weighted imaging (DWI), a marker for cellular density in tissue, might be of considerable interest [13].…”

Section: Introductionmentioning

confidence: 99%

Correlation of the apparent diffusion coefficient with the standardized uptake value in meningioma of the skull plane using [68]Ga-DOTATOC PET/MRI

Milosevic,

Styczen,

Haubold

et al. 2023

Nuclear Medicine Communications

Self Cite

View full text Add to dashboard Cite

Purpose To evaluate a correlation between an MRI-specific marker for cellular density [apparent diffusion coefficient (ADC)] and the expression of Somatostatin Receptors (SSTR) in patients with meningioma of the skull plane and orbital space. Methods 68Ga-DOTATOC PET/MR imaging was performed in 60 Patients with suspected or diagnosed meningiomas of the skull base and eye socket. Analysis of ADC values succeeded in 32 patients. ADC values (ADCmean and ADCmin) were analyzed using a polygonal region of interest. Tracer-uptake of target lesions was assessed according to corresponding maximal (SUVmax) and mean (SUVmean) values. Correlations between assessed parameters were evaluated using the Pearson correlation coefficient. Results One out of 32 patients (3%) was diagnosed with lymphoma by histopathological examination and therefore excluded from further analysis. Median ADCmean amounted to 822 × 10-5 mm²/s-1 (95% CI: 570–1497) and median ADCmin was 493 × 10-5 mm2/s-1 (95% CI: 162–783). There were no significant correlations between SUVmax and ADCmin (r = 0.60; P = 0.76) or ADCmean (r = -0.52; P = 0.79), respectively. However, Pearson’s test showed a weak, inverse but insignificant correlation between ADCmean and SUVmean (r = −0.33; P = 0.07). Conclusion The presented data displays no relevant correlations between increased SSTR expression and cellularity in patients with meningioma of the skull base. SSTR-PET and DWI thus may offer complementary information on tumor characteristics of meningioma.

show abstract

Fully Automated MR Based Virtual Biopsy of Cerebral Gliomas

Cited by 14 publications

References 39 publications

Radiomics for predicting MGMT status in cerebral glioblastoma: comparison of different MRI sequences

Radiomics for predicting MGMT status in cerebral glioblastoma: comparison of different MRI sequences

Artificial Intelligence in Brain Tumor Imaging: A Step toward Personalized Medicine

Correlation of the apparent diffusion coefficient with the standardized uptake value in meningioma of the skull plane using [68]Ga-DOTATOC PET/MRI

Contact Info

Product

Resources

About