Preoperative Apparent Diffusion Coefficient of Peritumoral Lesion Associate with Recurrence in Patients with Glioblastoma

LIT-Unet: a lightweight and effective model for medical image segmentation

This study aimed to design a simple and efficient automatic segmentation model for medical images, so as to facilitate doctors to make more accurate diagnosis and treatment plan. A hybrid lightweight network LIT-Unet with symmetric encoder-decoder U-shaped architecture is proposed. Synapse multi-organ segmentation dataset and automated cardiac diagnosis challenge (ACDC) dataset were used to test the segmentation performance of the method. Two indexes, Dice similarity coefficient (DSC ↑) and 95% Hausdorff distance (HD95 ↓), were used to evaluate and compare the segmentation ability with the current advanced methods. Ablation experiments were conducted to demonstrate the lightweight nature and effectiveness of our model. For Synapse dataset, our model achieves a higher DSC score (80.40%), an improvement of 3.8% over the typical hybrid model (TransUnet). The 95 HD value is low at 20.67%. For ACDC dataset, LIT-Unet achieves the optimal average DSC (%) of 91.84 compared with other networks listed. Compared to patch expanding, the DSC of our model is intuitively improved by 1.62% with the help of deformable token merging (DTM). These results show that the proposed hierarchical LIT-Unet can achieve significant accuracy and is expected to provide a reliable basis for clinical diagnosis and treatment.

Association of ADC of hyperintense lesions on FLAIR images with TERT promoter mutation status in glioblastoma IDH wild type

Background

Although mutations in telomerase reverse transcriptase (TERT) promoter (TERTp) are the most common alterations in glioblastoma (GBM), predicting TERTp mutation status by preoperative imaging is difficult. We determined whether tumour-surrounding hyperintense lesions on fluid-attenuated inversion recovery (FLAIR) were superior to those of contrast-enhanced lesions (CELs) in assessing TERTp mutation status using magnetic resonance imaging (MRI).

Methods

This retrospective study included 114 consecutive patients with primary isocitrate dehydrogenase (IDH)-wild-type GBM. The apparent diffusion coefficient (ADC) and volume of CELs and FLAIR hyperintense lesions (FHLs) were determined, and the correlation between MRI features and TERTp mutation status was analyzed. In a subset of cases, FHLs were histopathologically analyzed to determine the correlation between tumor cell density and ADC.

Results

TERTp mutations were present in 77 (67.5%) patients. The minimum ADC of FHLs was significantly lower in the TERTp-mutant group than in the TERTp-wild-type group (mean, 958.9 × 10-3 and 1092.1 × 10-3 mm2/s, respectively, P < 0.01). However, other MRI features, such as CEL and FHL volumes, minimum ADC of CELs, and FHL/CEL ratio, were not significantly different between the two groups. Histopathologic analysis indicated high tumor cell density in FHLs with low ADC.

Conclusion

The ADC of FHLs was significantly lower in IDH-wild-type GBM with TERTp mutations, suggesting that determining the ADC of FHLs on preoperative MRI might be helpful in predicting TERTp mutation status and surgical planning.

Added value of dynamic contrast-enhanced MR imaging in deep learning-based prediction of local recurrence in grade 4 adult-type diffuse gliomas patients

Local recurrences in patients with grade 4 adult-type diffuse gliomas mostly occur within residual non-enhancing T2 hyperintensity areas after surgical resection. Unfortunately, it is challenging to distinguish non-enhancing tumors from edema in the non-enhancing T2 hyperintensity areas using conventional MRI alone. Quantitative DCE MRI parameters such as Ktrans and Ve convey permeability information of glioblastomas that cannot be provided by conventional MRI. We used the publicly available nnU-Net to train a deep learning model that incorporated both conventional and DCE MRI to detect the subtle difference in vessel leakiness due to neoangiogenesis between the non-recurrence area and the local recurrence area, which contains a higher proportion of high-grade glioma cells. We found that the addition of Ve doubled the sensitivity while nonsignificantly decreasing the specificity for prediction of local recurrence in glioblastomas, which implies that the combined model may result in fewer missed cases of local recurrence. The deep learning model predictive of local recurrence may enable risk-adapted radiotherapy planning in patients with grade 4 adult-type diffuse gliomas.