Logistic Regression-Based Model Is More Efficient Than U-Net Model for Reliable Whole Brain Magnetic Resonance Imaging Segmentation

Deep Learning for MRI Segmentation and Molecular Subtyping in Glioblastoma: Critical Aspects from an Emerging Field

Deep learning (DL) has been applied to glioblastoma (GBM) magnetic resonance imaging (MRI) assessment for tumor segmentation and inference of molecular, diagnostic, and prognostic information. We comprehensively overviewed the currently available DL applications, critically examining the limitations that hinder their broader adoption in clinical practice and molecular research. Technical limitations to the routine application of DL include the qualitative heterogeneity of MRI, related to different machinery and protocols, and the absence of informative sequences, possibly compensated by artificial image synthesis. Moreover, taking advantage from the available benchmarks of MRI, algorithms should be trained on large amounts of data. Additionally, the segmentation of postoperative imaging should be further addressed to limit the inaccuracies previously observed for this task. Indeed, molecular information has been promisingly integrated in the most recent DL tools, providing useful prognostic and therapeutic information. Finally, ethical concerns should be carefully addressed and standardized to allow for data protection. DL has provided reliable results for GBM assessment concerning MRI analysis and segmentation, but the routine clinical application is still limited. The current limitations could be prospectively addressed, giving particular attention to data collection, introducing new technical advancements, and carefully regulating ethical issues.

Clinical applications of deep learning in neuroinflammatory diseases: A scoping review

BACKGROUND

Deep learning (DL) is an artificial intelligence technology that has aroused much excitement for predictive medicine due to its ability to process raw data modalities such as images, text, and time series of signals.

OBJECTIVES

Here, we intend to give the clinical reader elements to understand this technology, taking neuroinflammatory diseases as an illustrative use case of clinical translation efforts. We reviewed the scope of this rapidly evolving field to get quantitative insights about which clinical applications concentrate the efforts and which data modalities are most commonly used.

METHODS

We queried the PubMed database for articles reporting DL algorithms for clinical applications in neuroinflammatory diseases and the radiology.healthairegister.com website for commercial algorithms.

RESULTS

The review included 148 articles published between 2018 and 2024 and five commercial algorithms. The clinical applications could be grouped as computer-aided diagnosis, individual prognosis, functional assessment, the segmentation of radiological structures, and the optimization of data acquisition. Our review highlighted important discrepancies in efforts. The segmentation of radiological structures and computer-aided diagnosis currently concentrate most efforts with an overrepresentation of imaging. Various model architectures have addressed different applications, relatively low volume of data, and diverse data modalities. We report the high-level technical characteristics of the algorithms and synthesize narratively the clinical applications. Predictive performances and some common a priori on this topic are finally discussed.

CONCLUSION

The currently reported efforts position DL as an information processing technology, enhancing existing modalities of paraclinical investigations and bringing perspectives to make innovative ones actionable for healthcare.

Highly Sensitive 3-Tesla Real Inversion Recovery MRI Detects Leptomeningeal Contrast Enhancement in Chronic Active Multiple Sclerosis

BACKGROUND

Leptomeningeal contrast enhancement (LME) on T2-weighted Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRI is a reported marker of leptomeningeal inflammation, which is known to be associated with progression of multiple sclerosis (MS). However, this MRI approach, as typically implemented on clinical 3-tesla (T) systems, detects only a few enhancing foci in ~25% of patients and has thus been criticized as poorly sensitive.

PURPOSE

To compare an optimized 3D real-reconstruction inversion recovery (Real-IR) MRI sequence on a clinical 3 T scanner to T2-FLAIR for prevalence, characteristics, and clinical/radiological correlations of LME.

MATERIALS AND METHODS

We obtained 3D T2-FLAIR and Real-IR scans before and after administration of standard-dose gadobutrol in 177 scans of 154 participants (98 women, 64%; mean ± SD age: 49 ± 12 years), including 124 with an MS-spectrum diagnosis, 21 with other neurological and/or inflammatory disorders, and 9 without neurological history. We calculated contrast-to-noise ratios (CNR) in 20 representative LME foci and determined association of LME with cortical lesions identified at 7 T (n = 19), paramagnetic rim lesions (PRL) at 3 T (n = 105), and clinical/demographic data.

RESULTS

We observed focal LME in 73% of participants on Real-IR (70% in established MS, 33% in healthy volunteers, P < 0.0001), compared to 33% on T2-FLAIR (34% vs. 11%, P = 0.0002). Real-IR showed 3.7-fold more LME foci than T2-FLAIR ( P = 0.001), including all T2-FLAIR foci. LME CNR was 2.5-fold higher by Real-IR ( P < 0.0001). The major determinant of LME status was age. Although LME was not associated with cortical lesions, the number of PRL was associated with the number of LME foci on both T2-FLAIR ( P = 0.003) and Real-IR ( P = 0.0003) after adjusting for age, sex, and white matter lesion volume.

CONCLUSIONS

Real-IR a promising tool to detect, characterize, and understand the significance of LME in MS. The association between PRL and LME highlights a possible role of the leptomeninges in sustaining chronic inflammation.

Neuroimaging characterization of multiple sclerosis lesions in pediatric patients: an exploratory radiomics approach

Introduction

Multiple sclerosis (MS), a chronic inflammatory immune-mediated disease of the central nervous system (CNS), is a common condition in young adults, but it can also affect children. The aim of this study was to construct radiomic models of lesions based on magnetic resonance imaging (MRI, T2-weighted-Fluid-Attenuated Inversion Recovery), to understand the correlation between extracted radiomic features, brain and lesion volumetry, demographic, clinical and laboratorial data.

Methods

The neuroimaging data extracted from eleven scans of pediatric MS patients were analyzed. A total of 60 radiomic features based on MR T2-FLAIR images were extracted and used to calculate gray level co-occurrence matrix (GLCM). The principal component analysis and ROC analysis were performed to select the radiomic features, respectively. The realized classification task by the logistic regression models was performed according to these radiomic features.

Results

Ten most relevant features were selected from data extracted. The logistic regression applied to T2-FLAIR radiomic features revealed significant predictor for multiple sclerosis (MS) lesion detection. Only the variable "contrast" was statistically significant, indicating that only this variable played a significant role in the model. This approach enhances the classification of lesions from normal tissue.

Discussion and conclusion

Our exploratory results suggest that the radiomic models based on MR imaging (T2-FLAIR) may have a potential contribution to characterization of brain tissues and classification of lesions in pediatric MS.

Pseudo-Label Assisted nnU-Net enables automatic segmentation of 7T MRI from a single acquisition

Introduction

Automatic whole brain and lesion segmentation at 7T presents challenges, primarily from bias fields, susceptibility artifacts including distortions, and registration errors. Here, we sought to use deep learning algorithms (D/L) to do both skull stripping and whole brain segmentation on multiple imaging contrasts generated in a single Magnetization Prepared 2 Rapid Acquisition Gradient Echoes (MP2RAGE) acquisition on participants clinically diagnosed with multiple sclerosis (MS), bypassing registration errors.

Methods

Brain scans Segmentation from 3T and 7T scanners were analyzed with software packages such as FreeSurfer, Classification using Derivative-based Features (C-DEF), nnU-net, and a novel 3T-to-7T transfer learning method, Pseudo-Label Assisted nnU-Net (PLAn). 3T and 7T MRIs acquired within 9 months from 25 study participants with MS (Cohort 1) were used for training and optimizing. Eight MS patients (Cohort 2) scanned only at 7T, but with expert annotated lesion segmentation, was used to further validate the algorithm on a completely unseen dataset. Segmentation results were rated visually by experts in a blinded fashion and quantitatively using Dice Similarity Coefficient (DSC).

Results

Of the methods explored here, nnU-Net and PLAn produced the best tissue segmentation at 7T for all tissue classes. In both quantitative and qualitative analysis, PLAn significantly outperformed nnU-Net (and other methods) in lesion detection in both cohorts. PLAn's lesion DSC improved by 16% compared to nnU-Net.

Discussion

Limited availability of labeled data makes transfer learning an attractive option, and pre-training a nnUNet model using readily obtained 3T pseudo-labels was shown to boost lesion detection capabilities at 7T.