Learning-based analysis of amide proton transfer-weighted MRI to identify true progression in glioma patients

Performance of amide proton transfer imaging to differentiate true progression from therapy-related changes in gliomas and metastases

OBJECTIVES

Differentiating true progression or recurrence (TP/TR) from therapy-related changes (TRC) is complex in brain tumours. Amide proton transfer-weighted (APT) imaging is a chemical exchange saturation transfer (CEST) MRI technique that may improve diagnostic accuracy during radiological follow-up. This systematic review and meta-analysis elucidated the level of evidence and details of state-of-the-art imaging for APT-CEST in glioma and brain metastasis surveillance.

METHODS

PubMed, EMBASE, Web of Science, and Cochrane Library were systematically searched for original articles about glioma and metastasis patients who received APT-CEST imaging for suspected TP/TR within 2 years after (chemo)radiotherapy completion. Modified Quality Assessment of Diagnostic Accuracy Studies-2 criteria were applied. A meta-analysis was performed to pool results and to compare subgroups.

RESULTS

Fifteen studies were included for a narrative synthesis, twelve of which (500 patients) were deemed sufficiently homogeneous for a meta-analysis. Magnetisation transfer ratio asymmetry performed well in gliomas (sensitivity 0.88 [0.82-0.92], specificity 0.84 [0.72-0.91]) but not in metastases (sensitivity 0.64 [0.38-0.84], specificity 0.56 [0.33-0.77]). APT-CEST combined with conventional/advanced MRI rendered 0.92 [0.86-0.96] and 0.88 [0.72-0.95] in gliomas. Tumour type, TR prevalence, sex, and acquisition protocol were sources of significant inter-study heterogeneity in sensitivity (I2 = 62.25%; p < 0.01) and specificity (I2 = 66.31%; p < 0.001).

CONCLUSION

A growing body of literature suggests that APT-CEST is a promising technique for improving the discrimination of TP/TR from TRC in gliomas, with limited data on metastases.

CLINICAL RELEVANCE STATEMENT

This meta-analysis identified a utility for APT-CEST imaging regarding the non-invasive discrimination of brain tumour progression from therapy-related changes, providing a critical evaluation of sequence parameters and cut-off values, which can be used to improve response assessment and patient outcome.

KEY POINTS

Therapy-related changes mimicking progression complicate brain tumour treatment. Amide proton imaging improves the non-invasive discrimination of glioma progression from therapy-related changes. Magnetisation transfer ratio asymmetry measurement seems not to have added value in brain metastases.

Advances in diffuse glioma assessment: preoperative and postoperative applications of chemical exchange saturation transfer

Chemical Exchange Saturation Transfer (CEST) is a technique that uses specific off-resonance saturation pulses to pre-saturate targeted substances. This process influences the signal intensity of free water, thereby indirectly providing information about the pre-saturated substance. Among the clinical applications of CEST, Amide Proton Transfer (APT) is currently the most well-established. APT can be utilized for the preoperative grading of gliomas. Tumors with higher APTw signals generally indicate a higher likelihood of malignancy. In predicting preoperative molecular typing, APTw values are typically lower in tumors with favorable molecular phenotypes, such as isocitrate dehydrogenase (IDH) mutations, compared to IDH wild-type tumors. For differential diagnosis, the average APTw values of meningiomas are significantly lower than those of high-grade gliomas. Various APTw measurement indices assist in distinguishing central nervous system lesions with similar imaging features, such as progressive multifocal leukoencephalopathy, central nervous system lymphoma, solitary brain metastases, and glioblastoma. Regarding prognosis, APT effectively differentiates between tumor recurrence and treatment effects, and also possesses predictive capabilities for overall survival (OS) and progression-free survival (PFS).

IMPA-Net: Interpretable Multi-Part Attention Network for Trustworthy Brain Tumor Classification from MRI

Deep learning (DL) networks have shown attractive performance in medical image processing tasks such as brain tumor classification. However, they are often criticized as mysterious "black boxes". The opaqueness of the model and the reasoning process make it difficult for health workers to decide whether to trust the prediction outcomes. In this study, we develop an interpretable multi-part attention network (IMPA-Net) for brain tumor classification to enhance the interpretability and trustworthiness of classification outcomes. The proposed model not only predicts the tumor grade but also provides a global explanation for the model interpretability and a local explanation as justification for the proffered prediction. Global explanation is represented as a group of feature patterns that the model learns to distinguish high-grade glioma (HGG) and low-grade glioma (LGG) classes. Local explanation interprets the reasoning process of an individual prediction by calculating the similarity between the prototypical parts of the image and a group of pre-learned task-related features. Experiments conducted on the BraTS2017 dataset demonstrate that IMPA-Net is a verifiable model for the classification task. A percentage of 86% of feature patterns were assessed by two radiologists to be valid for representing task-relevant medical features. The model shows a classification accuracy of 92.12%, of which 81.17% were evaluated as trustworthy based on local explanations. Our interpretable model is a trustworthy model that can be used for decision aids for glioma classification. Compared with black-box CNNs, it allows health workers and patients to understand the reasoning process and trust the prediction outcomes.

MoViT: Memorizing Vision Transformers for Medical Image Analysis

The synergy of long-range dependencies from transformers and local representations of image content from convolutional neural networks (CNNs) has led to advanced architectures and increased performance for various medical image analysis tasks due to their complementary benefits. However, compared with CNNs, transformers require considerably more training data, due to a larger number of parameters and an absence of inductive bias. The need for increasingly large datasets continues to be problematic, particularly in the context of medical imaging, where both annotation efforts and data protection result in limited data availability. In this work, inspired by the human decision-making process of correlating new "evidence" with previously memorized "experience", we propose a Memorizing Vision Transformer (MoViT) to alleviate the need for large-scale datasets to successfully train and deploy transformer-based architectures. MoViT leverages an external memory structure to cache history attention snapshots during the training stage. To prevent overfitting, we incorporate an innovative memory update scheme, attention temporal moving average, to update the stored external memories with the historical moving average. For inference speedup, we design a prototypical attention learning method to distill the external memory into smaller representative subsets. We evaluate our method on a public histology image dataset and an in-house MRI dataset, demonstrating that MoViT applied to varied medical image analysis tasks, can outperform vanilla transformer models across varied data regimes, especially in cases where only a small amount of annotated data is available. More importantly, MoViT can reach a competitive performance of ViT with only 3.0% of the training data. In conclusion, MoViT provides a simple plug-in for transformer architectures which may contribute to reducing the training data needed to achieve acceptable models for a broad range of medical image analysis tasks.

CEST2022: Amide proton transfer-weighted MRI improves the diagnostic performance of multiparametric non-contrast-enhanced MRI techniques in patients with post-treatment high-grade gliomas

New or enlarged lesions in malignant gliomas after surgery and chemoradiation can be associated with tumor recurrence or treatment effect. Due to similar radiographic characteristics, conventional-and even some advanced MRI techniques-are limited in distinguishing these two pathologies. Amide proton transfer-weighted (APTw) MRI, a protein-based molecular imaging technique that does not require the administration of any exogenous contrast agent, was recently introduced into the clinical setting. In this study, we evaluated and compared the diagnostic performances of APTw MRI with several non-contrast-enhanced MRI sequences, such as diffusion-weighted imaging, susceptibility-weighted imaging, and pseudo-continuous arterial spin labeling. Thirty-nine scans from 28 glioma patients were obtained on a 3 T MRI scanner. A histogram analysis approach was employed to extract parameters from each tumor area. Statistically significant parameters (P < 0.05) were selected to train multivariate logistic regression models to evaluate the performance of MRI sequences. Multiple histogram parameters, particularly from APTw and pseudo-continuous arterial spin labeling images, demonstrated significant differences between treatment effect and recurrent tumor. The regression model trained on the combination of all significant histogram parameters achieved the best result (area under the curve = 0.89). We found that APTw images added value to other advanced MR images for the differentiation of treatment effect and tumor recurrence.

Accelerated and quantitative three-dimensional molecular MRI using a generative adversarial network

PURPOSE

To substantially shorten the acquisition time required for quantitative three-dimensional (3D) chemical exchange saturation transfer (CEST) and semisolid magnetization transfer (MT) imaging and allow for rapid chemical exchange parameter map reconstruction.

METHODS

Three-dimensional CEST and MT magnetic resonance fingerprinting (MRF) datasets of L-arginine phantoms, whole-brains, and calf muscles from healthy volunteers, cancer patients, and cardiac patients were acquired using 3T clinical scanners at three different sites, using three different scanner models and coils. A saturation transfer-oriented generative adversarial network (GAN-ST) supervised framework was then designed and trained to learn the mapping from a reduced input data space to the quantitative exchange parameter space, while preserving perceptual and quantitative content.

RESULTS

The GAN-ST 3D acquisition time was 42-52 s, 70% shorter than CEST-MRF. The quantitative reconstruction of the entire brain took 0.8 s. An excellent agreement was observed between the ground truth and GAN-based L-arginine concentration and pH values (Pearson's r > 0.95, ICC > 0.88, NRMSE < 3%). GAN-ST images from a brain-tumor subject yielded a semi-solid volume fraction and exchange rate NRMSE of3 . 8 ± 1 . 3 % $$ 3.8\pm 1.3\% $$ and4 . 6 ± 1 . 3 % $$ 4.6\pm 1.3\% $$ , respectively, and SSIM of96 . 3 ± 1 . 6 % $$ 96.3\pm 1.6\% $$ and95 . 0 ± 2 . 4 % $$ 95.0\pm 2.4\% $$ , respectively. The mapping of the calf-muscle exchange parameters in a cardiac patient, yielded NRMSE < 7% and SSIM > 94% for the semi-solid exchange parameters. In regions with large susceptibility artifacts, GAN-ST has demonstrated improved performance and reduced noise compared to MRF.

CONCLUSION

GAN-ST can substantially reduce the acquisition time for quantitative semi-solid MT/CEST mapping, while retaining performance even when facing pathologies and scanner models that were not available during training.

Molecular MRI-Based Monitoring of Cancer Immunotherapy Treatment Response

Immunotherapy constitutes a paradigm shift in cancer treatment. Its FDA approval for several indications has yielded improved prognosis for cases where traditional therapy has shown limited efficiency. However, many patients still fail to benefit from this treatment modality, and the exact mechanisms responsible for tumor response are unknown. Noninvasive treatment monitoring is crucial for longitudinal tumor characterization and the early detection of non-responders. While various medical imaging techniques can provide a morphological picture of the lesion and its surrounding tissue, a molecular-oriented imaging approach holds the key to unraveling biological effects that occur much earlier in the immunotherapy timeline. Magnetic resonance imaging (MRI) is a highly versatile imaging modality, where the image contrast can be tailored to emphasize a particular biophysical property of interest using advanced engineering of the imaging pipeline. In this review, recent advances in molecular-MRI based cancer immunotherapy monitoring are described. Next, the presentation of the underlying physics, computational, and biological features are complemented by a critical analysis of the results obtained in preclinical and clinical studies. Finally, emerging artificial intelligence (AI)-based strategies to further distill, quantify, and interpret the image-based molecular MRI information are discussed in terms of perspectives for the future.