Convolutional Neural Networks for Segmenting Cerebellar Fissures from Magnetic Resonance Imaging

Sensitivity of Advanced Magnetic Resonance Imaging to Progression over Six Months in Early Spinocerebellar Ataxia

BACKGROUND

Clinical trials for upcoming disease-modifying therapies of spinocerebellar ataxias (SCA), a group of rare movement disorders, lack endpoints sensitive to early disease progression, when therapeutics will be most effective. In addition, regulatory agencies emphasize the importance of biological outcomes.

OBJECTIVES

READISCA, a transatlantic clinical trial readiness consortium, investigated whether advanced multimodal magnetic resonance imaging (MRI) detects pathology progression over 6 months in preataxic and early ataxic carriers of SCA mutations.

METHODS

A total of 44 participants (10 SCA1, 25 SCA3, and 9 controls) prospectively underwent 3-T MR scanning at baseline and a median [interquartile range] follow-up of 6.2 [5.9-6.7] months; 44% of SCA participants were preataxic. Blinded analyses of annual changes in structural, diffusion MRI, MR spectroscopy, and the Scale for Assessment and Rating of Ataxia (SARA) were compared between groups using nonparametric testing. Sample sizes were estimated for 6-month interventional trials with 50% to 100% treatment effect size, leveraging existing large cohort data (186 SCA1, 272 SCA3) for the SARA estimate.

RESULTS

Rate of change in microstructural integrity (decrease in fractional anisotropy, increase in diffusivities) in the middle cerebellar peduncle, corona radiata, and superior longitudinal fasciculus significantly differed in SCAs from controls (P < 0.005), with high effect sizes (Cohen's d = 1-2) and moderate-to-high responsiveness (|standardized response mean| = 0.6-0.9) in SCAs. SARA scores did not change, and their rate of change did not differ between groups.

CONCLUSIONS

Diffusion MRI is sensitive to disease progression at very early-stage SCA1 and SCA3 and may provide a >5-fold reduction in sample sizes relative to SARA as endpoint for 6-month-long trials. © 2024 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Medical image identification methods: A review

The identification of medical images is an essential task in computer-aided diagnosis, medical image retrieval and mining. Medical image data mainly include electronic health record data and gene information data, etc. Although intelligent imaging provided a good scheme for medical image analysis over traditional methods that rely on the handcrafted features, it remains challenging due to the diversity of imaging modalities and clinical pathologies. Many medical image identification methods provide a good scheme for medical image analysis. The concepts pertinent of methods, such as the machine learning, deep learning, convolutional neural networks, transfer learning, and other image processing technologies for medical image are analyzed and summarized in this paper. We reviewed these recent studies to provide a comprehensive overview of applying these methods in various medical image analysis tasks, such as object detection, image classification, image registration, segmentation, and other tasks. Especially, we emphasized the latest progress and contributions of different methods in medical image analysis, which are summarized base on different application scenarios, including classification, segmentation, detection, and image registration. In addition, the applications of different methods are summarized in different application area, such as pulmonary, brain, digital pathology, brain, skin, lung, renal, breast, neuromyelitis, vertebrae, and musculoskeletal, etc. Critical discussion of open challenges and directions for future research are finally summarized. Especially, excellent algorithms in computer vision, natural language processing, and unmanned driving will be applied to medical image recognition in the future.

On the Cut-Off Value of the Anteroposterior Diameter of the Midbrain Atrophy in Spinocerebellar Ataxia Type 2 Patients

(1) Background: Spinocerebellar ataxias (SCA) is a term that refers to a group of hereditary ataxias, which are neurological diseases characterized by degeneration of the cells that constitute the cerebellum. Studies suggest that magnetic resonance imaging (MRI) supports diagnoses of ataxias, and linear measurements of the aneteroposterior diameter of the midbrain (ADM) have been investigated using MRI. These measurements correspond to studies in spinocerebellar ataxia type 2 (SCA2) patients and in healthy subjects. Our goal was to obtain the cut-off value for ADM atrophy in SCA2 patients. (2) Methods: This study evaluated 99 participants (66 SCA2 patients and 33 healthy controls). The sample was divided into estimations (80%) and validation (20%) samples. Using the estimation sample, we fitted a logistic model using the ADM and obtained the cut-off value through the inverse of regression. (3) Results: The optimal cut-off value of ADM was found to be 18.21 mm. The area under the curve (AUC) of the atrophy risk score was 0.957 (95% CI: 0.895-0.991). Using this cut-off on the validation sample, we found a sensitivity of 100.00% (95% CI: 76.84%-100.00%) and a specificity of 85.71% (95% CI: 42.13%-99.64%). (4) Conclusions: We obtained a cut-off value that has an excellent discriminatory capacity to identify SCA2 patients.

Clinically Meaningful Magnetic Resonance Endpoints Sensitive to Preataxic Spinocerebellar Ataxia Types 1 and 3

OBJECTIVE

This study was undertaken to identify magnetic resonance (MR) metrics that are most sensitive to early changes in the brain in spinocerebellar ataxia type 1 (SCA1) and type 3 (SCA3) using an advanced multimodal MR imaging (MRI) protocol in the multisite trial setting.

METHODS

SCA1 or SCA3 mutation carriers and controls (n = 107) underwent MR scanning in the US-European READISCA study to obtain structural, diffusion MRI, and MR spectroscopy data using an advanced protocol at 3T. Morphometric, microstructural, and neurochemical metrics were analyzed blinded to diagnosis and compared between preataxic SCA (n = 11 SCA1, n = 28 SCA3), ataxic SCA (n = 14 SCA1, n = 37 SCA3), and control (n = 17) groups using nonparametric testing accounting for multiple comparisons. MR metrics that were most sensitive to preataxic abnormalities were identified using receiver operating characteristic (ROC) analyses.

RESULTS

Atrophy and microstructural damage in the brainstem and cerebellar peduncles and neurochemical abnormalities in the pons were prominent in both preataxic groups, when patients did not differ from controls clinically. MR metrics were strongly associated with ataxia symptoms, activities of daily living, and estimated ataxia duration. A neurochemical measure was the most sensitive metric to preataxic changes in SCA1 (ROC area under the curve [AUC] = 0.95), and a microstructural metric was the most sensitive metric to preataxic changes in SCA3 (AUC = 0.92).

INTERPRETATION

Changes in cerebellar afferent and efferent pathways underlie the earliest symptoms of both SCAs. MR metrics collected with a harmonized advanced protocol in the multisite trial setting allow detection of disease effects in individuals before ataxia onset with potential clinical trial utility for subject stratification. ANN NEUROL 2023;93:686-701.