A deep learning anthropomorphic model observer for a detection task in PET.

BACKGROUND: Lesion detection is one of the most important clinical tasks in positron emission tomography (PET) for oncology. An anthropomorphic model observer (MO) designed to replicate human observers (HOs) in a detection task is an important tool for assessing task-based image quality. The channelized Hotelling observer (CHO) has been the most popular anthropomorphic MO. Recently, deep learning MOs (DLMOs), mostly based on convolutional neural networks (CNNs), have been investigated for various imaging modalities. However, there have been few studies on DLMOs for PET. PURPOSE: The goal of the study is to investigate whether DLMOs can predict HOs better than conventional MOs such as CHO in a two-alternative forced-choice (2AFC) detection task using PET images with real anatomical variability. METHODS: Two types of DLMOs were implemented: (1) CNN DLMO, and (2) CNN-SwinT DLMO that combines CNN and Swin Transformer (SwinT) encoders. Lesion-absent PET images were reconstructed from clinical data, and lesion-present images were reconstructed with adding simulated lesion sinogram data. Lesion-present and lesion-absent PET image pairs were labeled by eight HOs consisting of four radiologists and four image scientists in a 2AFC detection task. In total, 2268 pairs of lesion-present and lesion-absent images were used for training, 324 pairs for validation, and 324 pairs for test. CNN DLMO, CNN-SwinT DLMO, CHO with internal noise, and non-prewhitening matched filter (NPWMF) were compared in the same train-test paradigm. For comparison, six quantitative metrics including prediction accuracy, mean squared errors (MSEs) and correlation coefficients, which measure how well a MO predicts HOs, were calculated in a 9-fold cross-validation experiment. RESULTS: In terms of the accuracy and MSE metrics, CNN DLMO and CNN-SwinT DLMO showed better performance than CHO and NPWMF, and CNN-SwinT DLMO showed the best performance among the MOs evaluated. CONCLUSIONS: DLMO can predict HOs more accurately than conventional MOs such as CHO in PET lesion detection. Combining SwinT and CNN encoders can improve the DLMO prediction performance compared to using CNN only.

Automatic Quantification of Enlarged Perivascular Space in Patients With Traumatic Brain Injury Using Super-Resolution of T2-Weighted Images.

The perivascular space (PVS) is important to brain waste clearance and brain metabolic homeostasis. Enlarged PVS (ePVS) becomes visible on magnetic resonance imaging (MRI) and is best appreciated on T2-weighted (T2w) images. However, quantification of ePVS is challenging because standard-of-care T1-weighted (T1w) and T2w images are often obtained via two-dimensional (2D) acquisition, whereas accurate quantification of ePVS normally requires high-resolution volumetric three-dimensional (3D) T1w and T2w images. The purpose of this study was to investigate the use of a deep-learning-based super-resolution (SR) technique to improve ePVS quantification from 2D T2w images for application in patients with traumatic brain injury (TBI). We prospectively recruited 26 volunteers (age: 31 ± 12 years, 12 male/14 female) where both 2D T2w and 3D T2w images were acquired along with 3D T1w images to validate the ePVS quantification using SR T2w images. We then applied the SR method to retrospectively acquired 2D T2w images in 41 patients with chronic TBI (age: 41 ± 16 years, 32 male/9 female). ePVS volumes were automatically quantified within the whole-brain white matter and major brain lobes (temporal, parietal, frontal, occipital) in all subjects. Pittsburgh Sleep Quality Index (PSQI) scores were obtained on all patients with TBI. Compared with the silver standard (3D T2w), in the validation study, the SR T2w provided similar whole-brain white matter ePVS volume (r = 0.98, p < 0.0001), and similar age-related ePVS burden increase (r = 0.80, p < 0.0001). In the patient study, patients with TBI with poor sleep showed a higher age-related ePVS burden increase than those with good sleep. Sleep status is a significant interaction factor in the whole brain (p = 0.047) and the frontal lobe (p = 0.027). We demonstrate that images produced by SR of 2D T2w images can be automatically analyzed to produce results comparable to those obtained by 3D T2 volumes. Reliable age-related ePVS burden across the whole-brain white matter was observed in all subjects. Poor sleep, affecting the glymphatic function, may contribute to the accelerated increase of ePVS burden following TBI.

Investigation of probability maps in deep-learning-based brain ventricle parcellation.

Normal Pressure Hydrocephalus (NPH) is a brain disorder associated with ventriculomegaly. Accurate segmentation of the ventricle system into its sub-compartments from magnetic resonance images (MRIs) could help evaluate NPH patients for surgical intervention. In this paper, we modify a 3D U-net utilizing probability maps to perform accurate ventricle parcellation, even with grossly enlarged ventricles and post-surgery shunt artifacts, from MRIs. Our method achieves a mean dice similarity coefficient (DSC) on whole ventricles for healthy controls of 0.864 ± 0.047 and 0.961 ± 0.024 for NPH patients. Furthermore, with the benefit of probability maps, the proposed method provides superior performance on MRI with grossly enlarged ventricles (mean DSC value of 0.965 ± 0.027) or post-surgery shunt artifacts (mean DSC value of 0.964 ± 0.031). Results indicate that our method provides a high robust parcellation tool on the ventricular systems which is comparable to other state-of-the-art methods.

Label Propagation via Random Walk for Training Robust Thalamus Nuclei Parcellation Model from Noisy Annotations.

Data-driven thalamic nuclei parcellation depends on high-quality manual annotations. However, the small size and low contrast changes among thalamic nuclei, yield annotations that are often incomplete, noisy, or ambiguously labelled. To train a robust thalamic nuclei parcellation model with noisy annotations, we propose a label propagation algorithm based on random walker to refine the annotations before model training. A two-step model was trained to generate first the whole thalamus and then the nuclei masks. We conducted experiments on a mild traumatic brain injury~(mTBI) dataset with noisy thalamic nuclei annotations. Our model outperforms current state-of-the-art thalamic nuclei parcellations by a clear margin. We believe our method can also facilitate the training of other parcellation models with noisy labels.

Analysis of Tongue Muscle Strain During Speech From Multimodal Magnetic Resonance Imaging.

PURPOSE: Muscle groups within the tongue in healthy and diseased populations show different behaviors during speech. Visualizing and quantifying strain patterns of these muscle groups during tongue motion can provide insights into tongue motor control and adaptive behaviors of a patient. METHOD: We present a pipeline to estimate the strain along the muscle fiber directions in the deforming tongue during speech production. A deep convolutional network estimates the crossing muscle fiber directions in the tongue using diffusion-weighted magnetic resonance imaging (MRI) data acquired at rest. A phase-based registration algorithm is used to estimate motion of the tongue muscles from tagged MRI acquired during speech. After transforming both muscle fiber directions and motion fields into a common atlas space, strain tensors are computed and projected onto the muscle fiber directions, forming so-called strains in the line of actions (SLAs) throughout the tongue. SLAs are then averaged over individual muscles that have been manually labeled in the atlas space using high-resolution T2-weighted MRI. Data were acquired, and this pipeline was run on a cohort of eight healthy controls and two glossectomy patients. RESULTS: The crossing muscle fibers reconstructed by the deep network show orthogonal patterns. The strain analysis results demonstrate consistency of muscle behaviors among some healthy controls during speech production. The patients show irregular muscle patterns, and their tongue muscles tend to show more extension than the healthy controls. CONCLUSIONS: The study showed visual evidence of correlation between two muscle groups during speech production. Patients tend to have different strain patterns compared to the controls. Analysis of variations in muscle strains can potentially help develop treatment strategies in oral diseases. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.21957011.

Evaluating the impact of MR image harmonization on thalamus deep network segmentation.

Medical image segmentation is one of the core tasks of medical image analysis. Automatic segmentation of brain magnetic resonance images (MRIs) can be used to visualize and track changes of the brain's anatomical structures that may occur due to normal aging or disease. Machine learning techniques are widely used in automatic structure segmentation. However, the contrast variation between the training and testing data makes it difficult for segmentation algorithms to generate consistent results. To address this problem, an image-to-image translation technique called MR image harmonization can be used to match the contrast between different data sets. It is important for the harmonization to transform image intensity while maintaining the underlying anatomy. In this paper, we present a 3D U-Net algorithm to segment the thalamus from multiple MR image modalities and investigate the impact of harmonization on the segmentation algorithm. Manual delineations of thalamic nuclei on two data sets are available. However, we aim to analyze the thalamus in another large data set where ground truth labels are lacking. We trained two segmentation networks, one with unharmonized images and the other with harmonized images, on one data set with manual labels, and compared their performances on the other data set with manual labels. These two data groups were diagnosed with two brain disorders and were acquired with similar imaging protocols. The harmonization target is the large data set without manual labels, which also has a different imaging protocol. The networks trained on unharmonized and harmonized data showed no significant difference when evaluating on the other data set; demonstrating that image harmonization can maintain the anatomy and does not affect the segmentation task. The two networks were evaluated on the harmonization target data set and the network trained on harmonized data showed significant improvement over the network trained on unharmonized data. Therefore, the network trained on harmonized data provides the potential to process large amounts of data from other sites, even in the absence of site-specific training data.

Applications of a deep learning method for anti-aliasing and super-resolution in MRI.

Magnetic resonance (MR) images with both high resolutions and high signal-to-noise ratios (SNRs) are desired in many clinical and research applications. However, acquiring such images takes a long time, which is both costly and susceptible to motion artifacts. Acquiring MR images with good in-plane resolution and poor through-plane resolution is a common strategy that saves imaging time, preserves SNR, and provides one viewpoint with good resolution in two directions. Unfortunately, this strategy also creates orthogonal viewpoints that have poor resolution in one direction and, for 2D MR acquisition protocols, also creates aliasing artifacts. A deep learning approach called SMORE that carries out both anti-aliasing and super-resolution on these types of acquisitions using no external atlas or exemplars has been previously reported but not extensively validated. This paper reviews the SMORE algorithm and then demonstrates its performance in four applications with the goal to demonstrate its potential for use in both research and clinical scenarios. It is first shown to improve the visualization of brain white matter lesions in FLAIR images acquired from multiple sclerosis patients. Then it is shown to improve the visualization of scarring in cardiac left ventricular remodeling after myocardial infarction. Third, its performance on multi-view images of the tongue is demonstrated and finally it is shown to improve performance in parcellation of the brain ventricular system. Both visual and selected quantitative metrics of resolution enhancement are demonstrated.

Brain ventricle parcellation using a deep neural network: Application to patients with ventriculomegaly.

Numerous brain disorders are associated with ventriculomegaly, including both neuro-degenerative diseases and cerebrospinal fluid disorders. Detailed evaluation of the ventricular system is important for these conditions to help understand the pathogenesis of ventricular enlargement and elucidate novel patterns of ventriculomegaly that can be associated with different diseases. One such disease is normal pressure hydrocephalus (NPH), a chronic form of hydrocephalus in older adults that causes dementia. Automatic parcellation of the ventricular system into its sub-compartments in patients with ventriculomegaly is quite challenging due to the large variation of the ventricle shape and size. Conventional brain labeling methods are time-consuming and often fail to identify the boundaries of the enlarged ventricles. We propose a modified 3D U-Net method to perform accurate ventricular parcellation, even with grossly enlarged ventricles, from magnetic resonance images (MRIs). We validated our method on a data set of healthy controls as well as a cohort of 95 patients with NPH with mild to severe ventriculomegaly and compared with several state-of-the-art segmentation methods. On the healthy data set, the proposed network achieved mean Dice similarity coefficient (DSC) of 0.895 ±â€¯0.03 for the ventricular system. On the NPH data set, we achieved mean DSC of 0.973 ±â€¯0.02, which is significantly (p < 0.005) higher than four state-of-the-art segmentation methods we compared with. Furthermore, the typical processing time on CPU-base implementation of the proposed method is 2 min, which is much lower than the several hours required by the other methods. Results indicate that our method provides: 1) highly robust parcellation of the ventricular system that is comparable in accuracy to state-of-the-art methods on healthy controls; 2) greater robustness and significantly more accurate results on cases of ventricular enlargement; and 3) a tool that enables computation of novel imaging biomarkers for dilated ventricular spaces that characterize the ventricular system.

Shortcomings of Ventricle Segmentation Using Deep Convolutional Networks.

Normal Pressure Hydrocephalus (NPH) is a brain disorder that can present with ventriculomegaly and dementia-like symptoms, which often can be reversed through surgery. Having accurate segmentation of the ventricular system into its sub-compartments from magnetic resonance images (MRI) would be beneficial to better characterize the condition of NPH patients. Previous segmentation algorithms need long processing time and often fail to accurately segment severely enlarged ventricles in NPH patients. Recently, deep convolutional neural network (CNN) methods have been reported to have fast and accurate performance on medical image segmentation tasks. In this paper, we present a 3D U-net CNN-based network to segment the ventricular system in MRI. We trained three networks on different data sets and compared their performances. The networks trained on healthy controls (HC) failed in patients with NPH pathology, even in patients with normal appearing ventricles. The network trained on images from HC and NPH patients provided superior performance against state-of-the-art methods when evaluated on images from both data sets.

Multi-atlas segmentation of the hydrocephalus brain using an adaptive ventricle atlas.

Normal pressure hydrocephalus (NPH) is a brain disorder caused by disruption of the flow of cerebrospinal fluid (CSF). The dementia-like symptoms of NPH are often mistakenly attributed to Alzheimer's disease. However, if correctly diagnosed, NPH patients can potentially be treated and their symptoms reversed through surgery. Observing the dilated ventricles through magnetic resonance imaging (MRI) is one element in diagnosing NPH. Diagnostic accuracy therefore benefits from accurate, automatic parcellation of the ventricular system into its sub-compartments. We present an improvement to a whole brain segmentation approach designed for subjects with enlarged and deformed ventricles. Our method incorporates an adaptive ventricle atlas from an NPH-atlas-based segmentation as a prior and uses a more robust relaxation scheme for the multi-atlas label fusion approach that accurately labels the four sub-compartments of the ventricular system. We validated our method on NPH patients, demonstrating improvement over state-of-the-art segmentation techniques.

Deformable model reconstruction of the subarachnoid space.

The subarachnoid space is a layer in the meninges that surrounds the brain and is filled with trabeculae and cerebrospinal fluid. Quantifying the volume and thickness of the subarachnoid space is of interest in order to study the pathogenesis of neurodegenerative diseases and compare with healthy subjects. We present an automatic method to reconstruct the subarachnoid space with subvoxel accuracy using a nested deformable model. The method initializes the deformable model using the convex hull of the union of the outer surfaces of the cerebrum, cerebellum and brainstem. A region force is derived from the subject's Tl-weighted and T2-weighted MRI to drive the deformable model to the outer surface of the subarachnoid space. The proposed method is compared to a semi-automatic delineation from the subject's T2-weighted MRI and an existing multi-atlas-based method. A small pilot study comparing the volume and thickness measurements in a set of age-matched subjects with normal pressure hydrocephalus and healthy controls is presented to show the efficacy of the proposed method.

Whole Brain Parcellation with Pathology: Validation on Ventriculomegaly Patients.

Numerous brain disorders are associated with ventriculomegaly; normal pressure hydrocephalus (NPH) is one example. NPH presents with dementia-like symptoms and is often misdiagnosed as Alzheimer's due to its chronic nature and nonspecific presenting symptoms. However, unlike other forms of dementia NPH can be treated surgically with an over 80% success rate on appropriately selected patients. Accurate assessment of the ventricles, in particular its sub-compartments, is required to diagnose the condition. Existing segmentation algorithms fail to accurately identify the ventricles in patients with such extreme pathology. We present an improvement to a whole brain segmentation approach that accurately identifies the ventricles and parcellates them into four sub-compartments. Our work is a combination of patch-based tissue segmentation and multi-atlas registration-based labeling. We include a validation on NPH patients, demonstrating superior performance against state-of-the-art methods.