Improved Automatic Segmentation of White Matter Hyperintensities in MRI Based on Multilevel Lesion Features

Applications of artificial intelligence in nuclear medicine image generation

Recently, the application of artificial intelligence (AI) in medical imaging (including nuclear medicine imaging) has rapidly developed. Most AI applications in nuclear medicine imaging have focused on the diagnosis, treatment monitoring, and correlation analyses with pathology or specific gene mutation. It can also be used for image generation to shorten the time of image acquisition, reduce the dose of injected tracer, and enhance image quality. This work provides an overview of the application of AI in image generation for single-photon emission computed tomography (SPECT) and positron emission tomography (PET) either without or with anatomical information [CT or magnetic resonance imaging (MRI)]. This review focused on four aspects, including imaging physics, image reconstruction, image postprocessing, and internal dosimetry. AI application in generating attenuation map, estimating scatter events, boosting image quality, and predicting internal dose map is summarized and discussed.

Automatic brain lesion segmentation on standard magnetic resonance images: a scoping review

OBJECTIVES

Medical image analysis practices face challenges that can potentially be addressed with algorithm-based segmentation tools. In this study, we map the field of automatic MR brain lesion segmentation to understand the clinical applicability of prevalent methods and study designs, as well as challenges and limitations in the field.

DESIGN

Scoping review.

SETTING

Three databases (PubMed, IEEE Xplore and Scopus) were searched with tailored queries. Studies were included based on predefined criteria. Emerging themes during consecutive title, abstract, methods and whole-text screening were identified. The full-text analysis focused on materials, preprocessing, performance evaluation and comparison.

RESULTS

Out of 2990 unique articles identified through the search, 441 articles met the eligibility criteria, with an estimated growth rate of 10% per year. We present a general overview and trends in the field with regard to publication sources, segmentation principles used and types of lesions. Algorithms are predominantly evaluated by measuring the agreement of segmentation results with a trusted reference. Few articles describe measures of clinical validity.

CONCLUSIONS

The observed reporting practices leave room for improvement with a view to studying replication, method comparison and clinical applicability. To promote this improvement, we propose a list of recommendations for future studies in the field.

Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data - A systematic review

BACKGROUND

White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin.

METHOD

We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2.

RESULTS

The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their methods in public repositories.

CONCLUSIONS

We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

MR Image-Based Attenuation Correction of Brain PET Imaging: Review of Literature on Machine Learning Approaches for Segmentation

Recent emerging hybrid technology of positron emission tomography/magnetic resonance (PET/MR) imaging has generated a great need for an accurate MR image-based PET attenuation correction. MR image segmentation, as a robust and simple method for PET attenuation correction, has been clinically adopted in commercial PET/MR scanners. The general approach in this method is to segment the MR image into different tissue types, each assigned an attenuation constant as in an X-ray CT image. Machine learning techniques such as clustering, classification and deep networks are extensively used for brain MR image segmentation. However, only limited work has been reported on using deep learning in brain PET attenuation correction. In addition, there is a lack of clinical evaluation of machine learning methods in this application. The aim of this review is to study the use of machine learning methods for MR image segmentation and its application in attenuation correction for PET brain imaging. Furthermore, challenges and future opportunities in MR image-based PET attenuation correction are discussed.

Performance of five automated white matter hyperintensity segmentation methods in a multicenter dataset

White matter hyperintensities (WMHs) are a common manifestation of cerebral small vessel disease, that is increasingly studied with large, pooled multicenter datasets. This data pooling increases statistical power, but poses challenges for automated WMH segmentation. Although there is extensive literature on the evaluation of automated WMH segmentation methods, such evaluations in a multicenter setting are lacking. We performed WMH segmentations in sixty patients scanned on six different magnetic resonance imaging (MRI) scanners (10 patients per scanner) using five freely available and fully-automated WMH segmentation methods (Cascade, kNN-TTP, Lesion-TOADS, LST-LGA and LST-LPA). Different MRI scanner vendors and field strengths were included. We compared these automated WMH segmentations with manual WMH segmentations as a reference. Performance of each method both within and across scanners was assessed using spatial and volumetric correspondence with the reference segmentations by Dice’s similarity coefficient (DSC) and intra-class correlation coefficient (ICC) respectively. We found the best performance, both within and across scanners, for kNN-TTP, followed by LST-LPA and LST-LGA, with worse performance for Lesion-TOADS and Cascade. Our findings can serve as a guide for choosing a method and also highlight the importance to further improve and evaluate consistency of methods in a multicenter setting.

[18F]-Flutemetamol Uptake in Cortex and White Matter: Comparison with Cerebrospinal Fluid Biomarkers and [18F]-Fludeoxyglucose

Flutemetamol (¹⁸F-Flut) is an [¹⁸F]-labelled amyloid PET tracer with increasing availability. The main objectives of this study were to investigate 1) cerebrospinal fluid (CSF) Aβ 1-42 (Aβ₄₂) concentrations associated with regional ¹⁸F-Flut uptake, 2) associations between cortical ¹⁸F-Flut and [¹⁸F]-fludeoxyglucose (¹⁸F-FDG)-PET, and 3) the potential use of ¹⁸F-Flut in WM pathology. Cognitively impaired, nondemented subjects were recruited (n = 44). CSF was drawn, and ¹⁸F-Flut-PET, ¹⁸F-FDG-PET, and MRI performed. Our main findings were: 1) Different Alzheimer’s disease predilection areas showed increased ¹⁸F-Flut retention at different CSF Aβ₄₂ concentrations (posterior regions were involved at higher concentrations). 2) There were strong negative correlations between regional cortical ¹⁸F-Flut and ¹⁸F-FDG uptake. 3) Increased ¹⁸F-Flut uptake were observed in multiple subcortical regions in amyloid positive subjects, including investigated reference regions. However, WM hyperintensity ¹⁸F-Flut standardized uptake value ratios (SUVr) were not significantly different, thus we cannot definitely conclude that the higher uptake in ¹⁸F-Flut(+) is due to amyloid deposition. In conclusion, our findings support clinical use of CSF Aβ₄₂, putatively relate decreasing CSF Aβ₄₂ concentrations to a sequence of regional amyloid deposition, and associate amyloid pathology to cortical hypometabolism. However, we cannot conclude that ¹⁸F-Flut-PET is a suitable marker for WM pathology due to high aberrant WM uptake.

Innovation in the imaging perianal fistula: a step towards personalised medicine

BACKGROUND

Perianal fistula is a topic both hard to understand and to teach. The key to understanding the treatment options and the likely success is deciphering the exact morphology of the tract(s) and the amount of sphincter involved. Our aim was to explore alternative platforms better to understand complex perianal fistulas through three-dimensional (3D) imaging and reconstruction.

METHODS

Digital imaging and communications in medicine images of spectral attenuated inversion recovery magnetic resonance imaging (MRI) sequences were imported onto validated open-source segmentation software. A specialist consultant gastrointestinal radiologist performed segmentation of the fistula, internal and external sphincter. Segmented files were exported as stereolithography files. Cura (Ultimaker Cura 3.0.4) was used to prepare the files for printing on an Ultimaker 3 Extended 3D printer. Animations were created in collaboration with Touch Surgery™.

RESULTS

Three examples of 3D printed models demonstrating complex perianal fistula were created. The anatomical components are displayed in different colours: red: fistula tract; green: external anal sphincter and levator plate; blue: internal anal sphincter and rectum. One of the models was created to be split in half, to display the internal opening and allow complexity in the intersphincteric space to better evaluated. An animation of MRI fistulography of a trans-sphincteric fistula tract with a cephalad extension in the intersphincteric space was also created.

CONCLUSION

MRI is the reference standard for assessment of perianal fistula, defining anatomy and guiding surgery. However, communication of findings between radiologist and surgeon remains challenging. Feasibility of 3D reconstructions of complex perianal fistula is realized, with the potential to improve surgical planning, communication with patients, and augment training.

Patch-Based Label Fusion with Structured Discriminant Embedding for Hippocampus Segmentation

Automatic and accurate segmentation of hippocampal structures in medical images is of great importance in neuroscience studies. In multi-atlas based segmentation methods, to alleviate the misalignment when registering atlases to the target image, patch-based methods have been widely studied to improve the performance of label fusion. However, weights assigned to the fused labels are usually computed based on predefined features (e.g. image intensities), thus being not necessarily optimal. Due to the lack of discriminating features, the original feature space defined by image intensities may limit the description accuracy. To solve this problem, we propose a patch-based label fusion with structured discriminant embedding method to automatically segment the hippocampal structure from the target image in a voxel-wise manner. Specifically, multi-scale intensity features and texture features are first extracted from the image patch for feature representation. Margin fisher analysis (MFA) is then applied to the neighboring samples in the atlases for the target voxel, in order to learn a subspace in which the distance between intra-class samples is minimized and the distance between inter-class samples is simultaneously maximized. Finally, the k-nearest neighbor (kNN) classifier is employed in the learned subspace to determine the final label for the target voxel. In the experiments, we evaluate our proposed method by conducting hippocampus segmentation using the ADNI dataset. Both the qualitative and quantitative results show that our method outperforms the conventional multi-atlas based segmentation methods.