A Clinically-Compatible Workflow for Computer-Aided Assessment of Brain Disease Activity in Multiple Sclerosis Patients

Impact of automatic tools for detecting new lesions on therapeutic strategies offered to patients with MS by neurologists

BACKGROUND

Automatic tools for detecting new lesions in patients with MS between two MRI scans are now available to clinicians. They have been assessed from the radiologist's point of view, but their impact on the therapeutic strategies that neurologists offer their patients has not yet been documented.

OBJECTIVES

To compare neurologist's decisions according to whether a lesion detection support system had been used and describe variability between neurologists on decision-making for the same clinical cases.

METHODS

We submitted 28 clinical cases associated with pairs of MRI images and radiological reports (produced by the same radiologist without vs. with the help of a system to detect new lesions) to 10 neurologists who regularly follow patients with MS. They examined each clinical case twice (without vs. with support system) in two sessions several weeks apart, and their patient management decisions were recorded.

RESULTS

There was considerable variability between neurologists on decision-making (both with and without support system). When the support system had been used, neurologists more often made changes to patient management (75 % vs. 68 % of cases, p = 0.01) and spent significantly less time analyzing the clinical cases (249 s vs. 216 s, p == 3.10-4).

CONCLUSION

The use of a lesion detection support system has an impact not only on radiologists' reports, but also on neurologists' subsequent decision-making. This observation constitutes another strong argument for promoting the wider use of such systems in clinical routine. However, despite their use, there is still considerable variability in decision-making across neurologists, which should encourage us to refine the guidelines.

How far MS lesion detection and segmentation are integrated into the clinical workflow? A systematic review

INTRODUCTION

Over the past few years, the deep learning community has developed and validated a plethora of tools for lesion detection and segmentation in Multiple Sclerosis (MS). However, there is an important gap between validating models technically and clinically. To this end, a six-step framework necessary for the development, validation, and integration of quantitative tools in the clinic was recently proposed under the name of the Quantitative Neuroradiology Initiative (QNI).

AIMS

Investigate to what extent automatic tools in MS fulfill the QNI framework necessary to integrate automated detection and segmentation into the clinical neuroradiology workflow.

METHODS

Adopting the systematic Cochrane literature review methodology, we screened and summarised published scientific articles that perform automatic MS lesions detection and segmentation. We categorised the retrieved studies based on their degree of fulfillment of QNI's six-steps, which include a tool's technical assessment, clinical validation, and integration.

RESULTS

We found 156 studies; 146/156 (94%) fullfilled the first QNI step, 155/156 (99%) the second, 8/156 (5%) the third, 3/156 (2%) the fourth, 5/156 (3%) the fifth and only one the sixth.

CONCLUSIONS

To date, little has been done to evaluate the clinical performance and the integration in the clinical workflow of available methods for MS lesion detection/segmentation. In addition, the socio-economic effects and the impact on patients' management of such tools remain almost unexplored.

Multiple sclerosis clinical decision support system based on projection to reference datasets

OBJECTIVE

Multiple sclerosis (MS) is a multifactorial disease with increasingly complicated management. Our objective is to use on-demand computational power to address the challenges of dynamically managing MS.

METHODS

A phase 3 clinical trial data (NCT00906399) were used to contextualize the medication efficacy of peg-interferon beta-1a vs placebo on patients with relapsing-remitting MS (RRMS). Using a set of reference patients (PORs), selected based on adequate features similar to those of an individual patient, we visualize disease activity by measuring the percentage of relapses, accumulation of new T2 lesions on MRI, and worsening EDSS during the clinical trial.

RESULTS

We developed MS Vista, a functional prototype of clinical decision support system (CDSS), with a user-centered design and distributed infrastructure. MS Vista shows the medication efficacy of peginterferon beta-1a versus placebo for each individual patient with RRMS. In addition, MS Vista initiated the integration of a longitudinal magnetic resonance imaging (MRI) viewer and interactive dual physician-patient data display to facilitate communication.

INTERPRETATION

The pioneer use of PORs for each individual patient enables personalized analytics sustaining the dialog between neurologists, patients and caregivers with quantified evidence.

Clinical implementation of artificial intelligence in neuroradiology with development of a novel workflow-efficient picture archiving and communication system-based automated brain tumor segmentation and radiomic feature extraction

Purpose

Personalized interpretation of medical images is critical for optimum patient care, but current tools available to physicians to perform quantitative analysis of patient’s medical images in real time are significantly limited. In this work, we describe a novel platform within PACS for volumetric analysis of images and thus development of large expert annotated datasets in parallel with radiologist performing the reading that are critically needed for development of clinically meaningful AI algorithms. Specifically, we implemented a deep learning-based algorithm for automated brain tumor segmentation and radiomics extraction, and embedded it into PACS to accelerate a supervised, end-to- end workflow for image annotation and radiomic feature extraction.

Materials and methods

An algorithm was trained to segment whole primary brain tumors on FLAIR images from multi-institutional glioma BraTS 2021 dataset. Algorithm was validated using internal dataset from Yale New Haven Health (YHHH) and compared (by Dice similarity coefficient [DSC]) to radiologist manual segmentation. A UNETR deep-learning was embedded into Visage 7 (Visage Imaging, Inc., San Diego, CA, United States) diagnostic workstation. The automatically segmented brain tumor was pliable for manual modification. PyRadiomics (Harvard Medical School, Boston, MA) was natively embedded into Visage 7 for feature extraction from the brain tumor segmentations.

Results

UNETR brain tumor segmentation took on average 4 s and the median DSC was 86%, which is similar to published literature but lower than the RSNA ASNR MICCAI BRATS challenge 2021. Finally, extraction of 106 radiomic features within PACS took on average 5.8 ± 0.01 s. The extracted radiomic features did not vary over time of extraction or whether they were extracted within PACS or outside of PACS. The ability to perform segmentation and feature extraction before radiologist opens the study was made available in the workflow. Opening the study in PACS, allows the radiologists to verify the segmentation and thus annotate the study.

Conclusion

Integration of image processing algorithms for tumor auto-segmentation and feature extraction into PACS allows curation of large datasets of annotated medical images and can accelerate translation of research into development of personalized medicine applications in the clinic. The ability to use familiar clinical tools to revise the AI segmentations and natively embedding the segmentation and radiomic feature extraction tools on the diagnostic workstation accelerates the process to generate ground-truth data.

Image registration and appearance adaptation in non-correspondent image regions for new MS lesions detection

Manual detection of newly formed lesions in multiple sclerosis is an important but tedious and difficult task. Several approaches for automating the detection of new lesions have recently been proposed, but they tend to either overestimate the actual amount of new lesions or to miss many lesions. In this paper, an image registration convolutional neural network (CNN) that adapts the baseline image to the follow-up image by spatial deformations and simulation of new lesions is proposed. Simultaneously, segmentations of new lesions are generated, which are shown to reliably estimate the real new lesion load and to separate stable and progressive patients. Several applications of the proposed network emerge: image registration, detection and segmentation of new lesions, and modeling of new MS lesions. The modeled lesions offer the possibility to investigate the intensity profile of new lesions.

New MS lesion segmentation with deep residual attention gate U-Net utilizing 2D slices of 3D MR images

Multiple sclerosis (MS) is an autoimmune disease that causes lesions in the central nervous system of humans due to demyelinating axons. Magnetic resonance imaging (MRI) is widely used for monitoring and measuring MS lesions. Automated methods for MS lesion segmentation have usually been performed on individual MRI scans. Recently, tracking lesion activity for quantifying and monitoring MS disease progression, especially detecting new lesions, has become an important biomarker. In this study, a unique pipeline with a deep neural network that combines U-Net, attention gate, and residual learning is proposed to perform better new MS lesion segmentation using baseline and follow-up 3D FLAIR MR images. The proposed network has a similar architecture to U-Net and is formed from residual units which facilitate the training of deep networks. Networks with fewer parameters are designed with better performance through the skip connections of U-Net and residual units, which facilitate information propagation without degradation. Attention gates also learn to focus on salient features of the target structures of various sizes and shapes. The MSSEG-2 dataset was used for training and testing the proposed pipeline, and the results were compared with those of other proposed pipelines of the challenge and experts who participated in the same challenge. According to the results over the testing set, the lesion-wise F1 and dice scores were obtained as a mean of 48 and 44.30%. For the no-lesion cases, the number of tested and volume of tested lesions were obtained as a mean of 0.148 and 1.488, respectively. The proposed pipeline outperformed 22 proposed pipelines and ranked 8th in the challenge.