Track-to-Learn: A general framework for tractography with deep reinforcement learning

Rate of abnormalities in quantitative MR neuroimaging of persons with chronic traumatic brain injury

BACKGROUND

Mild traumatic brain injury (mTBI) can result in lasting brain damage that is often too subtle to detect by qualitative visual inspection on conventional MR imaging. Although a number of FDA-cleared MR neuroimaging tools have demonstrated changes associated with mTBI, they are still under-utilized in clinical practice.

METHODS

We investigated a group of 65 individuals with predominantly mTBI (60 mTBI, 48 due to motor-vehicle collision, mean age 47 ± 13 years, 27 men and 38 women) with MR neuroimaging performed in a median of 37 months post-injury. We evaluated abnormalities in brain volumetry including analysis of left-right asymmetry by quantitative volumetric analysis, cerebral perfusion by pseudo-continuous arterial spin labeling (PCASL), white matter microstructure by diffusion tensor imaging (DTI), and neurometabolites via magnetic resonance spectroscopy (MRS).

RESULTS

All participants demonstrated atrophy in at least one lobar structure or increased lateral ventricular volume. The globus pallidi and cerebellar grey matter were most likely to demonstrate atrophy and asymmetry. Perfusion imaging revealed significant reductions of cerebral blood flow in both occipital and right frontoparietal regions. Diffusion abnormalities were relatively less common though a subset analysis of participants with higher resolution DTI demonstrated additional abnormalities. All participants showed abnormal levels on at least one brain metabolite, most commonly in choline and N-acetylaspartate.

CONCLUSION

We demonstrate the presence of coup-contrecoup perfusion injury patterns, widespread atrophy, regional brain volume asymmetry, and metabolic aberrations as sensitive markers of chronic mTBI sequelae. Our findings expand the historic focus on quantitative imaging of mTBI with DTI by highlighting the complementary importance of volumetry, arterial spin labeling perfusion and magnetic resonance spectroscopy neurometabolite analyses in the evaluation of chronic mTBI.

What matters in reinforcement learning for tractography

Recently, deep reinforcement learning (RL) has been proposed to learn the tractography procedure and train agents to reconstruct the structure of the white matter without manually curated reference streamlines. While the performances reported were competitive, the proposed framework is complex, and little is still known about the role and impact of its multiple parts. In this work, we thoroughly explore the different components of the proposed framework, such as the choice of the RL algorithm, seeding strategy, the input signal and reward function, and shed light on their impact. Approximately 7,400 models were trained for this work, totalling nearly 41,000 h of GPU time. Our goal is to guide researchers eager to explore the possibilities of deep RL for tractography by exposing what works and what does not work with the category of approach. As such, we ultimately propose a series of recommendations concerning the choice of RL algorithm, the input to the agents, the reward function and more to help future work using reinforcement learning for tractography. We also release the open source codebase, trained models, and datasets for users and researchers wanting to explore reinforcement learning for tractography.

Special Issue "Machine Learning Methods for Biomedical Data Analysis"

Machine learning is an effective method for developing automatic algorithms for analysing sophisticated biomedical data [...].

Computational approaches for the reconstruction of optic nerve fibers along the visual pathway from medical images: a comprehensive review

Optic never fibers in the visual pathway play significant roles in vision formation. Damages of optic nerve fibers are biomarkers for the diagnosis of various ophthalmological and neurological diseases; also, there is a need to prevent the optic nerve fibers from getting damaged in neurosurgery and radiation therapy. Reconstruction of optic nerve fibers from medical images can facilitate all these clinical applications. Although many computational methods are developed for the reconstruction of optic nerve fibers, a comprehensive review of these methods is still lacking. This paper described both the two strategies for optic nerve fiber reconstruction applied in existing studies, i.e., image segmentation and fiber tracking. In comparison to image segmentation, fiber tracking can delineate more detailed structures of optic nerve fibers. For each strategy, both conventional and AI-based approaches were introduced, and the latter usually demonstrates better performance than the former. From the review, we concluded that AI-based methods are the trend for optic nerve fiber reconstruction and some new techniques like generative AI can help address the current challenges in optic nerve fiber reconstruction.

Generative Sampling in Bundle Tractography using Autoencoders (GESTA)

Current tractography methods use the local orientation information to propagate streamlines from seed locations. Many such seeds provide streamlines that stop prematurely or fail to map the true white matter pathways because some bundles are "harder-to-track" than others. This results in tractography reconstructions with poor white and gray matter spatial coverage. In this work, we propose a generative, autoencoder-based method, named GESTA (Generative Sampling in Bundle Tractography using Autoencoders), that produces streamlines achieving better spatial coverage. Compared to other deep learning methods, our autoencoder-based framework uses a single model to generate streamlines in a bundle-wise fashion, and does not require to propagate local orientations. GESTA produces new and complete streamlines for any given white matter bundle, including hard-to-track bundles. Applied on top of a given tractogram, GESTA is shown to be effective in improving the white matter volume coverage in poorly populated bundles, both on synthetic and human brain in vivo data. Our streamline evaluation framework ensures that the streamlines produced by GESTA are anatomically plausible and fit well to the local diffusion signal. The streamline evaluation criteria assess anatomy (white matter coverage), local orientation alignment (direction), and geometry features of streamlines, and optionally, gray matter connectivity. The GESTA framework offers considerable gains in bundle overlap using a reduced set of seeding streamlines with a 1.5x improvement for the "Fiber Cup", and 6x for the ISMRM 2015 Tractography Challenge datasets. Similarly, it provides a 4x white matter volume increase on the BIL&GIN callosal homotopic dataset, and successfully populates bundles on the multi-subject, multi-site, whole-brain in vivo TractoInferno dataset. GESTA is thus a novel deep generative bundle tractography method that can be used to improve the tractography reconstruction of the white matter.

Validate your white matter tractography algorithms with a reappraised ISMRM 2015 Tractography Challenge scoring system

Since 2015, research groups have sought to produce the ne plus ultra of tractography algorithms using the ISMRM 2015 Tractography Challenge as evaluation. In particular, since 2017, machine learning has made its entrance into the tractography world. The ISMRM 2015 Tractography Challenge is the most used phantom during tractography validation, although it contains limitations. Here, we offer a new scoring system for this phantom, where segmentation of the bundles is now based on manually defined regions of interest rather than on bundle recognition. Bundles are now more reliably segmented, offering more representative metrics for future users. New code is available online. Scores of the initial 96 submissions to the challenge are updated. Overall, conclusions from the 2015 challenge are confirmed with the new scoring, but individual tractogram scores have changed, and the data is much improved at the bundle- and streamline-level. This work also led to the production of a ground truth tractogram with less broken or looping streamlines and of an example of processed data, all available on the Tractometer website. This enhanced scoring system and new data should continue helping researchers develop and evaluate the next generation of tractography techniques.

Deep reinforcement learning and its applications in medical imaging and radiation therapy: a survey

Reinforcement learning takes sequential decision-making approaches by learning the policy through trial and error based on interaction with the environment. Combining deep learning and reinforcement learning can empower the agent to learn the interactions and the distribution of rewards from state-action pairs to achieve effective and efficient solutions in more complex and dynamic environments. Deep reinforcement learning (DRL) has demonstrated astonishing performance in surpassing the human-level performance in the game domain and many other simulated environments. This paper introduces the basics of reinforcement learning and reviews various categories of DRL algorithms and DRL models developed for medical image analysis and radiation treatment planning optimization. We will also discuss the current challenges of DRL and approaches proposed to make DRL more generalizable and robust in a real-world environment. DRL algorithms, by fostering the designs of the reward function, agents interactions and environment models, can resolve the challenges from scarce and heterogeneous annotated medical image data, which has been a major obstacle to implementing deep learning models in the clinic. DRL is an active research area with enormous potential to improve deep learning applications in medical imaging and radiation therapy planning.