A review of the automated detection of change in serial imaging studies of the brain

Evaluation of the Statistical Detection of Change Algorithm for Screening Patients with MS with New Lesion Activity on Longitudinal Brain MRI

BACKGROUND AND PURPOSE

Identification of new MS lesions on longitudinal MR imaging by human readers is time-consuming and prone to error. Our objective was to evaluate the improvement in the performance of subject-level detection by readers when assisted by the automated statistical detection of change algorithm.

MATERIALS AND METHODS

A total of 200 patients with MS with a mean interscan interval of 13.2 (SD, 2.4) months were included. Statistical detection of change was applied to the baseline and follow-up FLAIR images to detect potential new lesions for confirmation by readers (Reader + statistical detection of change method). This method was compared with readers operating in the clinical workflow (Reader method) for a subject-level detection of new lesions.

RESULTS

Reader + statistical detection of change found 30 subjects (15.0%) with at least 1 new lesion, while Reader detected 16 subjects (8.0%). As a subject-level screening tool, statistical detection of change achieved a perfect sensitivity of 1.00 (95% CI, 0.88-1.00) and a moderate specificity of 0.67 (95% CI, 0.59-0.74). The agreement on a subject level was 0.91 (95% CI, 0.87-0.95) between Reader + statistical detection of change and Reader, and 0.72 (95% CI, 0.66-0.78) between Reader + statistical detection of change and statistical detection of change.

CONCLUSIONS

The statistical detection of change algorithm can serve as a time-saving screening tool to assist human readers in verifying 3D FLAIR images of patients with MS with suspected new lesions. Our promising results warrant further evaluation of statistical detection of change in prospective multireader clinical studies.

Direct Evaluation of Treatment Response in Brain Metastatic Disease with Deep Neuroevolution

Cancer centers have an urgent and unmet clinical and research need for AI that can guide patient management. A core component of advancing cancer treatment research is assessing response to therapy. Doing so by hand, for example, as per RECIST or RANO criteria, is tedious and time-consuming, and can miss important tumor response information. Most notably, the prevalent response criteria often exclude lesions, the non-target lesions, altogether. We wish to assess change in a holistic fashion that includes all lesions, obtaining simple, informative, and automated assessments of tumor progression or regression. Because genetic sub-types of cancer can be fairly specific and patient enrollment in therapy trials is often limited in number and accrual rate, we wish to make response assessments with small training sets. Deep neuroevolution (DNE) is a novel radiology artificial intelligence (AI) optimization approach that performs well on small training sets. Here, we use a DNE parameter search to optimize a convolutional neural network (CNN) that predicts progression versus regression of metastatic brain disease. We analyzed 50 pairs of MRI contrast-enhanced images as our training set. Half of these pairs, separated in time, qualified as disease progression, while the other 25 image pairs constituted regression. We trained the parameters of a CNN via "mutations" that consisted of random CNN weight adjustments and evaluated mutation "fitness" as summed training set accuracy. We then incorporated the best mutations into the next generation's CNN, repeating this process for approximately 50,000 generations. We applied the CNNs to our training set, as well as a separate testing set with the same class balance of 25 progression and 25 regression cases. DNE achieved monotonic convergence to 100% training set accuracy. DNE also converged monotonically to 100% testing set accuracy. We have thus shown that DNE can accurately classify brain metastatic disease progression versus regression. Future work will extend the input from 2D image slices to full 3D volumes, and include the category of "no change." We believe that an approach such as ours can ultimately provide a useful and informative complement to RANO/RECIST assessment and volumetric AI analysis.

Assessment of automatic decision-support systems for detecting active T2 lesions in multiple sclerosis patients

BACKGROUND

Active (new/enlarging) T2 lesion counts are routinely used in the clinical management of multiple sclerosis. Thus, automated tools able to accurately identify active T2 lesions would be of high interest to neuroradiologists for assisting in their clinical activity.

OBJECTIVE

To compare the accuracy in detecting active T2 lesions and of radiologically active patients based on different visual and automated methods.

METHODS

One hundred multiple sclerosis patients underwent two magnetic resonance imaging examinations within 12 months. Four approaches were assessed for detecting active T2 lesions: (1) conventional neuroradiological reports; (2) prospective visual analyses performed by an expert; (3) automated unsupervised tool; and (4) supervised convolutional neural network. As a gold standard, a reference outcome was created by the consensus of two observers.

RESULTS

The automated methods detected a higher number of active T2 lesions, and a higher number of active patients, but a higher number of false-positive active patients than visual methods. The convolutional neural network model was more sensitive in detecting active T2 lesions and active patients than the other automated method.

CONCLUSION

Automated convolutional neural network models show potential as an aid to neuroradiological assessment in clinical practice, although visual supervision of the outcomes is still required.

The TRUTH confirmed: validation of an intraindividual comparison of gadobutrol and gadoteridol for imaging of glioblastoma using quantitative enhancement analysis

BACKGROUND

Previous intraindividual comparative studies evaluating gadobutrol and gadoteridol for contrast-enhanced magnetic resonance imaging (MRI) of brain tumours have relied on subjective image assessment, potentially leading to misleading conclusions. We used artificial intelligence algorithms to objectively compare the enhancement achieved with these contrast agents in glioblastoma patients.

METHODS

Twenty-seven patients from a prior study who received identical doses of 0.1 mmol/kg gadobutrol and gadoteridol (with appropriate washout in between) were evaluated. Quantitative enhancement (QE) maps of the normalised enhancement of voxels, derived from computations based on the comparison of contrast-enhanced T1-weighted images relative to the harmonised intensity on unenhanced T1-weighted images, were compared. Bland-Altman analysis, linear regression analysis and Pearson correlation coefficient (r) determination were performed to compare net QE and per-region of interest (per-ROI) average QE (net QE divided by the number of voxels).

RESULTS

No significant differences were observed for comparisons performed on net QE (mean difference -24.37 ± 620.8, p = 0.840, r = 0.989) or per-ROI average QE (0.0043 ± 0.0218, p = 0.313, r = 0.958). Bland-Altman analysis revealed better per-ROI average QE for gadoteridol-enhanced MRI in 19/27 (70.4%) patients although the mean difference (0.0043) was close to zero indicating high concordance and the absence of fixed bias.

CONCLUSIONS

The enhancement of glioblastoma achieved with gadoteridol and gadobutrol at 0.1 mmol/kg bodyweight is similar indicating that these agents have similar contrast efficacy and can be used interchangeably, confirming the results of a prior double-blind, randomised, intraindividual, crossover study.

Detection of Volume-Changing Metastatic Brain Tumors on Longitudinal MRI Using a Semiautomated Algorithm Based on the Jacobian Operator Field

BACKGROUND AND PURPOSE

Accurate follow-up of metastatic brain tumors has important implications for patient prognosis and management. The aim of this study was to develop and evaluate the accuracy of a semiautomated algorithm in detecting growing or shrinking metastatic brain tumors on longitudinal brain MRIs.

MATERIALS AND METHODS

We used 50 pairs of successive MR imaging datasets, 30 on 1.5T and 20 on 3T, containing contrast-enhanced 3D T1-weighted sequences. These yielded 150 growing or shrinking metastatic brain tumors. To detect them, we completed 2 major steps: 1) spatial normalization and calculation of the Jacobian operator field to quantify changes between scans, and 2) metastatic brain tumor candidate segmentation and detection of volume-changing metastatic brain tumors with the Jacobian operator field. Receiver operating characteristic analysis was used to assess the detection accuracy of the algorithm, and it was verified with jackknife resampling. The reference standard was based on detections by a neuroradiologist.

RESULTS

The areas under the receiver operating characteristic curves were 0.925 for 1.5T and 0.965 for 3T. Furthermore, at its optimal performance, the algorithm achieved a sensitivity of 85.1% and 92.1% and specificity of 86.7% and 91.3% for 1.5T and 3T, respectively. Vessels were responsible for most false-positives. Newly developed or resolved metastatic brain tumors were a major source of false-negatives.

CONCLUSIONS

The proposed algorithm could detect volume-changing metastatic brain tumors on longitudinal brain MRIs with statistically high accuracy, demonstrating its potential as a computer-aided change-detection tool for complementing the performance of radiologists, decreasing inter- and intraobserver variability, and improving efficacy.

Detection of time-varying structures by large deformation diffeomorphic metric mapping to aid reading of high-resolution CT images of the lung

Objectives

To evaluate the accuracy of advanced non-linear registration of serial lung Computed Tomography (CT) images using Large Deformation Diffeomorphic Metric Mapping (LDDMM).

Methods

Fifteen cases of lung cancer with serial lung CT images (interval: 62.2±26.9 days) were used. After affine transformation, three dimensional, non-linear volume registration was conducted using LDDMM with or without cascading elasticity control. Registration accuracy was evaluated by measuring the displacement of landmarks placed on vessel bifurcations for each lung segment. Subtraction images and Jacobian color maps, calculated from the transformation matrix derived from image warping, were generated, which were used to evaluate time-course changes of the tumors.

Results

The average displacement of landmarks was 0.02±0.16 mm and 0.12±0.60 mm for proximal and distal landmarks after LDDMM transformation with cascading elasticity control, which was significantly smaller than 3.11±2.47 mm and 3.99±3.05 mm, respectively, after affine transformation. Emerged or vanished nodules were visualized on subtraction images, and enlarging or shrinking nodules were displayed on Jacobian maps enabled by highly accurate registration of the nodules using LDDMM. However, some residual misalignments were observed, even with non-linear transformation when substantial changes existed between the image pairs.

Conclusions

LDDMM provides accurate registration of serial lung CT images, and temporal subtraction images with Jacobian maps help radiologists to find changes in pulmonary nodules.

Classification of time series of multispectral images with limited training data

Image classification usually requires the availability of reliable reference data collected for the considered image to train supervised classifiers. Unfortunately when time series of images are considered, this is seldom possible because of the costs associated with reference data collection. In most of the applications it is realistic to have reference data available for one or few images of a time series acquired on the area of interest. In this paper, we present a novel system for automatically classifying image time series that takes advantage of image(s) with an associated reference information (i.e., the source domain) to classify image(s) for which reference information is not available (i.e., the target domain). The proposed system exploits the already available knowledge on the source domain and, when possible, integrates it with a minimum amount of new labeled data for the target domain. In addition, it is able to handle possible significant differences between statistical distributions of the source and target domains. Here, the method is presented in the context of classification of remote sensing image time series, where ground reference data collection is a highly critical and demanding task. Experimental results show the effectiveness of the proposed technique. The method can work on multimodal (e.g., multispectral) images.

Change detection and classification in brain MR images using change vector analysis

The automatic detection of longitudinal changes in brain images is valuable in the assessment of disease evolution and treatment efficacy. Most existing change detection methods that are currently used in clinical research to monitor patients suffering from neurodegenerative diseases--such as Alzheimer's--focus on large-scale brain deformations. However, such patients often have other brain impairments, such as infarcts, white matter lesions and hemorrhages, which are typically overlooked by the deformation-based methods. Other unsupervised change detection algorithms have been proposed to detect tissue intensity changes. The outcome of these methods is typically a binary change map, which identifies changed brain regions. However, understanding what types of changes these regions underwent is likely to provide equally important information about lesion evolution. In this paper, we present an unsupervised 3D change detection method based on Change Vector Analysis. We compute and automatically threshold the Generalized Likelihood Ratio map to obtain a binary change map. Subsequently, we perform histogram-based clustering to classify the change vectors. We obtain a Kappa Index of 0.82 using various types of simulated lesions. The classification error is 2%. Finally, we are able to detect and discriminate both small changes and ventricle expansions in datasets from Mild Cognitive Impairment patients.

Fuzzy logic: A "simple" solution for complexities in neurosciences?

Background:

Fuzzy logic is a multi-valued logic which is similar to human thinking and interpretation. It has the potential of combining human heuristics into computer-assisted decision making, which is applicable to individual patients as it takes into account all the factors and complexities of individuals. Fuzzy logic has been applied in all disciplines of medicine in some form and recently its applicability in neurosciences has also gained momentum.

Methods:

This review focuses on the use of this concept in various branches of neurosciences including basic neuroscience, neurology, neurosurgery, psychiatry and psychology.

Results:

The applicability of fuzzy logic is not limited to research related to neuroanatomy, imaging nerve fibers and understanding neurophysiology, but it is also a sensitive and specific tool for interpretation of EEGs, EMGs and MRIs and an effective controller device in intensive care units. It has been used for risk stratification of stroke, diagnosis of different psychiatric illnesses and even planning neurosurgical procedures.

Conclusions:

In the future, fuzzy logic has the potential of becoming the basis of all clinical decision making and our understanding of neurosciences.

Part 1. Automated change detection and characterization in serial MR studies of brain-tumor patients

The goal of this study was to create an algorithm which would quantitatively compare serial magnetic resonance imaging studies of brain-tumor patients. A novel algorithm and a standard classify-subtract algorithm were constructed. The ability of both algorithms to detect and characterize changes was compared using a series of digital phantoms. The novel algorithm achieved a mean sensitivity of 0.87 (compared with 0.59 for classify-subtract) and a mean specificity of 0.98 (compared with 0.92 for classify-subtract) with regard to identification of voxels as changing or unchanging and classification of voxels into types of change. The novel algorithm achieved perfect specificity in seven of the nine experiments. The novel algorithm was additionally applied to a short series of clinical cases, where it was shown to identify visually subtle changes. Automated change detection and characterization could facilitate objective review and understanding of serial magnetic resonance imaging studies in brain-tumor patients.

Change detection & characterization: a new tool for imaging informatics and cancer research

Modern imaging systems are able to produce a rich and diverse array of information, regarding various facets of anatomy and function. The quantity of information produced by these systems is so bountiful, however, as to have the potential to become a hindrance to clinical assessment. In the context of serial image evaluation, computer-based change detection and characterization is one important mechanism to process the information produced by imaging systems, so as to reduce the quantity of data, direct the attention of the physician to regions of the data which are the most informative for their purposes, and present the data in the form in which it will be the most useful. Change detection and characterization algorithms may serve as a basis for the creation of an objective definition of progression, which will reduce inter and intra-observer variability, and facilitate earlier detection of disease and recurrence, which in turn may lead to improved outcomes. Decreased observer variability combined with increased acuity should make it easier to discover promising therapies. Quantitative measures of the response to these therapies should provide a means to compare the effectiveness of treatments under investigation. Change detection may be applicable to a broad range of cancers, in essentially all anatomical regions. The source of information upon which change detection comparisons may be based is likewise broad. Validation of algorithms for the longitudinal assessment of cancer patients is expected to be challenging, though not insurmountable, as the many facets of the problem mean that validation will likely need to be approached from a variety of vantage points. Change detection and characterization is quickly becoming a very active field of investigation, and it is expected that this burgeoning field will help to facilitate cancer care both in the clinic and research.

Change Detection & Characterization: A New Tool for Imaging Informatics and Cancer Research

Modern imaging systems are able to produce a rich and diverse array of information, regarding various facets of anatomy and function. The quantity of information produced by these systems is so bountiful, however, as to have the potential to become a hindrance to clinical assessment. In the context of serial image evaluation, computer-based change detection and characterization is one important mechanism to process the information produced by imaging systems, so as to reduce the quantity of data, direct the attention of the physician to regions of the data which are the most informative for their purposes, and present the data in the form in which it will be the most useful. Change detection and characterization algorithms may serve as a basis for the creation of an objective definition of progression, which will reduce inter and intra-observer variability, and facilitate earlier detection of disease and recurrence, which in turn may lead to improved outcomes. Decreased observer variability combined with increased acuity should make it easier to discover promising therapies. Quantitative measures of the response to these therapies should provide a means to compare the effectiveness of treatments under investigation. Change detection may be applicable to a broad range of cancers, in essentially all anatomical regions. The source of information upon which change detection comparisons may be based is likewise broad. Validation of algorithms for the longitudinal assessment of cancer patients is expected to be challenging, though not insurmountable, as the many facets of the problem mean that validation will likely need to be approached from a variety of vantage points. Change detection and characterization is quickly becoming a very active field of investigation, and it is expected that this burgeoning field will help to facilitate cancer care both in the clinic and research.