Development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal cancer.

OBJECTIVES: This retrospective cohort study developed a prognostic model incorporating PET texture analysis in patients with oesophageal cancer (OC). Internal validation of the model was performed. METHODS: Consecutive OC patients (n = 403) were chronologically separated into development (n = 302, September 2010-September 2014, median age = 67.0, males = 227, adenocarcinomas = 237) and validation cohorts (n = 101, September 2014-July 2015, median age = 69.0, males = 78, adenocarcinomas = 79). Texture metrics were obtained using a machine-learning algorithm for automatic PET segmentation. A Cox regression model including age, radiological stage, treatment and 16 texture metrics was developed. Patients were stratified into quartiles according to a prognostic score derived from the model. A p-value < 0.05 was considered statistically significant. Primary outcome was overall survival (OS). RESULTS: Six variables were significantly and independently associated with OS: age [HR =1.02 (95% CI 1.01-1.04), p < 0.001], radiological stage [1.49 (1.20-1.84), p < 0.001], treatment [0.34 (0.24-0.47), p < 0.001], log(TLG) [5.74 (1.44-22.83), p = 0.013], log(Histogram Energy) [0.27 (0.10-0.74), p = 0.011] and Histogram Kurtosis [1.22 (1.04-1.44), p = 0.017]. The prognostic score demonstrated significant differences in OS between quartiles in both the development (X2 143.14, df 3, p < 0.001) and validation cohorts (X2 20.621, df 3, p < 0.001). CONCLUSIONS: This prognostic model can risk stratify patients and demonstrates the additional benefit of PET texture analysis in OC staging. KEY POINTS: • PET texture analysis adds prognostic value to oesophageal cancer staging. • Texture metrics are independently and significantly associated with overall survival. • A prognostic model including texture analysis can help risk stratify patients.

Biopathologic Characterization and Grade Assessment of Breast Cancer With 3-D Multiparametric Ultrasound Combining Shear Wave Elastography and Backscatter Tensor Imaging.

OBJECTIVE: Despite recent improvements in medical imaging, the final diagnosis and biopathologic characterization of breast cancers currently still requires biopsies. Ultrasound is commonly used for clinical examination of breast masses. B-Mode and shear wave elastography (SWE) are already widely used to detect suspicious masses and differentiate benign lesions from cancers. But additional ultrasound modalities such as backscatter tensor imaging (BTI) could provide relevant biomarkers related to tissue organization. Here we describe a 3-D multiparametric ultrasound approach applied to breast carcinomas in the aims of (i) validating the ability of BTI to reveal the underlying organization of collagen fibers and (ii) assessing the complementarity of SWE and BTI to reveal biopathologic features of diagnostic interest. METHODS: Three-dimensional SWE and BTI were performed ex vivo on 64 human breast carcinoma samples using a linear ultrasound probe moved by a set of motors. Here we describe a 3-D multiparametric representation of the breast masses and quantitative measurements combining B-mode, SWE and BTI. RESULTS: Our results reveal for the first time that BTI can capture the orientation of the collagen fibers around tumors. BTI was found to be a relevant marker for assessing cancer stages, revealing a more tangent tissue orientation for in situ carcinomas than for invasive cancers. In invasive cases, the combination of BTI and SWE parameters allowed for classification of invasive tumors with respect to their grade with an accuracy of 95.7%. CONCLUSION: Our results highlight the potential of 3-D multiparametric ultrasound imaging for biopathologic characterization of breast tumors.

Decoding behavior from global cerebrovascular activity using neural networks.

Functional Ultrasound (fUS) provides spatial and temporal frames of the vascular activity in the brain with high resolution and sensitivity in behaving animals. The large amount of resulting data is underused at present due to the lack of appropriate tools to visualize and interpret such signals. Here we show that neural networks can be trained to leverage the richness of information available in fUS datasets to reliably determine behavior, even from a single fUS 2D image after appropriate training. We illustrate the potential of this method with two examples: determining if a rat is moving or static and decoding the animal's sleep/wake state in a neutral environment. We further demonstrate that our method can be transferred to new recordings, possibly in other animals, without additional training, thereby paving the way for real-time decoding of brain activity based on fUS data. Finally, the learned weights of the network in the latent space were analyzed to extract the relative importance of input data to classify behavior, making this a powerful tool for neuroscientific research.

PerceptFlow: Real-Time Ultrafast Doppler Image Enhancement Using Deep Convolutional Neural Network and Perceptual Loss.

Ultrafast ultrasound is an emerging imaging modality derived from standard medical ultrasound. It allows for a high spatial resolution of 100 µm and a temporal resolution in the millisecond range with techniques such as ultrafast Doppler imaging. Ultrafast Doppler imaging has become a priceless tool for neuroscience, especially for visualizing functional vascular structures and navigating the brain in real time. Yet, the quality of a Doppler image strongly depends on experimental conditions and is easily subject to artifacts and deterioration, especially with transcranial imaging, which often comes at the cost of higher noise and lower sensitivity to small blood vessels. A common solution to better visualize brain vasculature is either accumulating more information, integrating the image over several seconds or using standard filter-based enhancement techniques, which often over-smooth the image, thus failing both to preserve sharp details and to improve our perception of the vasculature. In this study we propose combining the standard Doppler accumulation process with a real-time enhancement strategy, based on deep-learning techniques, using perceptual loss (PerceptFlow). With our perceptual approach, we bypass the need for long integration times to enhance Doppler images. We applied and evaluated our proposed method on transcranial Doppler images of mouse brains, outperforming state-of-the-art filters. We found that, in comparison to standard filters such as the Gaussian filter (GF) and block-matching and 3-D filtering (BM3D), PerceptFlow was capable of reducing background noise with a significant increase in contrast and contrast-to-noise ratio, as well as better preserving details without compromising spatial resolution.

Proof of Concept of 3-D Backscatter Tensor Imaging Tomography for Non-invasive Assessment of Human Breast Cancer Collagen Organization.

Tumor growth, similarly to several other pathologies, tends to change the structural orientation of soft tissue fibers, which can become relevant markers for diagnosis. Current diagnosis protocols may require a biopsy for histological analysis, which is an invasive, painful and stressful procedure with a minimum turnaround time of 2 d. Otherwise, diagnosis may involve the use of complex methods with limited availability such as diffusion tensor imaging (magnetic resonance diffusion tensor imaging), which is not widely used in medical practice. Conversely, advanced methodologies in ultrasound imaging such as backscatter tensor imaging (BTI) might become a routine procedure in clinical practice at a limited cost. This method evaluates the local organization of soft tissues based on the spatial coherence of their backscattered ultrasonic echoes. Previous work has proven that BTI applied with matrix probes enables measurement of the orientation of soft tissue fibers, especially in the myocardium. The aims of the study described here were (i) to present for the first time a methodology for performing BTI in a volume on ex vivo human breast tumors using a linear probe and (ii) to display a first proof of concept of the link between BTI measurements and the orientation of collagen fibers.

Proposed Requirements for Cardiovascular Imaging-Related Machine Learning Evaluation (PRIME): A Checklist: Reviewed by the American College of Cardiology Healthcare Innovation Council.

Machine learning (ML) has been increasingly used within cardiology, particularly in the domain of cardiovascular imaging. Due to the inherent complexity and flexibility of ML algorithms, inconsistencies in the model performance and interpretation may occur. Several review articles have been recently published that introduce the fundamental principles and clinical application of ML for cardiologists. This paper builds on these introductory principles and outlines a more comprehensive list of crucial responsibilities that need to be completed when developing ML models. This paper aims to serve as a scientific foundation to aid investigators, data scientists, authors, editors, and reviewers involved in machine learning research with the intent of uniform reporting of ML investigations. An independent multidisciplinary panel of ML experts, clinicians, and statisticians worked together to review the theoretical rationale underlying 7 sets of requirements that may reduce algorithmic errors and biases. Finally, the paper summarizes a list of reporting items as an itemized checklist that highlights steps for ensuring correct application of ML models and the consistent reporting of model specifications and results. It is expected that the rapid pace of research and development and the increased availability of real-world evidence may require periodic updates to the checklist.

Mapping Biological Current Densities With Ultrafast Acoustoelectric Imaging: Application to the Beating Rat Heart.

Ultrafast acoustoelectric imaging (UAI) is a novel method for the mapping of biological current densities, which may improve the diagnosis and monitoring of cardiac activation diseases such as arrhythmias. This paper evaluates the feasibility of performing UAI in beating rat hearts. A previously described system based on a 256-channel ultrasound research platform fitted with a 5-MHz linear array was used for simultaneous UAI, ultrafast B-mode, and electrocardiogram (ECG) recordings. In this paper, rat hearts (n = 4) were retroperfused within a Langendorff isolated heart system. A pair of Ag/Cl electrodes were positioned on the epicardium to simultaneously record ECG and UAI signals for imaging frame rates of up to 1000 Hz and a mechanical index of 1.3. To account for the potential effect of motion on the UAI maps, acquisitions for n = 3 hearts were performed with and without suppression of the mechanical contraction using 2,3-butanedione monoxime. Current densities were detected for all four rats in the region of the atrio-ventricular node, with an average contrast-to-noise ratios of 12. The UAI signals' frequency matched the sinus rhythm, even without mechanical contraction, suggesting that the signals measured correspond to physiological electrical activation. UAI signals appeared at the apex and within the ventricular walls with a delay estimated at 29 ms. Finally, the signals from different electrode positions along the myocardium wall showed the possibility of mapping the electrical activation throughout the heart. These results show the potential of UAI for cardiac activation mapping in vivo and in real time.

Spatiotemporal matrix image formation for programmable ultrasound scanners.

As programmable ultrasound scanners become more common in research laboratories, it is increasingly important to develop robust software-based image formation algorithms that can be obtained in a straightforward fashion for different types of probes and sequences with a small risk of error during implementation. In this work, we argue that as the computational power keeps increasing, it is becoming practical to directly implement an approximation to the matrix operator linking reflector point targets to the corresponding radiofrequency signals via thoroughly validated and widely available simulations software. Once such a spatiotemporal forward-problem matrix is constructed, standard and thus highly optimized inversion procedures can be leveraged to achieve very high quality images in real time. Specifically, we show that spatiotemporal matrix image formation produces images of similar or enhanced quality when compared against standard delay-and-sum approaches in phantoms and in vivo, and show that this approach can be used to form images even when using non-conventional probe designs for which adapted image formation algorithms are not readily available.

Simultaneous positron emission tomography and ultrafast ultrasound for hybrid molecular, anatomical and functional imaging.

Positron emission tomography-computed tomography (PET-CT) is the most sensitive molecular imaging modality, but it does not easily allow for rapid temporal acquisition. Ultrafast ultrasound imaging (UUI)-a recently introduced technology based on ultrasonic holography-leverages frame rates of up to several thousand images per second to quantitatively map, at high resolution, haemodynamic, biomechanical, electrophysiological and structural parameters. Here, we describe a pre-clinical scanner that registers PET-CT and UUI volumes acquired simultaneously and offers multiple combinations for imaging. We demonstrate that PET-CT-UUI allows for simultaneous images of the vasculature and metabolism during tumour growth in mice and rats, as well as for synchronized multi-modal cardiac cine-loops. Combined anatomical, functional and molecular imaging with PET-CT-UUI represents a high-performance and clinically translatable technology for biomedical research.

An integrated and highly sensitive ultrafast acoustoelectric imaging system for biomedical applications.

Direct imaging of the electrical activation of the heart is crucial to better understand and diagnose diseases linked to arrhythmias. This work presents an ultrafast acoustoelectric imaging (UAI) system for direct and non-invasive ultrafast mapping of propagating current densities using the acoustoelectric effect. Acoustoelectric imaging is based on the acoustoelectric effect, the modulation of the medium's electrical impedance by a propagating ultrasonic wave. UAI triggers this effect with plane wave emissions to image current densities. An ultrasound research platform was fitted with electrodes connected to high common-mode rejection ratio amplifiers and sampled by up to 128 independent channels. The sequences developed allow for both real-time display of acoustoelectric maps and long ultrafast acquisition with fast off-line processing. The system was evaluated by injecting controlled currents into a saline pool via copper wire electrodes. Sensitivity to low current and low acoustic pressure were measured independently. Contrast and spatial resolution were measured for varying numbers of plane waves and compared to line per line acoustoelectric imaging with focused beams at equivalent peak pressure. Temporal resolution was assessed by measuring time-varying current densities associated with sinusoidal currents. Complex intensity distributions were also imaged in 3D. Electrical current densities were detected for injected currents as low as 0.56 mA. UAI outperformed conventional focused acoustoelectric imaging in terms of contrast and spatial resolution when using 3 and 13 plane waves or more, respectively. Neighboring sinusoidal currents with opposed phases were accurately imaged and separated. Time-varying currents were mapped and their frequency accurately measured for imaging frame rates up to 500 Hz. Finally, a 3D image of a complex intensity distribution was obtained. The results demonstrated the high sensitivity of the UAI system proposed. The plane wave based approach provides a highly flexible trade-off between frame rate, resolution and contrast. In conclusion, the UAI system shows promise for non-invasive, direct and accurate real-time imaging of electrical activation in vivo.

Toward a standard for the evaluation of PET-Auto-Segmentation methods following the recommendations of AAPM task group No. 211: Requirements and implementation.

PURPOSE: The aim of this paper is to define the requirements and describe the design and implementation of a standard benchmark tool for evaluation and validation of PET-auto-segmentation (PET-AS) algorithms. This work follows the recommendations of Task Group 211 (TG211) appointed by the American Association of Physicists in Medicine (AAPM). METHODS: The recommendations published in the AAPM TG211 report were used to derive a set of required features and to guide the design and structure of a benchmarking software tool. These items included the selection of appropriate representative data and reference contours obtained from established approaches and the description of available metrics. The benchmark was designed in a way that it could be extendable by inclusion of bespoke segmentation methods, while maintaining its main purpose of being a standard testing platform for newly developed PET-AS methods. An example of implementation of the proposed framework, named PETASset, was built. In this work, a selection of PET-AS methods representing common approaches to PET image segmentation was evaluated within PETASset for the purpose of testing and demonstrating the capabilities of the software as a benchmark platform. RESULTS: A selection of clinical, physical, and simulated phantom data, including "best estimates" reference contours from macroscopic specimens, simulation template, and CT scans was built into the PETASset application database. Specific metrics such as Dice Similarity Coefficient (DSC), Positive Predictive Value (PPV), and Sensitivity (S), were included to allow the user to compare the results of any given PET-AS algorithm to the reference contours. In addition, a tool to generate structured reports on the evaluation of the performance of PET-AS algorithms against the reference contours was built. The variation of the metric agreement values with the reference contours across the PET-AS methods evaluated for demonstration were between 0.51 and 0.83, 0.44 and 0.86, and 0.61 and 1.00 for DSC, PPV, and the S metric, respectively. Examples of agreement limits were provided to show how the software could be used to evaluate a new algorithm against the existing state-of-the art. CONCLUSIONS: PETASset provides a platform that allows standardizing the evaluation and comparison of different PET-AS methods on a wide range of PET datasets. The developed platform will be available to users willing to evaluate their PET-AS methods and contribute with more evaluation datasets.

ATLAAS: an automatic decision tree-based learning algorithm for advanced image segmentation in positron emission tomography.

Accurate and reliable tumour delineation on positron emission tomography (PET) is crucial for radiotherapy treatment planning. PET automatic segmentation (PET-AS) eliminates intra- and interobserver variability, but there is currently no consensus on the optimal method to use, as different algorithms appear to perform better for different types of tumours. This work aimed to develop a predictive segmentation model, trained to automatically select and apply the best PET-AS method, according to the tumour characteristics. ATLAAS, the automatic decision tree-based learning algorithm for advanced segmentation is based on supervised machine learning using decision trees. The model includes nine PET-AS methods and was trained on a 100 PET scans with known true contour. A decision tree was built for each PET-AS algorithm to predict its accuracy, quantified using the Dice similarity coefficient (DSC), according to the tumour volume, tumour peak to background SUV ratio and a regional texture metric. The performance of ATLAAS was evaluated for 85 PET scans obtained from fillable and printed subresolution sandwich phantoms. ATLAAS showed excellent accuracy across a wide range of phantom data and predicted the best or near-best segmentation algorithm in 93% of cases. ATLAAS outperformed all single PET-AS methods on fillable phantom data with a DSC of 0.881, while the DSC for H&N phantom data was 0.819. DSCs higher than 0.650 were achieved in all cases. ATLAAS is an advanced automatic image segmentation algorithm based on decision tree predictive modelling, which can be trained on images with known true contour, to predict the best PET-AS method when the true contour is unknown. ATLAAS provides robust and accurate image segmentation with potential applications to radiation oncology.

PETSTEP: Generation of synthetic PET lesions for fast evaluation of segmentation methods.

PURPOSE: This work describes PETSTEP (PET Simulator of Tracers via Emission Projection): a faster and more accessible alternative to Monte Carlo (MC) simulation generating realistic PET images, for studies assessing image features and segmentation techniques. METHODS: PETSTEP was implemented within Matlab as open source software. It allows generating three-dimensional PET images from PET/CT data or synthetic CT and PET maps, with user-drawn lesions and user-set acquisition and reconstruction parameters. PETSTEP was used to reproduce images of the NEMA body phantom acquired on a GE Discovery 690 PET/CT scanner, and simulated with MC for the GE Discovery LS scanner, and to generate realistic Head and Neck scans. Finally the sensitivity (S) and Positive Predictive Value (PPV) of three automatic segmentation methods were compared when applied to the scanner-acquired and PETSTEP-simulated NEMA images. RESULTS: PETSTEP produced 3D phantom and clinical images within 4 and 6 min respectively on a single core 2.7 GHz computer. PETSTEP images of the NEMA phantom had mean intensities within 2% of the scanner-acquired image for both background and largest insert, and 16% larger background Full Width at Half Maximum. Similar results were obtained when comparing PETSTEP images to MC simulated data. The S and PPV obtained with simulated phantom images were statistically significantly lower than for the original images, but led to the same conclusions with respect to the evaluated segmentation methods. CONCLUSIONS: PETSTEP allows fast simulation of synthetic images reproducing scanner-acquired PET data and shows great promise for the evaluation of PET segmentation methods.