Dataset Information

MimickNet, Mimicking Clinical Image Post- Processing Under Black-Box Constraints.

ABSTRACT: Image post-processing is used in clinical-grade ultrasound scanners to improve image quality (e.g., reduce speckle noise and enhance contrast). These post-processing techniques vary across manufacturers and are generally kept proprietary, which presents a challenge for researchers looking to match current clinical-grade workflows. We introduce a deep learning framework, MimickNet, that transforms conventional delay-and-summed (DAS) beams into the approximate Dynamic Tissue Contrast Enhanced (DTCE™) post-processed images found on Siemens clinical-grade scanners. Training MimickNet only requires post-processed image samples from a scanner of interest without the need for explicit pairing to DAS data. This flexibility allows MimickNet to hypothetically approximate any manufacturer's post-processing without access to the pre-processed data. MimickNet post-processing achieves a 0.940 ± 0.018 structural similarity index measurement (SSIM) compared to clinical-grade post-processing on a 400 cine-loop test set, 0.937 ± 0.025 SSIM on a prospectively acquired dataset, and 0.928 ± 0.003 SSIM on an out-of-distribution cardiac cine-loop after gain adjustment. To our knowledge, this is the first work to establish deep learning models that closely approximate ultrasound post-processing found in current medical practice. MimickNet serves as a clinical post-processing baseline for future works in ultrasound image formation to compare against. Additionally, it can be used as a pretrained model for fine-tuning towards different post-processing techniques. To this end, we have made the MimickNet software, phantom data, and permitted in vivo data open-source at https://github.com/ouwen/MimickNet.

SUBMITTER: Huang O

PROVIDER: S-EPMC7286793 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

MimickNet, Mimicking Clinical Image Post- Processing Under Black-Box Constraints.

Huang Ouwen O Long Will W Bottenus Nick N Lerendegui Marcelo M Trahey Gregg E GE Farsiu Sina S Palmeri Mark L ML

IEEE transactions on medical imaging 20200131 6

Image post-processing is used in clinical-grade ultrasound scanners to improve image quality (e.g., reduce speckle noise and enhance contrast). These post-processing techniques vary across manufacturers and are generally kept proprietary, which presents a challenge for researchers looking to match current clinical-grade workflows. We introduce a deep learning framework, MimickNet, that transforms conventional delay-and-summed (DAS) beams into the approximate Dynamic Tissue Contrast Enhanced (DTC ...[more]

PMID: 32012003

Similar Datasets

Project description:BackgroundAlthough computed tomography (CT) with three-dimensional (3D) rendering of the calcaneus is used for diagnostic evaluation of disorders, morphological measurements for the calcaneus are mostly based on a two-dimensional plane. The purposes of this study were to design a method for 3D morphological measurements of the normal calcaneus based on CT post-processing techniques, to measure morphological parameters in the male and female groups and describe gender differences of the parameters, and to investigate the reliability of such measurements.MethodsOne hundred and seventy-nine patients (83 men and 96 women) with a mean age of 40.6 (range, 21 to 59) years who underwent CT scans for their feet were reviewed retrospectively. The 3D structure of a normal calcaneus after shaded surface display reconstruction was extracted by interactive and automatic segmentation. Morphological measurements were achieved by means of a 3D measurement method based on CT image post-processing. Lengths and heights of the main parts of the calcaneus, Gissane's angle, Böhler's angle and the area of articular facet were worked out in 3D space. Gender-related size differences of parameters were compared using analysis of covariance (ANCOVA), adjusting for body height. Intra-observer and inter-observer reliabilities were assessed using intraclass correlation coefficients (ICCs) and the root mean square standard deviation (RMS-SD) for precision study.ResultsA large range of measurement values was found. Only the length of the anterior process was without gender difference (p > 0.05). The other parameters in the male group were greater than those in the female group (p < 0.01 for each, ANCOVA). All parameters had excellent reliability and reproducibility (ICC > 0.8). Precision was acceptable for intra-observer RMS-SD (linear, angular and areal measurements no more than 0.6 mm, 1.2° and 0.25 mm2, respectively). Inter-observer RMS-SD ranged from 0.4 to 1.6 mm for linear measurements, 1.2 to 2.5° for angles and 0.24 to 0.40 mm2 for areas.ConclusionsThree-dimensional morphological measurement based on a CT post-processing technique was highly reliable and repeatable for calcaneal anatomic morphological measurement. The current data will be helpful for anatomic reduction of calcaneal fractures and calcaneal malunion.

Project description:Software systems typically have an input domain that can be subdivided into sub-domains, each of which generates similar or related outputs. Testing it on the boundaries between these sub-domains is critical to ensure high-quality software. Therefore, boundary value analysis and testing have been a fundamental part of the software testing toolbox for a long time and are typically taught early to software engineering students. Despite its many argued benefits, boundary value analysis for a given software specification or application is typically described in abstract terms. This allows for variation in how testers apply it and in the benefits they see. Additionally, its adoption has been limited since it requires a specification or model to be analysed. We propose an automated black-box boundary value detection method to support software testers in performing systematic boundary value analysis. This dynamic method can be utilized even without a specification or model. The proposed method is based on a metric referred to as the program derivative, which quantifies the level of boundariness of test inputs. By combining this metric with search algorithms, we can identify and rank pairs of inputs as good boundary candidates, i.e., inputs that are in close proximity to each other but with outputs that are far apart. We have implemented the AutoBVA approach and evaluated it on a curated dataset of example programs. Furthermore, we have applied the approach broadly to a sample of 613 functions from the base library of the Julia programming language. The approach could identify boundary candidates that highlight diverse boundary behaviours in over 70% of investigated systems under test. The results demonstrate that even a simple variant of the program derivative, combined with broad sampling and search over the input space, can identify interesting boundary candidates for a significant portion of the functions under investigation. In conclusion, we also discuss the future extension of the approach to encompass more complex systems under test cases and datatypes.

Dataset Information

MimickNet, Mimicking Clinical Image Post- Processing Under Black-Box Constraints.

Publications

MimickNet, Mimicking Clinical Image Post- Processing Under Black-Box Constraints.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets