Assessment of Volumetric Dense Tissue Segmentation in Tomosynthesis Using Deep Virtual Clinical Trials

The adoption of artificial intelligence (AI) in medical imaging requires careful evaluation of machine-learning algorithms. We propose the use of a "deep virtual clinical trial" (DeepVCT) method to effectively evaluate the performance of AI algorithms. In this paper, DeepVCTs have been proposed to elucidate limitations of AI applications and predictions of clinical outcomes, avoiding biases in study designs. The DeepVCT method was used to evaluate the performance of nnU-Net models in assessing volumetric breast density (VBD) from digital breast tomosynthesis (DBT) images. In total, 2,010 anatomical breast models were simulated. Projections were simulated using the acquisition geometry of a clinical DBT system. The projections were reconstructed using 0.1, 0.2, and 0.5 mm plane spacing. nnU-Net models were developed using the center-most planes of the reconstructions with the respective ground-truth. The results show that the accuracy of the nnU-Net improves significantly with DBT images reconstructed with 0.1 mm plane spacing (78.4×205.3×40.1 mm3). The segmentations resulted in Dice values up to 0.84 with area under the receiver operating characteristic curve of 0.92. The optimization of plane spacing for VBD assessment was used as an exemplar of a DeepVCT application, allowing us to interpret better the input parameters and outcomes of the nnU-Net. Thus, DeepVCTs can provide a plethora of evidence to predict the efficacy of these algorithms using large-scale simulation-based data.

Standardization in Quantitative Imaging: A Multicenter Comparison of Radiomic Features from Different Software Packages on Digital Reference Objects and Patient Data Sets

Radiomic features are being increasingly studied for clinical applications. We aimed to assess the agreement among radiomic features when computed by several groups by using different software packages under very tightly controlled conditions, which included standardized feature definitions and common image data sets. Ten sites (9 from the NCI's Quantitative Imaging Network] positron emission tomography–computed tomography working group plus one site from outside that group) participated in this project. Nine common quantitative imaging features were selected for comparison including features that describe morphology, intensity, shape, and texture. The common image data sets were: three 3D digital reference objects (DROs) and 10 patient image scans from the Lung Image Database Consortium data set using a specific lesion in each scan. Each object (DRO or lesion) was accompanied by an already-defined volume of interest, from which the features were calculated. Feature values for each object (DRO or lesion) were reported. The coefficient of variation (CV), expressed as a percentage, was calculated across software packages for each feature on each object. Thirteen sets of results were obtained for the DROs and patient data sets. Five of the 9 features showed excellent agreement with CV < 1%; 1 feature had moderate agreement (CV < 10%), and 3 features had larger variations (CV ≥ 10%) even after attempts at harmonization of feature calculations. This work highlights the value of feature definition standardization as well as the need to further clarify definitions for some features.

Carotid artery wall motion analysis from B-mode ultrasound using adaptive block matching: in silico evaluation and in vivo application

Valid risk stratification for carotid atherosclerotic plaques represents a crucial public health issue toward preventing fatal cerebrovascular events. Although motion analysis (MA) provides useful information about arterial wall dynamics, the identification of motion-based risk markers remains a significant challenge. Considering that the ability of a motion estimator (ME) to handle changes in the appearance of motion targets has a major effect on accuracy in MA, we investigated the potential of adaptive block matching (ABM) MEs, which consider changes in image intensities over time. To assure the validity in MA, we optimized and evaluated the ABM MEs in the context of a specially designed in silico framework. ABM(FIRF2), which takes advantage of the periodicity characterizing the arterial wall motion, was the most effective ABM algorithm, yielding a 47% accuracy increase with respect to the conventional block matching. The in vivo application of ABM(FIRF2) revealed five potential risk markers: low movement amplitude of the normal part of the wall adjacent to the plaques in the radial (RMA(PWL)) and longitudinal (LMA(PWL)) directions, high radial motion amplitude of the plaque top surface (RMA(PTS)), and high relative movement, expressed in terms of radial strain (RSI(PL)) and longitudinal shear strain (LSSI(PL)), between plaque top and bottom surfaces. The in vivo results were reproduced by OF(LK(WLS)) and ABM(KF-K2), MEs previously proposed by the authors and with remarkable in silico performances, thereby reinforcing the clinical values of the markers and the potential of those MEs. Future in vivo studies will elucidate with confidence the full potential of the markers.