Single Projection Research Articles

Navigator-based slice tracking for kidney pCASL using spin-echo EPI acquisition.

To apply a navigator-based slice-tracking method to prospectively compensate respiratory motion for kidney pseudo-continuous arterial spin labeling (pCASL), using spin-echo (SE) EPI acquisition. A single gradient-echo slice selection and projection readout at the location of the diaphragm along the inferior-superior direction was applied as a navigator. Navigator acquisition and fat suppression were inserted before each transverse imaging slice of the readouts of a 2D-SE-EPI-based pCASL sequence. Motion information was calculated after exclusion of the signal saturation in the navigator signal caused by EPI excitations. The motion information was then used to directly adjust the slice positioning in real time. The respiratory motion from the navigator signal was calculated, and slice positioning was changed in real time based on the motion information. We could show that motion compensation reduces kidney movement, and that the coefficients of variation across renal perfusion values were significantly reduced when motion correction was applied. The average reduction of coefficients of variation was approximately 20%, resulting in a more accurate and detailed structure of the respective perfusion maps. This study demonstrates the feasibility of a navigator-based slice-tracking technique in kidney imaging with a SE-EPI readout pCASL sequence to reduce kidney motion.

Semi-XctNet: Volumetric images reconstruction network from a single projection image via semi-supervised learning

Deep learning networks have achieved remarkable progress in various tasks of medical imaging. Most of the recent success in computer vision highly depend on large amounts of carefully annotated data, whereas labelling is arduous, time-consuming and in need of expertise. In this paper, a semi-supervised learning method, Semi-XctNet, is proposed for volumetric images reconstruction from a single X-ray image. In our framework, the effect of regularization on pixel-level prediction is enhanced by introducing a transformation consistent strategy into the model. Furthermore, a multi-stage training strategy is designed to ameliorate the generalization performance of the teacher network. An assistant module is also introduced to improve the pixel quality of pseudo-labels, thereby further improving the reconstruction accuracy of the semi-supervised model. The semi-supervised method proposed in this paper has been extensively validated on the LIDC-IDRI lung cancer detection public data set. Quantitative results show that SSIM (structural similarity measurement) and PSNR (peak signal noise ratio) are 0.8384 and 28.7344 respectively. Compared with the state-of-the-arts, Semi-XctNet exhibits excellent reconstruction performance, thus demonstrating the effectiveness of our method on the task of volumetric images reconstruction network from a single X-ray image.

A decade of atom-counting in STEM: From the first results toward reliable 3D atomic models from a single projection

Quantitative structure determination is needed in order to study and understand nanomaterials at the atomic scale. Materials characterisation resulting in precise structural information is a crucial point to understand the structure–property relation of materials. Counting the number of atoms and retrieving the 3D atomic structure of nanoparticles plays an important role here. In this paper, an overview will be given of the atom-counting methodology and its applications over the past decade. The procedure to count the number of atoms will be discussed in detail and it will be shown how the performance of the method can be further improved. Furthermore, advances toward mixed element nanostructures, 3D atomic modelling based on the atom-counting results, and quantifying the nanoparticle dynamics will be highlighted.

Noise Considerations for Tomographic Reconstruction of Single-Projection Digital Holographic Interferometry-Based Radiation Dosimetry

Optical Calorimetry (OC) is a 2D Digital Holographic Interferometry (DHI)-based measurement technique with potential applications for the 3D dosimetry of ultra-high dose rate (FLASH) radiation therapy beams through tomographic reconstruction. This application requires accurate measurements of DHI signals in environments with low signal-to-noise ratios (SNRs) in order to accurately measure absorbed energy to a medium per unit mass (Dose). However, tomographic reconstruction accuracy is sensitive to noise in the measurements. In this study, a virtual model of an OC dosimeter was used to characterize and model major sources of noise within a DHI setup, allowing for the modelled noise sources to be selectively reduced. The tomographic reconstruction of the 3D dose distribution was achieved using the inverse Abel transform. Reducing the noise contribution from atmospheric turbulence and mechanical vibration by one half improved the central axis reconstruction error from 6.5% to 1.3% and 1.1%, respectively, and the mean dose difference from 2.9% to 0.4% and 0.3%, respectively. This indicates the potential of the tomographic DHI-based 3D OC dosimeter to reconstruct accurate 3D dose distributions from a single projection if the specified sources of noise can be reduced to acceptable levels. The used methodology is applicable to any application of tomographic DHI where reconstruction quality is highly sensitive to noise.

A single projection algorithm with double inertial extrapolation steps for solving pseudomonotone variational inequalities in Hilbert space

In this work, we investigate a single projection method with double inertial extrapolation steps and self-adaptive step sizes for solving pseudomonotone variational inequality problems in a real Hilbert space. Weak and linear convergence are presented under suitable conditions. Some simple numerical examples are given to illustrate the performance of the proposed algorithm.

CT-based data generation for foreign object detection on a single X-ray projection

Although X-ray imaging is used routinely in industry for high-throughput product quality control, its capability to detect internal defects has strong limitations. The main challenge stems from the superposition of multiple object features within a single X-ray view. Deep Convolutional neural networks can be trained by annotated datasets of X-ray images to detect foreign objects in real-time. However, this approach depends heavily on the availability of a large amount of data, strongly hampering the viability of industrial use with high variability between batches of products. We present a computationally efficient, CT-based approach for creating artificial single-view X-ray data based on just a few physically CT-scanned objects. By algorithmically modifying the CT-volume, a large variety of training examples is obtained. Our results show that applying the generative model to a single CT-scanned object results in image analysis accuracy that would otherwise be achieved with scans of tens of real-world samples. Our methodology leads to a strong reduction in training data needed, improved coverage of the combinations of base and foreign objects, and extensive generalizability to additional features. Once trained on just a single CT-scanned object, the resulting deep neural network can detect foreign objects in real-time with high accuracy.

Reduced volume of diabetic pancreatic islets in rodents detected by synchrotron X-ray phase-contrast microtomography and deep learning network

The pancreatic islet is a highly structured micro-organ that produces insulin in response to rising blood glucose. Here we develop a label-free and automatic imaging approach to visualize the islets in situ in diabetic rodents by the synchrotron radiation X-ray phase-contrast microtomography (SRμCT) at the ID17 station of the European Synchrotron Radiation Facility. The large-size images (3.2mm×15.97mm) were acquired in the pancreas in STZ-treated mice and diabetic GK rats. Each pancreas was dissected by 3000 reconstructed images. The image datasets were further analysed by a self-developed deep learning method, AA-Net. All islets in the pancreas were segmented and visualized by the three-dimension (3D) reconstruction. After quantifying the volumes of the islets, we found that the number of larger islets (=>1500 μm3) was reduced by 2-fold (wt 1004±94 vs GK 419±122, P<0.001) in chronically developed diabetic GK rat, while in STZ-treated diabetic mouse the large islets were decreased by half (189±33 vs 90±29, P<0.001) compared to the untreated mice. Our study provides a label-free tool for detecting and quantifying pancreatic islets in situ. It implies the possibility of monitoring the state of pancreatic islets in vivo diabetes without labelling.

Evaluation of global teleconnections in CMIP6 climate projections using complex networks

Abstract. In climatological research, the evaluation of climate models is one of the central research subjects. As an expression of large-scale dynamical processes, global teleconnections play a major role in interannual to decadal climate variability. Their realistic representation is an indispensable requirement for the simulation of climate change, both natural and anthropogenic. Therefore, the evaluation of global teleconnections is of utmost importance when assessing the physical plausibility of climate projections. We present an application of the graph-theoretical analysis tool δ-MAPS, which constructs complex networks on the basis of spatio-temporal gridded data sets, here sea surface temperature and geopotential height at 500 hPa. Complex networks complement more traditional methods in the analysis of climate variability, like the classification of circulation regimes or empirical orthogonal functions, assuming a new non-linear perspective. While doing so, a number of technical tools and metrics, borrowed from different fields of data science, are implemented into the δ-MAPS framework in order to overcome specific challenges posed by our target problem. Those are trend empirical orthogonal functions (EOFs), distance correlation and distance multicorrelation, and the structural similarity index. δ-MAPS is a two-stage algorithm. In the first place, it assembles grid cells with highly coherent temporal evolution into so-called domains. In a second step, the teleconnections between the domains are inferred by means of the non-linear distance correlation. We construct 2 unipartite and 1 bipartite network for 22 historical CMIP6 climate projections and 2 century-long coupled reanalyses (CERA-20C and 20CRv3). Potential non-stationarity is taken into account by the use of moving time windows. The networks derived from projection data are compared to those from reanalyses. Our results indicate that no single climate projection outperforms all others in every aspect of the evaluation. But there are indeed models which tend to perform better/worse in many aspects. Differences in model performance are generally low within the geopotential height unipartite networks but higher in sea surface temperature and most pronounced in the bipartite network representing the interaction between ocean and atmosphere.

Spatial Alignment of Organoids Tracking Subclonal Chemotherapy Resistance in Pancreatic and Ampullary Cancer.

Pancreatic and ampullary cancers remain highly morbid diseases for which accurate clinical predictions are needed for precise therapeutic predictions. Patient-derived cancer organoids have been widely adopted; however, prior work has focused on well-level therapeutic sensitivity. To characterize individual oligoclonal units of therapeutic response, we introduce a low-volume screening assay, including an automated alignment algorithm. The oligoclonal growth response was compared against validated markers of response, including well-level viability and markers of single-cell viability. Line-specific sensitivities were compared with clinical outcomes. Automated alignment algorithms were generated to match organoids across time using coordinates across a single projection of Z-stacked images. After screening for baseline size (50 μm) and circularity (&gt;0.4), the match efficiency was found to be optimized by accepting the diffusion thresholded with the root mean standard deviation of 75 μm. Validated well-level viability showed a limited correlation with the mean organoid size (R = 0.408), and a normalized growth assayed by normalized changes in area (R = 0.474) and area (R = 0.486). Subclonal populations were defined by both residual growth and the failure to induce apoptosis and necrosis. For a culture with clinical resistance to gemcitabine and nab-paclitaxel, while a therapeutic challenge induced a robust effect in inhibiting cell growth (GΔ = 1.53), residual oligoclonal populations were able to limit the effect on the ability to induce apoptosis (GΔ = 0.52) and cell necrosis (GΔ = 1.07). Bioengineered approaches are feasible to capture oligoclonal heterogeneity in organotypic cultures, integrating ongoing efforts for utilizing organoids across cancer types as integral biomarkers and in novel therapeutic development.

Deep learning for x-ray scatter correction in dedicated breast CT.

Accurate correction of x-ray scatter in dedicated breast computed tomography (bCT) imaging may result in improved visual interpretation and is crucial to achieve quantitative accuracy during image reconstruction and analysis. To develop a deep learning (DL) model to correct for x-ray scatter in bCT projection images. A total of 115 patient scans acquired with a bCT clinical system were segmented into the major breast tissue types (skin, adipose, and fibroglandular tissue). The resulting breast phantoms were divided into training (n=110) and internal validation cohort (n=5). Training phantoms were augmented by a factor of four by random translation of the breast in the image field of view. Using a previously validated Monte Carlo (MC) simulation algorithm, 12 primary and scatter bCT projection images with a 30-degree step were generated from each phantom. For each projection, the thickness map and breast location in the field of view were also calculated. A U-Net based DL model was developed to estimate the scatter signal based on the total input simulated image and trained single-projection-wise, with the thickness map and breast location provided as additional inputs. The model was internally validated using MC-simulated projections and tested using an external data set of 10 phantoms derived from images acquired with a different bCT system. For this purpose, the mean relative difference (MRD) and mean absolute error (MAE) were calculated. To test for accuracy in reconstructed images, a full bCT acquisition was mimicked with MC-simulations and then assessed by calculating the MAE and the structural similarity (SSIM). Subsequently, scatter was estimated and subtracted from the bCT scans of three patients to obtain the scatter-corrected image. The scatter-corrected projections were reconstructed and compared with the uncorrected reconstructions by evaluating the correction of the cupping artifact, increase in image contrast, and contrast-to-noise ratio (CNR). The mean MRD and MAE across all cases (min, max) for the internal validation set were 0.04% (-1.1%, 1.3%) and 2.94% (2.7%, 3.2%), while for the external test set they were -0.64% (-1.6%, 0.2%) and 2.84% (2.3%, 3.5%), respectively. For MC-simulated reconstruction slices, the computed SSIM was 0.99 and the MAE was 0.11% (range: 0%, 0.35%) with a single outlier slice of 2.06%. For the three patient bCT reconstructed images, the correction increased the contrast by a mean of 25% (range: 20%, 30%), and reduced the cupping artifact. The mean CNR increased by 0.32 after scatter correction, which was not found to be significant (95% confidence interval: [-0.01, 0.65], p=0.059). The time required to correct the scatter in a single bCT projection was 0.2 s on an NVIDIA GeForce GTX 1080 GPU. The developed DL model could accurately estimate scatter in bCT projection images and could enhance contrast and correct for cupping artifact in reconstructed patient images without significantly affecting the CNR. The time required for correction would allow its use in daily clinical practice, and the reported accuracy will potentially allow quantitative reconstructions.

Navigator-based slice tracking for prospective motion correction in kidney vessel architecture imaging

ObjectivesTo apply a navigator-based slice tracking method to prospectively compensate the respiratory motion for kidney vessel architecture imaging (VAI). Materials and methodsA dual gradient echo spin echo 2D EPI sequence was developed for kidney VAI. A single gradient-echo slice selection and projection readout at the location of the diaphragm along the inferior-superior direction was applied as a navigator. Navigator acquisition and fat suppression were inserted before each transverse imaging slice. Motion information was calculated after exclusion of the signal saturation in the navigator signal caused by imaging slices. The motion information was then directly sent back to the sequence and slice positioning was adjusted in real-time. The whole sequence was applied during a contrast agent pass-through. ResultsVAI parametric maps show the structural heterogeneity of the renal vasculature. The respiratory motion from the navigator signal was precisely calculated and slice positioning was changed in real-time based on the motion information. The vibration amplitude of the signal intensity of the liver tissue at the liver-lung interface in the case of prospective motion correction (PMC) on is about 28% of the PMC off case. Compared to the case of PMC off, the coefficient of variation was reduced 30% of the case of PMC on. ConclusionsThis study demonstrates the feasibility of the motion-compensating technique in kidney VAI. The sequence may improve the evaluation of microvasculature in kidney diseases.

Pattern Encoding of Robust M-Array Driven by Texture Constraints

M-Array pattern encoding is widely used in structured light for 3D reconstruction due to its single projection and single imaging characteristics. The robustness of M-Array in 3D reconstruction can be assessed by the accuracy of the global positioning of the code-word and the density of the decodable feature points. This paper proposes a pattern encoding method of robust M-Array based on texture constraints. M-Arrays are formed by matching and splicing candidate sub-windows, which are composed of symbols obtained from an M-Sequence one by one. To construct an M-Array with more texture information, both the number of edges and the maximum rectangular area within the sub-window are constrained. A novel three-level backtracking mechanism reduces the time complexity. Four indicators are introduced to evaluate the robustness of the M-Array and used to compare the proposed method with existing methods. The results show that the proposed method has low similarity between adjacent sub-windows and high uniformity of symbol distribution globally, indicating better accuracy of sub-window decoding. A 3D reconstruction experiment in the actual scenes proves that the point cloud density and accuracy obtained by solving the M-Array pattern constructed by the method proposed are better.

A guide to the design of the virtual element methods for second- and fourth-order partial differential equations

&lt;abstract&gt;&lt;p&gt;We discuss the design and implementation details of two conforming virtual element methods for the numerical approximation of two partial differential equations that emerge in phase-field modeling of fracture propagation in elastic material. The two partial differential equations are: (i) a linear hyperbolic equation describing the momentum balance and (ii) a fourth-order elliptic equation modeling the damage of the material. Inspired by &lt;sup&gt;[&lt;xref ref-type="bibr" rid="b1"&gt;1&lt;/xref&gt;,&lt;xref ref-type="bibr" rid="b2"&gt;2&lt;/xref&gt;,&lt;xref ref-type="bibr" rid="b3"&gt;3&lt;/xref&gt;]&lt;/sup&gt;, we develop a new conforming VEM for the discretization of the two equations, which is implementation-friendly, i.e., different terms can be implemented by exploiting a single projection operator. We use $ C^0 $ and $ C^1 $ virtual elements for the second-and fourth-order partial differential equation, respectively. For both equations, we review the formulation of the virtual element approximation and discuss the details pertaining the implementation.&lt;/p&gt;&lt;/abstract&gt;

NuTracker: a coordinate-based neural network representation of lung motion for intrafraction tumor tracking with various surrogates in radiotherapy

Objective. Tracking tumors and surrounding tissues in real-time is critical for reducing errors and uncertainties during radiotherapy. Existing methods are either limited by the linear representation or scale poorly with the volume resolution. To address both issues, we propose a novel coordinate-based neural network representation of lung motion to predict the instantaneous 3D volume at arbitrary spatial resolution from various surrogates: patient surface, fiducial marker, and single kV projection. Approach. The proposed model, namely NuTracker, decomposes the 4DCT into a template volume and dense displacement fields (DDFs), and uses two coordinate neural networks to predict them from spatial coordinates and surrogate states. The predicted template is spatially warped with the predicted DDF to produce the deformed volume for a given surrogate state. The nonlinear coordinate networks enable representing complex motion at infinite resolution. The decomposition allows imposing different regularizations on the spatial and temporal domains. The meta-learning and multi-task learning are used to train NuTracker across patients and tasks, so that commonalities and differences can be exploited. NuTracker was evaluated on seven patients implanted with markers using a leave-one-phase-out procedure. Main results. The 3D marker localization error is 0.66 mm on average and <1 mm at 95th-percentile, which is about 26% and 32% improvement over the predominant linear methods. The tumor coverage and image quality are improved by 5.7% and 11% in terms of dice and PSNR. The difference in the localization error for different surrogates is small and is not statistically significant. Cross-population learning and multi-task learning contribute to performance. The model tolerates surrogate drift to a certain extent. Significance. NuTracker can provide accurate estimation for entire tumor volume based on various surrogates at infinite resolution. It is of great potential to apply the coordinate network to other imaging modalities, e.g. 4DCBCT and other tasks, e.g. 4D dose calculation.

Unravelling global future scenarios in the perspective of bioeconomy planning

The transition to bioeconomy and the broader low-fossil carbon economy requires long-term investments, whose environmental and economic performance will be affected by various future conditions. When assessing the consequences of such future investments, considering multiple background future scenarios instead of one single projection could greatly enhance the robustness of the decision support. Here, we systematically reviewed six internationally well-recognized global environmental scenario studies and one intelligence report, selected as highly relevant in terms of bioeconomy implications. The aim was to uncover the key variables and cause-effect relationships at play in these scenario studies. Through constructing causal loop diagrams for each reviewed study, we identified the variables with the greatest number of causal connections, the “cause” and “effect” variables, and the most reported cause-effect relationships across all studies. Our main findings are: (1) the top 5 causal variables are mitigation policies, technological progress, consumers’ awareness, economic growth and education level, while (2) the top 5 affected variables are climate change, materials use, food security, natural ecosystems, and social justice. Amongst the top 10 causal and affected variables (3), 68 connected pairs were identified with no disagreement in their causal relationship direction. The three most reported pairs were (4) mitigation policy → climate change, healthy and sustainable diet → land use, and population → materials use. Finally, (5) we highlighted that all the reviewed studies share a limited worldview where economy and cost-competitiveness is the dominant consideration defining the future sustainability.

Evaluation of a Novel Infrared Thermography Projection to Assess Udder Health in Primigravid Dairy Heifers.

Heifer mastitis in early lactation impacts negatively on animal welfare, milk production and longevity. A major challenge for the prevention and control of mastitis in dairy heifers is to establish when intramammary infection occurs because pre-partum secretum sampling is risky. We evaluated a ventrodorsal projection to capture thermal images of the entire udder of primigravid and compared results against caudocranial projection, which is used in lactating cattle. Based on the analysis of 119 heifers and images taken at 2 months and 2 weeks pre-partum, a very strong positive correlation (r = 0.91 and r = 0.96, respectively) was shown between caudocranial and ventrodorsal projections of hind quarters. Quarter maximum gradient temperatures were consistently greater on ventrodorsal projection than on caudocranial projection, and less variable than minimum gradient temperatures. The collection of ventrodorsal images is a simple one-step method involving the imaging of the entire udder in a manner safe for both the cattle and handlers. Together, these results demonstrate that a single projection can be used to scan the entire udder of primigravid dairy heifers in commercial farm conditions, with the potential to implement this as a routine method for the early detection of intramammary infection based on udder surface temperature.

Projecting Compound Flood Hazard Under Climate Change With Physical Models and Joint Probability Methods

AbstractAccurate delineation of compound flood hazard requires joint simulation of rainfall‐runoff and storm surges within high‐resolution flood models, which may be computationally expensive. There is a need for supplementing physical models with efficient, probabilistic methodologies for compound flood hazard assessment that can be applied under a range of climate and environment conditions. Here we propose an extension to the joint probability optimal sampling method (JPM‐OS), which has been widely used for storm surge assessment, and apply it for rainfall‐surge compound hazard assessment under climate change at the catchment‐scale. We utilize thousands of synthetic tropical cyclones (TCs) and physics‐based models to characterize storm surge and rainfall hazards at the coast. Then we implement a Bayesian quadrature optimization approach (JPM‐OS‐BQ) to select a small number (∼100) of storms, which are simulated within a high‐resolution flood model to characterize the compound flood hazard. We show that the limited JPM‐OS‐BQ simulations can capture historical flood return levels within 0.25 m compared to a high‐fidelity Monte Carlo approach. We find that the combined impact of 2100 sea‐level rise (SLR) and TC climatology changes on flood hazard change in the Cape Fear Estuary, NC will increase the 100‐year flood extent by 27% and increase inundation volume by 62%. Moreover, we show that probabilistic incorporation of SLR in the JPM‐OS‐BQ framework leads to different 100‐year flood maps compared to using a single mean SLR projection. Our framework can be applied to catchments across the United States Atlantic and Gulf coasts under a variety of climate and environment scenarios.

Two-View Mammogram Synthesis from Single-View Data Using Generative Adversarial Networks

While two-view mammography taking both mediolateral-oblique (MLO) and cranio-caudual (CC) views is the current standard method of examination in breast cancer screening, single-view mammography is still being performed in some countries on women of specific ages. The rate of cancer detection is lower with single-view mammography than for two-view mammography, due to the lack of available image information. The goal of this work is to improve single-view mammography’s ability to detect breast cancer by providing two-view mammograms from single projections. The synthesis of novel-view images from single-view data has recently been achieved using generative adversarial networks (GANs). Here, we apply complete representation GAN (CR-GAN), a novel-view image synthesis model, aiming to produce CC-view mammograms from MLO views. Additionally, we incorporate two adaptations—the progressive growing (PG) technique and feature matching loss—into CR-GAN. Our results show that use of the PG technique reduces the training time, while the synthesized image quality is improved when using feature matching loss, compared with the method using only CR-GAN. Using the proposed method with the two adaptations, CC views similar to real views are successfully synthesized for some cases, but not all cases; in particular, image synthesis is rarely successful when calcifications are present. Even though the image resolution and quality are still far from clinically acceptable levels, our findings establish a foundation for further improvements in clinical applications. As the first report applying novel-view synthesis in medical imaging, this work contributes by offering a methodology for two-view mammogram synthesis.

Dynamic flame temperature tomography utilizing multi-camera common optical path

In the single projection direction, we propose a multi-camera common optical path system for three-dimensional radiation thermometry of dynamic flame, which is realized in the form of prism cascade. Different cameras can focus on certain sections of the flame along the main optical axis synchronously and independently. The image recorded by each camera linearly consists of a focused flame section and other remaining sections with defocused state. On the basis of point spread function, the spatial object-image mapping relationship is established by convolution, and the tomography of flame sections is performed by deconvolution. Then, the flame temperature is reconstructed by use of Planck's Law. The effectiveness of proposed method is verified by experiments, which could characterize the spatiotemporal evolution of flame temperature. Furthermore, it is expected to be able to achieve compatible measurements with high spatial and high temporal resolution.

MRI can accurately diagnose breast cancer during lactation.

To test the diagnostic performance of breast dynamic contrast-enhanced (DCE) MRI during lactation. Datasets of 198 lactating patients, including 66 pregnancy-associated breast cancer (PABC) patients and 132 controls, who were scanned by DCE on 1.5-T MRI, were retrospectively evaluated. Six blinded, expert radiologists independently read a single DCE maximal intensity projection (MIP) image for each case and were asked to determine whether malignancy was suspected and the background-parenchymal-enhancement (BPE) grade. Likewise, computer-aided diagnosis CAD MIP images were independently read by the readers. Contrast-to-noise ratio (CNR) analysis was measured and compared among four consecutive acquisitions of DCE subtraction images. For MIP-DCE images, the readers achieved the following means: sensitivity 93.3%, specificity 80.3%, positive-predictive-value 70.4, negative-predictive-value 96.2, and diagnostic accuracy of 84.6%, with a substantial inter-rater agreement (Kappa = 0.673, p value < 0.001). Most false-positive interpretations were attributed to either the MIP presentation, an underlying benign lesion, or an asymmetric appearance due to prior treatments. CAD's derived diagnostic accuracy was similar (p = 0.41). BPE grades were significantly increased in the healthy controls compared to the PABC cohort (p < 0.001). CNR significantly decreased by 11-13% in each of the four post-contrast images (p < 0.001). Breast DCE MRI maintains its high efficiency among the lactating population, probably due to a vascular-steal phenomenon, which causes a significant reduction of BPE in cancer cases. Upon validation by prospective, multicenter trials, this study could open up the opportunity for breast MRI to be indicated in the screening and diagnosis of lactating patients, with the aim of facilitating an earlier diagnosis of PABC. • A single DCE MIP image was sufficient to reach a mean sensitivity of 93.3% and NPV of 96.2%, to stress the high efficiency of breast MRI during lactation. • Reduction in BPE among PABC patients compared to the lactating controls suggests that several factors, including a possible vascular steal phenomenon, may affect cancer patients. • Reduction in CNR along four consecutive post-contrast acquisitions highlights the differences in breast carcinoma and BPE kinetics and explains the sufficient conspicuity on the first subtracted image.