arXiv subjects

Elizabeth J. Sutton

Publications and source records attributed to Elizabeth J. Sutton.

3 recordsLinked to original sources

arXiv2026

Quantitative Chemical Exchange Saturation Transfer Imaging with Golden-Angle Radial k-Space and Locally Low-Rank Reconstruction

Chemical exchange saturation transfer magnetic resonance fingerprinting (CEST-MRF) is a promising quantitative molecular imaging technique. To reduce scan time, current CEST-MRF implementations typically use echo-planar imaging (EPI) readouts, which are prone to geometric distortion and signal dropout. In this study, we developed a motion-robust geometrically accurate CEST-MRF method using radial k-space sampling, locally low-rank reconstruction, and neural network-based quantification. The acquisition schedule was optimized using deep learning, and its accuracy was validated in numerical simulations with digital phantoms. The number of spokes per measurement was determined through simulations and in vivo ablation studies in healthy volunteers. Five healthy subjects underwent repeated scans, and regions of interest were defined for analysis. Tissue maps generated with the proposed method were compared with values obtained from nonlinear least-squares (NLS) fitting of multi-saturation-power z-spectra. Motion sensitivity and test-retest reproducibility were evaluated using the coefficient of variation (CV) and intraclass correlation coefficient (ICC). Clinical feasibility was demonstrated in a subject with a history of remote middle cerebral artery infarction. The results show that 3D quantitative CEST maps can be acquired in 11 minutes using 34 spokes per measurement. Numerical simulations yielded mean errors below 14% for all tissue parameters, while in vivo parameter estimates agreed well with both NLS-derived values and prior brain CEST-MRF studies. The mean ICC across all tissue maps was 0.92 in white matter and 0.87 in gray matter, with mean inter-subject CVs of 5.4% and 3.4%, respectively. For the radial acquisition, the mean error between motion and no-motion conditions was 8.6%. Changes in CEST-MRF tissue parameters were consistent with clinically diagnosed cystic gliosis.

physics.med-ph↗

arXiv2024

Predicting breast cancer with AI for individual risk-adjusted MRI screening and early detection

Women with an increased life-time risk of breast cancer undergo supplemental annual screening MRI. We propose to predict the risk of developing breast cancer within one year based on the current MRI, with the objective of reducing screening burden and facilitating early detection. An AI algorithm was developed on 53,858 breasts from 12,694 patients who underwent screening or diagnostic MRI and accrued over 12 years, with 2,331 confirmed cancers. A first U-Net was trained to segment lesions and identify regions of concern. A second convolutional network was trained to detect malignant cancer using features extracted by the U-Net. This network was then fine-tuned to estimate the risk of developing cancer within a year in cases that radiologists considered normal or likely benign. Risk predictions from this AI were evaluated with a retrospective analysis of 9,183 breasts from a high-risk screening cohort, which were not used for training. Statistical analysis focused on the tradeoff between number of omitted exams versus negative predictive value, and number of potential early detections versus positive predictive value. The AI algorithm identified regions of concern that coincided with future tumors in 52% of screen-detected cancers. Upon directed review, a radiologist found that 71.3% of cancers had a visible correlate on the MRI prior to diagnosis, 65% of these correlates were identified by the AI model. Reevaluating these regions in 10% of all cases with higher AI-predicted risk could have resulted in up to 33% early detections by a radiologist. Additionally, screening burden could have been reduced in 16% of lower-risk cases by recommending a later follow-up without compromising current interval cancer rate. With increasing datasets and improving image quality we expect this new AI-aided, adaptive screening to meaningfully reduce screening burden and improve early detection.

physics.med-ph↗

arXiv2022

Radiologist-level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans

Purpose: To develop a deep network architecture that would achieve fully automated radiologist-level segmentation of cancers at breast MRI. Materials and Methods: In this retrospective study, 38229 examinations (composed of 64063 individual breast scans from 14475 patients) were performed in female patients (age range, 12-94 years; mean age, 52 years +/- 10 [standard deviation]) who presented between 2002 and 2014 at a single clinical site. A total of 2555 breast cancers were selected that had been segmented on two-dimensional (2D) images by radiologists, as well as 60108 benign breasts that served as examples of noncancerous tissue; all these were used for model training. For testing, an additional 250 breast cancers were segmented independently on 2D images by four radiologists. Authors selected among several three-dimensional (3D) deep convolutional neural network architectures, input modalities, and harmonization methods. The outcome measure was the Dice score for 2D segmentation, which was compared between the network and radiologists by using the Wilcoxon signed rank test and the two one-sided test procedure. Results: The highest-performing network on the training set was a 3D U-Net with dynamic contrast-enhanced MRI as input and with intensity normalized for each examination. In the test set, the median Dice score of this network was 0.77 (interquartile range, 0.26). The performance of the network was equivalent to that of the radiologists (two one-sided test procedures with radiologist performance of 0.69-0.84 as equivalence bounds, P <= .001 for both; n = 250). Conclusion: When trained on a sufficiently large dataset, the developed 3D U-Net performed as well as fellowship-trained radiologists in detailed 2D segmentation of breast cancers at routine clinical MRI.

cs.LG↗