Breast cancer remains a global challenge, causing over 600,000 deaths in 2018 (ref.
). To achieve earlier cancer detection, health organizations worldwide recommend screening mammography, which is ...estimated to decrease breast cancer mortality by 20-40% (refs.
). Despite the clear value of screening mammography, significant false positive and false negative rates along with non-uniformities in expert reader availability leave opportunities for improving quality and access
. To address these limitations, there has been much recent interest in applying deep learning to mammography
, and these efforts have highlighted two key difficulties: obtaining large amounts of annotated training data and ensuring generalization across populations, acquisition equipment and modalities. Here we present an annotation-efficient deep learning approach that (1) achieves state-of-the-art performance in mammogram classification, (2) successfully extends to digital breast tomosynthesis (DBT; '3D mammography'), (3) detects cancers in clinically negative prior mammograms of patients with cancer, (4) generalizes well to a population with low screening rates and (5) outperforms five out of five full-time breast-imaging specialists with an average increase in sensitivity of 14%. By creating new 'maximum suspicion projection' (MSP) images from DBT data, our progressively trained, multiple-instance learning approach effectively trains on DBT exams using only breast-level labels while maintaining localization-based interpretability. Altogether, our results demonstrate promise towards software that can improve the accuracy of and access to screening mammography worldwide.
A randomized, phase III, placebo-controlled, partially blinded clinical trial (REGAL Recent in in Glioblastoma Alone and With Lomustine) was conducted to determine the efficacy of cediranib, an oral ...pan-vascular endothelial growth factor (VEGF) receptor tyrosine kinase inhibitor, either as monotherapy or in combination with lomustine versus lomustine in patients with recurrent glioblastoma.
Patients (N = 325) with recurrent glioblastoma who previously received radiation and temozolomide were randomly assigned 2:2:1 to receive (1) cediranib (30 mg) monotherapy; (2) cediranib (20 mg) plus lomustine (110 mg/m(2)); (3) lomustine (110 mg/m(2)) plus a placebo. The primary end point was progression-free survival based on blinded, independent radiographic assessment of postcontrast T1-weighted and noncontrast T2-weighted magnetic resonance imaging (MRI) brain scans.
The primary end point of progression-free survival (PFS) was not significantly different for either cediranib alone (hazard ratio HR = 1.05; 95% CI, 0.74 to 1.50; two-sided P = .90) or cediranib in combination with lomustine (HR = 0.76; 95% CI, 0.53 to 1.08; two-sided P = .16) versus lomustine based on independent or local review of postcontrast T1-weighted MRI.
This study did not meet its primary end point of PFS prolongation with cediranib either as monotherapy or in combination with lomustine versus lomustine in patients with recurrent glioblastoma, although cediranib showed evidence of clinical activity on some secondary end points including time to deterioration in neurologic status and corticosteroid-sparing effects.
The study goal was to determine whether changes in relative cerebral blood volume (rCBV) derived from dynamic susceptibility contrast (DSC) MRI are predictive of overall survival (OS) in patients ...with recurrent glioblastoma multiforme (GBM) when measured 2, 8, and 16 weeks after treatment initiation.
Patients with recurrent GBM (37/123) enrolled in ACRIN 6677/RTOG 0625, a multicenter, randomized, phase II trial of bevacizumab with irinotecan or temozolomide, consented to DSC-MRI plus conventional MRI, 21 with DSC-MRI at baseline and at least 1 postbaseline scan. Contrast-enhancing regions of interest were determined semi-automatically using pre- and postcontrast T1-weighted images. Mean tumor rCBV normalized to white matter (nRCBV) and standardized rCBV (sRCBV) were determined for these regions of interest. The OS rates for patients with positive versus negative changes from baseline in nRCBV and sRCBV were compared using Wilcoxon rank-sum and Kaplan-Meier survival estimates with log-rank tests.
Patients surviving at least 1 year (OS-1) had significantly larger decreases in nRCBV at week 2 (P = .0451) and sRCBV at week 16 (P = .014). Receiver operating characteristic analysis found the percent changes of nRCBV and sRCBV at week 2 and sRCBV at week 16, but not rCBV data at week 8, to be good prognostic markers for OS-1. Patients with positive change from baseline rCBV had significantly shorter OS than those with negative change at both week 2 and week 16 (P = .0015 and P = .0067 for nRCBV and P = .0251 and P = .0004 for sRCBV, respectively).
Early decreases in rCBV are predictive of improved survival in patients with recurrent GBM treated with bevacizumab.
Currently, the most widely used criteria for assessing response to therapy in high-grade gliomas are based on two-dimensional tumor measurements on computed tomography (CT) or magnetic resonance ...imaging (MRI), in conjunction with clinical assessment and corticosteroid dose (the Macdonald Criteria). It is increasingly apparent that there are significant limitations to these criteria, which only address the contrast-enhancing component of the tumor. For example, chemoradiotherapy for newly diagnosed glioblastomas results in transient increase in tumor enhancement (pseudoprogression) in 20% to 30% of patients, which is difficult to differentiate from true tumor progression. Antiangiogenic agents produce high radiographic response rates, as defined by a rapid decrease in contrast enhancement on CT/MRI that occurs within days of initiation of treatment and that is partly a result of reduced vascular permeability to contrast agents rather than a true antitumor effect. In addition, a subset of patients treated with antiangiogenic agents develop tumor recurrence characterized by an increase in the nonenhancing component depicted on T2-weighted/fluid-attenuated inversion recovery sequences. The recognition that contrast enhancement is nonspecific and may not always be a true surrogate of tumor response and the need to account for the nonenhancing component of the tumor mandate that new criteria be developed and validated to permit accurate assessment of the efficacy of novel therapies. The Response Assessment in Neuro-Oncology Working Group is an international effort to develop new standardized response criteria for clinical trials in brain tumors. In this proposal, we present the recommendations for updated response criteria for high-grade gliomas.
Several factors have to be considered for implementing an accurate attenuation-correction (AC) method in a combined MR-PET scanner. In this work, some of these challenges were investigated, and an AC ...method based entirely on the MRI data obtained with a single dedicated sequence was developed and used for neurologic studies performed with the MR-PET human brain scanner prototype.
The focus was on the problem of bone-air segmentation, selection of the linear attenuation coefficient for bone, and positioning of the radiofrequency coil. The impact of these factors on PET data quantification was studied in simulations and experimental measurements performed on the combined MR-PET scanner. A novel dual-echo ultrashort echo time (DUTE) MRI sequence was proposed for head imaging. Simultaneous MR-PET data were acquired, and the PET images reconstructed using the proposed DUTE MRI-based AC method were compared with the PET images that had been reconstructed using a CT-based AC method.
Our data suggest that incorrectly accounting for the bone tissue attenuation can lead to large underestimations (>20%) of the radiotracer concentration in the cortex. Assigning a linear attenuation coefficient of 0.143 or 0.151 cm(-1) to bone tissue appears to give the best trade-off between bias and variability in the resulting images. Not identifying the internal air cavities introduces large overestimations (>20%) in adjacent structures. On the basis of these results, the segmented CT AC method was established as the silver standard for the segmented MRI-based AC method. For an integrated MR-PET scanner, in particular, ignoring the radiofrequency coil attenuation can cause large underestimations (i.e., <or=50%) in the reconstructed images. Furthermore, the coil location in the PET field of view has to be accurately known. High-quality bone-air segmentation can be performed using the DUTE data. The PET images obtained using the DUTE MRI- and CT-based AC methods compare favorably in most of the brain structures.
A DUTE MRI-based AC method considering all these factors was implemented. Preliminary results suggest that this method could potentially be as accurate as the segmented CT method and could be used for quantitative neurologic MR-PET studies.
Head motion is difficult to avoid in long PET studies, degrading the image quality and offsetting the benefit of using a high-resolution scanner. As a potential solution in an integrated MR-PET ...scanner, the simultaneously acquired MRI data can be used for motion tracking. In this work, a novel algorithm for data processing and rigid-body motion correction (MC) for the MRI-compatible BrainPET prototype scanner is described, and proof-of-principle phantom and human studies are presented.
To account for motion, the PET prompt and random coincidences and sensitivity data for postnormalization were processed in the line-of-response (LOR) space according to the MRI-derived motion estimates. The processing time on the standard BrainPET workstation is approximately 16 s for each motion estimate. After rebinning in the sinogram space, the motion corrected data were summed, and the PET volume was reconstructed using the attenuation and scatter sinograms in the reference position. The accuracy of the MC algorithm was first tested using a Hoffman phantom. Next, human volunteer studies were performed, and motion estimates were obtained using 2 high-temporal-resolution MRI-based motion-tracking techniques.
After accounting for the misalignment between the 2 scanners, perfectly coregistered MRI and PET volumes were reproducibly obtained. The MRI output gates inserted into the PET list-mode allow the temporal correlation of the 2 datasets within 0.2 ms. The Hoffman phantom volume reconstructed by processing the PET data in the LOR space was similar to the one obtained by processing the data using the standard methods and applying the MC in the image space, demonstrating the quantitative accuracy of the procedure. In human volunteer studies, motion estimates were obtained from echo planar imaging and cloverleaf navigator sequences every 3 s and 20 ms, respectively. Motion-deblurred PET images, with excellent delineation of specific brain structures, were obtained using these 2 MRI-based estimates.
An MRI-based MC algorithm was implemented for an integrated MR-PET scanner. High-temporal-resolution MRI-derived motion estimates (obtained while simultaneously acquiring anatomic or functional MRI data) can be used for PET MC. An MRI-based MC method has the potential to improve PET image quality, increasing its reliability, reproducibility, and quantitative accuracy, and to benefit many neurologic applications.
The abnormal vasculature of the tumor microenvironment supports progression and resistance to treatment. Judicious application of antiangiogenic therapy may normalize the structure and function of ...the tumor vasculature, promoting improved blood perfusion. However, direct clinical evidence is lacking for improvements in blood perfusion after antiangiogenic therapy. In this study, we used MRI to assess tumor blood perfusion in 30 recurrent glioblastoma patients who were undergoing treatment with cediranib, a pan-VEGF receptor tyrosine kinase inhibitor. Tumor blood perfusion increased durably for more than 1 month in 7 of 30 patients, in whom it was associated with longer survival. Together, our findings offer direct clinical evidence in support of the hypothesis that vascular normalization can increase tumor perfusion and help improve patient survival.
Previous research in non-human primates has shown that the superior longitudinal fascicle (SLF), a major intrahemispheric fiber tract, is actually composed of four separate components. In humans, ...only post-mortem investigations have been available to examine the trajectory of this tract. This study evaluates the hypothesis that the four subcomponents observed in non-human primates can also be found in the human brain using in vivo diffusion tensor magnetic resonance imaging (DT-MRI). The results of our study demonstrated that the four subdivisions could indeed be identified and segmented in humans. SLF I is located in the white matter of the superior parietal and superior frontal lobes and extends to the dorsal premotor and dorsolateral prefrontal regions. SLF II occupies the central core of the white matter above the insula. It extends from the angular gyrus to the caudal–lateral prefrontal regions. SLF III is situated in the white matter of the parietal and frontal opercula and extends from the supramarginal gyrus to the ventral premotor and prefrontal regions. The fourth subdivision of the SLF, the arcuate fascicle, stems from the caudal part of the superior temporal gyrus arches around the caudal end of the Sylvian fissure and extends to the lateral prefrontal cortex along with the SLF II fibers. Since DT-MRI allows the precise definition of only the stem portion of each fiber pathway, the origin and termination of the subdivisions of SLF are extrapolated from the available data in experimental material from non-human primates.