We propose a spatial compounding technique and variational framework to improve 3D ultrasound image quality by compositing multiple ultrasound volumes acquired from different probe orientations. In ...the composite volume, instead of intensity values, we estimate a tensor at every voxel. The resultant tensor image encapsulates the directional information of the underlying imaging data and can be used to generate ultrasound volumes from arbitrary, potentially unseen, probe positions. Extending the work of Hennersperger et al., we introduce a log-Euclidean framework to ensure that the tensors are positive-definite, eventually ensuring non-negative images. Additionally, we regularise the underpinning ill-posed variational problem while preserving edge information by relying on a total variation penalisation of the tensor field in the log domain. We present results on in vivo human data to show the efficacy of the approach.
Convolutional neural networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they have not demonstrated sufficiently accurate and robust results ...for clinical use. In addition, they are limited by the lack of image-specific adaptation and the lack of generalizability to previously unseen object classes. To address these problems, we propose a novel deep learning-based framework for interactive segmentation by incorporating CNNs into a bounding box and scribble-based segmentation pipeline. We propose image-specific fine-tuning to make a CNN model adaptive to a specific test image, which can be either unsupervised (without additional user interactions) or supervised (with additional scribbles). We also propose a weighted loss function considering network and interaction-based uncertainty for the fine-tuning. We applied this framework to two applications: 2D segmentation of multiple organs from fetal MR slices, where only two types of these organs were annotated for training; and 3D segmentation of brain tumor core (excluding edema) and whole brain tumor (including edema) from different MR sequences, where only tumor cores in one MR sequence were annotated for training. Experimental results show that 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs; 2) image-specific fine-tuning with the proposed weighted loss function significantly improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.
Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have become the state-of-the-art automatic ...segmentation methods. However, fully automatic results may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentations. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose to combine user interactions with CNNs through geodesic distance transforms, and propose a resolution-preserving network that gives a better dense prediction. In addition, we integrate user interactions as hard constraints into a back-propagatable Conditional Random Field. We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains comparable and even higher accuracy with fewer user interventions and less time compared with traditional interactive methods.
Increased hepatocyte growth factor/MET signaling is associated with poor prognosis and acquired resistance to epidermal growth factor receptor (EGFR) -targeted drugs in patients with non-small-cell ...lung cancer (NSCLC). We investigated whether dual inhibition of MET/EGFR results in clinical benefit in patients with NSCLC.
Patients with recurrent NSCLC were randomly assigned at a ratio of one to one to receive onartuzumab plus erlotinib or placebo plus erlotinib; crossover was allowed at progression. Tumor tissue was required to assess MET status by immunohistochemistry (IHC). Coprimary end points were progression-free survival (PFS) in the intent-to-treat (ITT) and MET-positive (MET IHC diagnostic positive) populations; additional end points included overall survival (OS), objective response rate, and safety.
There was no improvement in PFS or OS in the ITT population (n = 137; PFS hazard ratio HR, 1.09; P = .69; OS HR, 0.80; P = .34). MET-positive patients (n = 66) treated with erlotinib plus onartuzumab showed improvement in both PFS (HR, .53; P = .04) and OS (HR, .37; P = .002). Conversely, clinical outcomes were worse in MET-negative patients treated with onartuzumab plus erlotinib (n = 62; PFS HR, 1.82; P = .05; OS HR, 1.78; P = .16). MET-positive control patients had worse outcomes versus MET-negative control patients (n = 62; PFS HR, 1.71; P = .06; OS HR, 2.61; P = .004). Incidence of peripheral edema was increased in onartuzumab-treated patients.
Onartuzumab plus erlotinib was associated with improved PFS and OS in the MET-positive population. These results combined with the worse outcomes observed in MET-negative patients treated with onartuzumab highlight the importance of diagnostic testing in drug development.
To review the evidence regarding a decrease in worldwide sperm parameters and discuss potential causative factors.
The topic of worldwide decline in sperm parameters is contentious; however, recent ...high-quality studies have demonstrated that there is indeed a decline in sperm parameters. Several retrospective and basic science studies have shown possible links for this decline in sperm parameters such as obesity, diet, and environmental toxins.
There exist substantial data to suggest a decline in sperm counts over time. Although causative factors have yet to be fully elucidated, potential causes include, increased rates of obesity, poor diet, and exposure to environmental toxins. How this decline in sperm counts reflects fertility has yet to be determined. As such, further studies are necessary to evaluate whether this decline in sperm count correlates with decreased fecundity and how to identify and mitigate potential causative factors.
PI3K-Akt-mTOR and androgen receptor (AR) signaling are commonly aberrantly activated in metastatic castration-resistant prostate cancer (mCRPC), with PTEN loss associating with poor prognosis. We ...therefore conducted a phase Ib/II study of the combination of ipatasertib, an Akt inhibitor, with the CYP17 inhibitor abiraterone in patients with mCRPC.
Patients were randomized 1:1:1 to ipatasertib 400 mg, ipatasertib 200 mg, or placebo, with abiraterone 1,000 mg orally. Coprimary efficacy endpoints were radiographic progression-free survival (rPFS) in the intent-to-treat population and in patients with PTEN-loss tumors.
rPFS was prolonged in the ipatasertib cohort versus placebo, with similar trends in overall survival and time-to-PSA progression. A larger rPFS prolongation for the combination was demonstrated in PTEN-loss tumors versus those without. The combination was well tolerated, with no treatment-related deaths.
In mCRPC, combined blockade with abiraterone and ipatasertib showed superior antitumor activity to abiraterone alone, especially in patients with PTEN-loss tumors.
.
PDF
