Search

To simultaneously register all the longitudinal images acquired in a radiotherapy course for analyzing patients' anatomy changes for adaptive radiotherapy (ART).To address the unique needs of ART, we designed Seq2Morph, a novel deep learning-based deformable image registration (DIR) network. Seq2Morph was built upon VoxelMorph which is a general-purpose framework for learning-based image registration. The major upgrades are (1) expansion of inputs to all weekly cone-beam computed tomography (CBCTs) acquired for monitoring treatment responses throughout a radiotherapy course, for registration to their planning CT; (2) incorporation of 3D convolutional long short-term memory between the encoder and decoder of VoxelMorph, to parse the temporal patterns of anatomical changes; and (3) addition of bidirectional pathways to calculate and minimize inverse consistency errors (ICEs). Longitudinal image sets from 50 patients, including a planning CT and 6 weekly CBCTs per patient, were utilized for network training and cross-validation. The outputs were deformation vector fields for all the registration pairs. The loss function was composed of a normalized cross-correlation for image intensity similarity, a DICE for contour similarity, an ICE, and a deformation regularization term. For performance evaluation, DICE and Hausdorff distance (HD) for the manual versus predicted contours of tumor and esophagus on weekly basis were quantified and further compared with other state-of-the-art algorithms, including conventional VoxelMorph and large deformation diffeomorphic metric mapping (LDDMM).Visualization of the hidden states of Seq2Morph revealed distinct spatiotemporal anatomy change patterns. Quantitatively, Seq2Morph performed similarly to LDDMM, but significantly outperformed VoxelMorph as measured by GTV DICE: (0.799±0.078, 0.798±0.081, and 0.773±0.078), and 50% HD (mm): (0.80±0.57, 0.88±0.66, and 0.95±0.60). The per-patient inference of Seq2Morph took 22 s, much less than LDDMM (∼30 min).Seq2Morph can provide accurate and fast DIR for longitudinal image studies by exploiting spatial-temporal patterns. It closely matches the clinical workflow and has the potential to serve both online and offline ART.

Kinesin family member 18B (KIF18B) is a new tumor-associated protein that contributes to the carcinogenesis of multiple malignancies. However, the detailed relevance of KIF18B in breast cancer has not been fully elucidated. This work aimed was to evaluate a possible relationship between KIF18B and breast cancer progression. Our findings show KIF18B is increased in breast cancer and demonstrate that high KIF18B level predicts a reduced survival rate. Cellular functional studies revealed that knockdown of KIF18B markedly reduces the proliferation, invasion, and epithelial-mesenchymal transition of breast cancer cells and enhances their chemosensitivity toward doxorubicin. Further studies showed that KIF18B modulates the level of phospho-Akt, phospho-glycogen synthase kinase-3β, and β-catenin. Notably, suppression of Akt abolished KIF18B-overexpression-induced increases in activation of Wnt/β-catenin pathway. In addition, re-expression of β-catenin reversed KIF18B-silencing-induced cancer-promoting effect. In vivo animal experiments elucidated that knockdown of KIF18B significantly weakened the tumorigenicity of breast cancer cells. Taken together, data of this study illustrate that KIF18B exerts a potential cancer-promoting function in breast cancer via enhancement of Wnt/β-catenin pathway through modulation of the Akt/GSK-3β axis.

Purpose To evaluate pix2pix and CycleGAN and to assess the effects of multiple combination strategies on accuracy for patch-based synthetic computed tomography (sCT) generation for magnetic resonance (MR)-only treatment planning in head and neck (HN) cancer patients. Materials and methods Twenty-three deformably registered pairs of CT and mDixon FFE MR datasets from HN cancer patients treated at our institution were retrospectively analyzed to evaluate patch-based sCT accuracy via the pix2pix and CycleGAN models. To test effects of overlapping sCT patches on estimations, we (a) trained the models for three orthogonal views to observe the effects of spatial context, (b) we increased effective set size by using per-epoch data augmentation, and (c) we evaluated the performance of three different approaches for combining overlapping Hounsfield unit (HU) estimations for varied patch overlap parameters. Twelve of twenty-three cases corresponded to a curated dataset previously used for atlas-based sCT generation and were used for training with leave-two-out cross-validation. Eight cases were used for independent testing and included previously unseen image features such as fused vertebrae, a small protruding bone, and tumors large enough to deform normal body contours. We analyzed the impact of MR image preprocessing including histogram standardization and intensity clipping on sCT generation accuracy. Effects of mDixon contrast (in-phase vs water) differences were tested with three additional cases. The sCT generation accuracy was evaluated using mean absolute error (MAE) and mean error (ME) in HU between the plan CT and sCT images. Dosimetric accuracy was evaluated for all clinically relevant structures in the independent testing set and digitally reconstructed radiographs (DRRs) were evaluated with respect to the plan CT images. Results The cross-validated MAEs for the whole-HN region using pix2pix and CycleGAN were 66.9 ± 7.3 vs 82.3 ± 6.4 HU, respectively. On the independent testing set with additional artifacts and previously unseen image features, whole-HN region MAEs were 94.0 ± 10.6 and 102.9 ± 14.7 HU for pix2pix and CycleGAN, respectively. For patients with different tissue contrast (water mDixon MR images), the MAEs increased to 122.1 ± 6.3 and 132.8 ± 5.5 HU for pix2pix and CycleGAN, respectively. Our results suggest that combining overlapping sCT estimations at each voxel reduced both MAE and ME compared to single-view non-overlapping patch results. Absolute percent mean/max dose errors were 2% or less for the PTV and all clinically relevant structures in our independent testing set, including structures with image artifacts. Quantitative DRR comparison between planning CTs and sCTs showed agreement of bony region positions to Conclusions The dosimetric and MAE based accuracy, along with the similarity between DRRs from sCTs, indicate that pix2pix and CycleGAN are promising methods for MR-only treatment planning for HN cancer. Our methods investigated for overlapping patch-based HU estimations also indicate that combining transformation estimations of overlapping patches is a potential method to reduce generation errors while also providing a tool to potentially estimate the MR to CT aleatoric model transformation uncertainty. However, because of small patient sample sizes, further studies are required.

Emerging evidence has indicated that suppression of tumorigenicity 7-like (ST7L) is a tumour suppressor in multiple types of cancers. However, the functional involvement of ST7L has not been studied in breast cancer. In the present study, we aimed to investigate the potential biological function of ST7L in breast cancer. Herein, we found that ST7L expression was frequently downregulated in breast cancer cell lines. Functional assays revealed that ST7L overexpression significantly inhibited the proliferation and invasion of breast cancer cells, while ST7L silencing showed opposite effect. Notably, ST7L was found to decrease glycogen synthase kinase (GSK)-3β phosphorylation and downregulate active β-catenin protein expression, thereby leading to repression of β-catenin transcriptional activity. Activation of Wnt/β-catenin signalling by treatment of GSK-3β inhibitor significantly abrogated ST7L-mediated antitumour effect. Additionally, ST7L overexpression blunted the tumorigenicity of breast cancer cells in vivo in xenograft mice. Taken together, our results demonstrate that ST7L exerts antitumor function in breast cancer associated with the suppression of Wnt/β-catenin signalling, suggesting ST7L as a potential therapeutic target for breast cancer.

OBJECTIVES To investigate the feasibility of using 2-dimensional ultrasound (US) and shear wave elastography (SWE) to evaluate infants with late-referral congenital muscular torticollis (CMT). METHODS A total of 46 infants with late-referral CMT were enrolled and divided into 4 groups according to the degree of the passive range of motion (PROM) deficit in neck rotation. We introduced 6 metrics to represent the US features of the sternocleidomastoid muscle detected by 2-dimensional US and SWE studies. RESULTS There were no significant differences in the age at referral, sex, weight, or side of involvement between the 4 groups (P > .05). The thickness and shear modulus of the involved sternocleidomastoid muscle were positively correlated with the degree of the PROM deficit in neck rotation in late-referral infants with CMT (r = 0.71 and 0.82, respectively; P

Purpose To evaluate the discriminatory value of carotid artery wall thickness and elasticity for thyroid dysfunction in Hashimoto's thyroiditis (HT) patients. Methods A total of 180 female HT patients were assigned to three groups on the basis of laboratory testing: HT hyperthyroidism group (group A), HT hypothyroidism group (group B), and HT euthyroid group (group C). We used radiofrequency sonographic signal analysis for the measurement of intima-media thickness and arterial stiffness. Results Intima-media thickness was significantly higher in group A than in other groups. After stepwise variable selection, distensibility coefficient (DC), compliance coefficient, stiffness index (β), and pulse wave velocity (PWV) were selected to discriminate different thyroid hormone levels, resulting in the following discriminant function: Z1 = −0.398DC + 0.803PWV. The receiver-operator characteristic curve analysis showed that the critical points were DC = 0.022 kPa−1 and PWV = 5.36 m/s for HT hyperthyroidism, and DC = 0.016 kPa−1 and PWV = 6.875 m/s for HT hypothyroidism. Conclusions DC and PWV may be useful for the evaluation of thyroid function in HT patients. © 2016 Wiley Periodicals, Inc. J Clin Ultrasound, 2016