Purpose Accurate and timely organs‐at‐risk (OARs) segmentation is key to efficient and high‐quality radiation therapy planning. The purpose of this work is to develop a deep learning‐based method to automatically segment multiple thoracic OARs on chest computed tomography (CT) for radiotherapy treatment planning. Methods We propose an adversarial training strategy to train deep neural networks for the segmentation of multiple organs on thoracic CT images. The proposed design of adversarial networks, called U‐Net‐generative adversarial network (U‐Net‐GAN), jointly trains a set of U‐Nets as generators and fully convolutional networks (FCNs) as discriminators. Specifically, the generator, composed of U‐Net, produces an image segmentation map of multiple organs by an end‐to‐end mapping learned from CT image to multiorgan‐segmented OARs. The discriminator, structured as an FCN, discriminates between the ground truth and segmented OARs produced by the generator. The generator and discriminator compete against each other in an adversarial learning process to produce the optimal segmentation map of multiple organs. Our segmentation results were compared with manually segmented OARs (ground truth) for quantitative evaluations in geometric difference, as well as dosimetric performance by investigating the dose‐volume histogram in 20 stereotactic body radiation therapy (SBRT) lung plans. Results This segmentation technique was applied to delineate the left and right lungs, spinal cord, esophagus, and heart using 35 patients’ chest CTs. The averaged dice similarity coefficient for the above five OARs are 0.97, 0.97, 0.90, 0.75, and 0.87, respectively. The mean surface distance of the five OARs obtained with proposed method ranges between 0.4 and 1.5 mm on average among all 35 patients. The mean dose differences on the 20 SBRT lung plans are −0.001 to 0.155 Gy for the five OARs. Conclusion We have investigated a novel deep learning‐based approach with a GAN strategy to segment multiple OARs in the thorax using chest CT images and demonstrated its feasibility and reliability. This is a potentially valuable method for improving the efficiency of chest radiotherapy treatment planning.

The authors propose an iterative image-domain decomposition method for DECT. The method combines noise suppression and material decomposition into an iterative process and achieves both goals simultaneously. By exploring the full variance-covariance properties of the decomposed images and utilizing the edge predetection, the proposed algorithm shows superior performance on noise suppression with high image spatial resolution and low-contrast detectability.

No abstract

No abstract

Chromosomal deletion is frequent at the region between BRCA2 and RB1 in the q14 band of chromosome 13 (13q14) in human cancers, including prostate cancer, suggesting the presence of a tumor suppressor gene. However, no reasonable candidate has been identified thus far. In this study, we did genetic and functional analyses to identify and evaluate the 13q14 tumor suppressor gene. Hemizygous and homozygous deletions in cell lines/xenografts of prostate cancer mapped the deletion locus to 919 kb, which harbors only one known gene, the FOXO1A transcription factor. Deletion at FOXO1A was detected in 31% to 34% in 6 cell lines, 27 xenografts, and 72 clinical specimens of prostate cancer, and was significantly more frequent than deletions at surrounding loci. In addition, FOXO1A was transcriptionally down-regulated in some prostate cancers. Functionally, ectopic expression of FOXO1A inhibited, and its knockdown promoted, cell proliferation or survival. Furthermore, FOXO1A inhibited androgen-and androgen receptor-mediated gene regulation and cell proliferation. Consistent with the understanding of FOXO1A biology, our findings suggest that FOXO1A is the 13q14 tumor suppressor gene, at least in prostate cancer. As a wellestablished negative effector in the phosphatidylinositol 3-kinase/AKT signaling pathway, FOXO1A inactivation in cancer would impair the therapeutic effect of phosphatidylinositol 3-kinase/AKT inhibitors in cancer treatment. (Cancer Res 2006; 66(14): 6998-7006)

Deriving accurate structural maps for attenuation correction (AC) of whole-body PET remains challenging. Common problems include truncation, inter-scan motion, and erroneous transformation of structural voxel-intensities to PET μ-map values (e.g. modality artifacts, implanted devices, or contrast agents). This work presents a deep learning-based attenuation correction (DL-AC) method to generate attenuation corrected PET (AC PET) from nonattenuation corrected PET (NAC PET) images for whole-body PET imaging, without the use of structural information. 3D patch-based cycle-consistent generative adversarial networks (CycleGAN) is introduced to include a NAC-PET-to-AC-PET mapping and an inverse mapping from AC PET to NAC PET, which constrains the NAC-PET-to-AC-PET mapping to be closer to a one-to-one mapping. Since NAC PET images share similar anatomical structures to the AC PET image but lack contrast information, residual blocks, which aim to learn the differences between NAC PET and AC PET, are used to construct generators of CycleGAN. After training, patches from NAC PET images were fed into NAC-PET-to-AC-PET mapping to generate DL-AC PET patches. DL-AC PET image was then reconstructed through patch fusion. We conducted a retrospective study on 55 datasets of whole-body PET/CT scans to evaluate the proposed method. In comparing DL-AC PET with original AC PET, average mean error (ME) and normalized mean square error (NMSE) of the whole-body were 0.62%±1.26% and 0.72%±0.34%. The average intensity changes measured on sequential PET images with AC and DL-AC on both normal tissues and lesions differ less than 3%. There was no significant difference of the intensity changes between AC and DL-AC PET, which demonstrate DL-AC PET images generated by the proposed DL-AC method can reach a same level to that of original AC PET images. The method demonstrates excellent quantification accuracy and reliability and is applicable to PET data collected on a single PET scanner or hybrid platform (PET/CT or PET/MRI).

Mounting evidence suggests that the gut microbiota contribute to colorectal cancer (CRC) tumorigenesis, in which the symbiotic Fusobacterium nucleatum (Fn) selectively increases immunosuppressive myeloid-derived suppressor cells (MDSCs) to hamper the host’s anticancer immune response. Here, a specifically Fn-binding M13 phage was screened by phage display technology. Then, silver nanoparticles (AgNP) were assembled electrostatically on its surface capsid protein (M13@Ag) to achieve specific clearance of Fn and remodel the tumor-immune microenvironment. Both in vitro and in vivo studies showed that of M13@Ag treatment could scavenge Fn in gut and lead to reduction in MDSC amplification in the tumor site. In addition, antigen-presenting cells (APCs) were activated by M13 phages to further awaken the host immune system for CRC suppression. M13@Ag combined with immune checkpoint inhibitors (α-PD1) or chemotherapeutics (FOLFIRI) significantly prolonged overall mouse survival in the orthotopic CRC model.

To engineer patient‐derived cells into therapy‐purposed biologics is a promising solution to realize personalized treatments. Without using gene‐editing technology, a live cell‐typed therapeutic is engineered for tumor treatment by artificially reprogramming macrophages with hyaluronic acid‐decorated superparamagnetic iron oxide nanoparticles (HIONs). This nanoparticle‐assisted cell‐reprogramming strategy demonstrates profound advantages, due to the combined contributions from the biological regulation of HIONs and the intrinsic nature of macrophages. Firstly, the reprogrammed macrophages present a substantial improvement in their innate capabilities, such as more effective tumor targeting and more efficient generation of bioactive components (e.g., reactive oxygen species, bioactive cytokines) to suppress tumor growth. Furthermore, this cell therapeutic exhibits cytostatic/proapoptotic effects specific to cancer cells. Secondly, HIONs enable macrophages more resistant to the intratumoral immunosuppressive environment. Thirdly, the macrophages are endowed with a strong ability to prime in situ protumoral M2 macrophages into antitumor M1 phenotype in a paracrine‐like manner. Consequently, a synergistic tumor‐inhibition effect is achieved. This study shows that engineering nanomaterial‐reprogrammed live cells as therapeutic biologics may be a more preferable option to the commonly used approaches where nanomaterials are administrated to induce bioresponse of certain cells in vivo.