No abstract

• CT texture analysis is noninvasive and effective for gastric cancer. • Portal venous CT images correlated significantly with differentiation degree and Lauren classification. • Standard deviation, entropy and minimum attenuation in arterial phase reflect vascular invasion.

To achieve accurate and fast deformable image registration (DIR) for pulmonary CT, we proposed a Multi-scale DIR framework with unsupervised Joint training of Convolutional Neural Network (MJ-CNN). MJ-CNN contains three models at multi-scale levels for a coarse-to-fine DIR to avoid being trapped in a local minimum. It is trained based on image similarity and deformation vector field (DVF) smoothness, requiring no supervision of ground-truth DVF. The three models are first trained sequentially and separately for their own registration tasks, and then are trained jointly for an end-to-end optimization under the multi-scale framework. In this study, MJ-CNN was trained using public SPARE 4D-CT data. The trained MJ-CNN was then evaluated on public DIR-LAB 4D-CT dataset as well as clinical CT-to-CBCT and CBCT-to-CBCT registration. For 4D-CT interphase registration, MJ-CNN achieved comparable accuracy to conventional iteration optimizationbased methods, and showed the smallest registration errors compared to recently published deep learning-based DIR methods, demonstrating the efficacy of the proposed multi-scale joint training scheme. Besides, MJ-CNN trained using one dataset (SPARE) could generalize to a different dataset (DIR-LAB) acquired by different scanners and imaging protocols. Furthermore, MJ-CNN trained on 4D-CTs also performed well on CT-to-CBCT and CBCT-to-CBCT registration without any re-training or fine-tuning, demonstrating MJ-CNN's robustness against applications and imaging techniques. MJ-CNN took about 1.4 s for DVF estimation and required no manual-tuning of parameters during the evaluation. MJ-CNN is able to perform accurate DIR for pulmonary CT with nearly real-time speed, making it very applicable for clinical tasks.

No abstract

No abstract

No abstract

Digital tomosynthesis (DTS) has been proposed as a fast low-dose imaging technique for image-guided radiation therapy (IGRT). However, due to the limited scanning angle, DTS reconstructed by the conventional FDK method suffers from significant distortions and poor plane-to-plane resolutions without full volumetric information, which severely limits its capability for image guidance. Although existing deep learning-based methods showed feasibilities in restoring volumetric information in DTS, they ignored the inter-patient variabilities by training the model using group patients. Consequently, the restored images still suffered from blurred and inaccurate edges. In this study, we presented a DTS enhancement method based on a patient-specific deep learning model to recover the volumetric information in DTS images. The main idea is to use the patient-specific prior knowledge to train the model to learn the patient-specific correlation between DTS and the ground truth volumetric images. To validate the performance of the proposed method, we enrolled both simulated and real on-board projections from lung cancer patient data. Results demonstrated the benefits of the proposed method: (1) qualitatively, DTS enhanced by the proposed method shows CT-like high image quality with accurate and clear edges; (2) quantitatively, the enhanced DTS has low-intensity errors and high structural similarity with respect to the ground truth CT images; (3) in the tumor localization study, compared to the ground truth CT-CBCT registration, the enhanced DTS shows 3D localization errors of ≤0.7 mm and ≤1.6 mm for studies using simulated and real projections, respectively; and (4), the DTS enhancement is nearly real-time. Overall, the proposed method is effective and efficient in enhancing DTS to make it a valuable tool for IGRT applications.

BackgroundWhole-lesion apparent diffusion coefficient (ADC) histogram analysis has been introduced and proved effective in assessment of multiple tumors. However, the application of whole-volume ADC histogram analysis in gastrointestinal tumors has just started and never been reported in T and N staging of gastric cancers.MethodsEighty patients with pathologically confirmed gastric carcinomas underwent diffusion weighted (DW) magnetic resonance imaging before surgery prospectively. Whole-lesion ADC histogram analysis was performed by two radiologists independently. The differences of ADC histogram parameters among different T and N stages were compared with independent-samples Kruskal-Wallis test. Receiver operating characteristic (ROC) analysis was performed to evaluate the performance of ADC histogram parameters in differentiating particular T or N stages of gastric cancers.ResultsThere were significant differences of all the ADC histogram parameters for gastric cancers at different T (except ADCmin and ADCmax) and N (except ADCmax) stages. Most ADC histogram parameters differed significantly between T1 vs T3, T1 vs T4, T2 vs T4, N0 vs N1, N0 vs N3, and some parameters (ADC5%, ADC10%, ADCmin) differed significantly between N0 vs N2, N2 vs N3 (all P < 0.05). Most parameters except ADCmax performed well in differentiating different T and N stages of gastric cancers. Especially for identifying patients with and without lymph node metastasis, the ADC10% yielded the largest area under the ROC curve of 0.794 (95% confidence interval, 0.677–0.911). All the parameters except ADCmax showed excellent inter-observer agreement with intra-class correlation coefficients higher than 0.800.ConclusionWhole-volume ADC histogram parameters held great potential in differentiating different T and N stages of gastric cancers preoperatively.Electronic supplementary materialThe online version of this article (10.1186/s12885-017-3622-9) contains supplementary material, which is available to authorized users.