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 inter-phase registration, MJ-CNN achieved comparable accuracy to conventional iteration optimization-based 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.

Edges tend to be over-smoothed in total variation (TV) regularized under-sampled images. In this paper, symmetric residual convolutional neural network (SR-CNN), a deep learning based model, was proposed to enhance the sharpness of edges and detailed anatomical structures in under-sampled cone-beam computed tomography (CBCT). For training, CBCT images were reconstructed using TV-based method from limited projections simulated from the ground truth CT, and were fed into SR-CNN, which was trained to learn a restoring pattern from under-sampled images to the ground truth. For testing, under-sampled CBCT was reconstructed using TV regularization and was then augmented by SR-CNN. Performance of SR-CNN was evaluated using phantom and patient images of various disease sites acquired at different institutions both qualitatively and quantitatively using structure similarity (SSIM) and peak signal-to-noise ratio (PSNR). SR-CNN substantially enhanced image details in the TV-based CBCT across all experiments. In the patient study using real projections, SR-CNN augmented CBCT images reconstructed from as low as 120 half-fan projections to image quality comparable to the reference fully-sampled FDK reconstruction using 900 projections. In the tumor localization study, improvements in the tumor localization accuracy were made by the SR-CNN augmented images compared with the conventional FDK and TV-based images. SR-CNN demonstrated robustness against noise levels and projection number reductions and generalization for various disease sites and datasets from different institutions. Overall, the SR-CNN-based image augmentation technique was efficient and effective in considerably enhancing edges and anatomical structures in under-sampled 3D/4D-CBCT, which can be very valuable for image-guided radiotherapy.

Objective: The purpose of this work is to develop and validate a learning-based method to derive electron density from routine anatomical MRI for potential MRI-based SBRT treatment planning. Methods: We proposed to integrate dense block into cycle generative adversarial network (GAN) to effectively capture the relationship between the CT and MRI for CT synthesis. A cohort of 21 patients with co-registered CT and MR pairs were used to evaluate our proposed method by the leave-one-out cross-validation. Mean absolute error, peak signal-to-noise ratio and normalized cross-correlation were used to quantify the imaging differences between the synthetic CT (sCT) and CT. The accuracy of Hounsfield unit (HU) values in sCT for dose calculation was evaluated by comparing the dose distribution in sCT-based and CT-based treatment planning. Clinically relevant dose–volume histogram metrics were then extracted from the sCT-based and CT-based plans for quantitative comparison. Results: The mean absolute error, peak signal-to-noise ratio and normalized cross-correlation of the sCT were 72.87 ± 18.16 HU, 22.65 ± 3.63 dB and 0.92 ± 0.04, respectively. No significant differences were observed in the majority of the planning target volume and organ at risk dose–volume histogram metrics ( p > 0.05). The average pass rate of γ analysis was over 99% with 1%/1 mm acceptance criteria on the coronal plane that intersects with isocenter. Conclusion: The image similarity and dosimetric agreement between sCT and original CT warrant further development of an MRI-only workflow for liver stereotactic body radiation therapy. Advances in knowledge: This work is the first deep-learning-based approach to generating abdominal sCT through dense-cycle-GAN. This method can successfully generate the small bony structures such as the rib bones and is able to predict the HU values for dose calculation with comparable accuracy to reference CT images.

Automated medical data analysis demonstrated a significant role in modern medicine, and cancer diagnosis/prognosis to achieve highly reliable and generalizable systems. In this study, an automated breast cancer screening method in ultrasound imaging is proposed. A convolutional deep autoencoder model is presented for simultaneous segmentation and radiomic extraction. The model segments the breast lesions while concurrently extracting radiomic features. With our deep model, we perform breast lesion segmentation, which is linked to low-dimensional deep-radiomic extraction (four features). Similarly, we used high dimensional conventional imaging throughputs and applied spectral embedding techniques to reduce its size from 354 to 12 radiomics. A total of 780 ultrasound images—437 benign, 210, malignant, and 133 normal—were used to train and validate the models in this study. To diagnose malignant lesions, we have performed training, hyperparameter tuning, cross-validation, and testing with a random forest model. This resulted in a binary classification accuracy of 78.5% (65.1–84.1%) for the maximal (full multivariate) cross-validated model for a combination of radiomic groups.