Purpose Accurate deformable registration between computed tomography (CT) and cone‐beam CT (CBCT) images of pancreatic cancer patients treated with high biologically effective radiation doses is essential to assess changes in organ‐at‐risk (OAR) locations and shapes and to compute delivered dose. This study describes the development and evaluation of a deep‐learning (DL) registration model to predict OAR segmentations on the CBCT derived from segmentations on the planning CT. Methods The DL model is trained with CT‐CBCT image pairs of the same patient, on which OAR segmentations of the small bowel, stomach, and duodenum have been manually drawn. A transformation map is obtained, which serves to warp the CT image and segmentations. In addition to a regularity loss and an image similarity loss, an OAR segmentation similarity loss is also used during training, which penalizes the mismatch between warped CT segmentations and manually drawn CBCT segmentations. At test time, CBCT segmentations are not required as they are instead obtained from the warped CT segmentations. In an IRB‐approved retrospective study, a dataset consisting of 40 patients, each with one planning CT and two CBCT scans, was used in a fivefold cross‐validation to train and evaluate the model, using physician‐drawn segmentations as reference. Images were preprocessed to remove gas pockets. Network performance was compared to two intensity‐based deformable registration algorithms (large deformation diffeomorphic metric mapping [LDDMM] and multimodality free‐form [MMFF]) as baseline. Evaluated metrics were Dice similarity coefficient (DSC), change in OAR volume within a volume of interest (enclosing the low‐dose PTV plus 1 cm margin) from planning CT to CBCT, and maximum dose to 5 cm3 of the OAR [D(5cc)]. Results Processing time for one CT‐CBCT registration with the DL model at test time was less than 5 seconds on a GPU‐based system, compared to an average of 30 minutes for LDDMM optimization. For both small bowel and stomach/duodenum, the DL model yielded larger median DSC and smaller interquartile variation than either MMFF (paired t‐test P < 10−4 for both type of OARs) or LDDMM (P < 10−3 and P = 0.03 respectively). Root‐mean‐square deviation (RMSD) of DL‐predicted change in small bowel volume relative to reference was 22% less than for MMFF (P = 0.007). RMSD of DL‐predicted stomach/duodenum volume change was 28% less than for LDDMM (P = 0.0001). RMSD of DL‐predicted D(5cc) in small bowel was 39% less than for MMFF (P = 0.001); in stomach/duodenum, RMSD of DL‐predicted D(5cc) was 18% less than for LDDMM (P < 10−3). Conclusions The proposed deep network CT‐to‐CBCT deformable registration model shows improved segmentation accuracy compared to intensity‐based algorithms and achieves an order‐of‐magnitude reduction in processing time.

We describe a dataset from patients who received ablative radiation therapy for locally advanced pancreatic cancer (LAPC), consisting of computed tomography (CT) and cone-beam CT (CBCT) images with physician-drawn organ-at-risk (OAR) contours. The image datasets (one CT for treatment planning and two CBCT scans at the time of treatment per patient) were collected from 40 patients. All scans were acquired with the patient in the treatment position and in a deep inspiration breath-hold state. Six radiation oncologists delineated the gastrointestinal OARs consisting of small bowel, stomach and duodenum, such that the same physician delineated all image sets belonging to the same patient. Two trained medical physicists further edited the contours to ensure adherence to delineation guidelines. The image and contour files are available in DICOM format and are publicly available from The Cancer Imaging Archive (https://doi.org/10.7937/TCIA.ESHQ-4D90, Version 2). The dataset can serve as a criterion standard for evaluating the accuracy and reliability of deformable image registration and auto-segmentation algorithms, as well as a training set for deep-learning-based methods.

Computed tomography (CT) is a widely used medical imaging modality for diagnosing various diseases. Among CT techniques, 4-dimensional CT perfusion (4D-CTP) of the brain is established in most centers for diagnosing strokes and is considered the gold standard for hyperacute stroke diagnosis. However, because the detrimental effects of high radiation doses from 4D-CTP may cause serious health risks in stroke survivors, our research team aimed to introduce a novel image-processing technique. Our singular value decomposition (SVD)-based image-processing technique can improve image quality, first, by separating several image components using SVD and, second, by reconstructing signal component images to remove noise, thereby improving image quality. For the demonstration in this study, 20 4D-CTP dynamic images of suspected acute stroke patients were collected. Both the images that were and were not processed via the proposed method were compared. Each acquired image was objectively evaluated using contrast-to-noise and signal-to-noise ratios. The scores of the parameters assessed for the qualitative evaluation of image quality improved to an excellent rating (p < 0.05). Therefore, our SVD-based image-denoising technique improved the diagnostic value of images by improving their quality. The denoising technique and statistical evaluation can be utilized in various clinical applications to provide advanced medical services.

In daily living, people are challenged to focus on their goal while eliminating interferences. Specifically, this study investigated the pre-frontal cortex (PFC) activity while attention control was tested using the self-made color-word interference test (CWIT) with a functional near-infrared spectroscopy device (fNIRS). Among 11 healthy Korean university students, overall the highest scores were obtained in the congruent Korean condition 1 (CKC-1) and had the least vascular response (VR) as opposed to the incongruent Korean condition 2 (IKC-2). The individual’s automatic reading response caused less brain activation while IKC-2 involves color suppression. Across the three trials per each condition, no significant differences (SD) in scores and in VR since there was no intervention did. Meanwhile, SD was observed between CKC-1 and English Congruent Condition 3 (ECC-3) across trials. However, SD was only observed on the third trial of VR. In the connectivity analysis, right and left PFC are activated on ECC-3. In CKC-1 and IKC-2, encompassing dorsomedial and dorsolateral although CKC-1 has less connection and connectivity due to less brain activation as compared. Therefore, aside from VR, brain connectivity could be identified non-invasively using fNIRS without ionizing radiation and at low-cost.

No abstract