Learning to Infer Inner-Body Under Clothing From Monocular Video.

Accurately estimating the human inner-body under clothing is very important for body measurement, virtual try-on and VR/AR applications. In this article, we propose the first method to allow everyone to easily reconstruct their own 3D inner-body under daily clothing from a self-captured video with the mean reconstruction error of 0.73cm within 15s. This avoids privacy concerns arising from nudity or minimal clothing. Specifically, we propose a novel two-stage framework with a Semantic-guided Undressing Network (SUNet) and an Intra-Inter Transformer Network (IITNet). SUNet learns semantically related body features to alleviate the complexity and uncertainty of directly estimating 3D inner-bodies under clothing. IITNet reconstructs the 3D inner-body model by making full use of intra-frame and inter-frame information, which addresses the misalignment of inconsistent poses in different frames. Experimental results on both public datasets and our collected dataset demonstrate the effectiveness of the proposed method. The code and dataset is available for research purposes at http://cic.tju.edu.cn/faculty/likun/projects/Inner-Body.

Value of 4D CT Angiography Combined with Whole Brain CT Perfusion Imaging Feature Analysis under Deep Learning in Imaging Examination of Acute Ischemic Stroke.

This study was aimed at investigating the application of deep learning 4D computed tomography angiography (CTA) combined with whole brain CT perfusion (CTP) imaging in acute ischemic stroke (AIS). A total of 46 patients with ischemic stroke were selected from the hospital as the research objects. Image quality was analyzed after the 4D CTA images were obtained by perfusion imaging. The results showed that whole brain perfusion imaging based on FCN can achieve automatic segmentation. FCN segmentation results took a short time, an average of 2-3 seconds, and the Dice similarity coefficient (DSC) and mean absolute distance (MAD) were lower than those of other algorithms. FCN segmentation distance was 17.87. The parameters of the central area, the peripheral area, and the mirror area of the perfusion map were compared, and the mean transit time (MTT) and time to peak (TTP) of the lesion were prolonged compared with the mirror area. Moreover, the peripheral CBV was increased, and the differences between the parameters were significant (P < 0.05). In conclusion, using the deep learning FCN network, 4D CTA combined with whole brain CTP imaging technology can effectively analyze the perfusion state and achieve clinically personalized treatment.

THE USE OF LOW-DOSE CT WITH ADAPTIVE STATISTICAL ITERATIVE RECONSTRUCTION FOR THE DIAGNOSIS OF URINARY CALCULI.

This study aimed to explore the diagnosis of urinary calculi through utilisation of low-dose computed tomography (LDCT) with adaptive statistical iterative reconstruction (ASIR). Data from 140 patients that had undergone pathological or operative diagnosis with urinary calculi were analysed. Patients were divided into two groups based on whether they received conventional-dose computed tomography (CDCT) or LDCT, respectively, followed by filtered back projection or ASIR. Average CDCT radiation doses were roughly 4-fold higher than LDCT doses. Despite this difference, there were no significant differences between groups with respect to stone size or location, image quality (P = 0.261), image noise (P = 0.153) and diagnostic efficacy (P = 0.371). LDCT is an effective approach to urinary calculi diagnosis, performing to ASIR while decreasing the effective radiation dose, improving the safety of this procedure.

Effectiveness of the conservative therapy for spontaneous isolated iliac artery dissection: Preliminary results.

Purpose To investigate the effectiveness of conservative therapy for spontaneous isolated iliac artery dissection (SIIAD). Methods From February 2006 to May 2016, all patients with SIIAD were included and analyzed. The diagnosis of SIIAD was made based on contrast-enhanced computed tomography. The imaging morphologic characteristics, treatments, and outcomes for each patient were analyzed. Results A total of 11 patients (10 male and 1 female, age 71.1 ± 7.8 years) were included in this study. Of the 11 patients, 8 patients were asymptomatic and the SIIADs were discovered during the course of computed tomography for other diseases, and 3 patients were symptomatic. Initial computed tomography findings: iliac arterial calcification ( n = 7); compression of the true lumen ( n = 6), with stenosis of the true lumen from 25% to 50% ( n = 3) and ≥ 50% ( n = 3); thrombosed false lumen partially ( n = 4), and no thrombosis in false lumen ( n = 7); dissecting aneurysm ( n = 11); entry points ( n = 11); re-entry points ( n = 1); no dissection extended to the internal iliac or common femoral artery. Conservative treatment was performed in six patients, and the remaining five patients need no treatment. During 23.3 ± 14.2 months follow-up, none recurred symptoms and signs of symptomatic SIIAD; partial remodeling of SIIAD was achieved in four patients, and the remaining seven patients with no change of SIIAD. There was no presence of new false lumen enhancement on contrast-enhanced computed tomography during follow-up. Conclusions SIIAD without arterial rupture or lower limb necrosis can be safely treated with conservative therapy.