Jian Wu

Bio: Jian Wu is an academic researcher from Zhejiang University. The author has contributed to research in topics: Web service & Service (business). The author has an hindex of 32, co-authored 379 publications receiving 4978 citations. Previous affiliations of Jian Wu include Nanjing Medical University.

UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation

Abstract: Recently, a growing interest has been seen in deep learning-based semantic segmentation. UNet, which is one of deep learning networks with an encoder-decoder architecture, is widely used in medical image segmentation. Combining multi-scale features is one of important factors for accurate segmentation. UNet++ was developed as a modified Unet by designing an architecture with nested and dense skip connections. However, it does not explore sufficient information from full scales and there is still a large room for improvement. In this paper, we propose a novel UNet 3+, which takes advantage of full-scale skip connections and deep supervisions. The full-scale skip connections incorporate low-level details with high-level semantics from feature maps in different scales; while the deep supervision learns hierarchical representations from the full-scale aggregated feature maps. The proposed method is especially benefiting for organs that appear at varying scales. In addition to accuracy improvements, the proposed UNet 3+ can reduce the network parameters to improve the computation efficiency. We further propose a hybrid loss function and devise a classification-guided module to enhance the organ boundary and reduce the over-segmentation in a non-organ image, yielding more accurate segmentation results. The effectiveness of the proposed method is demonstrated on two datasets. The code is available at: github.com/ZJUGiveLab/UNet-Version

Sintilimab plus a bevacizumab biosimilar (IBI305) versus sorafenib in unresectable hepatocellular carcinoma (ORIENT-32): a randomised, open-label, phase 2-3 study.

Abstract: Summary Background China has a high burden of hepatocellular carcinoma, and hepatitis B virus (HBV) infection is the main causative factor. Patients with hepatocellular carcinoma have a poor prognosis and a substantial unmet clinical need. The phase 2–3 ORIENT-32 study aimed to assess sintilimab (a PD-1 inhibitor) plus IBI305, a bevacizumab biosimilar, versus sorafenib as a first-line treatment for unresectable HBV-associated hepatocellular carcinoma. Methods This randomised, open-label, phase 2–3 study was done at 50 clinical sites in China. Patients aged 18 years or older with histologically or cytologically diagnosed or clinically confirmed unresectable or metastatic hepatocellular carcinoma, no previous systemic treatment, and a baseline Eastern Cooperative Oncology Group (ECOG) performance status of 0 or 1 were eligible for inclusion. In the phase 2 part of the study, patients received intravenous sintilimab (200 mg every 3 weeks) plus intravenous IBI305 (15 mg/kg every 3 weeks). In the phase 3 part, patients were randomly assigned (2:1) to receive either sintilimab plus IBI305 (sintilimab–bevacizumab biosimilar group) or sorafenib (400 mg orally twice daily; sorafenib group), until disease progression or unacceptable toxicity. Randomisation was done using permuted block randomisation, with a block size of six, via an interactive web response system, and stratified by macrovascular invasion or extrahepatic metastasis, baseline α-fetoprotein, and ECOG performance status. The primary endpoint of the phase 2 part of the study was safety, assessed in all patients who received at least one dose of study drug. The co-primary endpoints of the phase 3 part of the study were overall survival and independent radiological review committee (IRRC)-assessed progression-free survival according to Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 in the intention-to-treat population. The study is registered with ClinicalTrials.gov , NCT03794440 . The study is closed to new participants and follow-up is ongoing for long-term outcomes. Findings Between Feb 11, 2019 and Jan 15, 2020, we enrolled 595 patients: 24 were enrolled directly into the phase 2 safety run-in and 571 were randomly assigned to sintilimab–bevacizumab biosimilar (n=380) or sorafenib (n=191). In the phase 2 part of the trial, 24 patients received at least one dose of the study drug, with an objective response rate of 25·0% (95% CI 9·8–46·7). Based on the preliminary safety and activity data of the phase 2 part, in which grade 3 or worse treatment-related adverse events occurred in seven (29%) of 24 patients, the randomised phase 3 part was started. At data cutoff (Aug 15, 2020), the median follow-up was 10·0 months (IQR 8·5–11·7) in the sintilimab–bevacizumab biosimilar group and 10·0 months (8·4–11·7) in the sorafenib group. Patients in the sintilimab–bevacizumab biosimilar group had a significantly longer IRRC-assessed median progression-free survival (4·6 months [95% CI 4·1–5·7]) than did patients in the sorafenib group (2·8 months [2·7–3·2]; stratified hazard ratio [HR] 0·56, 95% CI 0·46–0·70; p Interpretation Sintilimab plus IBI305 showed a significant overall survival and progression-free survival benefit versus sorafenib in the first-line setting for Chinese patients with unresectable, HBV-associated hepatocellular carcinoma, with an acceptable safety profile. This combination regimen could provide a novel treatment option for such patients. Funding Innovent Biologics. Translation For the Chinese translation of the abstract see Supplementary Materials section.

Sequential recommender system based on hierarchical attention network

Abstract: With a large amount of user activity data accumulated, it is crucial to exploit user sequential behavior for sequential recommendations. Conventionally, user general taste and recent demand are combined to promote recommendation performances. However, existing methods often neglect that user long-term preference keep evolving over time, and building a static representation for user general taste may not adequately reflect the dynamic characters. Moreover, they integrate user-item or itemitem interactions through a linear way which limits the capability of model. To this end, in this paper, we propose a novel two-layer hierarchical attention network, which takes the above properties into account, to recommend the next item user might be interested. Specifically, the first attention layer learns user long-term preferences based on the historical purchased item representation, while the second one outputs final user representation through coupling user long-term and short-term preferences. The experimental study demonstrates the superiority of our method compared with other state-of-the-art ones.

Camrelizumab in Combination with Apatinib in Patients with Advanced Hepatocellular Carcinoma (RESCUE): A Nonrandomized, Open-label, Phase II Trial.

Abstract: Purpose: We assessed the efficacy and safety of camrelizumab [an anti-programmed death (PD-1) mAb] plus apatinib (a VEGFR-2 tyrosine kinase inhibitor) in patients with advanced hepatocellular carcinoma (HCC). Patients and Methods: This nonrandomized, open-label, multicenter, phase II study enrolled patients with advanced HCC who were treatment-naive or refractory/intolerant to first-line targeted therapy. Patients received intravenous camrelizumab 200 mg (for bodyweight ≥50 kg) or 3 mg/kg (for bodyweight Results: Seventy patients in the first-line setting and 120 patients in the second-line setting were enrolled. As of January 10, 2020, the ORR was 34.3% [24/70; 95% confidence interval (CI), 23.3–46.6] in the first-line and 22.5% (27/120; 95% CI, 15.4–31.0) in the second-line cohort per IRC. Median progression-free survival in both cohorts was 5.7 months (95% CI, 5.4–7.4) and 5.5 months (95% CI, 3.7–5.6), respectively. The 12-month survival rate was 74.7% (95% CI, 62.5–83.5) and 68.2% (95% CI, 59.0–75.7), respectively. Grade ≥3 treatment-related adverse events (TRAE) were reported in 147 (77.4%) of 190 patients, with the most common being hypertension (34.2%). Serious TRAEs occurred in 55 (28.9%) patients. Two (1.1%) treatment-related deaths occurred. Conclusions: Camrelizumab combined with apatinib showed promising efficacy and manageable safety in patients with advanced HCC in both the first-line and second-line setting. It might represent a novel treatment option for these patients. See related commentary by Pinato et al., p. 908

Improving automatic source code summarization via deep reinforcement learning

Abstract: Code summarization provides a high level natural language description of the function performed by code, as it can benefit the software maintenance, code categorization and retrieval. To the best of our knowledge, most state-of-the-art approaches follow an encoder-decoder framework which encodes the code into a hidden space and then decode it into natural language space, suffering from two major drawbacks: a) Their encoders only consider the sequential content of code, ignoring the tree structure which is also critical for the task of code summarization; b) Their decoders are typically trained to predict the next word by maximizing the likelihood of next ground-truth word with previous ground-truth word given. However, it is expected to generate the entire sequence from scratch at test time. This discrepancy can cause an exposure bias issue, making the learnt decoder suboptimal. In this paper, we incorporate an abstract syntax tree structure as well as sequential content of code snippets into a deep reinforcement learning framework (i.e., actor-critic network). The actor network provides the confidence of predicting the next word according to current state. On the other hand, the critic network evaluates the reward value of all possible extensions of the current state and can provide global guidance for explorations. We employ an advantage reward composed of BLEU metric to train both networks. Comprehensive experiments on a real-world dataset show the effectiveness of our proposed model when compared with some state-of-the-art methods.

Acute Kidney Injury Network: report of an initiative to improve outcomes in acute kidney injury

Abstract: Acute kidney injury (AKI) is a complex disorder for which currently there is no accepted definition. Having a uniform standard for diagnosing and classifying AKI would enhance our ability to manage these patients. Future clinical and translational research in AKI will require collaborative networks of investigators drawn from various disciplines, dissemination of information via multidisciplinary joint conferences and publications, and improved translation of knowledge from pre-clinical research. We describe an initiative to develop uniform standards for defining and classifying AKI and to establish a forum for multidisciplinary interaction to improve care for patients with or at risk for AKI. Members representing key societies in critical care and nephrology along with additional experts in adult and pediatric AKI participated in a two day conference in Amsterdam, The Netherlands, in September 2005 and were assigned to one of three workgroups. Each group's discussions formed the basis for draft recommendations that were later refined and improved during discussion with the larger group. Dissenting opinions were also noted. The final draft recommendations were circulated to all participants and subsequently agreed upon as the consensus recommendations for this report. Participating societies endorsed the recommendations and agreed to help disseminate the results. The term AKI is proposed to represent the entire spectrum of acute renal failure. Diagnostic criteria for AKI are proposed based on acute alterations in serum creatinine or urine output. A staging system for AKI which reflects quantitative changes in serum creatinine and urine output has been developed. We describe the formation of a multidisciplinary collaborative network focused on AKI. We have proposed uniform standards for diagnosing and classifying AKI which will need to be validated in future studies. The Acute Kidney Injury Network offers a mechanism for proceeding with efforts to improve patient outcomes.

Radiographic Atlas of Skeletal Development of the Hand and Wrist

Abstract: The Brush Foundation studies on human growth and development, begun in 1931 and terminated in 1942, have been intensively reviewed and studied by Dr Greulich and Miss Pyle in the formulation of this Radiographic Atlas of Skeletal Development of the Hand and Wrist Serial radiographs of from 2 to 20 hand-films made at successive examinations of each of 1000 boys and girls made up the radiographic material Standards were selected that were judged to be the most representative of the central tendency or anatomic mode of each chronologic age group from birth through 18 years

Asia–Pacific clinical practice guidelines on the management of hepatocellular carcinoma: a 2017 update

Abstract: There is great geographical variation in the distribution of hepatocellular carcinoma (HCC), with the majority of all cases worldwide found in the Asia–Pacific region, where HCC is one of the leading public health problems. Since the “Toward Revision of the Asian Pacific Association for the Study of the Liver (APASL) HCC Guidelines” meeting held at the 25th annual conference of the APASL in Tokyo, the newest guidelines for the treatment of HCC published by the APASL has been discussed. This latest guidelines recommend evidence-based management of HCC and are considered suitable for universal use in the Asia–Pacific region, which has a diversity of medical environments.