JLJiangang Liu

Jiangang Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jiangang Liu has a total of 173 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Preoperative prediction of positive surgical margins in prostate cancer using multimodal deep learning model: a multicenter study

    by Xu Fu, Jie Bao, Xiaomeng Qiao, Junkang Shen, Yueyue Zhang, Pengfei Jin, Yanting Ji, Ji Zhang, Yueting Su, Libiao Ji, et al.

  • Navigating Uncertainty in MRI Diagnosis: A Human‐ AI Collaborative Strategy for Stratifying Clinically Significant Prostate Cancer

    by Xu Fu, Jie Bao, Xiaomeng Qiao, Junkang Shen, Yueyue Zhang, Pengfei Jin, Yanting Ji, Ji Zhang, Yueting Su, Libiao Ji, et al.

    Background: Deep learning (DL) methods have shown potential for predicting clinically significant prostate cancer (csPCa), but radiologists often face challenges in effectively leveraging these techniques for csPCa prediction. Purpose: To develop an automated DL model based on biparametric‐MRI (bpMRI) and propose a human‐machine collaborative strategy for predicting csPCa. Study Type: Retrospective. Population: A total of 4305 patients were enrolled. Centers 1–2 and 4–7 comprised the training (2437 patients, mean age 68 ± 8) and the internal validation (581 patients, mean age 67 ± 8) cohorts; Centers 8–10 comprised the external validation cohort 1 (622 patients, mean age 71 ± 8), and Center 3 comprised the external validation cohort 2 (665 patients, age not available). Field Strength/Sequence: T2‐weighted imaging (T2WI) using fast or turbo spin echo and diffusion‐weighted imaging (DWI) using single‐shot echo planar imaging were acquired at 1.5 and 3 T. Assessment: A DL model (UFormer) including prostate segmentation and csPCa prediction was constructed using bpMRI. Its performance was evaluated in two external validation cohorts (EVCs) and compared with that of radiologists. Further, a UFormer‐radiologist collaborative predictive strategy was proposed. Statistical Tests: Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, DeLong test, and McNemar test. p < 0.05 was considered significant. Results: Compared with radiologists' Prostate Imaging Reporting and Data System (PI‐RADS) assessment, UFormer‐combined radiologists showed significantly higher AUC and accuracy of 0.918 ± 0.012 and 0.857 ± 0.014 for the less‐experienced radiologists, 0.931 ± 0.010 and 0.870 ± 0.014 for the more‐experienced radiologists, respectively, due to greatly increasing specificity by 121.7% for the less‐experienced radiologists and 60.2% for the more‐experienced radiologists in EVC1. Additionally, UFormer identified 86.5% and 93.9% of non‐csPCa patients, who had been interpreted originally as PI‐RADS 3 by more‐ and less‐experienced radiologists, respectively. Data Conclusions: UFormer enhanced the predictive performance of radiologists and narrowed performance gaps between experience levels. The UFormer‐radiologist collaborative paradigm combined model advantages with PI‐RADS assessment, providing a strategy for clinical application. Evidence Level: 4. Technical Efficacy: Stage 2.

  • DDMPI: Diffusion Denoising for Magnetic Particle Imaging at the Low Concentration

    by Lishuang Guo, Yu An, Chenbin Ma, Jiaqian Li, Zhen Dong, Jie Tian, Jiangang Liu

    Magnetic particle imaging (MPI) has demonstrated its advantages of high sensitivity and temporal resolution in various preclinical applications. However, during the imaging process, the signal is susceptible to different noises, resulting in severe stripe artifacts in reconstructed MPI images. This phenomenon will be further aggravated in scenarios with low-concentration particles, which is a standard practice in biological applications, thereby seriously hindering the identification of key information. To solve this problem, we propose a joint optimization approach called diffusion denoising model for MPI (DDMPI) that integrates diffusion model with Transformer to remove the artifacts directly from MPI images obtained in the low-concentration scenarios. In DDMPI, a latent encoder generates prior features containing the relevance mapping between the contents and the artifacts within MPI images, and a conditional latent diffusion model optimizes these prior features. A U-shape Transformer module incorporates the prior features by a hierarchical integration module and utilizes a strip-self-attention module to capture the spatial distribution of the artifacts. Ablation experiments demonstrate the effectiveness of these modules in DDMPI. Extensive experiments, including simulation, phantom and in vivo experiments, demonstrate that DDMPI effectively removes artifacts and recovers fine details. Additionally, DDMPI is independent of the primary image reconstruction methods of various scanning devices. Thus, DDMPI can be not only practically applied to in vivo imaging but also flexibly combined with various existing MPI devices to effectively improve the imaging quality and provide critical information about diseases.


  • Open Access

    Exploring the diagnostic potential: magnetic particle imaging for brain diseases

    by Li-Shuang Guo, Yu An, Ze-Yu Zhang, Chen-Bin Ma, Jia-Qian Li, Zhen Dong, Jie Tian, Zhen-Yu Liu, Jian-Gang Liu


  • Open Access

    Early prediction of neoadjuvant therapy response in breast cancer using MRI-based neural networks: data from the ACRIN 6698 trial and a prospective Chinese cohort

    by Siyao Du, Wanfang Xie, Si Gao, Ruimeng Zhao, Huidong Wang, Jie Tian, Jiangang Liu, Zhenyu Liu, Lina Zhang

    Early prediction of treatment response to neoadjuvant therapy (NAT) in breast cancer patients can facilitate timely adjustment of treatment regimens. We aimed to develop and validate a MRI-based enhanced self-attention network (MESN) for predicting pathological complete response (pCR) based on longitudinal images at the early stage of NAT. Two imaging datasets were utilized: a subset from the ACRIN 6698 trial (dataset A, n = 227) and a prospective collection from a Chinese hospital (dataset B, n = 245). These datasets were divided into three cohorts: an ACRIN 6698 training cohort (n = 153) from dataset A, an ACRIN 6698 test cohort (n = 74) from dataset A, and an external test cohort (n = 245) from dataset B. The proposed MESN allowed for the integration of multiple timepoint features and extraction of dynamic information from longitudinal MR images before and after early-NAT. We also constructed the Pre model based on pre-NAT MRI features. Clinicopathological characteristics were added to these image-based models to create integrated models (MESN-C and Pre-C), and their performance was evaluated and compared. The MESN-C yielded area under the receiver operating characteristic curve (AUC) values of 0.944 (95% CI: 0.906 − 0.973), 0.903 (95%CI: 0.815 − 0.965), and 0.861 (95%CI: 0.811 − 0.906) in the ACRIN 6698 training, ACRIN 6698 test and external test cohorts, respectively, which were significantly higher than those of the clinical model (AUC: 0.720 [95%CI: 0.587 − 0.842], 0.738 [95%CI: 0.669 − 0.796] for the two test cohorts, respectively; p < 0.05) and Pre-C (AUC: 0.697 [95%CI: 0.554 − 0.819], 0.726 [95%CI: 0.666 − 0.797] for the two test cohorts, respectively; p < 0.05). High AUCs of the MESN-C maintained in the ACRIN 6698 standard (AUC = 0.853 [95%CI: 0.676 − 1.000]) and experimental (AUC = 0.905 [95%CI: 0.817 − 0.993]) subcohorts, and the interracial and external subcohort (AUC = 0.861 [95%CI: 0.811 − 0.906]). Moreover, the MESN-C increased the positive predictive value from 48.6 to 71.3% compared with Pre-C model, and maintained a high negative predictive value (80.4–86.7%). The MESN-C using longitudinal multiparametric MRI after a short-term therapy achieved favorable performance for predicting pCR, which could facilitate timely adjustment of treatment regimens, increasing the rates of pCR and avoiding toxic effects. Trial registration at https://www.chictr.org.cn/ . Registration number: ChiCTR2000038578, registered September 24, 2020.


  • Radiomics based on preoperative magnetic resonance imaging predict the cell lineages of nonfunctioning pituitary neuroendocrine tumors

    by Xuening Zhao, Xu Fu, Xiaochen Wang, Sihui Wang, Lingxu Chen, Mengyuan Yuan, Jiangang Liu, Shengjun Sun

    Objective Accurate preoperative predict the cell lineages of non-functioning pituitary neuroendocrine tumors (NFPitNETs) can help neurosurgeons develop treatment strategies. This study aimed to predict the three cell lineages of NFPitNETs using radiomics based on MRI. Methods NFPitNETs patients from January 2019 and January 2023 were retrospectively enrolled, with adenoma lineages including SF-1 (n = 239), TPIT (n = 204), and PIT-1 (n = 100). Sagittal T1-weighted images (T1WI), contrast-enhanced (CE) sagittal T1WI, CE-coronal T1WI, and axial T2WI were obtained for tumor segmentation on ITK-SNAP. Pyradiomics was used for features extracted. Variance threshold method, t-test, and LASSO were used for feature selection. Support vector machine (SVM) and random forest (RF) were used to predict the three-lineages adenomas based on their radiomics and semantic features. Receiver operating characteristic curve—area under the curve (ROC-AUC) analysis was used to assess the model’s performance. Results A total of 543 patients with NFPitNETs (mean age, 49.46 ± 12.39) were included. Patients with SF-1 adenomas had a higher mean age than those with TPIT and PIT-1 adenomas (52.84 ± 11.56 vs 49.94 ± 10.54 vs 40.42 ± 13.41, p < 0.001). Female patients are more common in TPIT and PIT-1 adenomas than SF-1 ones (96.57% vs 69% vs 41%, p < 0.001). The SVM model incorporating semantic and radiomics features based on CE-coronal T1WI performed the best, with a macro-average AUC of 0.899. CE-coronal T1WI were the best among all the MR sequences for predicting the cell lineages of NFPitNETs. Conclusion Radiomics based on preoperative MRI can help predict the cell lineages of NFPitNETs, which prove useful to neurosurgeons to develop treatment strategies.


  • Open Access

    3D-AttenNet model can predict clinically significant prostate cancer in PI-RADS category 3 patients: a retrospective multicenter study

    by Jie Bao, Litao Zhao, Xiaomeng Qiao, Zhenkai Li, Yanting Ji, Yueting Su, Libiao Ji, Junkang Shen, Jiangang Liu, Jie Tian, et al.

    Purposes: The presence of clinically significant prostate cancer (csPCa) is equivocal for patients with prostate imaging reporting and data system (PI-RADS) category 3. We aim to develop deep learning models for re-stratify risks in PI-RADS category 3 patients. Methods: This retrospective study included a bi-parametric MRI of 1567 consecutive male patients from six centers (Centers 1–6) between Jan 2015 and Dec 2020. Deep learning models with double channel attention modules based on MRI (AttenNet) for predicting PCa and csPCa were constructed separately. Each model was first pretrained using 1144 PI-RADS 1–2 and 4–5 images and then retrained using 238 PI-RADS 3 images from three training centers (centers 1–3), and tested using 185 PI-RADS 3 images from the other three testing centers (centers 4–6). Results: Our AttenNet models achieved excellent prediction performances in testing cohort of center 4–6 with the area under the receiver operating characteristic curves (AUC) of 0.795 (95% CI: [0.700, 0.891]), 0.963 (95% CI: [0.915, 1]) and 0.922 (95% CI: [0.810, 1]) in predicting PCa, and the corresponding AUCs were 0.827 (95% CI: [0.703, 0.952]) and 0.926 (95% CI: [0.846, 1]) in predicting csPCa in testing cohort of center 4 and center 5. In particular, 71.1% to 92.2% of non-csPCa patients were identified by our model in three testing cohorts, who can spare from invasive biopsy or RP procedure. Conclusions: Our model offers a noninvasive screening clinical tool to re-stratify risks in PI-RADS 3 patients, thereby reducing unnecessary invasive biopsies and improving the effectiveness of biopsies. Critical relevance statement: The deep learning model with MRI can help to screen out csPCa in PI-RADS category 3. Key Points: AttenNet models included channel attention and soft attention modules. 71.1–92.2% of non-csPCa patients were identified by the AttenNet model. The AttenNet models can be a screen clinical tool to re-stratify risks in PI-RADS 3 patients. Graphical


  • Open Access

    Radiomics for differential diagnosis of Bosniak II-IV renal masses via CT imaging

    by Xun Zhao, Ye Yan, Wanfang Xie, Zijian Qin, Litao Zhao, Cheng Liu, Shudong Zhang, Jiangang Liu, Lulin Ma

    The management of complex renal cysts is guided by the Bosniak classification system, which may be inadequate for risk stratification of patients to determine the appropriate intervention. Radiomics models based on CT imaging may provide additional useful information. A total of 322 patients with Bosniak II-IV cysts were included in the study from January 2010 to December 2019. Contrast-enhanced CT scans were performed on all patients. ITK-snap was used for segmentation, and the PyRadiomics 3.0.1 package was used for feature extraction. The radiomics features were screened via the least absolute shrinkage and selection operator (LASSO) regression method. After feature selection, a logistic regression (LR) model, support vector machine (SVM) model and random forest (RF) model were constructed. In the present study, 217 benign renal cysts (67.4%) and 105 cystic renal cell carcinomas (32.6%) were identified. According to the Bosniak classification, the sample included 179 (55.6%) Bosniak II cysts, 38 (11.8%) Bosniak IIF cysts, 44 (13.7%) Bosniak III cysts and 61 (18.9%) Bosniak IV cysts. A total of 1334 radiomics features were extracted from both unenhanced and cortical CT scans. After LASSO regression, all the models (LR, SVM and RF) showed satisfactory discrimination and reliability in both unenhanced and cortical CT scans (AUC > 0.950). In the Bosniak IIF-III subgroup analysis, the diagnostic accuracy of the LR model was very low for both the unenhanced and cortical scans. In contrast, the SVM model and RF model showed excellent and stable performance in classifying Bosniak IIF-III cysts. The AUCs of the models were all > 0.85, with a maximum of 0.941. The sensitivity, specificity, accuracy, and AUC of the RF model were 0.889, 0.913, 0.902, and 0.941, respectively. Our data indicate that radiomics models can effectively distinguish between cystic renal cell carcinoma (cRCC) and complex renal cysts (Bosniak II-IV). Radiomics models may still have high diagnostic accuracy even for Bosniak IIF-III cysts that are clinically difficult to distinguish. However, external validation of these findings is still needed.


  • Open Access

    Automatic knee osteoarthritis severity grading based on X-ray images using a hierarchical classification method

    by Jian Pan, Yuangang Wu, Zhenchao Tang, Kaibo Sun, Mingyang Li, Jiayu Sun, Jiangang Liu, Jie Tian, Bin Shen

    This study aims to develop a hierarchical classification method to automatically assess the severity of knee osteoarthritis (KOA). This retrospective study recruited 4074 patients. Clinical diagnostic indicators and clinical diagnostic processes were applied to develop a hierarchical classification method that involved four sub-task classifications. These four sub-task classifications were the classification of Kellgren-Lawrence (KL) grade 0–2 and KL grade 3–4, KL grade 3 and KL grade 4, KL grade 0 and KL grade 1–2, and KL grade 1 and KL grade 2, respectively. To extract the features of clinical diagnostic indicators, four U-Net models were first used to segment the total joint space (TJS), the lateral joint space (LJS), the medial joint space (MJS), and osteophytes, respectively. Based on the segmentation result of TJS, the region of knee subchondral bone was generated. Then, geometric features were extracted based on segmentation results of the LJS, MJS, TJS, and osteophytes, while radiomic features were extracted from the knee subchondral bone. Finally, the geometric features, radiomic features, and combination of geometric features and radiomic features were used to construct the geometric model, radiomic model, and combined model in KL grading, respectively. A strict decision strategy was used to evaluate the performance of the hierarchical classification method in all X-ray images of testing cohort. The U-Net models achieved relatively satisfying performances in the segmentation of the TJS, the LJS, the MJS, and the osteophytes with the dice similarity coefficient of 0.88, 0.86, 0.88, and 0.64 respectively. The combined models achieved the best performance in KL grading. The accuracy of combined models was 98.50%, 81.65%, 82.07%, and 74.10% in the classification of KL grade 0–2 and KL grade 3–4, KL grade 3 and KL grade 4, KL grade 0 and KL grade 1–2, and KL grade 1 and KL grade 2, respectively. For all X-ray images of the testing cohort, the accuracy of the hierarchical classification method was 65.98%. The hierarchical classification method developed in the current study is a feasible approach to assess the severity of KOA.