Bin Liu

• PhD, Professor
• Dalian University of Technology

Recently, adversarial learning-based U-Net models have achieved encouraging performance in MRI brain tumor segmentation. However, existing works still have limitations in capturing global dependencies and inter-channel semantic information of brain tumor images. To address these issues, this work proposes a novel cycle generative adversarial Transf...

Segmenting anterior and posterior cruciate ligaments (ACL/PCL) presents challenges in medical imaging due to diverse characteristics, including size, shape, and intensity. Our study uses superpixel-based spectral clustering for knee cruciate ligament segmentation in 2D DICOM slices, renowned for generating high-quality clusters. The proposed method...

Background Accurate delineation of knee bone boundaries is crucial for computer-aided diagnosis (CAD) and effective treatment planning in knee diseases. Current methods often struggle with precise segmentation due to the knee joint’s complexity, which includes intricate bone structures and overlapping soft tissues. These challenges are further comp...

Recently, multiple instance learning (MIL) has been successfully used in weakly supervised breast cancer classification on whole‐slide imaging (WSI) and has become an important assistance for breast cancer diagnosis. However, existing MIL methods have limitations in considering the global contextual information of pathological images. Additionally,...

Objective. Brain tumor segmentation on magnetic resonance imaging (MRI) plays an important role in assisting the diagnosis and treatment of cancer patients. Recently, cascaded U-Net models have achieved excellent performance via conducting coarse-to-fine segmentation of MRI brain tumors. However, they are still restricted by obvious global and loca...

In the surgery of knee cruciate ligament repair, how to accurately and personalized obtain cruciate ligament insertion centers is the key issue and a great challenge for surgeons. Current artificial judgment is often with deviation, which increases the risk of surgical failure, complications, and the need for a second surgery. Surgical failure can...

Introduction In this paper, a semiautomatic image segmentation method for the serialized body slices of the Visible Human Project (VHP) is proposed. Methods In our method, we first verified the effectiveness of the shared matting method for the VHP slices and utilized it to segment a single image. Then, to meet the need for the automatic segmentat...

The shape of a knee prosthesis has an important impact on the effect of total knee arthroplasty. Comparing to a standard common prosthesis, the personalized prosthesis has inherent advantages. However, how to construct a personalized knee prosthesis has not been studied deeply. In this paper, we present an automatic method framework of modeling per...

Automatic sketch colorization is a challenging task that aims to generate a color image from a sketch, primarily due to its inherently ill-posed nature. While many approaches have shown promising results, two significant challenges remain: limited color patterns and a wide range of artifacts such as color bleeding and semantic inconsistencies among...

Comminuted fractures are orthopedic traumas with greater surgical difficulty. In clinical treatment, a great challenge is precise reduction of multiple broken bone fragments; Another great challenge is personalized and precise internal fixation after reduction. For these two issues, we designed an automated method framework for precise reduction an...

Recently, U-Net architecture with its strong adaptability has become prevalent in the field of MRI brain tumor segmentation. Meanwhile, researchers have demonstrated that introducing attention mechanisms, especially self-attention, into U-Net can effectively improve the performance of segmentation models. However, the self-attention has disadvantag...

Background Early detection of central nervous system (CNS) anomalies in human embryos through prenatal screening is crucial for timely intervention and improved patient outcomes. Fetal brain mid-sagittal ultrasound images (FBMUIs) play a pivotal role as a diagnostic tool for detecting structural abnormalities. However, the automatic localization an...

Drug delivery in brain has been challenging due to the existence of blood brain barrier, which prevents most drugs from entering the target site in brain. Compared to systematic drug administration, localized and site-specific drug delivery in a minimally invasive manner is effective for the treatment of brain disease. Its implementation however re...

In video action recognition, the existing methods mostly utilize global average pooling at the end of the network to aggregate spatio-temporal features of the video to generate global video representations, which are insufficient in modeling complex spatio-temporal feature distributions and capturing spatio-temporal dynamic information. To address...

For Chinaware fragments, it is difficult to assemble them directly without considering the wonderful patterns painted on them. Given the simplicity of the Chinaware designs, each object contains similar textures and patterns. Compared to the oddly diverse appliance modeling, the difference between fragments of different Chinaware is small. The frag...

Micro-hole perforation on skull is urgently desired for minimally invasive insertion of micro-tools in brain for diagnostic or treatment purpose. However, a micro drill bit would easily fracture, making it difficult to safely generate a micro-hole on the hard skull. In this study, we present a method for ultrasonic vibration assisted micro-hole per...

Automatic brain tumor segmentation on MRI is a prerequisite to provide a quantitative and intuitive assistance for clinical diagnosis and treatment. Meanwhile, 3D deep neural network related brain tumor segmentation models have demonstrated considerable accuracy improvement over corresponding 2D methodologies. However, 3D brain tumor segmentation m...

Automatic sketch colorization is a challenging task in both computer graphics and computer vision since all the color, texture, shading generation have to be created based on the abstract sketch. Besides, it is a subjective task in painting process, which needs illustrators to comprehend drawing priori (DP), such as hue variation, saturation contra...

Computer‐aided classification of pathological images is of the great significance for breast cancer diagnosis. In recent years, deep learning methods for breast cancer pathological image classification have made breakthrough progress, becoming the mainstream in this field. To capture more discriminant deep features for breast cancer pathological im...

Whole slide histopathology images (WSIs) play a crucial role in diagnosing lymph node metastasis of breast cancer, which usually lack fine-grade annotations of tumor regions and have large resolutions (typically 10^5 x 10^5 pixels). Multi-instance learning has gradually become a dominant weakly supervised learning framework for WSI classification w...

In our daily life, we prefer to describe the location of a person with semantic words such as ‘travel’, ‘cinema’ rather than geographic terminology like GPS coordinates (32°24′ 12‵ N, 2°90′ 26:5‵ E). This is because semantic places are easier to understand compared with precise geographic location. Existing methods only take text-image pairs into c...

Background: 4D ultrasound images of human fetal heart are important for medical applications such as evaluation of fetal heart function and early diagnosis of congenital heart diseases. However, due to the high noise and low contrast characteristics in fetal ultrasound images, denoising and enhancements are important. Methods: In this paper, a s...

To achieve the automatic reassembly (piecing) of utensil fragments, a fracture surface extraction method based on the learning of local geometric features (core focus) and a utensil reassembly method (secondary focus) are presented in this paper. The steps of the methodological framework are as follows. First, based on obtained 3D models of utensil...

Background: There is a great demand for the extraction of organ models from three-dimensional (3D) medical images in clinical medicine diagnosis and treatment. Objective: We aimed to aid doctors in seeing the real shape of human organs more clearly and vividly. Methods: The method uses the minimum eigenvectors of Laplacian matrix to automatica...

Extracting 3D structures from voxel based images can make doctors more directly observe the situation of the target in the clinic, making it easier for doctors to diagnose the condition and make the medicine teaching more directly and easier to understand. For this purpose, we propose a 3D volume image segmentation method based on the max-flow/min-...

Convolutional neural networks (CNNs), successfully used in a great number of medical image analysis applications, have also achieved the state-of-the-art performance in breast cancer histopathology image (BCHI) classification problem recently. However, due to the large varieties among within-class images and insufficient data volume, it is still a...

Automatic segmentation of brain tumors from magnetic resonance imaging (MRI) is a challenging task due to the uneven, irregular and unstructured size and shape of tumors. Recently, brain tumor segmentation methods based on the symmetric U-Net architecture have achieved favorable performance. Meanwhile, the effectiveness of enhancing local responses...

Brain tumor segmentation technology plays a pivotal role in the process of diagnosis and treatment of MRI brain tumors. It helps doctors to locate and measure tumors, as well as develop treatment and rehabilitation strategies. Recently, MRI brain tumor segmentation methods based on U-Net architecture have become popular as they largely improve the...

Bearings are very common mechanical components that are widely used in all kinds of machines. Currently, bearing surface defect detection is mainly completed by naked-eye observation. This manual detection mode has low reliability and is time consuming (especially for miniature bearings). In this paper, we present an automatic synthetic tiny defect...

Background In some medical applications (e.g., virtual surgery), standard human organ models are very important and useful. Now that real human body slice image sets have been collected by several countries, it is possible to obtain real standard organ models. Introduction Understanding how to abandon the traditional model construction method of P...

Embedding second-order operations into deep convolutional neural networks (CNNs) has recently shown impressive performance for a number of vision tasks. Specifically, the two-branch second-order response transform (SoRT) network introduces the element-wise product transform into intermediate layers of CNNs, which facilitates the cross-branch respon...

Background Glioma is one of the most common and aggressive primary brain tumors that endanger human health. Tumors segmentation is a key step in assisting the diagnosis and treatment of cancer disease. However, it is a relatively challenging task to precisely segment tumors considering characteristics of brain tumors and the device noise. Recently,...

As a recent research hot issue, obtaining the accurate 3 D organ models of Visible Human Project (VHP) has many significances. Therefore, how to extract the organ regions of interest (ROI) in the large-scale color slice image data set has become an urgent issue to be solved. In this paper, we propose a method framework based on OneCut algorithm and...

Background: Long bone fractures are a type of physical damage with high incidence rates that have serious impacts on the normal lives of humans. Aims: How to obtain a preoperative internal fixation plate model before cutting muscle has become a critical issue. Materials and methods: In this paper, we present a new personalized modeling system...

Objective: In this paper, a framework to visualize and model internal fixation plates is presented for computer-aided personalized and minimally invasive curved bone fracture surgery. Methods: We focus on personalized reverse reconstruction of the bone fracture plate based on three-dimensional (3D) mesh models obtained from a 3D optical scanner....

For the epilepsy disease, many studies about the thickness of cortex among various brain regions haven been implemented. However, there is few research about the cell distribution of the gray matter of adjacent gyrus and sulcus. Our studies indicate it is possible different that the thickness of the GFAP-IR interlaminar astrocytes somas between in...

Grenade throwing is a routine military training and testing subject among many armies of the world. However, the conventional manual measurement mode has many defects: poor efficiency, large training field needing and important data losing. So how to utilize simple device and simple method framework to replace the actual test procedure becomes an i...

Recently, deep hashing has achieved excellent performance in large-scale image retrieval by simultaneously learning deep features and hash function. However, state-of-the-art methods for this task have so far failed to explore feature statistics higher than first-order. To address this problem, we propose two novel deep high-order supervised hashin...

In this paper, a visualization and modeling method for the internal fixation plate in personalized and minimally invasive long bone fracture surgery is presented. This framework mainly includes six sub-steps: firstly, the Principal Component Analysis (PCA) method is used to extract the 3D axis of the broken bone; secondly, the Gauss mapping method...

Recently, second-order statistical modeling methods with convolutional features have shown impressive potential as image representation for vision tasks. Among them, bilinear convolutional neural network (B-CNN) has attracted a lot of attentions due to its simplicity and effectiveness. It captures the second-order local feature statistics via outer...

Background: For the cerebrovascular Digital Subtraction Angiography (DSA), how to restrain the patient motion artifact to improve the quality of subtraction image has an important effect on the clinical diagnosis. Methods: Currently, image registration is the main way to extract the blood vessels. However, there is usually massive calculation in th...

Currently, high-speed cameras has been a very common equipment in many important application fields. How to effectively and automatically extract the ROI (region of interest) for the slow-motion video has been a novel interesting challenge. In recent research work, we designed a ROI extraction framework for the video frames produced by high-speed c...

Cerebrovascular pathology is one of the main fatal diseases which seriously affect the human's health. Extracting the accurate image of cerebral vascular tissue is the key of clinical diagnosis. However, the motion artifacts in DSA images seriously affected the quality of vascular subtraction image. In this paper, an automatic and accurate segmenta...

In this paper, a new solution to hyper scale serialized visible human slices is proposed. A closed-form solution and distance transform strategy are synthetically utilized to solve the problem of low-quality image and nonapplicability in the ROI matting and seed point extraction procedure. Closed-form solution calculates a globally optimal result o...

In order to obtain 3D models of the organs in Visible Human Project, in this paper, an improved sequential human body slice segmentation framework for Visible Human is proposed. Two main steps are included in this framework: First, a model based on color similarity is applied to distinguish neighboring pixels; Second, a solution on the basis of geo...

This paper describes an automatic and accurate segmentation method to extract the acetabulum tissue from sequential CT images. The hip joint consists of acetabulum and femoral head. In the personalized femoral head prosthesis designing by reverse engineering technology, obtaining the accurate acetabulum shape is the most important task. However, du...

A system is presented for the segmentation of white matter fiber tracts in pediatric diffusion tensor magnetic resonance imaging (DTI) images. DTI is an in vivo method to delineate the connectivity of white matter fiber tracts in human brain by fiber tractography. Fiber tractography is a promising method to visualize the whole bundles of fiber trac...

Diffusion tensor magnetic resonance imaging (DTI) provides a vivo way to describe the connectivity of the white matter fiber tracts in human brain by fiber tractography. However, the fiber tractography cannot offer a quantitative description of the white matter fiber tracts. The traditional manual segmentation method requires neuroanatomical expert...

For curing the worldwide disease — avascular necrosis of femoral head, the matching quality between the femoral head prosthesis and the acetabulum plays an important role in the operative treatment of the artificial femoral head replacement. In order to obtain a more accurate model of the femoral head prosthesis for the specified patient, a new per...

Nowadays, numerous social videos have pervaded on the web. Social web videos are characterized with the accompanying rich contextual information which describe the content of videos and thus greatly facilitate video search and browsing. Generally, those contextual data such as tags are provided at the whole video level, without temporal indication...

In this paper, a modeling and visualizing system for assisting surgeons in correctly registering for the closed fracture reduction surgery is presented. By using this system, the geometric parameters of the target fixation plate before the long bone fracture operation can be obtained. The main processing scheme consists of following steps: Firstly...

Along with the high-speed cameras are more and more widely applied, how to automatically segment the region of interest in the slow-motion video is a new issue. In this paper, a color slow-motion video segmentation method is proposed. The main strategy is based on region growing and pixel color difference. A rapid color similarity computing method...

In this paper, a rapid and automatic color image segmentation method for the serialized slices of the Visible Human is proposed. The main strategy is based on region growing and pixel color difference. A rapid color similarity computing method is improved and applied for classifying different pixels. An algorithm based on corrosion from four direct...

FPGA (Field-Programmable Gate Array) technology can provide excellent accuracy and efficiency for Chip verification, which has become the key bottleneck of SoC design. Due to the resource constraints of single FPGA chip, Multi-FPGA architecture was applied to the verification of the large scale SoC design. In recent years, a variety of Multi-FPGA v...

The matching quality between the femoral head prosthesis and the acetabulum plays an important role in the operative treatment of the artificial femoral head replacement. In order to obtain a more accurate model of the femoral head prosthesis for the target sufferer, an improved individualized modeling system was presented in this paper. It was dif...

In order to reduce the motion artifact caused by the patient in cerebral DSA images, a non-rigid registration method based on stretching transformation is presented in this paper. Unlike other traditional methods, it does not need bilinear interpolation which is rather time-consuming and even produce 'originally non-existent gray value'. By this me...

Numerous web videos associated with rich metadata are available on the Internet today. While such metadata like video tags bring us facilitation and opportunities for video search and multimedia content understanding, some challenges also arise due to the fact that those video tags are usually annotated at the video level, while many tags actually...

In the cerebrovascular digital subtraction angiography (DSA), patient motion is the primary cause of image quality degradation. In this article, we describe a nonrigid image registration system for motion artifact reduction in DSA which is fully automatic, effective, and computationally very efficient. In this system, the mask image is partitioned...

The matching quality between the femoral head prosthesis and the acetabulum plays an important role in the operative treatment of femoral head prosthetics and femoral head replacement. To obtain the optimal model of the femoral head prosthesis for the target sufferer, an individualized modeling system is shown in this paper. It can recover the necr...

In this paper, we present a novel system, named ViewFocus, to explore the world on Google Maps by leveraging and mining the large amount of user-uploaded geo-tagged photos. Compared with current available online geolocation-oriented photo exploring websites, such as Flickr and Panoramio, ViewFocus is characterized with its ability of supporting pre...

In this paper, a new method for reconstructing the model of the necrotic femoral head is presented. It can reconstruct the optimal femoral head prosthesis model utilizing the reverse technology. This new method not only affords a theoretical model for the accurate operation position fixing in orthopaedic clinic, but also provides an innovative prac...

In order to obtain the optimal model of femoral head prosthesis, a novel modeling method is proposed in this paper. It can revert the necrotic femoral head into the satisfactory model that primely matched with the acetabulum. This new method not only affords a theoretical model for the accurate operation position fixing in orthopaedic clinic, but a...

For the sake of getting the optimal femoral head prosthesis model, a novel modeling method is proposed. It can reconstruct the shape of the subsided femoral head owing to ischemic necrosis. In this paper, two male sufferers with different necrosis extent were chosen as the experimental subject for contrastive simulation. The prosthetic models highl...

The paper proposes a novel simulation method which can obtain geometric parameters of the target fixation plate before costal fracture operation. Its main processing scheme consists of following steps: Firstly, the Curvelet transform is utilized to denoise CT images of the fracture part and its 3-D reconstruction is implemented; Secondly, ridge lin...

The matching quality between the femoral head prosthesis and the acetabulum plays an important role in the operative treatment with femoral head prosthetics and total hip replacement. For the sake of getting the optimal femoral head prosthesis model of the target sufferer, a novel modeling method is proposed. It can reconstruct the shape of the sub...

The paper proposes a novel simulation method of obtaining the geometric parameters of a target fixation plate before the long bone fracture operation. Its main processing scheme consists of the following steps: First, Curvelet transform is utilized to denoise CT images of the fracture part and 3-D models are reconstructed; Second, axial lines of fr...

A novel simulation method is proposed to obtain the geometric parameters of target prebending plate before the operation for complete fracture. The main processing scheme consists of the following steps: Firstly the serial tomograms of fracture part from CT scan are got and denoised by Curvelet transform and 3-D reconstructing; Secondly a method ba...

A color image segmentation method was presented for Virtual Chinese Human Project. Using this policy, the color slice images of refrigerant body can be segmented in series automatically. This new method was mainly based on region-growing arithmetic. A combination of color and texture was performed for comparability evaluation. Window-median arithme...

A novel modeling method which can restore the shape of the femoral head with collapse induced by ischemic necrosis is proposed. First, sequential tomograms of the hip are obtained from a CT scan; secondly, an accurate and automatic method is used to extract the profile of the acetabulum; thirdly, a hybrid method is utilized to gather fiducial marks...

In order to reduce the resulting artifacts after subtraction operation in Digital Subtraction Angiography (DSA), this paper presents an algorithm for spatial transformation based on inverse stretching. It is a new method of gray scale mapping for Mask Image. In the experiment the Mask Image was plotted into rectangular blocks of 32 × 32 pixels to b...

The quality of fit between femoral head and acetabulum plays an important role in the operative treatment with femoral head repairing or total hip replacement. For the sake of getting the quondam femoral head model of the aiming sufferer in health, a novel modeling method is proposed. It can restore the state of the sinking femoral head owing to is...

We developed a new reverse engineering based method for the reconstruction of patient specific models of femoral head for surgery of ANFH. Three dimensional models were reconstructed from the 3D CT dataset and approximated with 3D fitting algorithms based on reverse engineering. In this paper, a strategy of classifying femur from hip joint CT datas...

This paper proposes a novel template-based raycasting scheme using Shear-Warp factorization for expediting parallel viewing of volumetric datasets. The volume coding scheme based on an efficient octree data structure is presented and the octree blocks are adaptively chosen to minimize unnecessary access process. The algorithm exploits the uniform s...