Jianning Li

Jianning Li
Graz University of Technology | TU Graz · Institute for Computer Graphics and Vision

Dipl.-Ing.

About

59
Publications
4,932
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
312
Citations

Publications

Publications (59)
Preprint
Full-text available
The HoloLens (Microsoft Corp., Redmond, WA), a head-worn, optically see-through augmented reality display, is the main player in the recent boost in medical augmented reality research. In medical settings, the HoloLens enables the physician to obtain immediate insight into patient information, directly overlaid with their view of the clinical scena...
Conference Paper
Automatizing cranial implant design has become an increasingly important avenue in biomedical research. Benefits in terms of financial resources, time and patient safety necessitate the formulation of an efficient and accurate procedure for the same. This paper attempts to provide a new research direction to this problem, through an adversarial dee...
Preprint
Full-text available
Data has become the most valuable resource in today's world. With the massive proliferation of data-driven algorithms, such as deep learning-based approaches, the availability of data is of great interest. In this context, high-quality training, validation and testing datasets are particularly needed. Volumetric data is a very important resource in...
Article
Full-text available
Deep learning has remarkably impacted several different scientific disciplines over the last few years. For example, in image processing and analysis, deep learning algorithms were able to outperform other cutting-edge methods. Additionally, deep learning has delivered state-of-the-art results in tasks like autonomous driving, outclassing previous...
Preprint
Full-text available
Designing implants for large and complex cranial defects is a challenging task, even for professional designers. Current efforts on automating the design process focused mainly on convolutional neural networks (CNN), which have produced state-of-the-art results on reconstructing synthetic defects. However, existing CNN-based methods have been diffi...
Conference Paper
Aortic dissection is an acute condition of the aorta. It typically starts with an intimal tear and continues with the separation of the aortic wall layers. This situation typically leads to the creation of a second lumen, i.e., the false lumen, where blood can flow into. For diagnosis of this pathology, computed tomography angiography (CTA) is usua...
Conference Paper
Cardiovascular diseases are one of the strongest burdens in healthcare. If misdiagnosed, they can lead to life-threatening complications. This is especially true for aortic dissections, which may require immediate surgery depending on the categorization and still lead to late adverse events. Aortic dissection occurs when the aortic duct splits into...
Poster
Full-text available
This work analyses filters for vessel enhancement considering aortic dissection (AD).
Poster
Full-text available
This work revisits a successful modeling technique, called convolution surfaces, to visualize the three dimensional structure of aortic dissections by considering computed tomography angiography (CTA) images.
Preprint
Full-text available
Traditional convolutional neural network (CNN) methods rely on dense tensors, which makes them suboptimal for spatially sparse data. In this paper, we propose a CNN model based on sparse tensors for efficient processing of large and sparse medical images. In contrast to a dense CNN that takes the entire voxel grid as input, a sparse CNN processes o...
Article
Imaging modalities such as computed tomography (CT) and magnetic resonance imaging (MRI) are widely used in diagnostics, clinical studies, and treatment planning. Automatic algorithms for image analysis have thus become an invaluable tool in medicine. Examples of this are two- and three-dimensional visualizations, image segmentation, and the regist...
Data
The datasets include 56 CTA scans from mostly healthy aortas, covering the aortic arch and its branches and the abdominal aortas with the iliac arteries. Furthermore, we include segmentations (masks) of the aortas and its branches (aortic vessel trees) as binary mask images. Note: The collections includes one case with an abdominal aortic aneurysm...
Conference Paper
Surgical navigation requires tracking of instruments with respect to the patient. Conventionally, tracking is done with stationary cameras, and the navigation information is displayed on a stationary display. In contrast, an augmented reality (AR) headset can superimpose surgical navigation information directly in the surgeon’s view. However, AR ne...
Book
The second AutoImplant cranial implant design challenge (AutoImplant 2021, https://autoimplant2021.grand-challenge.org/) was organized as a satellite event of the Medical Image Computing and Computer Assisted Interventions (MICCAI 2021) conference, focusing specifically on the clinical usability of the automatic cranial implant design algorithms. T...
Chapter
Medical images, especially volumetric images, are of high resolution and often exceed the capacity of standard desktop GPUs. As a result, most deep learning-based medical image analysis tasks require the input images to be downsampled, often substantially, before these can be fed to a neural network. However, downsampling can lead to a loss of imag...
Chapter
Cranial implant design is aimed to repair skull defects caused by brain related diseases like brain tumor and high intracranial pressure. Researches have found that deep neural networks could potentially help accelerate the design procedure and get better results. However, most algorithms fail to handle the generalization problem: deep learning mod...
Chapter
Patient-specific implant (PSI) design is a challenging task and requires a specialist, who will spend a significant amount of time using computer aided design tools for implant creation, since patient-specific skull features have to be accounted for. Automating this process could potentially allow intraoperative PSI availability at a relatively low...
Preprint
Full-text available
Objective: Surveillance imaging of chronic aortic diseases, such as dissections, relies on obtaining and comparing cross-sectional diameter measurements at predefined aortic landmarks, over time. Due to a lack of robust tools, the orientation of the cross-sectional planes is defined manually by highly trained operators. We show how manual annotatio...
Article
Full-text available
Deep learning belongs to the field of artificial intelligence, where machines perform tasks that typically require some kind of human intelligence. Deep learning tries to achieve this by drawing inspiration from the learning of a human brain. Similar to the basic structure of a brain, which consists of (billions of) neurons and connections between...
Article
Full-text available
In this article, we present a skull database containing 500 healthy skulls segmented from high-resolution head computed-tomography (CT) scans and 29 defective skulls segmented from craniotomy head CTs. Each healthy skull contains the complete anatomical structures of human skulls, including the cranial bones, facial bones and other subtle structure...
Data
Database of 500 High-resolution Healthy Human Skulls and 29 Craniotomy Skulls and Implants.
Article
Introduction: Researchers and engineers have found their importance in healthcare industry including recent updates in patient-specific implant (PSI) design. CAD/CAM technology played an important role in the design and development of Artificial Intelligence (AI) based implants. The across the globe have their interest focused on the design and man...
Preprint
Full-text available
Medical images, especially volumetric images, are of high resolution and often exceed the capacity of standard desktop GPUs. As a result, most deep learning-based medical image analysis tasks require the input images to be downsampled, often substantially, before these can be fed to a neural network. However, downsampling can lead to a loss of imag...
Preprint
Full-text available
The aortic vessel tree is composed of the aorta and its branching arteries, and plays a key role in supplying the whole body with blood. Aortic diseases, like aneurysms or dissections, can lead to an aortic rupture, whose treatment with open surgery is highly risky. Therefore, patients commonly undergo drug treatment under constant monitoring, whic...
Article
A fast and fully automatic design of 3D printed patient-specific cranial implants is highly desired in cranioplasty - the process to restore a defect on the skull. We formulate skull defect restoration as a 3D volumetric shape completion task, where a partial skull volume is completed automatically. The difference between the completed skull and th...
Article
The aim of this paper is to provide a comprehensive overview of the MICCAI 2020 AutoImplant Challenge1. The approaches and publications submitted and accepted within the challenge will be summarized and reported, highlighting common algorithmic trends and algorithmic diversity. Furthermore, the evaluation results will be presented, compared and dis...
Technical Report
Full-text available
Cranioplasty is the surgical process where a skull defect resulting from previous surgery or injury is repaired using an implant that restores the original protective and aesthetic function of the skull. Implications range from decompressive craniectomies to performing brain surgery. Although the patient’s autologous bone is routinely used as the i...
Poster
Full-text available
Aortic dissections (AD) are injuries of the inner vessel wall of (human) aorta. As this disease poses a significant threat to a patient’s life, it is crucial to observe and analyze the progression of the dissection over the course of the disease. The examinations of the aorta are usually proceeded with the application of Computed Tomography (CT) or...
Poster
Full-text available
We extended an existing web-based tool called Studierfenster (http://studierfenster.icg.tugraz.at/) for this contribution, which was built by students from TU Graz, with a semi-automatic aortic centerline calculation functionality. Studierfenster is a tool that renders three-dimensional volumes, defined by the user, and allows the user to perform m...
Poster
Full-text available
We introduce a fully automatic system for cranial implant design, a common task in cranioplasty operations. The system is currently integrated in Studierfenster (http://studierfenster.tugraz.at/), an online, cloud-based medical image processing platform for medical imaging applications. Enhanced by deep learning algorithms, the system automatically...
Article
Full-text available
The article introduces two complementary datasets intended for the development of data-driven solutions for cranial implant design, which remains to be a time-consuming and laborious task in current clinical routine of cranioplasty. The two datasets, referred to as the SkullBreak and SkullFix in this article, are both adapted from a public head CT...
Article
Full-text available
Patient-specific craniofacial implants are used to repair skull bone defects after trauma or surgery. Currently, cranial implants are designed and produced by third-party suppliers, which is usually time-consuming and expensive. Recent advances in additive manufacturing made the in-hospital or in-operation-room fabrication of personalized implants...
Book
This book constitutes the Second Automatization of Cranial Implant Design in Cranioplasty Challenge, AutoImplant 2021, which was held in conjunction with the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2021, in Strasbourg, France, in September, 2021. The challenge took place virtually due to t...
Conference Paper
This data descriptor elaborates on a dataset that can be used for the development of automatic, data-driven approaches for cra-nial implant design, which is a challenging task in cranioplasty. The dataset includes 210 complete skulls as well as their corresponding defective skulls and the implants, resulting in a total of 210 × 3 = 630 files in NRR...
Conference Paper
In this study, we proposed two methods for AutoImplant (https://autoimplant.grand-challenge.org/)-the cranial implant design challenge. The shape of the implant is predicted based on the inputted defective skull. This task can be accomplished either by directly predicting the implant with the defective skull, or indirectly rebuilding the complete s...
Conference Paper
Cranioplasty is the process of repairing cranial defects or deformations, which may be the result of injuries or necessary medical treatments such as brain tumor surgery. For this procedure, it is necessary to generate a high-quality cranial implant, which needs to be shaped individually for each skull and each defect. This tends to be a very time...
Book
The AutoImplant Cranial Implant Design Challenge (AutoImplant 2020: https:// autoimplant.grand-challenge.org/) was initialized jointly by the Graz University of Technology (TU Graz) and the Medical University of Graz (MedUni Graz), Austria, through an interdisciplinary project “Clinical Additive Manufacturing for Medical Applications” (CAMed: https...
Article
Background and Objective: Augmented reality (AR) can help to overcome current limitations in computer assisted head and neck surgery by granting “X-ray vision” to physicians. Still, the acceptance of AR in clinical applications is limited by technical and clinical challenges. We aim to demonstrate the benefit of a marker-free, instant calibration A...
Preprint
Full-text available
Deep learning belongs to the field of artificial intelligence, where machines perform tasks that typically require some kind of human intelligence. Deep learning tries to achieve this by mimicking the learning of a human brain. Similar to the basic structure of a brain, which consists of (billions of) neurons and connections between them, a deep le...
Chapter
Aortic dissection (AD) is a condition of the main artery of the human body, resulting in the formation of a new flow channel, or false lumen (FL). The disease is usually diagnosed with a computed tomography angiography (CTA) scan during the acute phase. A better understanding of the causes of AD requires knowledge of aortic geometry prior to the ev...
Conference Paper
Augmented reality for medical applications allows physicians to obtain an inside view into the patient without surgery. In this context , we present an augmented reality application running on a standard smartphone or tablet computer, providing visualizations of medical image data, overlaid with the patient, in a video see-through fashion. Our syst...
Conference Paper
Aortic dissection (AD) is a condition of the main artery of the human body, resulting in the formation of a new flow channel, or false lumen (FL). The disease is usually diagnosed with a computed tomography angiography (CTA) scan during the acute phase. A better understanding of the causes of AD requires knowledge of aortic geometry prior to the ev...
Preprint
Full-text available
Deep learning had a remarkable impact in different scientific disciplines during the last years. This was demonstrated in numerous tasks, where deep learning algorithms were able to outperform the state-of-art methods, also in image processing and analysis. Moreover, deep learning delivers good results in tasks like autonomous driving, which could...
Poster
Full-text available
A cranial defect usually occurs after injury, tumor invasion or infection. The current process of cranial implant design and manufacturing usually involves costly commercial software and highly-trained professional users. An automatic, lowcost design and manufacturing of cranial implants can bring significant benefits and improvements to the curren...
Poster
Full-text available
Cranioplasty is the process of repairing cranial defects or deformations. The aim of this procedure is to re-establish the aesthetic shape of the head and to protect the brain from further injuries. Shaping the needed cranial implant is often a costly and time-consuming work. Inspired by the development of a web-based fully automated cranial implan...
Chapter
In this study, we present a baseline approach for AutoImplant (https://autoimplant.grand-challenge.org/) – the cranial implant design challenge, which can be formulated as a volumetric shape learning task. In this task, the defective skull, the complete skull and the cranial implant are represented as binary voxel grids. To accomplish this task, th...
Article
Aortic dissection (AD) is a condition of the main artery of the human body, resulting in the formation of a new flow channel, or false lumen. The disease is usually diagnosed with a computed tomography angiography scan during the acute phase. A better understanding of the causes of AD requires knowledge of the aortic geometry (segmentation), includ...
Preprint
Full-text available
In this study, we present a baseline approach for AutoImplant (https://autoimplant.grand-challenge.org/) - the cranial implant design challenge, which, as suggested by the organizers, can be formulated as a volumetric shape learning task. In this task, the defective skull, the complete skull and the cranial implant are represented as binary voxel g...
Preprint
Full-text available
We introduce a fully automatic system for cranial implant design, a common task in cranioplasty operations. The system is currently integrated in Studierfenster (http://studierfenster.tugraz.at/), an online, cloud-based medical image processing platform for medical imaging applications. Enhanced by deep learning algorithms, the system automatically...
Research Proposal
Full-text available
cite as: Jan Egger, Jianning Li, Xiaojun Chen, Ute Schäfer, Gord von Campe, Marcell Krall, Ulrike Zefferer, Christina Gsaxner, Antonio Pepe, Dieter Schmalstieg. (2020, March 19). Towards the Automatization of Cranial Implant Design in Cranioplasty. Zenodo. http://doi.org/10.5281/zenodo.3715953
Poster
Full-text available
Given underlying computer simulations, this work provides a way to visualize Aortic Dissection (AD) in a realistic manner. Based on Virtual Reality (VR), the solution provides a visual user experience that is immersive: while conservative methods might require a researcher to sight a huge amount of medical images, VR allows the researcher to examin...
Conference Paper
Full-text available
The human organism is a highly complex system that is prone to various diseases. Some diseases are more dangerous than others, especially those that affect the circulatory system or the aorta in particular. The aorta is the largest artery in the human body. Its wall comprises several layers. When the intima, i.e. the innermost layer of the aortic w...
Conference Paper
Volumetric examinations of the aorta are nowadays of crucial importance for the management of critical pathologies such as aortic dissection, aortic aneurism, and other pathologies, which affect the morphology of the artery. These examinations usually begin with the acquisition of a Computed Tomography Angiography (CTA) scan from the patient, which...
Poster
Full-text available
Fast and fully automatic design of 3-D printed patient-specific cranial implant is highly desired in cranioplasty. To this end, various deep learning-based approaches are investigated. To facilitate supervised training, a database containing 200 high-resolution healthy CT skulls acquired in clinical routine is constructed. Due to the unavailability...

Network

Cited By

Projects

Project (1)
Project
Generative models are powerful deep learning methods that have demonstrated great potential for applications in the medical domain. Their performance has continuously improved over the last few years. They address several challenges that are due to the lack of sufficient publicly available medical training data, by providing approaches for synthetic dataset creation, unsupervised pre-training, transfer learning, or generation of missing image modalities. However, generative models often generalize poorly, e.g., to data from different domains and are criticized as black boxes due to a lack of interpretability and controllability. Some of these concerns can be handled by analyzing and disentangling the latent space representation of generative models, encouraging a comprehensive, human interpretable, and compressed representation of the data. The goal of this MICCAI workshop is to analyze the different proposed definitions of disentangled representations, review state-of-the-art methods to achieve disentanglement, evaluate and compare existing quality metrics, as well as to discuss new ideas and methods. By considering the mathematical background alongside applied methods, the workshop will combine theory and practice. Furthermore, these foundations will be discussed in the context of present and future medical applications. Results of the workshop and future directions of the disentanglement approach for medical applications are planned to be summarized in a workshop paper.