BrainLes 2018 MICCAI workshop
  • slide 2

    MICCAI BrainLes 2018 workshop

  • slide 3

    MICCAI BrainLes 2018 workshop

  • slide 4

    MICCAI BrainLes 2018 workshop

  • slide 5

    MICCAI BrainLes 2018 workshop

  • slide 1

    MICCAI BrainLes 2018 welcomes you to Granada


Welcome to the Brain Lesion (BrainLes) workshop, a satellite event of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) on September 16, 2018.

Provide an overview of medical image analysis advances in glioma, multiple sclerosis (MS), stroke and trauma brain injuries (TBI). We let researchers from the medical image analysis domain meet with radiologists and neurologists, and discuss these diseases and traumas, with the goal of comparing related neuroimaging biomarkers.
Glioma is the most common type of brain tumors. MS is an inflammatory and demyelinating disease. Stroke is the sudden loss of neurologic function caused by an interruption of the blood supply to the brain. Although these are different diseases that affect the brain in different ways, they share apparent similarities across various imaging modalities, such as the strong heterogeneity of the disease's spatial pattern and the complex pathological landscape that complicates their prognosis. Their unpredictable appearance and shape make them challenging to be assessed in multi-modal brain imaging, as even in healthy-appearing brain tissue there are alterations that are often not visible on conventional MRI sequences, and hence they can be confused with each other.

We solicit manuscript that use methods of medical image analysis focusing on:
  • Lesion segmentation (glioma, MS, stroke, TBI).
  • Longitudinal data analysis.
  • Novel MRI sequences and contrast agents.
  • Diffusion imaging.
  • Clinical related aspects.
  • Neurosonography.
  • Connectomics.
  • Dynamical models.
  • Radiomics/Radiogenomics.
The event will be held in conjunction with the challenges on Brain Tumor Segmentation (BraTS), and ISLES Segmentation to complement each other. BrainLes workshop allows more freedom within the scope of medical imaging and brain lesions, whereas BraTS and WMH challenges are segmentation challenges with their independent datasets. The workshop and the challenges will be held on the same day as a unique full-day event.

Submit your paper according to the deadline through the CMT submission system.
The workshop papers will be initially submitted as an 8-pages manuscript and then we will ask the authors to extend their manuscripts (also with pictures and tables) up to 12 pages after the workshop without peer-review. Feel free to submit a paper between 8 and 12 pages. Additionally we allow the submission of extended papers FROM THE CHALLENGES as post-proceedings, those are also peer-reviewed.
The format of the workshop is mainly based on double-blinded peer-reviewed papers. We limit to 8 pages manuscript to be in-line with the main conference. Please use the LNCS template, available both in LaTeX (link here) and in MS Word (link here) format, directly from Springer (link here). No guidelines on the dataset are given, to give freedom to the authors to report results on their current works. However, the authors can also use the available data from previous and current BraTS challenges. Due to time constrains only the top papers can have oral presentations, and the remaining will be presented during the workshop's poster session.

Plans for dissemination:
Extended versions of all accepted papers will be published as LCNS proceedings by: Springer-Verlag.
The post-proceedings of previous editions of "Brain-Lesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries" can be downloaded from the Springer-Verlag website, at the BrainLes 2015, the BrainLes 2016, and BrainLes 2017 pages.

The registration can be performed through MICCAI's main registration webpage as for the main conference. VISA-Invitation letters can be provided only to those registered to the workshop.


Paper submission

Deadline June 25th, 2018 (11:59pm PST)
Extended July 15, 2018 (11:59pm PST)

Reviews Due

Deadline July 27, 2018

Camera-ready MICCAI Submission

Deadline August 30, 2018.

Challenges' post-proceeding LNCS Submission

Deadline November 10, 2018.

Camera-ready MICCAI Submission

Deadline August 30, 2018.

Challenges' post-proceeding Submission

Deadline November 5th, 2018.

Workshop: 16 September 2018

Ragini Verma is a tenured Professor in the Department of Radiology, at the Perelman School of Medicine of the University of Pennsylvania.
Ragini Verma’s research focuses on computational brain connectomics, which is the study of brain connectivity using computational and mathematical algorithms. Her research encompasses diffusion imaging, multi-modal connectomics (combination of structure and function), and genetic underpinnings of the brain’s network structure. These methods find application in several research and translational projects in brain tumors (neurosurgical and radiation planning), autism spectrum disorder, traumatic brain injury, development and sex differences. Dr. Verma is successfully running several large population studies in these areas, and is concentrating on issues involved in such studies: multi-site acquisition and quality control, state of the art methods, and development of tools that can be easily used by clinicians.
Dr. Verma will give a talk on using diffusion imaging and connectomics in brain tumors and brain injury, from the perspective of surgical and treatment planning.

Thomas C. Booth is a Senior Lecturer (equivalent of US Associate Professor) in the Department of Neuroimaging at King’s College London and an Honorary Consultant Neuroradiologist at King’s College Hospital. His interests are in neuro-oncology, neurovascular and incidental finding research. He first started to enjoy machine learning during his Ph.D. at the University of Cambridge. Here, his focus was on brain tumour treatment response assessment using brain tumour MRI structural images – something he continues to research now as he is reminded continuously how important neuro-oncology diagnostics are when presenting patients at the neuro-oncology multi-disciplinary team meetings in a busy London teaching hospital.
He sits on the National Cancer Research Institute Brain Tumour Committee and the Royal College of Radiologists Academic Committee. He was recently awarded the inaugural Royal College of Radiologists Outstanding Researcher Award.
Dr. Booth’s talk will be an update on machine learning in neuro-oncology diagnostics.

Bjoern Menze is an Assistant Professor of Computer Science and of Medicine at TU Munich, holding a Rudolf Moessbauer tenure-track professorship of the TUM Institute for Advanced Study. He is heading the Image-based Biomedical Modeling group at the TUM Institute of Medical Engineering and the Center for Translational Cancer Reseach. Before, he was member of the Asclepios team at the Inria Sophia-Antipolis, the Computer Vision Lab at ETH Zurich, and the Medical Computer Vision group of CSAIL at MIT.
Prof. Menze’s research is exploring topics at the interface of image-based modeling, computational physiology, and machine learning. In this, the focus of his group on applications in clinical neuroimaging and the modeling of tumor growth, striving towards transforming the descriptive interpretation of biomedical images into a model-driven analysis that infers properties of the underlying physiological and patho-physiological processes by using models from biophysics and computational physiology. The group is also interested in how to apply such models to big data bases in order to learn about correlations between model features and disease patterns at a population scale.
Bjoern Menze organized workshops at MICCAI, ISBI, NIPS and CVPR in the fields of medical computer vision and neuroimage processing, served as guest editor for Medical Image Analysis and as a member of the programm committee of MICCAI, and as a member of the editorial board of Medical Image Analysis. He received the Medical Image Analyis-MICCAI Award for the best paper of MICCAI 2014, and the Young Scientist Publication Impact Award at MICCAI 2015. He is the initiator and lead organizers of the Multimodal Brain Tumor Image Segmentation (BRATS) Challenge since 2012.
Dr. Menze's talk will focus on the final summarizing meta-analysis of the BraTS 2012-2016 results.

G Anthony (Tony) Reina is a machine learning engineer with the Artificial Intelligence Products Group at Intel Corporation in Santa Clara, USA.
His research focuses on deep learning algorithm optimization for 3D medical imaging, image compression, and federated learning. After his medical degree he spent 5 years as a post-doctoral researcher studying population vector encoding of motor cortical activity which led to some of the first intracortical brain-computer interfaces to restore arm movement in humans. He also patented an augmented reality telemedicine interface which allows surgeons to consult on a live case via a remote connection. He holds a Masters degree in Data Science and Engineering and a Bachelors degree in Biomedical Engineering.
Dr. Reina will discuss Intel's efforts to promote training of 3D medical imaging on full sized MRI images without tiling or downsampling.


Program Committee (alphabetical order):


Granada Conference Centre,
S/N, Paseo del Violón, 18006 Granada, Spain.