HMIMIA 2019: Hybrid Machine Intelligence for Medical Image Analysis |
Website | http://mia.teamsb.net/ |
Submission link | https://easychair.org/conferences/?conf=hmimia2019 |
Abstract registration deadline | July 31, 2018 |
Submission deadline | November 10, 2018 |
With massive influx of multi-modality image data in the field of medical image processing, analysis and understanding the requirement for intelligent paradigms is always prompted for addressing the complex real life problems of an array of medical imaging applications including computer assisted diagnosis, image guided radiation therapy, landmark detection, imaging genomics, and brain connectomics. The objective of such computational paradigm is to give rise to fail safe and robust solutions to the emerging problems faced by mankind in the domain of medical science and technology. Typical applications encompass the fields of Medical Image enhancement, segmentation, classification, object detection to name a few. Recent years have witnessed the revolution in the field of medical image analysis and computer vision by employing machine learning and computational intelligent algorithms. However, the applicability of these algorithms remains to be investigated in routine clinical practice owing to unstructured and considering volume of the medical image data produced. The traditional medical image processing approaches often need to cope with complex medical image processing problems with a profusion of images like MRI, CT Scan, X-Ray and USG images in various applications. Owing to adaptive and complex behavior of intelligent computer vision programs with the advancement and considering the volume of medical image data sets the combination of medical image analysis and understanding with machine learning algorithms received lots of attention. Imparting intelligence in a machine is the need of the hour. Several intelligent techniques have been in vogue over the year in this direction. Among these techniques, the machine learning techniques stand in good stead. However, it is often noted that the classical machine intelligent techniques often fall short in offering a formidable solution in the field of medical image analysis and pattern recognition. On and above, if the different components of the machine learning are conjoined together, the resultant hybrid machine intelligence is found to be more efficient and robust by design and performance. The expression "machine learning" usually refers to the ability of a computer to learn a specific task from data or experimental observation without explicitly programed. Even though it's commonly considered a synonym of machine intelligence, there is still no commonly accepted definition of machine learning. But generally, machine learning is a set of methodologies and approaches to address complex real-world problems to which mathematical or traditional modelling can be useless for a few reasons: the processes might be too complex for mathematical reasoning, it might contain some uncertainties during the process, or the process might simply be stochastic in nature. Machine Intelligence therefore uses a combination of four main complementary techniques. The fuzzy logic which enables the computer to understand natural language, artificial neural networks which permits the system to learn experiential data by operating like the biological one, learning theory and probabilistic methods which helps dealing with uncertainty imprecision. Except those main principles, currently popular approaches include biologically inspired algorithms such as swarm intelligence and artificial immune systems, which can be seen as a part of evolutionary computation, image processing and artificial intelligence, which tends to be confused with Machine Intelligence. But although both Machine Intelligence (MI) and Artificial Intelligence (AI) seek similar goals, there's a clear distinction between them. Machine Intelligence is thus a way of performing like human beings. Indeed, the characteristic of "intelligence" is usually attributed to humans. More recently, many products and items also claim to be "intelligent", an attribute which is directly linked to the reasoning and decision making. We are entering a phase where we are going to see the advances in digitization. As a consequence, the diversified field of applications in medical image processing has been evolved over the years with rapid advancement in digital technologies. An innovative integration of machine intelligence in medical image processing is very likely to have a great benefit to the field, which will contribute to a better understanding of complex and huge volume of unstructured medical images. The number of image processing algorithms that incorporate some learning components is expected to increase, as adaptation is needed. However, an increase in adaptation is often linked to an increase in complexity, and one has to efficiently control any machine intelligence technique to properly adapt it to medical image processing problems. Indeed, processing huge amounts of medical images means being able to process huge quantities of unstructured data often of high dimensions, which is problematic for most machine intelligent techniques. Therefore, an interaction with the medical image data and with image priors is necessary to drive model selection strategies. The primary purpose of this book is to increase the awareness of medical image processing researchers to the impact of machine learning and computational intelligent algorithms. Thus, the proposed book aims to introduce to the prospective readers the latest trends in machine learning technologies and computational intelligence for intelligent medical image analysis.
Call for Chapters
Recommended Topics
Topics of interest:
We invite contributory chapters for submissions on all topics related to medical imaging using hybrid machine intelligent techniques. Topics discussed will include, but are not limited to:
- Semantic segmentation of medical images
- Medical image generation and enhancement methods using deep learning
- Multi-modal image registration with deep learning
- Content-Based Image Retrieval (CBIR) of medical images
- Interventional image analysis with deep learning
- Computer-aided detection and diagnosis using medical imaging
- Medical Image synthesis and Reconstruction
- Transfer learning for medical imaging
- 3D medical image analysis
- 4D medical image analysis
- Learning with noisy labels in medical imaging
- Learning with sparse data/labels in medical imaging
- Unsupervised deep learning for medical image analysis
- Supervised deep learning for medical image analysis
- Uncertainty estimation
- Integration of imaging and clinical data
- Data augmentation for medical images
- End-to-end learning for prognosis and treatment selection
Submission Procedure
- Prospective authors are invited to submit a 3- 4 pages Abstract of the paper along with title of the paper and author details. Abstract should highlight the novelty and contribution of the proposed article.
- Authors need to submit this abstract using the Easy Chair submission link
- Easy Chair link for Submission
To finalize the manuscript, below listed documents would help you while preparing/finalizing the book manuscript:
ittees of several national and international conferences.
Important Dates
- Proposal Submission: 31st July 2018
- Notification of Acceptance of Proposals: 10th August 2018
- Full Chapter Submission: 10th November 2018
- Chapter Review Notification: 10th December 2018
- Interim Version Due: 10th January 2019
- Final Notification: 20th January 2019
- Final Revised Chapter Due: 10th February 2019
- Final Acceptance: 20th February 2019
Contact
Prof. (Dr.) Siddhartha Bhattacharyya
RCC Institute of Information Technology
Canal South Road, Beliaghata, Kolkata – 700 015, India
Mobile: +919830354195
Email: dr.siddhartha.bhattacharyya@gmail.com
Prof. Debanjan Konar
Assistant Professor,
Dept of Computer Science and Engineering
Sikkim Manipal Institute of Technology,
Majitar, East Sikkim, Sikkim-737136, India
Contact No: +91-9821928536
Email: debanjan.k@smit.smu.edu.in