MEDECOM

Plougastel-Daoulas, France
Plougastel-Daoulas, France

Time filter

Source Type

Bouslimi D.,Telecom Bretagne | Coatrieux G.,Telecom Bretagne | Quantin C.,CHRU Dijon | Quantin C.,University of Burgundy | And 2 more authors.
Studies in Health Technology and Informatics | Year: 2014

Teleassistance is defined by the help provided through a telemedicine network by a medical practitioner to one other medical practitioner faced to a difficult case. One of the main limiting factors of its development is the fear of the practitioners to be involved in a litigation. In such a situation, the main issue is to determine as quick and as certain as possible if the damage is in relation with the tort of negligence and the liabilities of each involved physician. After a brief summary of the legal context, we present a protocol combining joint watermarking-encryption and a third party to enforce exchange traceability and therefore to bring valuable electronic evidence in case of teleassistance litigations. © 2014 European Federation for Medical Informatics and IOS Press.


Bouslimi D.,Telecom Bretagne | Bouslimi D.,French Institute of Health and Medical Research | Coatrieux G.,Telecom Bretagne | Coatrieux G.,French Institute of Health and Medical Research | And 4 more authors.
IRBM | Year: 2015

Objectives: Teleassistance is defined as the help provided through a telemedicine network by a practitioner to another one faced with a difficult situation. Beyond securing communication, another main issue is to provide evidence that some data have been exchanged in order to determine the liabilities of each practitioner involved in a telemedicine session in case of litigation. Material and methods: The purpose of this work is the definition of a teleassistance protocol that allows achieving these goals. To do so, we first identify needs in terms of security and evidence considering the example of the French legislation and then propose a secure teleassistance protocol that takes advantage of the Joint Watermarking-Encryption (JWE) approach. The originality of this approach is that it offers watermarking functionalities in both encrypted and decrypted domains and is compliant with the DICOM standard. Results: We describe the functioning of the proposed teleassistance protocol. This protocol is able to secure exchanged data and bring evidence that an exchange took place and that data have been communicated. The security analysis of our protocol shows that it is resistant to non-repudiation issues and collusion attacks. Conclusion: The use of joint watermarking-encryption allows i) ensuring confidentiality of exchanged data while giving access to proofs of their integrity and of their origins even though data are encrypted; and ii) identifying which data were involved in a telemedicine session by means of secure links established between them. The proposed protocol is compliant with the DICOM standard. © 2015 Elsevier Masson SAS.


PubMed | Health Claim Medical Chair ESC Dijon France., CHRU Dijon, French Institute of Health and Medical Research and MEDECOM
Type: | Journal: Studies in health technology and informatics | Year: 2014

Teleassistance is defined by the help provided through a telemedicine network by a medical practitioner to one other medical practitioner faced to a difficult case. One of the main limiting factors of its development is the fear of the practitioners to be involved in a litigation. In such a situation, the main issue is to determine as quick and as certain as possible if the damage is in relation with the tort of negligence and the liabilities of each involved physician. After a brief summary of the legal context, we present a protocol combining joint watermarking-encryption and a third party to enforce exchange traceability and therefore to bring valuable electronic evidence in case of teleassistance litigations.


Bouslimi D.,Telecom Bretagne | Coatrieux G.,Telecom Bretagne | Cozic M.,MEDECOM | Roux Ch.,Ecole Nationale Superieure des Mines de Saint - Etienne CMP
2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 | Year: 2014

In this paper, we propose a novel crypto-watermarking system for the purpose of verifying the reliability of images and tracing them, i.e. identifying the person at the origin of an illegal distribution. This system couples a common watermarking method, based on Quantization Index Modulation (QIM), and a joint watermarking-decryption (JWD) approach. At the emitter side, it allows the insertion of a watermark as a proof of reliability of the image before sending it encrypted; at the reception, another watermark, a proof of traceability, is embedded during the decryption process. The scheme we propose makes interoperate such a combination of watermarking approaches taking into account risks of interferences between embedded watermarks, allowing the access to both reliability and traceability proofs. Experimental results confirm the efficiency of our system, and demonstrate it can be used to identify the physician at the origin of a disclosure even if the image has been modified. © 2014 IEEE.


Quellec G.,French Institute of Health and Medical Research | Lamard M.,French Institute of Health and Medical Research | Lamard M.,University of Western Brittany | Cozic M.,Medecom | And 4 more authors.
IEEE Transactions on Medical Imaging | Year: 2016

This paper describes a computer-Aided detection and diagnosis system for breast cancer, the most common form of cancer among women, using mammography. The system relies on the Multiple-Instance Learning (MIL) paradigm, which has proven useful for medical decision support in previous works from our team. In the proposed framework, breasts are first partitioned adaptively into regions. Then, features derived from the detection of lesions (masses and microcalcifications) as well as textural features, are extracted from each region and combined in order to classify mammography examinations as 'normal' or 'abnormal'. Whenever an abnormal examination record is detected, the regions that induced that automated diagnosis can be highlighted. Two strategies are evaluated to define this anomaly detector. In a first scenario, manual segmentations of lesions are used to train an SVM that assigns an anomaly index to each region; local anomaly indices are then combined into a global anomaly index. In a second scenario, the local and global anomaly detectors are trained simultaneously, without manual segmentations, using various MIL algorithms (DD, APR, mi-SVM, MI-SVM and MILBoost). Experiments on the DDSM dataset show that the second approach, which is only weakly-supervised, surprisingly outperforms the first approach, even though it is strongly-supervised. This suggests that anomaly detectors can be advantageously trained on large medical image archives, without the need for manual segmentation. © 1982-2012 IEEE.


Sanchez De La Rosa R.,Telecom Bretagne | Lamard M.,French Institute of Health and Medical Research | Lamard M.,University of Western Brittany | Cazuguel G.,French Institute of Health and Medical Research | And 3 more authors.
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS | Year: 2015

This paper describes an experimental computer-aided detection and diagnosis system for breast cancer, the most common form of cancer among women, using mammography. The system relies on the Multiple-Instance Learning (MIL) paradigm, which has proven useful for medical decision support in previous works from our team. In the proposed framework, the breasts are first partitioned adaptively into regions. Then, either textural features, or features derived from the detection of masses and microcalcifications, are extracted from each region. Finally, feature vectors extracted from each region are combined using an MIL algorithm (Citation k-NN or mi-Graph), in order to recognize 'normal' mammography examinations or to categorize examinations as 'normal', 'benign' or 'cancer'. An accuracy of 91.1% (respectively 62.1%) was achieved for normality recognition (respectively three-class categorization) in a subset of 720 mammograms from the DDSM dataset. The paper also discusses future improvements, that will make the most of the MIL paradigm, in order to improve 'benign' versus 'cancer' discrimination in particular. © 2015 IEEE.


Bouslimi D.,Telecom Bretagne | Bouslimi D.,French Institute of Health and Medical Research | Coatrieux G.,Telecom Bretagne | Coatrieux G.,French Institute of Health and Medical Research | And 3 more authors.
Signal Processing: Image Communication | Year: 2016

In this paper, we propose a novel approach which allows embedding a message into an encrypted image; a message that can be accessed whether the image is encrypted or not. To do so, the proposed solution relies on the insertion into the image of a predefined watermark, a “pre-watermark”, before the encryption process. Message insertion (resp. extraction) is then commonly conducted into (resp. from) the encrypted image. It is the impact of this data hiding process onto the “pre-watermark” that gives us access to the message into the spatial domain, i.e. after the decryption process. By doing so, the watermark processing process is independent of the knowledge of the encryption key and one only just has to know the watermarking key so as to embed the message and extract it from the encrypted or decrypted image. Reciprocally, encryption/decryption processes are completely independent from message embedding/extraction. We illustrate the feasibility of our approach considering the RC4 stream cipher algorithm and the Least Significant Bit substitution watermarking modulation. Experiments conducted on natural test images and ultrasound medical images demonstrate the general capabilities of our system to securely make available a message in both spatial and encrypted domains while minimizing image distortion. We further discuss the use of different encryption and watermarking algorithms and we illustrate how our system can be used for ensuring image integrity and authenticity control. © 2016 Elsevier B.V.


Bouslimi D.,Telecom Bretagne | Coatrieux G.,Telecom Bretagne | Cozic M.,MED.e.COM | Roux C.,Telecom Bretagne
IEEE Transactions on Information Technology in Biomedicine | Year: 2012

In this paper, we propose a joint encryption/water-marking system for the purpose of protecting medical images. This system is based on an approach which combines a substitutive watermarking algorithm, the quantization index modulation, with an encryption algorithm: a stream cipher algorithm (e.g., the RC4) or a block cipher algorithm (e.g., the AES in cipher block chaining (CBC) mode of operation). Our objective is to give access to the outcomes of the image integrity and of its origin even though the image is stored encrypted. If watermarking and encryption are conducted jointly at the protection stage, watermark extraction and decryption can be applied independently. The security analysis of our scheme and experimental results achieved on 8-bit depth ultrasound images as well as on 16-bit encoded positron emission tomography images demonstrate the capability of our system to securely make available security attributes in both spatial and encrypted domains while minimizing image distortion. Furthermore, by making use of the AES block cipher in CBC mode, the proposed system is compliant with or transparent to the DICOM standard. © 2012 IEEE.


Karasad M.,Institute Mines Telecom | Bouslimi D.,Institute Mines Telecom | Cozic M.,MEDECOM | Coatrieux G.,Institute Mines Telecom
3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016 | Year: 2016

In this paper, we propose a new watermarking scheme for digital radiographic images which takes advantage of the quantum noise. This later is inherent to their acquisition process and is also the dominant noise. Once this noise extracted from the image, we modulate it for message embedding with Quantization Index Modulation under the constraint the watermarked noise respects the original noise distribution. By doing so, it is expected that the image diagnosis value is preserved. Experiments conducted on a set of 75 radiology images of different anatomical structures of the body show that the image distortion, evaluated through several image quality metrics, is very low (PSNR∼77.24dB) while offering a relatively important capacity (capacity∼0.15bpp) that can support different watermarking based security objectives. © 2016 IEEE.


Bouslimi D.,French Institute of Health and Medical Research | Coatrieux G.,French Institute of Health and Medical Research | Cozic M.,MEDECOM | Roux C.,French Institute of Health and Medical Research
IFMBE Proceedings | Year: 2014

In this paper, we propose a novel scheme which allows embedding a message, a set of security attributes, into encrypted images. This message can be accessed whether the image is encrypted or not for the purpose of verifying the reliability of images. The proposed solution relies on the insertion into the image of a predefined watermark, a "pre-watermark", before the encryption process. Message insertion and extraction are then conducted into the encrypted image. It is the impact of this data hiding process onto the "pre-watermark" that gives us access to the message after the image has been decrypted. The proposed scheme has been implemented considering the RC4 stream cipher algorithm and the Least Significant Bit substitution watermarking method. Experimental results achieved on 8 bit depth ultrasound images demonstrate the capability of our system to make available security attributes in both spatial and encrypted domains while minimizing image distortion. © 2014, Springer International Publishing Switzerland.

Loading MEDECOM collaborators
Loading MEDECOM collaborators