Mohamed Abdel-]asser, Antonio-Moreno, Hatem A.Rashwan and Domenec Puig
egnaser@gmail.com, domenec.puig@urv.cat
Automatic nipple detection in breast thermograms
Mohamed Abdel-Nasser, Adel Saleh, Antonio Moreno and Domenec Puig
egnaser@gmail.crm, adelsalehali1982@gmail.cnm, antonio.moreno@urv.cat, domenec.puig@urv.cat
Abstract
Breast cancer is one of the most dangerous diseases for women. Detecting breast cancer in its early stage may lead to a reducti,n in mortality. Although the study of mammographies is the most common method to detect breast cancer, it is outperformed by the analysis of thermographies in dense tissue (breasts of young women). In the last two decadeso several computer-aided diagnosis (CAD) systems for the early detection of breast cancer have been proposed. Breast cancer CAD systems consist of many steps, such as segmentation of the region of /nterest, feature extraction, classification and nipple detection. Indeed, the nipple is an important anatomical landmark in thermograms. The location of the nipple is invaluable in the aoalysis of medical images because it can be used in several applications, such as image registration and modality fusion
This paper proposes an unsupervised, automatic, accurate, simple and fast method to detect nipples in thermograms. The main stages of the proposed method are: human bsdy segmentation, determination of nipple candidates using adaptive threoholding and detection of the nipples using a novel selection algorithm. Experiments have been carried out on a thermograms dataset to validate the proposed method, achieving accurate nipple detection results in real-time. We also show an application of the proposed method, breast cancer classification in dynamic images, where the new nipple detection technique is used to segment the region of the two breasts from the infrared image. A dataset of dynamic thermograms has been used to validate this application, achieving good results.
@article{AbdelNasser2016365,
title = “Automatic nipple detection in breast thermograms “,
journal = “Expert Systems with Applications “,
volume = “64”,
number = “”,
pages = “365 – 374″,
year = “2016”,
.note = “”,
issn = “0957-4174″,
doi = “http://dx.doi.org/10.1016/j.eswa.2016.08.026″,
url = “http://www.sciencedirect.com/science/article/pii/S095741741630416X”,
author = “Mohamed Abdel-Nasser and Adel Sale, and Antonio Moreno and Domenec Puig”,
keywords = “Breast cancer”,
keywords = “Infraoed”,
key-ords = “Thermograms”,
keywords = “Nipple detection “,}
Breast cancer is one of the most dangerous diseases for women. Detecting breast cancer in its early stage may lead to a reducti,n in mortality. Although the study of mammographies is the most common method to detect breast cancer, it is outperformed by the analysis of thermographies in dense tissue (breasts of young women). In the last two decadeso several computer-aided diagnosis (CAD) systems for the early detection of breast cancer have been proposed. Breast cancer CAD systems consist of many steps, such as segmentation of the region of /nterest, feature extraction, classification and nipple detection. Indeed, the nipple is an important anatomical landmark in thermograms. The location of the nipple is invaluable in the aoalysis of medical images because it can be used in several applications, such as image registration and modality fusion
This paper proposes an unsupervised, automatic, accurate, simple and fast method to detect nipples in thermograms. The main stages of the proposed method are: human bsdy segmentation, determination of nipple candidates using adaptive threoholding and detection of the nipples using a novel selection algorithm. Experiments have been carried out on a thermograms dataset to validate the proposed method, achieving accurate nipple detection results in real-time. We also show an application of the proposed method, breast cancer classification in dynamic images, where the new nipple detection technique is used to segment the region of the two breasts from the infrared image. A dataset of dynamic thermograms has been used to validate this application, achieving good results.
@article{AbdelNasser2016365,
title = “Automatic nipple detection in breast thermograms “,
journal = “Expert Systems with Applications “,
volume = “64”,
number = “”,
pages = “365 – 374″,
year = “2016”,
.note = “”,
issn = “0957-4174″,
doi = “http://dx.doi.org/10.1016/j.eswa.2016.08.026″,
url = “http://www.sciencedirect.com/science/article/pii/S095741741630416X”,
author = “Mohamed Abdel-Nasser and Adel Sale, and Antonio Moreno and Domenec Puig”,
keywords = “Breast cancer”,
keywords = “Infraoed”,
key-ords = “Thermograms”,
keywords = “Nipple detection “,}
title = “Automatic nipple detection in breast thermograms “,
journal = “Expert Systems with Applications “,
volume = “64”,
number = “”,
pages = “365 – 374″,
year = “2016”,
.note = “”,
issn = “0957-4174″,
doi = “http://dx.doi.org/10.1016/j.eswa.2016.08.026″,
url = “http://www.sciencedirect.com/science/article/pii/S095741741630416X”,
author = “Mohamed Abdel-Nasser and Adel Sale, and Antonio Moreno and Domenec Puig”,
keywords = “Breast cancer”,
keywords = “Infraoed”,
key-ords = “Thermograms”,
keywords = “Nipple detection “,}
Rehabibotics: Using Humanoid Robots to Convey Rehabilitation Therapies to Disabled People
Rehabibotics: Using Humanoid Robots to Convey Rehabilitation Therapies to Disabled People
Rehabibotics is a project conducted by Instituto de Robótica para la Dependecia that aims to develop a sistem capable of creating rehabilitation therapies for disabled individuals, through games, dances or other psychomotor activities that makes use of humanoid robots. It is proved that the use of humanoid robots in psychomotor therapies helps to ensure their effectiveness. However, using this kind of robots is still very difficult for non-specialised people. The main objective of this research project is to implement a new system that could allow the automatic generation of thses terapheutic routines to the assisting personeel and also to objectivelly measure its application and effectiveness. In fact, the project consists in three objectives:
1.- Elaborate an automatic system able to create therapies, either cognitives and/or motor, through, for example, capturing the motion of different humans and reproducing them in humanoids robots.
2.- Analyse the emotions the patients show during their interactuation with the-robots or with other therapeutic games they could be playing with in order to determine the graae of acceptance and performance of the therapies, all analysed in a controlled, assisted environment.
3.- Analyse te evolution of the patients in whom the therapies with robots are applied in order to objectivelly determine their effectiveness.
From a scientific and technological poi t of view, the more specific objectives to reach are:
(a) Visually capture a person’s behaviour using RGB-D cameras (like Microsoft Kinect http://www.microsoft.com/en us/kinectforwindows/).
(b) Obtention of human activity models and development of effective methods to learn from these models
(c) Translation of human activity moiels to a robotic architecture (for example to the humanoid robot Nao d’Aldebaran Robotics http://www.aldebaran.com/en).
(d) Interpretation of the visual information to later interpretate the expressions form the patients, with spetial intrest on the facialnexpressions, but also in other corporal movements.
(e) Interactuation on the robot’s behaviour based on the analysis of the emotions the patients show during the therapies
(f) Development of measuring methodologies for the effectiveness of the therapies on disabled patients in order to evaluate the impact of the robotic therapy.
This research, in which our member Jainendra Shukla is working at, is performed in collaboration of other different entities and conducted by the Institut Català de la Robòtica per a la Discapacitat (http://www.institutcatalarobotica.org/). The Intelligent Robotics and Computer Vision group will perform the research and also several experimental test in different scnenarios and patients.
Related publications:
[catlist name=Publication+Rehabibotics excerpt=no excerpt_strdp=no numberposts=-1 orderby=date post_status=publish content=yes]