We present a study of multiple sclerosis segmentation algorithms conducted at the international MICCAI 2016 challenge. This challenge was operated using a new open-science computing infrastructure. This allowed for the automatic and independent evaluation of a large range of algorithms in a fair and completely automatic manner. This computing infrastructure was used to evaluate thirteen methods of MS lesions segmentation, exploring a broad range of state-of-theart algorithms, against a high-quality database of 53 MS cases coming from four centers following a common definition of the acquisition protocol. Each case was annotated manually by an unprecedented number of seven different experts. Results of the challenge highlighted that automatic algorithms, including the recent machine learning methods (random forests, deep learning, …), are still trailing human expertise on both detection and delineation criteria. In addition, we demonstrate that computing a statistically robust consensus of the algorithms performs closer to human expertise on one score (segmentation) although still trailing on detection scores.

Email address: Olivier.Commowick@inria.fr (Olivier Commowick) Preprint submitted to Nature Scientific Reports July 12, 2018 . CC-BY 4.0 International license It is made available under a (which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.The copyright holder for this preprint . http://dx.doi.org/10.1101/367557 doi: bioRxiv preprint first posted online Jul. 13, 2018; We present a study of multiple sclerosis segmentation algorithms conducted at the international MICCAI 2016 challenge. This challenge was operated using a new open-science computing infrastructure. This allowed for the automatic and independent evaluation of a large range of algorithms in a fair and completely automatic manner. This computing infrastructure was used to evaluate thirteen methods of MS lesions segmentation, exploring a broad range of state-of-theart algorithms, against a high-quality database of 53 MS cases coming from four centers following a common definition of the acquisition protocol. Each case was annotated manually by an unprecedented number of seven different experts. Results of the challenge highlighted that automatic algorithms, including the recent machine learning methods (random forests, deep learning, . . . ), are still trailing human expertise on both detection and delineation criteria.In addition, we demonstrate that computing a statistically robust consensus of the algorithms performs closer to human expertise on one score (segmentation) although still trailing on detection scores.

No abstract

According to the World Health Organization, breast cancer is the most common form of cancer in women. It is the second leading cause of death among women round the world, becoming the most fatal form of cancer. Despite the existence of several imaging techniques useful to aid at the diagnosis of breast cancer, x-ray mammography is still the most used and effective imaging technology. Consequently, mammographic image segmentation is a fundamental task to support image analysis and diagnosis, taking into account shape analysis of mammary lesions and their borders. However, mammogram segmentation is a very hard process, once it is highly dependent on the types of mammary tissues.The GrowCut algorithm is a relatively new method to perform general image segmentation based on the selection of just a few points inside and outside the region of interest, reaching good results at difficult segmentation cases when these points are correctly selected. In this work we present a new semi-supervised segmentation algorithm based on the modification of the GrowCut algorithm to perform automatic mammographic image segmentation once a region of interest is selected by a specialist. In our proposal, we used fuzzy Gaussian membership functions to modify the evolution rule of the original GrowCut algorithm, in order to estimate the uncertainty of a pixel being object or background. The main impact of the proposed method is the significant reduction of expert effort in the initialization of seed points of GrowCut to perform accurate segmentation, once it removes the need of selection of background seeds. Furthermore, the proposed method is robust to wrong seed positioning and can be extended to other seed based techniques. These characteristics have impact on expert and intelligent systems, once it helps to develop a segmentation method with lower required specialist knowledge, being robust and as efficient as state of the art techniques. We also constructed an automatic point selection process based on the simulated annealing optimization method, avoiding the need of human intervention. The proposed approach was qualitatively compared with other state-of-the-art segmentation techniques, considering the shape of segmented regions. In order to validate our proposal, we built an image classifier using a classical multilayer perceptron. We used Zernike moments to extract segmented image features. This analysis employed 685 mammograms from IRMA breast cancer database, using fat and fibroid tissues. Results show that the proposed technique could achieve a classification rate of 91.28% for fat tissues, evidencing the feasibility of our approach.

Breast cancer is already one of the most common form of cancer worldwide. Mammography image analysis is still the most effective diagnostic method to promote the early detection of breast cancer. Accurately segmenting tumors in digital mammography images is important to improve diagnosis capabilities of health specialists and avoid misdiagnosis. In this work, we evaluate the feasibility of applying GrowCut to segment regions of tumor and we propose two GrowCut semi-supervised versions. All the analysis was performed by evaluating the application of segmentation techniques to a set of images obtained from the Mini-MIAS mammography image database. GrowCut segmentation was compared to Region Growing, Active Contours, Random Walks and Graph Cut techniques. Experiments showed that GrowCut, when compared to the other techniques, was able to acquire better results for the metrics analyzed. Moreover, the proposed semi-supervised versions of GrowCut was proved to have a clinically satisfactory quality of segmentation. main described by Litière, Werutsky, et al. (2012). However, imaging devices used by BMH (Brazilian Ministry of Health) for the detection of breast cancer are quite inefficient at the evaluation of the nodule size, and these methods depend substantially on the professional examiner's experience (Porto, Teixeira and da Silva 2013). Furthermore, digital image diagnosis is complex, mainly because of the large variability of cases. Many cases seen in clinic practice do not fit classic images and descriptions precisely (JUHL, Crummy and Kuhlman 2000). For these reasons, mammography computer aided diagnosis (CAD) has been playing an import role to assist radiologists in improving the accuracy of their diagnoses. Consequently, traditional techniques in image processing have been applied in the medical field to make diagnosis less susceptible to errors through accurate identification of anatomic anomalies (Da-xi, Yuan and Sheng 2010; Ye, Zheng and Hao 2010).Recent works, as those of Liu, Xu, et al. (2011) and Mohamed, Behiels and Dewaele (2009), are quite accurate in identifying the location of tumors. However, little research has been done to verify the quality of segmentation. The shape of the segmented tumor is a determinant factor in the mammogram diagnosis. It is related to the gravity of the tumor and the difference of a few centimeters in the maximum diameter can determine if a surgery is necessary or not. However, it can be very difficult to detect the contour of the tumor accurately depending on several factors, such as shape of the tumor, density, size, location and image quality.? uses the general purpose user interactive technique GrowCut (Vezhnevets and Konouchine 2005) applied to segment images of mammography. This technique has been successfully applied in other areas, including medical image segmentation (Yamasaki, Chen, et al. 2012). The GrowCut also has the advantage of having no parameters to tune, which usually is not common in segmentation methods. ? applies the GrowCut algorithm for the first t...