What Is the Role of Annotations in the Detection of Dermoscopic Structures?

There has been an increasing demand for computer-aided diagnosis systems to become self-explainable. However, in fields such as dermoscopy image analysis this comes at the cost of asking physicians to annotate datasets in a detailed way, such that they simultaneously identify and manually segment regions of medical interest (dermoscopic criteria) in the images. The segmentations are then used to train an automatic detection system to reproduce the procedure. Unfortunately, providing manual segmentations is a cumbersome and time consuming task that may not be generalized to large amounts of data. Thus, this work aims to understand how much information is really needed for a system to learn to detect dermoscopic criteria. In particular, we will show that given sufficient data, it is possible to train a model to detect dermoscopic criteria solely using global annotations at the image level, and achieve similar performances to that of a fully supervised approach, where the model has access to local annotations at the pixel level (segmentations).

[1]  Jitendra Malik,et al.  Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Catarina Barata,et al.  A System for the Detection of Pigment Network in Dermoscopy Images Using Directional Filters , 2012, IEEE Transactions on Biomedical Engineering.

[3]  P. C. Siddalingaswamy,et al.  Techniques and algorithms for computer aided diagnosis of pigmented skin lesions - A review , 2018, Biomed. Signal Process. Control..

[4]  Kemal Polat,et al.  Automatic sleep staging in obstructive sleep apnea patients using photoplethysmography, heart rate variability signal and machine learning techniques , 2016, Neural Computing and Applications.

[5]  A. Jemal,et al.  Cancer statistics, 2019 , 2019, CA: a cancer journal for clinicians.

[6]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Jorge S. Marques,et al.  Development of a clinically oriented system for melanoma diagnosis , 2017, Pattern Recognit..

[8]  João Paulo Papa,et al.  Computational methods for pigmented skin lesion classification in images: review and future trends , 2018, Neural Computing and Applications.

[9]  Jorge S. Marques,et al.  A Survey of Feature Extraction in Dermoscopy Image Analysis of Skin Cancer , 2019, IEEE Journal of Biomedical and Health Informatics.

[10]  Angela Ferrari,et al.  Interactive atlas of dermoscopy , 2000 .

[11]  M. Emre Celebi,et al.  Dermoscopy Image Analysis: Overview and Future Directions , 2019, IEEE Journal of Biomedical and Health Informatics.

[12]  Michael I. Jordan,et al.  Modeling annotated data , 2003, SIGIR.

[13]  Noel C. F. Codella,et al.  Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC) , 2016, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[14]  Ali Madooei,et al.  Learning to Detect Blue–White Structures in Dermoscopy Images With Weak Supervision , 2015, IEEE Journal of Biomedical and Health Informatics.