Cite as: C.D. Lekamlage, F. Afzal, E. Westerberg and A. Cheddad, “Mini-DDSM: Mammography-based Automatic Age Estimation,” in
the 3rd International Conference on Digital Medicine and Image Processing (DMIP 2020), ACM, Kyoto, Japan, November 06-09, 2020.
Mini-DDSM: Mammography-based Automatic Age Estimation
CHARITHA DISSANAYAKE, LEKAMLAGE
Blekinge Institute of Technology, SE-371 79 Karlskrona, Sweden
FABIA, AFZAL
Blekinge Institute of Technology, SE-371 79 Karlskrona, Sweden
ERIK, WESTERBERG
Blekinge Institute of Technology, SE-371 79 Karlskrona, Sweden
ABBAS, CHEDDAD
(SMIEEE, ACM)
Blekinge Institute of Technology, SE-371 79 Karlskrona, Sweden
Age estimation has attracted attention for its various medical applications. There are many studies on human age estimation from
biomedical images. However, there is no research done on mammograms for age estimation, as far as we know. The purpose of this study
is to devise an AI-based model for estimating age from mammogram images. Due to lack of public mammography data sets that have the
age attribute, we resort to using a web crawler to download thumbnail mammographic images and their age fields from the public data
set; the Digital Database for Screening Mammography. The original images in this data set unfortunately can only be retrieved by a
software which is broken. Subsequently, we extracted deep learning features from the collected data set, by which we built a model using
Random Forests regressor to estimate the age automatically. The performance assessment was measured using the mean absolute error
values. The average error value out of 10 tests on random selection of samples was around 8 years. In this paper, we show the merits of
this approach to fill up missing age values. We ran logistic and linear regression models on another independent data set to further validate
the advantage of our proposed work. This paper also introduces the free-access Mini-DDSM data set.
CCS CONCEPTS • Health informatics • Health care information systems • Supervised learning by regression
Additional Keywords and Phrases: Applied Machine Learning, Mammograms, Image Segmentation, Deep Learning,
Feature Extraction, Regression Analysis, Age Estimation.
1. INTRODUCTION
Biomedical imaging is a technique of creating a visual representation of the body that can be used for medical
diagnoses and clinical analyses. Biomedical imaging involves the use of various technologies such as X-rays,
CT-scans, magnetic resonance imaging (MRI), ultrasound, mammography, light (endoscopy, OCT) or
radioactive pharmaceuticals (nuclear medicine: SPECT, PET) for diagnosing and helping to treat medical
conditions of patients more efficiently. Along with that biomedical images can be used for estimating the age
of a person. We were able to find many studies on human age estimation from face images, dental images, MRI,
X-rays etc for different purposes. For example, in one of the studies [1], researchers work on predicting the age
of a patient from a chest X-ray by using deep learning methods. Similarly, some researchers presented a
software-based solution for estimating age automatically based on 3D MRI images of the hand [2].
Bone age
assessment (BAA) can be useful in a variety of situations. For example, it can be used to predict how
much longer children will grow when they will hit puberty or even their final height [3]. It can also be used
to monitor the progress of children being treated for conditions that affect growth. BAA is also very useful
when it comes to identifying people lacking proper identification [4]. In recent years, there has been a
significant increase in the number of refugees lacking proper identification seeking asylum in Europe.
Unaccompanied individuals under the age of 18 are eligible for special rights according to the United
*
Corresponding author: abbas.cheddad@bth.se
