2. Abstract
• Inherited retinal diseases cause severe visual deficits in children. They are classified as outer and inner
retina diseases, and often cause blindness in childhood.
• The diagnosis for this type of illness is challenging, given the wide range of clinical and genetic causes
(with over 200 causative genes). It is routinely based on a complex pattern of clinical tests, including
invasive ones, not always appropriate for infants or young children.
• A different approach is thus needed, that exploits Chromatic Pupillometry, a technique increasingly used
to assess outer and inner retina functions.
• This paper presents a novel Clinical Decision Support System (CDSS), based on Machine Learning
using Chromatic Pupillometry in order to support Inherited retinal diseases in pediatric subjects.
3. • An approach that combines hardware and software is proposed: a dedicated medical equipment
(pupillometer) is used with a purposely designed custom machine learning decision support system.
• Two distinct Support Vector Machines (SVMs), one for each eye, classify the features extracted from
the pupillometric data.
• The designed CDSS has been used for diagnosis of Retinitis Pigmentosa in pediatric subjects. The
results, obtained by combining the two SVMs in an ensemble model, show satisfactory performance of
the system, that achieved 0.846 accuracy, 0.937 sensitivity and 0.786 specificity.
• This is the first study that applies machine learning to pupillometric data in order to diagnose a genetic
disease in pediatric age.
4. Introduction
• Inherited Retinal Diseases (IRDs) represent a significant cause of severe visual deficits in children. They
frequently cause of blindness in childhood (1/3000 individuals).
• IRDs can be divided into diseases of the outer retina, namely photoreceptor degenerations (e.g., Leber
Congenital Amaurosis, Retinitis Pig-mentosa, Stargardt disease, Cone Dystrophy, Acromatopsia,
Choroideremia, etc.), and diseases of the inner retina, mainly retinal ganglion cell degeneration (e.g.
congenital glaucoma, dominant optic atrophy, Leber hereditary optic neuropathy).
• Both conditions are characterized by extremely high genetic heterogeneity with over 200 causative
genes identified to date, which represent a remarkable obstacle to a rapid and effective diagnosis also
considering that the same gene could cause different and heterogeneous clinical phenotypes.
5. Pupillometer
• Pupillometer, the measurement of pupil size
and reactivity, is a key part of the clinical
neurological exam for patients with a wide
variety of neurological injuries. It is also
used in psychology.
• It is used to measure the ability of pupils to
change size.
6. Literature Survey
A machine learning approach to medical image classification: Detecting age-related macular
degeneration in fundus images.
AUTHORS: Andres Garcia Floriano, Oscar Camacho Nieto
ABSTRACT: Age-Related Macular Degeneration (AMD) is a dangerous, chronic, and progressive illness that mostly
affects people over 60 years old. This disease is related to the appearance of drusen: deposits of extracellular material
located in the macular region. One way to effectively and non-invasively pre-diagnose AMD is by detecting the presence
of drusen in fundus images. In this work we propose a new method that combines Digital Image Processing, Mathematical
Morphology and a robust and powerful Machine Learning model: a Support Vector Machine (SVM). The enclosed
macular region is subjected to a contrast enhancement method, followed by the application of basic morphological
operations. We use invariant moments as the features of the processed image. The resulting vector is classified by an SVM
as positive or negative for drusen. The proposed method is able to discriminate between healthy and afflicted cases with a
classification accuracy that outperforms many well-regarded state-of-the-art methods.
7.
8. Existing System
• Clinical tests, particularly invasive ones, that are frequently used in the clinical evaluation of
inherited retinal diseases are typically based on a complex pattern and are not necessarily
suitable for newborns or young children.
• For instance, sedating the youngsters is frequently necessary for electrophysiological testing,
which is the most informative clinical inquiry for the detection of inner and outer retinal
problems.
• The effects of sedation on the retinal response necessitate a sophisticated healthcare setting
(such as an operating room, a paediatric anesthesiologist, specialised equipment, etc.), which is
expensive for the health system.
9. • Thus, making a clinical diagnosis is difficult and necessitates the use of specialised
facilities. As a result, it takes a while for the young patients and their family members
to undergo an accurate and thorough screening.
• The electrophysiological responses are frequently below the noise level (for example,
extinguished scotopic electroretinogram response is the condition confirming the
diagnosis). Therefore, these responses are not appropriate for tracking changes in
visual capability, which is important for assessing disease progression and the
effectiveness of treatments.
10. Disadvantages of Existing System
• Clinical diagnosis is difficult and necessitates the use of specialised facilities.
As a result, it takes a while for the young patients and their family members to
undergo an accurate and thorough screening.
11. Proposed System
• As a result of the device's high accuracy and the fact that it doesn't require a
significant number of clinical tests to detect disease, the author of this research
describes an idea to identify hereditary diseases affecting children's eyes.
• In order to diagnose eye pupil disease in children using any of the currently
available methods—which is bad for the health of children—the author uses a
Pupillometry device, which continuously measures pupil diameters and stores that
information in raw format in the file.
12. • Later, I used the Machine Learning SVM method to analyse the data and find any ailment.
Here, I trained two distinct SVM classifiers using data from the right and left eye pupils, and
then uses ensemble model classifier to execute OR operations between the two classifiers to
produce a classifier with higher accuracy.
• If the pupil diameter is large, the SVM will assign the disease class label as 1, and if the pupil
diameter is normal, the classifier will assign value 0.
• As an extension I will use KNN, SVM, Descision tree.
13. Advantages of Proposed System
• The research that uses machine learning to analyse pupillometric data to identify a hereditary
condition in children.