A Convolutional Neural Network for the Automatic Diagnosis of Collagen VI related Muscular Dystrophies
This work addresses the problem of diagnosing low-prevalence congenital muscular dystrophies for medical professionals, but it is incremental as it applies an existing CNN method to a new medical dataset without major methodological innovations.
The paper tackles the challenge of diagnosing rare collagen VI-related muscular dystrophies by developing a convolutional neural network (CNN) system that analyzes confocal microscopy images, achieving a method that identifies problematic areas and provides a global quantitative evaluation for patient state assessment.
The development of machine learning systems for the diagnosis of rare diseases is challenging mainly due the lack of data to study them. Despite this challenge, this paper proposes a system for the Computer Aided Diagnosis (CAD) of low-prevalence, congenital muscular dystrophies from confocal microscopy images. The proposed CAD system relies on a Convolutional Neural Network (CNN) which performs an independent classification for non-overlapping patches tiling the input image, and generates an overall decision summarizing the individual decisions for the patches on the query image. This decision scheme points to the possibly problematic areas in the input images and provides a global quantitative evaluation of the state of the patients, which is fundamental for diagnosis and to monitor the efficiency of therapies.