Call us Today ! +918886268863 | [email protected]

Deep Learning Classification of Systemic Sclerosis Skin Using the MobileNetV2 Model

Deep Learning Classification of Systemic Sclerosis Skin Using the MobileNetV2 Model

Introduction:

Systemic sclerosis (SSc) is an autoimmune disease characterized by wide-spread fibrosis of the skin and internal organs. Based on the extent of skin involvement, the disease can be classified into two types: limited cutaneous SSc (LcSSc) and diffuse cutaneous SSc (DcSSc). Both subsets can include internal organ involvement, with more severe organ involvement occurring more frequently in DcSSc [1]. The internal organ complications of SSc are associated with high case-specific disability rates and mortality rates, posing a heavy socio-economic burden for society. Several studies have shown that organ involvement could occur far earlier than expected in the early phase of the disease.

Abstract:

Systemic sclerosis (SSc) is a rare autoimmune, systemic disease with prominent fibrosis of skin and internal organs. Early diagnosis of the disease is crucial for designing effective therapy and management plans. Machine learning algorithms, especially deep learning, have been found to be greatly useful in biology, medicine, healthcare, and biomedical applications, in the areas of medical image processing and speech recognition. However, the need for a large training data set and the requirement for a graphics processing unit (GPU) have hindered the wide application of machine learning algorithms as a diagnostic tool in resource-constrained environments (e.g., clinics). Methods: In this paper, we propose a novel mobile deep learning network for the characterization of SSc skin. The proposed network architecture consists of the UNet, a dense connectivity convolutional neural network (CNN) with added classifier layers that when combined with limited training data, yields better image segmentation and more accurate classification, and a mobile training module. In addition, to improve the computational efficiency and diagnostic accuracy, the highly efficient training model called “MobileNetV2,” which is designed for mobile and embedded applications, was used to train the network.

Existing work:

Previous studies have investigated machine learning in bioinformatics [15], biology and medicine [16], computational biology [17], [18], biomedicine [19], [20], and super resolution imaging [21].

Statistical and machine learning techniques have also been used in psychiatry [22], [23]. It has also shown potential in autoimmune disease diagnosis, prognosis prediction, and classification of diseases such as lupus [24], [25], rheumatoid arthritis [26], [27], and inflammatory bowel disease [28]. Machine learning techniques, especially deep neural networks (DNNs), have been effectively used in several biomedical applications, including protein structure prediction [29]–[31], anomaly classification [32]–[34], segmentation [35], recognition [36], [37], and brain decoding [38] since DNNs can infer suitable high-level representations without much domain-specific knowledge and prior feature construction.

Disadvantage:

  • Less performance

Proposed work:

We propose a novel mobile deep learning network for the characterization of SSc skin. The proposed network architecture consists of the UNet, a dense connectivity convolutional neural network (CNN) with added classifier layers that when combined with limited training data, yields better image segmentation and more accurate classification, and a mobile training module. In addition, to improve the computational efficiency and diagnostic accuracy, the highly efficient training model called “MobileNetV2,” which is designed for mobile and embedded applications, was used to train the network.

Advantage:

  • Inexpensive
  • Easy to implementation

Algorithms:

  • MobileNetV2

System requirements:

  Software requirements:

  • Operating system           :   Windows.
  • Coding Language :   Python.

Hardware components:

System                 :   Pentium IV 2.4 GHz or intel

Hard Disk                      :   40 GB.

Floppy Drive       :   1.44 Mb.

Mouse                  :   Optical Mouse.

Ram                      :   512 Mb.

Conclusion:

Our preliminary study, intended to show the efficacy of the proposed network architecture, holds promise in the characterization of SSc. We believe that the proposed network architecture could easily be implemented in a clinical setting, providing a simple, inexpensive, and accurate screening tool for SSc.

March 19, 2022

0 responses on "Deep Learning Classification of Systemic Sclerosis Skin Using the MobileNetV2 Model"

Leave a Message

Template Design © VibeThemes. All rights reserved.