figshare
Browse
khosravi-reinforcementlearning-2022.pdf (2.44 MB)

RLMD-PA: A Reinforcement Learning-Based Myocarditis Diagnosis Combined with a Population-Based Algorithm for Pretraining Weights

Download (2.44 MB)
Version 2 2024-06-05, 09:57
Version 1 2022-11-08, 03:06
journal contribution
posted on 2024-06-05, 09:57 authored by SV Moravvej, Roohallah AlizadehsaniRoohallah Alizadehsani, S Khanam, Z Sobhaninia, A Shoeibi, Fahime KhozeimehFahime Khozeimeh, ZA Sani, RS Tan, Abbas KhosraviAbbas Khosravi, S Nahavandi, NA Kadri, MM Azizan, N Arunkumar, UR Acharya
Myocarditis is heart muscle inflammation that is becoming more prevalent these days, especially with the prevalence of COVID-19. Noninvasive imaging cardiac magnetic resonance (CMR) can be used to diagnose myocarditis, but the interpretation is time-consuming and requires expert physicians. Computer-aided diagnostic systems can facilitate the automatic screening of CMR images for triage. This paper presents an automatic model for myocarditis classification based on a deep reinforcement learning approach called as reinforcement learning-based myocarditis diagnosis combined with population-based algorithm (RLMD-PA) that we evaluated using the Z-Alizadeh Sani myocarditis dataset of CMR images prospectively acquired at Omid Hospital, Tehran. This model addresses the imbalanced classification problem inherent to the CMR dataset and formulates the classification problem as a sequential decision-making process. The policy of architecture is based on convolutional neural network (CNN). To implement this model, we first apply the artificial bee colony (ABC) algorithm to obtain initial values for RLMD-PA weights. Next, the agent receives a sample at each step and classifies it. For each classification act, the agent gets a reward from the environment in which the reward of the minority class is greater than the reward of the majority class. Eventually, the agent finds an optimal policy under the guidance of a particular reward function and a helpful learning environment. Experimental results based on standard performance metrics show that RLMD-PA has achieved high accuracy for myocarditis classification, indicating that the proposed model is suitable for myocarditis diagnosis.

History

Journal

Contrast Media and Molecular Imaging

Volume

2022

Article number

8733632

Pagination

1-15

Location

New York, N.Y.

Open access

  • Yes

ISSN

1555-4309

eISSN

1555-4317

Language

eng

Publication classification

C1 Refereed article in a scholarly journal

Publisher

Hindawi Publishing Corporation

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC