PMID- 32012032
OWN - NLM
STAT- MEDLINE
DCOM- 20210503
LR  - 20210503
IS  - 2168-2208 (Electronic)
IS  - 2168-2194 (Linking)
VI  - 24
IP  - 8
DP  - 2020 Aug
TI  - Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable 
      Filterbanks.
PG  - 2189-2198
LID - 10.1109/JBHI.2020.2970252 [doi]
AB  - OBJECTIVE: Cardiac auscultation is the most practiced non-invasive and 
      cost-effective procedure for the early diagnosis of heart diseases. While machine 
      learning based systems can aid in automatically screening patients, the 
      robustness of these systems is affected by numerous factors including the 
      stethoscope/sensor, environment, and data collection protocol. This article 
      studies the adverse effect of domain variability on heart sound abnormality 
      detection and develops strategies to address this problem. METHODS: We propose a 
      novel Convolutional Neural Network (CNN) layer, consisting of time-convolutional 
      (tConv) units, that emulate Finite Impulse Response (FIR) filters. The filter 
      coefficients can be updated via backpropagation and be stacked in the front-end 
      of the network as a learnable filterbank. RESULTS: On publicly available 
      multi-domain datasets, the proposed method surpasses the top-scoring systems 
      found in the literature for heart sound abnormality detection (a binary 
      classification task). We utilized sensitivity, specificity, F-1 score and Macc 
      (average of sensitivity and specificity) as performance metrics. Our systems 
      achieved relative improvements of up to 11.84% in terms of MAcc, compared to 
      state-of-the-art methods. CONCLUSION: The results demonstrate the effectiveness 
      of the proposed learnable filterbank CNN architecture in achieving robustness 
      towards sensor/domain variability in PCG signals. SIGNIFICANCE: The proposed 
      methods pave the way for deploying automated cardiac screening systems in 
      diversified and underserved communities.
FAU - Humayun, Ahmed Imtiaz
AU  - Humayun AI
FAU - Ghaffarzadegan, Shabnam
AU  - Ghaffarzadegan S
FAU - Ansari, Md Istiaq
AU  - Ansari MI
FAU - Feng, Zhe
AU  - Feng Z
FAU - Hasan, Taufiq
AU  - Hasan T
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20200131
PL  - United States
TA  - IEEE J Biomed Health Inform
JT  - IEEE journal of biomedical and health informatics
JID - 101604520
SB  - IM
MH  - Algorithms
MH  - Databases, Factual
MH  - Heart Diseases/diagnosis
MH  - Heart Sounds/*physiology
MH  - Humans
MH  - *Neural Networks, Computer
MH  - *Phonocardiography/classification/methods
MH  - Sensitivity and Specificity
MH  - *Signal Processing, Computer-Assisted
EDAT- 2020/02/06 06:00
MHDA- 2021/05/04 06:00
CRDT- 2020/02/04 06:00
PHST- 2020/02/06 06:00 [pubmed]
PHST- 2021/05/04 06:00 [medline]
PHST- 2020/02/04 06:00 [entrez]
AID - 10.1109/JBHI.2020.2970252 [doi]
PST - ppublish
SO  - IEEE J Biomed Health Inform. 2020 Aug;24(8):2189-2198. doi: 
      10.1109/JBHI.2020.2970252. Epub 2020 Jan 31.