Sökning: id:"swepub:oai:DiVA.org:su-209697" >
Exploring LRP and G...
Exploring LRP and Grad-CAM visualization to interpret multi-label-multi-class pathology prediction using chest radiography
-
- Alam, Mahbub Ul (författare)
- Stockholms universitet,Institutionen för data- och systemvetenskap
-
- Baldvinsson, Jón Rúnar (författare)
- Skatturinn (Iceland Revenue and Customs), Reykjavík, Iceland
-
- Wang, Yuxia (författare)
- Qamcom Research and Technology, Stockholm, Sweden
-
(creator_code:org_t)
- IEEE conference proceedings, 2022
- 2022
- Engelska.
-
Ingår i: 2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS). - : IEEE conference proceedings. - 9781665467704 ; , s. 258-263
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- The area of interpretable deep neural networks has received increased attention in recent years due to the need for transparency in various fields, including medicine, healthcare, stock market analysis, compliance with legislation, and law. Layer-wise Relevance Propagation (LRP) and Gradient-weighted Class Activation Mapping (Grad-CAM) are two widely used algorithms to interpret deep neural networks. In this work, we investigated the applicability of these two algorithms in the sensitive application area of interpreting chest radiography images. In order to get a more nuanced and balanced outcome, we use a multi-label classification-based dataset and analyze the model prediction by visualizing the outcome of LRP and Grad-CAM on the chest radiography images. The results show that LRP provides more granular heatmaps than Grad-CAM when applied to the CheXpert dataset classification model. We posit that this is due to the inherent construction difference of these algorithms (LRP is layer-wise accumulation, whereas Grad-CAM focuses primarily on the final sections in the model's architecture). Both can be useful for understanding the classification from a micro or macro level to get a superior and interpretable clinical decision support system.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Deep Learning
- Interpretability
- LRP
- Grad- CAM
- Chest X-ray
- Visualization
- Clinical Decision Support System
- data- och systemvetenskap
- Computer and Systems Sciences
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas