Uncertainty-aware image classification on 3D CT lung
Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved..
Early detection is crucial for lung cancer to prolong the patient's survival. Existing model architectures used in such systems have shown promising results. However, they lack reliability and robustness in their predictions and the models are typically evaluated on a single dataset, making them overconfident when a new class is present. With the existence of uncertainty, uncertain images can be referred to medical experts for a second opinion. Thus, we propose an uncertainty-aware framework that includes three phases: data preprocessing and model selection and evaluation, uncertainty quantification (UQ), and uncertainty measurement and data referral for the classification of benign and malignant nodules using 3D CT images. To quantify the uncertainty, we employed three approaches; Monte Carlo Dropout (MCD), Deep Ensemble (DE), and Ensemble Monte Carlo Dropout (EMCD). We evaluated eight different deep learning models consisting of ResNet, DenseNet, and the Inception network family, all of which achieved average F1 scores above 0.832, and the highest average value of 0.845 was obtained using InceptionResNetV2. Furthermore, incorporating the UQ demonstrated significant improvement in the overall model performance. Upon evaluation of the uncertainty estimate, MCD outperforms the other UQ models except for the metric, URecall, where DE and EMCD excel, implying that they are better at identifying incorrect predictions with higher uncertainty levels, which is vital in the medical field. Finally, we show that using a threshold for data referral can greatly improve the performance further, increasing the accuracy up to 0.959.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:172 |
|---|---|
| Enthalten in: |
Computers in biology and medicine - 172(2024) vom: 19. März, Seite 108324 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Zahari, Rahimi [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
CT |
|---|
| Anmerkungen: |
Date Completed 26.03.2024 Date Revised 26.03.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.compbiomed.2024.108324 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM369976320 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM369976320 | ||
| 003 | DE-627 | ||
| 005 | 20240326235927.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240322s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.compbiomed.2024.108324 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1349.xml |
| 035 | |a (DE-627)NLM369976320 | ||
| 035 | |a (NLM)38508053 | ||
| 035 | |a (PII)S0010-4825(24)00408-6 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Zahari, Rahimi |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Uncertainty-aware image classification on 3D CT lung |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 26.03.2024 | ||
| 500 | |a Date Revised 26.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved. | ||
| 520 | |a Early detection is crucial for lung cancer to prolong the patient's survival. Existing model architectures used in such systems have shown promising results. However, they lack reliability and robustness in their predictions and the models are typically evaluated on a single dataset, making them overconfident when a new class is present. With the existence of uncertainty, uncertain images can be referred to medical experts for a second opinion. Thus, we propose an uncertainty-aware framework that includes three phases: data preprocessing and model selection and evaluation, uncertainty quantification (UQ), and uncertainty measurement and data referral for the classification of benign and malignant nodules using 3D CT images. To quantify the uncertainty, we employed three approaches; Monte Carlo Dropout (MCD), Deep Ensemble (DE), and Ensemble Monte Carlo Dropout (EMCD). We evaluated eight different deep learning models consisting of ResNet, DenseNet, and the Inception network family, all of which achieved average F1 scores above 0.832, and the highest average value of 0.845 was obtained using InceptionResNetV2. Furthermore, incorporating the UQ demonstrated significant improvement in the overall model performance. Upon evaluation of the uncertainty estimate, MCD outperforms the other UQ models except for the metric, URecall, where DE and EMCD excel, implying that they are better at identifying incorrect predictions with higher uncertainty levels, which is vital in the medical field. Finally, we show that using a threshold for data referral can greatly improve the performance further, increasing the accuracy up to 0.959 | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a CT | |
| 650 | 4 | |a Deep ensemble | |
| 650 | 4 | |a Lung cancer | |
| 650 | 4 | |a Monte Carlo | |
| 650 | 4 | |a Uncertainty quantification | |
| 700 | 1 | |a Cox, Julie |e verfasserin |4 aut | |
| 700 | 1 | |a Obara, Boguslaw |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Computers in biology and medicine |d 1970 |g 172(2024) vom: 19. März, Seite 108324 |w (DE-627)NLM000382272 |x 1879-0534 |7 nnns |
| 773 | 1 | 8 | |g volume:172 |g year:2024 |g day:19 |g month:03 |g pages:108324 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.compbiomed.2024.108324 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 172 |j 2024 |b 19 |c 03 |h 108324 | ||