Prognosis Prediction of Lung Cancer Patients Using CT Images : Feature Extraction by Convolutional Neural Network and Prediction by Machine Learning
PURPOSE: Lung cancer accounts for the largest number of deaths among malignant tumors. Recently, more and more patients are concerned about their own life expectancy. CT examination is essential for the diagnosis of lung cancer. However, it is difficult to accurately predict the prognosis using CT images. In this study, we developed a method to predict the prognosis of lung cancer patients from CT images using a convolutional neural network (CNN) and a machine learning method.
METHODS: In this study, the CT images of 173 lung cancer patients were collected. First, we selected the slice with the largest tumor size in each case and extracted features using a CNN. Next, we performed feature selection using information gain and predicted alive or death by classifiers. An artificial neural network or Naïve Bayes was used as a classifier and alive and death were predicted at one-year intervals from one year to five years later.
RESULTS: We evaluated the prediction accuracy via the three-fold cross-validation method and found that the prediction accuracies were around 80% for all periods from 1 to 5 years. In the evaluation of the survival curve, the shape of the curve was close to the actual curve.
CONCLUSION: These results indicate that feature extraction by a CNN and classification by the machine learning method may be effective in predicting the prognosis of lung cancer patients using CT images.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:78 |
|---|---|
| Enthalten in: |
Nihon Hoshasen Gijutsu Gakkai zasshi - 78(2022), 8 vom: 20. Aug., Seite 829-837 |
| Sprache: |
Japanisch |
|---|
| Beteiligte Personen: |
Oshita, Yuki [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Convolutional neural network |
|---|
| Anmerkungen: |
Date Completed 23.08.2022 Date Revised 23.08.2022 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.6009/jjrt.2022-1224 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM343316072 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM343316072 | ||
| 003 | DE-627 | ||
| 005 | 20231226020149.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2022 xx |||||o 00| ||jpn c | ||
| 024 | 7 | |a 10.6009/jjrt.2022-1224 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1144.xml |
| 035 | |a (DE-627)NLM343316072 | ||
| 035 | |a (NLM)35811128 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a jpn | ||
| 100 | 1 | |a Oshita, Yuki |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Prognosis Prediction of Lung Cancer Patients Using CT Images |b Feature Extraction by Convolutional Neural Network and Prediction by Machine Learning |
| 264 | 1 | |c 2022 | |
| 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 23.08.2022 | ||
| 500 | |a Date Revised 23.08.2022 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a PURPOSE: Lung cancer accounts for the largest number of deaths among malignant tumors. Recently, more and more patients are concerned about their own life expectancy. CT examination is essential for the diagnosis of lung cancer. However, it is difficult to accurately predict the prognosis using CT images. In this study, we developed a method to predict the prognosis of lung cancer patients from CT images using a convolutional neural network (CNN) and a machine learning method | ||
| 520 | |a METHODS: In this study, the CT images of 173 lung cancer patients were collected. First, we selected the slice with the largest tumor size in each case and extracted features using a CNN. Next, we performed feature selection using information gain and predicted alive or death by classifiers. An artificial neural network or Naïve Bayes was used as a classifier and alive and death were predicted at one-year intervals from one year to five years later | ||
| 520 | |a RESULTS: We evaluated the prediction accuracy via the three-fold cross-validation method and found that the prediction accuracies were around 80% for all periods from 1 to 5 years. In the evaluation of the survival curve, the shape of the curve was close to the actual curve | ||
| 520 | |a CONCLUSION: These results indicate that feature extraction by a CNN and classification by the machine learning method may be effective in predicting the prognosis of lung cancer patients using CT images | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a convolutional neural network | |
| 650 | 4 | |a lung cancer | |
| 650 | 4 | |a machine learning | |
| 650 | 4 | |a predict prognosis | |
| 650 | 4 | |a survival curve | |
| 700 | 1 | |a Takeuchi, Nonoko |e verfasserin |4 aut | |
| 700 | 1 | |a Teramoto, Atsushi |e verfasserin |4 aut | |
| 700 | 1 | |a Kondo, Masashi |e verfasserin |4 aut | |
| 700 | 1 | |a Imaizumi, Kazuyoshi |e verfasserin |4 aut | |
| 700 | 1 | |a Saito, Kuniaki |e verfasserin |4 aut | |
| 700 | 1 | |a Fujita, Hiroshi |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Nihon Hoshasen Gijutsu Gakkai zasshi |d 1993 |g 78(2022), 8 vom: 20. Aug., Seite 829-837 |w (DE-627)NLM074820923 |x 1881-4883 |7 nnns |
| 773 | 1 | 8 | |g volume:78 |g year:2022 |g number:8 |g day:20 |g month:08 |g pages:829-837 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.6009/jjrt.2022-1224 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 78 |j 2022 |e 8 |b 20 |c 08 |h 829-837 | ||