2022
DOI: 10.1109/tcsvt.2021.3073021
|View full text |Cite
|
Sign up to set email alerts
|

Characterization of Pulmonary Nodules in Computed Tomography Images Based on Pseudo-Labeling Using Radiology Reports

Abstract: A computer-aided diagnosis (CAD) system that characterizes nodules in medical images can help radiologists determine its malignancy. Preparing large volumes of labeled data for CAD systems, however, requires advanced medical knowledge. This makes it extremely difficult to develop such systems, despite their growing demand. In this paper, we propose a new training method to build an image classifier for characterization of nodules utilizing pseudo-labels, i.e., image labels automatically retrieved from radiolog… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 12 publications
(6 citation statements)
references
References 25 publications
0
6
0
Order By: Relevance
“…There are some methods for extracting the characteristics of a tumor. Some of these methods aim to generate a radiology report from a single lung CT image automatically 3,4 . In these methods, the characteristics of tumors are extracted, and then radiology reports are generated based on them.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…There are some methods for extracting the characteristics of a tumor. Some of these methods aim to generate a radiology report from a single lung CT image automatically 3,4 . In these methods, the characteristics of tumors are extracted, and then radiology reports are generated based on them.…”
Section: Related Workmentioning
confidence: 99%
“…The automatic characterization systems that analyze only single phase have been proposed for lung nodules 3,4 and for liver tumors 5 , but as far as we know, this is the first system in terms of analyzing multiple phases.…”
Section: Our Contributionsmentioning
confidence: 99%
“…This approach helps identify identical sentences with the same symbols (Friedlin et al, 2011). In recent work, Niu et al (2021) and Momoki et al (2022) have illustrated different approaches to labelling radiology reports. In Niu et al (2021), a labelled dependent attention model is designed with the idea of jointly embedding labels and words, where both the modules will learn from the word weight.…”
Section: Radiology Report Processingmentioning
confidence: 99%
“…In Niu et al (2021), a labelled dependent attention model is designed with the idea of jointly embedding labels and words, where both the modules will learn from the word weight. In Momoki et al (2022), an image classifier is built using a pseudo label from a radiology report. Both techniques prove to be efficient compared to the existing methods.…”
Section: Radiology Report Processingmentioning
confidence: 99%
“…Pseudo-labeling allows for a simple and effective way to improve the predictive performance of trained machine learning models when labeling more data is costly and large amounts of unlabeled data are available. Pseudo-labeling can be easily implemented with various machine learning algorithms applied to different datasets (if unlabeled data is available) and domains, including applications in agriculture [5,6], medicine [7], person re-identi cation [8], and remote sensing [9] for example. The simplicity and versatility of pseudo-labeling were our main motivations for evaluating the application of this technique for training deep neural networks for animal identi cation.…”
Section: Introductionmentioning
confidence: 99%