Skip to main content
Top
Published in:

Open Access 04-04-2023 | Ultrasound | Original Article–Physics & Engineering

A study on the optimal condition of ground truth area for liver tumor detection in ultrasound images using deep learning

Authors: Taisei Tosaki, Makoto Yamakawa, Tsuyoshi Shiina

Published in: Journal of Medical Ultrasonics | Issue 2/2023

Login to get access

Abstract

Purpose

In recent years, efforts to apply artificial intelligence (AI) to the medical field have been growing. In general, a vast amount of high-quality training data is necessary to make great AI. For tumor detection AI, annotation quality is important. In diagnosis and detection of tumors using ultrasound images, humans use not only the tumor area but also the surrounding information, such as the back echo of the tumor. Therefore, we investigated changes in detection accuracy when changing the size of the region of interest (ROI, ground truth area) relative to liver tumors in the training data for the detection AI.

Methods

We defined D/L as the ratio of the maximum diameter (D) of the liver tumor to the ROI size (L). We created training data by changing the D/L value, and performed learning and testing with YOLOv3.

Results

Our results showed that the detection accuracy was highest when the training data were created with a D/L ratio between 0.8 and 1.0. In other words, it was found that the detection accuracy was improved by setting the ground true bounding box for detection AI training to be in contact with the tumor or slightly larger. We also found that when the D/L ratio was distributed in the training data, the wider the distribution, the lower the detection accuracy.

Conclusions

Therefore, we recommend that the detector be trained with the D/L value close to a certain value between 0.8 and 1.0 for liver tumor detection from ultrasound images.
Literature
2.
go back to reference Fujioka T, Mori M, Kubota K, et al. The utility of deep learning in breast ultrasonic imaging: a review. Diagnostics (Basel). 2020;10:1055.CrossRefPubMed Fujioka T, Mori M, Kubota K, et al. The utility of deep learning in breast ultrasonic imaging: a review. Diagnostics (Basel). 2020;10:1055.CrossRefPubMed
3.
go back to reference Jiang Y, Inciardi MF, Edwards AV, et al. Interpretation time using a concurrent-read computer-aided detection system for automated breast ultrasound in breast cancer screening of women with dense breast tissue. Am J Roentgenol. 2018;211:452–61.CrossRef Jiang Y, Inciardi MF, Edwards AV, et al. Interpretation time using a concurrent-read computer-aided detection system for automated breast ultrasound in breast cancer screening of women with dense breast tissue. Am J Roentgenol. 2018;211:452–61.CrossRef
4.
go back to reference Yang S, Gao X, Liu L, et al. Performance and reading time of automated breast US with or without computer-aided detection. Radiology. 2019;292:540–9.CrossRefPubMed Yang S, Gao X, Liu L, et al. Performance and reading time of automated breast US with or without computer-aided detection. Radiology. 2019;292:540–9.CrossRefPubMed
5.
go back to reference Xu X, Bao L, Tan Y, et al. 1000-Case reader study of radiologists’ performance in interpretation of automated breast volume scanner images with a computer-aided detection system. Ultrasound Med Biol. 2018;44:1694–702.CrossRefPubMed Xu X, Bao L, Tan Y, et al. 1000-Case reader study of radiologists’ performance in interpretation of automated breast volume scanner images with a computer-aided detection system. Ultrasound Med Biol. 2018;44:1694–702.CrossRefPubMed
8.
go back to reference Cao Z, Duan L, Yang G, et al. An experimental study on breast lesion detection and classification from ultrasound images using deep learning architectures. BMC Med Imaging. 2019;19:51.CrossRefPubMedPubMedCentral Cao Z, Duan L, Yang G, et al. An experimental study on breast lesion detection and classification from ultrasound images using deep learning architectures. BMC Med Imaging. 2019;19:51.CrossRefPubMedPubMedCentral
9.
go back to reference Zhang X, Lin X, Zhang Z, et al. Artificial intelligence medical ultrasound equipment: application of breast lesions detection. Ultrason Imaging. 2020;42:191–202.CrossRefPubMed Zhang X, Lin X, Zhang Z, et al. Artificial intelligence medical ultrasound equipment: application of breast lesions detection. Ultrason Imaging. 2020;42:191–202.CrossRefPubMed
10.
go back to reference Xie S, Yu J, Liu T, et al. Thyroid nodule detection in ultrasound images with convolutional neural networks. 2019 14th ICIEA. 2019; 1442–6 Xie S, Yu J, Liu T, et al. Thyroid nodule detection in ultrasound images with convolutional neural networks. 2019 14th ICIEA. 2019; 1442–6
11.
go back to reference Zhang L, Zhuang Y, Hua Z, et al. Automated location of thyroid nodules in ultrasound images with improved YOLOV3 network. J Xray Sci Technol. 2021;29:75–90.PubMed Zhang L, Zhuang Y, Hua Z, et al. Automated location of thyroid nodules in ultrasound images with improved YOLOV3 network. J Xray Sci Technol. 2021;29:75–90.PubMed
12.
go back to reference Song W, Li S, Liu J, et al. Multitask cascade convolution neural networks for automatic thyroid nodule detection and recognition. IEEE J Biomed Health Inform. 2019;23:1215–24.CrossRefPubMed Song W, Li S, Liu J, et al. Multitask cascade convolution neural networks for automatic thyroid nodule detection and recognition. IEEE J Biomed Health Inform. 2019;23:1215–24.CrossRefPubMed
13.
go back to reference Yamakawa M, Shiina T, Nishida N, et al. Optimal cropping for input images used in a convolutional neural network for ultrasonic diagnosis of liver tumors. Jap J App Phys. 2020;59:SKKE09.CrossRef Yamakawa M, Shiina T, Nishida N, et al. Optimal cropping for input images used in a convolutional neural network for ultrasonic diagnosis of liver tumors. Jap J App Phys. 2020;59:SKKE09.CrossRef
15.
go back to reference Akkus Z, Cai J, Boonrod A, et al. A survey of deep-learning applications in ultrasound: artificial intelligence-powered ultrasound for improving clinical workflow. J Am Coll Radiol. 2019;16(9 Pt B):1318–28.CrossRefPubMed Akkus Z, Cai J, Boonrod A, et al. A survey of deep-learning applications in ultrasound: artificial intelligence-powered ultrasound for improving clinical workflow. J Am Coll Radiol. 2019;16(9 Pt B):1318–28.CrossRefPubMed
16.
go back to reference Nishida N, Yamakawa M, Shiina T, et al. Current status and perspectives for computer-aided ultrasonic diagnosis of liver lesions using deep learning technology. Hepatol Int. 2019;13:416–21.CrossRefPubMed Nishida N, Yamakawa M, Shiina T, et al. Current status and perspectives for computer-aided ultrasonic diagnosis of liver lesions using deep learning technology. Hepatol Int. 2019;13:416–21.CrossRefPubMed
17.
go back to reference Nishida N, Kudo M. Artificial intelligence in medical imaging and its application in sonography for the management of liver tumor. Front Oncol. 2020;10: 594580.CrossRefPubMedPubMedCentral Nishida N, Kudo M. Artificial intelligence in medical imaging and its application in sonography for the management of liver tumor. Front Oncol. 2020;10: 594580.CrossRefPubMedPubMedCentral
18.
go back to reference Nishida N, Yamakawa M, Shiina T, et al. Artificial intelligence (AI) models for the ultrasonographic diagnosis of liver tumors and comparison of diagnostic accuracies between AI and human experts. J Gastroenterol. 2022;57:309–21.CrossRefPubMedPubMedCentral Nishida N, Yamakawa M, Shiina T, et al. Artificial intelligence (AI) models for the ultrasonographic diagnosis of liver tumors and comparison of diagnostic accuracies between AI and human experts. J Gastroenterol. 2022;57:309–21.CrossRefPubMedPubMedCentral
19.
go back to reference Dadoun H, Rousseau AL, Kerviler E, et al. Deep learning for the detection, localization, and characterization of focal liver lesions on abdominal US images. Radiol AI. 2022;4: 210110. Dadoun H, Rousseau AL, Kerviler E, et al. Deep learning for the detection, localization, and characterization of focal liver lesions on abdominal US images. Radiol AI. 2022;4: 210110.
20.
go back to reference Xu Y, Zhu L, Yang Y, et al. Training robust object detectors from noisy category labels and imprecise bounding boxes. IEEE Trans Image Process. 2021;30:5782–92.CrossRefPubMed Xu Y, Zhu L, Yang Y, et al. Training robust object detectors from noisy category labels and imprecise bounding boxes. IEEE Trans Image Process. 2021;30:5782–92.CrossRefPubMed
21.
go back to reference Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection. IEEE CVPR. 2016;2016:779–88. Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection. IEEE CVPR. 2016;2016:779–88.
22.
go back to reference Redmon J, Farhadi A. YOLO9000: better, faster, stronger. IEEE CVPR. 2017;2017:6517–25. Redmon J, Farhadi A. YOLO9000: better, faster, stronger. IEEE CVPR. 2017;2017:6517–25.
24.
go back to reference Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector. In: Computer vision—ECCV 2016. New York: Springer; 2016. p. 21–37.CrossRef Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector. In: Computer vision—ECCV 2016. New York: Springer; 2016. p. 21–37.CrossRef
25.
go back to reference Girshick R. Fast R-CNN. IEEE ICCV. 2015;2015:1440–8. Girshick R. Fast R-CNN. IEEE ICCV. 2015;2015:1440–8.
26.
go back to reference Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell. 2015;39:1137–49.CrossRef Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell. 2015;39:1137–49.CrossRef
27.
go back to reference Huang J, Rathod V, Sun C, et al. Speed/accuracy trade-offs for modern convolutional object detectors. IEEE CVPR. 2017;2017:3296–305. Huang J, Rathod V, Sun C, et al. Speed/accuracy trade-offs for modern convolutional object detectors. IEEE CVPR. 2017;2017:3296–305.
Metadata
Title
A study on the optimal condition of ground truth area for liver tumor detection in ultrasound images using deep learning
Authors
Taisei Tosaki
Makoto Yamakawa
Tsuyoshi Shiina
Publication date
04-04-2023
Publisher
Springer Nature Singapore
Published in
Journal of Medical Ultrasonics / Issue 2/2023
Print ISSN: 1346-4523
Electronic ISSN: 1613-2254
DOI
https://doi.org/10.1007/s10396-023-01301-2

Other articles of this Issue 2/2023

Journal of Medical Ultrasonics 2/2023 Go to the issue