EUVIMEDEUVIMED entdecken
Crossref

Development of an Artificial Intelligence System for Distinguishing Malignant from Benign Soft-Tissue Tumors Using Contrast-Enhanced MR Images

Toru Hirozane, Masahiro Hashimoto, Hasnine Haque, Yuki Arita, Tomoaki Mori, Naofumi Asano, Robert Nakayama, Takeshi Morii, Naobumi Hosogane, Morio Matsumoto, Masaya Nakamura, Masahiro Jinzaki

Oncology · 23.10.2024 · 103 (7) · 580-590

DOI: 10.1159/000542228 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Oncology, online erschienen am 23.10.2024. Verfasst von Toru Hirozane und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopaedic Surgery, Keio University School of Medicine, Shinjuku, Japan. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Soft Tissue Neoplasms, Artificial Intelligence, Contrast Media. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The integration of artificial intelligence (AI) into orthopedics has enhanced the diagnosis of various conditions; however, its use in diagnosing soft-tissue tumors remains limited owing to its complexity. This study aimed to develop and assess an AI-driven diagnostic support system for magnetic resonance imaging (MRI)-based soft-tissue tumor diagnosis, potentially improving accuracy and aiding radiologists and orthopedic surgeons.

Methods

An experienced orthopedic oncologist and radiologist annotated 720 images from 77 cases (41 benign and 36 malignant soft-tissue tumors). Eleven tumor subtypes were identified and classified into benign and malignant groups based on histological diagnosis. Utilizing the standard machine learning classifier pipeline, we examined and down-selected imaging protocols and their predominant radiomic features within the tumor’s three-dimensional region to differentiate between benign and malignant tumors. Among the scan protocols, contrast-enhanced T1-weighted fat-suppressed images showed the most accurate classification based on radiomic features. We focused on the two-dimensional features from the largest tumor boundary surface and its neighboring slices, leveraging texture-based radiomic and deep convolutional neural network features from a pretrained VGG19 model.

Results

The test data comprised 44 contrast-enhanced images (22 benign and 22 malignant soft-tissue tumors) containing six malignant and five benign subtypes distinct from the training data. We compared expert and nonexpert human performances against AI by assessing malignancy detection and the time required for classification. The AI model showed comparable accuracy (AUC 0.91) to that of radiologists (AUC 0.83) and orthopedic surgeons (AUC 0.73). Notably, the AI model processed data approximately 400 times faster than its human counterparts, showcasing its capacity to significantly boost diagnostic efficiency.

Conclusion

We developed an AI-driven diagnostic support system for MRI-based soft-tissue tumor diagnosis. While additional refinement is necessary for clinical applications, our system has exhibited promising potential in differentiating between benign and malignant soft-tissue tumors based on MRI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingSoft Tissue NeoplasmsArtificial IntelligenceContrast MediaHumansFemaleMaleMiddle AgedDiagnosis, DifferentialAdultNeural Networks, ComputerAgedImage Interpretation, Computer-Assisted

Stichwörter der Autor:innen

Artificial intelligenceMagnetic resonance imagingSarcomaSoft-tissue tumors

Substanzen

Contrast Media

Autor:innen und Institutionen

  • Department of Orthopaedic Surgery, Keio University School of Medicine, Shinjuku, Japan.
  • Department of Orthopaedic Surgery, Kyorin University Faculty of Medicine, Mitaka, Japan.
  • Department of Radiology, Keio University School of Medicine, Shinjuku, Japan.
  • GE HealthCare, Hino, Japan.

Zitieren

APA

Hirozane, T., Hashimoto, M., Haque, H., Arita, Y., Mori, T., Asano, N., Nakayama, R., Morii, T., Hosogane, N., Matsumoto, M., Nakamura, M., & Jinzaki, M. (2024). Development of an Artificial Intelligence System for Distinguishing Malignant from Benign Soft-Tissue Tumors Using Contrast-Enhanced MR Images. Oncology, 103(7), 580-590. https://doi.org/10.1159/000542228

Vancouver

Hirozane T, Hashimoto M, Haque H, Arita Y, Mori T, Asano N, et al. Development of an Artificial Intelligence System for Distinguishing Malignant from Benign Soft-Tissue Tumors Using Contrast-Enhanced MR Images. Oncology. 2024;103(7):580-590. doi:10.1159/000542228

BibTeX
@article{Hirozane2024,
  author = {Hirozane, Toru and Hashimoto, Masahiro and Haque, Hasnine and Arita, Yuki and Mori, Tomoaki and Asano, Naofumi and Nakayama, Robert and Morii, Takeshi and Hosogane, Naobumi and Matsumoto, Morio and Nakamura, Masaya and Jinzaki, Masahiro},
  title = {Development of an Artificial Intelligence System for Distinguishing Malignant from Benign Soft-Tissue Tumors Using Contrast-Enhanced MR Images},
  journal = {Oncology},
  year = {2024},
  volume = {103},
  number = {7},
  pages = {580--590},
  doi = {10.1159/000542228}
}
Kostenlos starten →