Hirosaki team at the NTCIR-18 RadNLP2024 Shared Task: Few-Shot Learning and Prompt Engineering for TNM Staging Classification of English Radiology Reports Using Large Language Models.

Ryutaro Mori; Koichi Okuda; Shota Hosokawa; Taisei Komoda; Tsudou Watanabe; Yasuyuki Takahashi

WEKO3

lat lon distance

[[sub_check.contents]]

[[sub_radio.contents]]

Field does not validate

[[sub_attr.contents]]　

インデックスツリー

アイテム

Hirosaki team at the NTCIR-18 RadNLP2024 Shared Task: Few-Shot Learning and Prompt Engineering for TNM Staging Classification of English Radiology Reports Using Large Language Models.

https://doi.org/10.20736/0002002065

名前 / ファイル	ライセンス	アクション
05-NTCIR18-RADNLP-MoriR.pdf (760.7 KB)

アイテムタイプ

デフォルトアイテムタイプ（フル）(1)

公開日

2025-06-06

タイトル

Hirosaki team at the NTCIR-18 RadNLP2024 Shared Task: Few-Shot Learning and Prompt Engineering for TNM Staging Classification of English Radiology Reports Using Large Language Models.

言語

作成者

Ryutaro Mori
Koichi Okuda
Shota Hosokawa
Taisei Komoda
Tsudou Watanabe
Yasuyuki Takahashi

内容記述

内容記述タイプ

Abstract

内容記述

We participated in the NTCIR-18 RadNLP2024 shared task [1] and investigated the automation of TNM classification using large language models (LLMs), specifically GPT-4o-mini, GPT-4o, and o1-mini. Our approach integrates cosine similarity-based retrieval using embedding vectors and few-shot learning to enhance classification accuracy. As a result of the experiment, o1-mini achieved the highest classification accuracy. However, the accuracy on the test data declined by approximately 30% compared to the validation data. In particular, the low classification accuracy of the T factor highlighted challenges in interpreting tumor size and extent of infiltration. In this paper, we analyze these results and report our approach to this task along with official results.

言語

出版者

NII Institutional Repository

言語

日付

2025-06-06

日付タイプ

Issued

言語

eng

資源タイプ

資源タイプ識別子

http://purl.org/coar/resource_type/c_5794

資源タイプ

conference paper

ID登録

10.20736/0002002065

ID登録タイプ

JaLC

Versions

Ver.1

2025-06-04 08:01:56.832231

Show All versions

Cite as

Other

エクスポート

OAI-PMH

JPCOAR 2.0
JPCOAR 1.0
DublinCore
DDI

Other Formats

インデックスリンク

インデックスツリー

アイテム

Hirosaki team at the NTCIR-18 RadNLP2024 Shared Task: Few-Shot Learning and Prompt Engineering for TNM Staging Classification of English Radiology Reports Using Large Language Models.

× Ryutaro Mori

× Koichi Okuda

× Shota Hosokawa

× Taisei Komoda

× Tsudou Watanabe

× Yasuyuki Takahashi

Versions

Share

Cite as

Other

エクスポート

コミュニティ

メニューを最小化

インデックスリンク

インデックスツリー

アイテム

Hirosaki team at the NTCIR-18 RadNLP2024 Shared Task: Few-Shot Learning and Prompt Engineering for TNM Staging Classification of English Radiology Reports Using Large Language Models.

× Ryutaro Mori

× Koichi Okuda

× Shota Hosokawa

× Taisei Komoda

× Tsudou Watanabe

× Yasuyuki Takahashi

Versions

Share

Cite as

Other

エクスポート

コミュニティ