Saved in:
Bibliographic Details
Main Authors: Zheng, Chengxin, Ji, Junzhong, Shi, Yanzhao, Zhang, Xiaodan, Qu, Liangqiong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.19676
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929522273681408
author Zheng, Chengxin
Ji, Junzhong
Shi, Yanzhao
Zhang, Xiaodan
Qu, Liangqiong
author_facet Zheng, Chengxin
Ji, Junzhong
Shi, Yanzhao
Zhang, Xiaodan
Qu, Liangqiong
contents Brain CT report generation is significant to aid physicians in diagnosing cranial diseases. Recent studies concentrate on handling the consistency between visual and textual pathological features to improve the coherence of report. However, there exist some challenges: 1) Redundant visual representing: Massive irrelevant areas in 3D scans distract models from representing salient visual contexts. 2) Shifted semantic representing: Limited medical corpus causes difficulties for models to transfer the learned textual representations to generative layers. This study introduces a Pathological Clue-driven Representation Learning (PCRL) model to build cross-modal representations based on pathological clues and naturally adapt them for accurate report generation. Specifically, we construct pathological clues from perspectives of segmented regions, pathological entities, and report themes, to fully grasp visual pathological patterns and learn cross-modal feature representations. To adapt the representations for the text generation task, we bridge the gap between representation learning and report generation by using a unified large language model (LLM) with task-tailored instructions. These crafted instructions enable the LLM to be flexibly fine-tuned across tasks and smoothly transfer the semantic representation for report generation. Experiments demonstrate that our method outperforms previous methods and achieves SoTA performance. Our code is available at "https://github.com/Chauncey-Jheng/PCRL-MRG".
format Preprint
id arxiv_https___arxiv_org_abs_2409_19676
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle See Detail Say Clear: Towards Brain CT Report Generation via Pathological Clue-driven Representation Learning
Zheng, Chengxin
Ji, Junzhong
Shi, Yanzhao
Zhang, Xiaodan
Qu, Liangqiong
Computer Vision and Pattern Recognition
Artificial Intelligence
Brain CT report generation is significant to aid physicians in diagnosing cranial diseases. Recent studies concentrate on handling the consistency between visual and textual pathological features to improve the coherence of report. However, there exist some challenges: 1) Redundant visual representing: Massive irrelevant areas in 3D scans distract models from representing salient visual contexts. 2) Shifted semantic representing: Limited medical corpus causes difficulties for models to transfer the learned textual representations to generative layers. This study introduces a Pathological Clue-driven Representation Learning (PCRL) model to build cross-modal representations based on pathological clues and naturally adapt them for accurate report generation. Specifically, we construct pathological clues from perspectives of segmented regions, pathological entities, and report themes, to fully grasp visual pathological patterns and learn cross-modal feature representations. To adapt the representations for the text generation task, we bridge the gap between representation learning and report generation by using a unified large language model (LLM) with task-tailored instructions. These crafted instructions enable the LLM to be flexibly fine-tuned across tasks and smoothly transfer the semantic representation for report generation. Experiments demonstrate that our method outperforms previous methods and achieves SoTA performance. Our code is available at "https://github.com/Chauncey-Jheng/PCRL-MRG".
title See Detail Say Clear: Towards Brain CT Report Generation via Pathological Clue-driven Representation Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2409.19676