基于深度学习的前列腺癌分期CT骨病变检测与分类:一项开发研究
这项回顾性研究利用297例前列腺癌分期CT(81例转移)开发了两个AI模型,分别用于骨病变检测分割和良恶性分类,并在45例未见数据上评估。检测模型对转移和良性病变检出率分别为73.1%和72.4%,患者水平转移检出达100%;分类模型F1为94.8%(放射科医生勾画轮廓)和92.4%(AI分割轮廓),PPV和NPV与中初级和高级放射科医生相当。
要点
- AI分割模型对转移和良性骨病变检出率分别为73.1%和72.4%,患者水平转移检出达100%。
- 基于放射科医生轮廓的分类AI F1为94.8%,基于AI分割轮廓为92.4%。
- 分类AI的PPV和NPV与中初级和高级放射科医生相当,纯AI流程NPV超过高级放射科医生。
核心结论
- 该病变检测与分类AI模型在区分前列腺癌分期CT上的良性与转移性病变方面,表现与中初级和高级放射科医生相当。
研究设计与样本
- 回顾性研究,使用297例前列腺癌分期CT(81例转移,4601个良性病变和1911个转移性病变)开发两个AI模型,转移经随访扫描、骨活检或PET/CT验证。
关键影像表现/征象
- 在45例未见分期CT(12例转移性前列腺癌)的669个良性病变和364个转移性病变中,分割AI检出73.1%的转移性病变(266/364)和72.4%的良性病变(484/669)。
- 每例扫描平均多出12个分割(范围1-31)。
- 所有转移性扫描均至少检出一个转移性病变,患者水平检出达100%。
诊断标准与关键数值
- 分割AI平均Dice评分为0.53(中位数0.59,范围0-0.87)。
- 分类AI基于放射科医生轮廓的F1为94.8%,基于分割AI轮廓的F1为92.4%,中位假阳性为0(范围0-3)。
- 基于放射科医生轮廓,分类AI的PPV为40.0%、NPV为96.2%,中初级放射科医生PPV为32.0%、NPV为95.7%,高级放射科医生PPV为50.0%、NPV为91.9%。
- 基于分割AI轮廓,分类AI的PPV为20.0%、NPV为93.8%,中初级放射科医生PPV为32.0%、NPV为95.7%,高级放射科医生PPV为50.0%、NPV为91.9%。
临床应用与阅片要点
- 分割AI可辅助检出骨病变,但平均每例扫描多出12个分割(范围1-31),阅片时需注意假阳性分割。
- 分类AI基于放射科医生轮廓时PPV和NPV与中初级和高级放射科医生相当,纯AI流程NPV超过高级放射科医生。
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Efficiently detecting and characterizing metastatic bone lesions on staging CT is crucial for prostate cancer (PCa) care. However, it demands significant expert time and additional imaging such as PET/CT. We aimed to develop an ensemble of two automated deep learning AI models for 1) bone lesion detection and segmentation and 2) benign vs. metastatic lesion classification on staging CTs and to compare its performance with radiologists.
MATERIALS AND METHODS: This retrospective study developed two AI models using 297 staging CT scans (81 metastatic) with 4601 benign and 1911 metastatic lesions in PCa patients. Metastases were validated by follow-up scans, bone biopsy, or PET/CT. Segmentation AI (3DAISeg) was developed using the lesion contours delineated by a radiologist. 3DAISeg performance was evaluated with the Dice similarity coefficient, and classification AI (3DAIClass) performance on AI and radiologist contours was assessed with F1-score and accuracy. Training/validation/testing data partitions of 70:15:15 were used. A multi-reader study was performed with two junior and two senior radiologists within a subset of the testing dataset (n = 36).
RESULTS: In 45 unseen staging CT scans (12 metastatic PCa) with 669 benign and 364 metastatic lesions, 3DAISeg detected 73.1% of metastatic (266/364) and 72.4% of benign lesions (484/669). Each scan averaged 12 extra segmentations (range: 1-31). All metastatic scans had at least one detected metastatic lesion, achieving a 100% patient-level detection. The mean Dice score for 3DAISeg was 0.53 (median: 0.59, range: 0-0.87). The F1 for 3DAIClass was 94.8% (radiologist contours) and 92.4% (3DAISeg contours), with a median false positive of 0 (range: 0-3). Using radiologist contours, 3DAIClass had PPV and NPV rates comparable to junior and senior radiologists: PPV (semi-automated approach AI 40.0% vs. Juniors 32.0% vs. Seniors 50.0%) and NPV (AI 96.2% vs. Juniors 95.7% vs. Seniors 91.9%). When using 3DAISeg, 3DAIClass mimicked junior radiologists in PPV (pure-AI 20.0% vs. Juniors 32.0% vs. Seniors 50.0%) but surpassed seniors in NPV (pure-AI 93.8% vs. Juniors 95.7% vs. Seniors 91.9%).
CONCLUSION: Our lesion detection and classification AI model performs on par with junior and senior radiologists in discerning benign and metastatic lesions on staging CTs obtained for PCa.
引用
- Belue MJ, Harmon SA, Yang D, et al. Deep Learning-Based Detection and Classification of Bone Lesions on Staging Computed Tomography in Prostate Cancer: A Development Study. Acad Radiol. 2024. PMID: 38262813. doi:10.1016/j.acra.2024.01.009
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。