文献速递骨肌DR

多任务深度学习在X线片原发骨肿瘤分割与分类中的应用

Multitask Deep Learning for Segmentation and Classification of Primary Bone Tumors on Radiographs.
PubMed 文献 · Radiology · 2021-09-07

本研究回顾性分析2000年1月至2020年6月934例经组织病理学确诊的原发骨肿瘤患者X线片,开发多任务深度学习模型同时完成边界框定位、分割和良恶性分类,并在111例外部队列中验证。模型分类准确率80.2%,敏感度62.9%,特异度88.2%,准确率高于两名放射科住院医师,与两名骨肌 fellowship 放射科医师相当。

要点

  • 模型可在X线片上同时完成骨肿瘤边界框定位、分割和良恶性分类。
  • 外部队列分类准确率80.2%,特异度88.2%,但敏感度仅62.9%。
  • 模型分类准确率高于放射科住院医师,与骨肌专科放射科医师相当。

核心结论

  • 多任务深度学习模型可在X线片上准确同时完成原发骨肿瘤的边界框定位、分割和良恶性分类。

研究设计与样本

  • 回顾性研究分析2000年1月至2020年6月治疗前X线片,以组织病理学为参考标准,内部数据集934例(平均年龄33岁±19,419例女性;良性667例,恶性267例)。

诊断标准与关键数值

  • 外部队列良恶性分类准确率80.2%(89/111;95% CI:72.8,87.6),敏感度62.9%(22/35;95% CI:47,79),特异度88.2%(67/76;95% CI:81,96)。
  • 边界框定位IoU为0.52±0.34,分割平均Dice分数为0.60±0.37。
  • 模型分类准确率高于两名放射科住院医师(71.2%和64.9%;P=.002和P<.001),与两名骨肌 fellowship 放射科医师(83.8%和82.9%;P=.13和P=.25)相当。

临床应用与阅片要点

  • 模型高特异度、较低敏感度提示其更适用于排除恶性,阴性结果需结合临床及影像综合判断。
  • 边界框IoU和Dice分数中等,分割结果不宜直接作为精确测量依据。

局限性

  • 回顾性研究设计,外部验证样本量较小(111例)。
  • 敏感度62.9%,漏诊恶性骨肿瘤风险较高。

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

Background An artificial intelligence model that assesses primary bone tumors on radiographs may assist in the diagnostic workflow. Purpose To develop a multitask deep learning (DL) model for simultaneous bounding box placement, segmentation, and classification of primary bone tumors on radiographs. Materials and Methods This retrospective study analyzed bone tumors on radiographs acquired prior to treatment and obtained from patient data from January 2000 to June 2020. Benign or malignant bone tumors were diagnosed in all patients by using the histopathologic findings as the reference standard. By using split-sample validation, 70% of the patients were assigned to the training set, 15% were assigned to the validation set, and 15% were assigned to the test set. The final performance was evaluated on an external test set by using geographic validation, with accuracy, sensitivity, specificity, and 95% CIs being used for classification, the intersection over union (IoU) being used for bounding box placements, and the Dice score being used for segmentations. Results Radiographs from 934 patients (mean age, 33 years ± 19 [standard deviation]; 419 women) were evaluated in the internal data set, which included 667 benign bone tumors and 267 malignant bone tumors. Six hundred fifty-four patients were in the training set, 140 were in the validation set, and 140 were in the test set. One hundred eleven patients were in the external test set. The multitask DL model achieved 80.2% (89 of 111; 95% CI: 72.8, 87.6) accuracy, 62.9% (22 of 35; 95% CI: 47, 79) sensitivity, and 88.2% (67 of 76; CI: 81, 96) specificity in the classification of bone tumors as malignant or benign. The model achieved an IoU of 0.52 ± 0.34 for bounding box placements and a mean Dice score of 0.60 ± 0.37 for segmentations. The model accuracy was higher than that of two radiologic residents (71.2% and 64.9%; P = .002 and P < .001, respectively) and was comparable with that of two musculoskeletal fellowship-trained radiologists (83.8% and 82.9%; P = .13 and P = .25, respectively) in classifying a tumor as malignant or benign. Conclusion The developed multitask deep learning model allowed for accurate and simultaneous bounding box placement, segmentation, and classification of primary bone tumors on radiographs. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Carrino in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. von Schacky CE, Wilhelm NJ, Schäfer VS, et al. Multitask Deep Learning for Segmentation and Classification of Primary Bone Tumors on Radiographs. Radiology. 2021. PMID: 34491126. doi:10.1148/radiol.2021204531

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。