|
目前，不少人工智能软件对于乳腺钼靶影像的分析水平已经达到或超过放射科医师，能够大大提高乳腺癌筛查的效率。 2020年8月27日，《美国医学会杂志》肿瘤学分册在线发表瑞典卡罗林学院、卡罗林大学医院、圣戈兰医院、皇家理工学院、生命科学实验中心的研究报告，对3种商品化人工智能计算机辅助检测软件独立分析乳腺钼靶筛查影像的能力进行了比较，并对其结合放射科医师的筛查效果进行了评定。 该病例对照回顾研究随机抽取2008～2015年瑞典卡罗林大学医院8805例年龄40～74岁过去无乳房植入物或乳腺癌女性的乳腺钼靶筛查双人读片结果进行回顾分析，其中739例乳腺癌患者、8066例健康对照者，中位年龄分别为60岁、54岁（四分位50～66岁、47～63岁）。根据筛查时或筛查后12个月内病理检查确定阳性随访结果，根据2年无癌随访确定阴性随访结果。来自不同供应商的3种人工智能计算机辅助检测软件（AI-1、AI-2、AI-3）对全部乳腺钼靶影像进行分析，获得癌症可疑评分。对于正常或异常的临界值定义为第一读片放射科医师平均特异度（96.6%）。 结果，癌症阳性病例包括筛查时检出的618例（84%）和筛查后12个月内临床检出的121例（16%）。 3种人工智能软件的真假阳性率（又称接受者、受试者、观测者操作特征）曲线下面积：
当第一读片放射科医师平均特异度（真阴性率）为96.6%时，灵敏度（真阳性率）分别为：
当放射科医师结合人工智能时，特异度、灵敏度分别为：
因此，该研究结果首次对几种用于钼靶筛查的人工智能计算机辅助检测软件进行独立比较，结果表明商品化人工智能计算机辅助检测软件能够用于女性乳腺钼靶筛查影像分析，诊断效果良好，故有必要进一步开展前瞻临床研究对其独立读片能力进行验证。与第一读片放射科医师结合第二读片放射科医师相比，第一读片放射科医师结合最佳人工智能软件，可以发现更多癌症阳性病例。 对此，美国哈佛大学医学院麻省总医院放射科教授康斯坦斯·多宾斯·雷曼发表同期评论：人工智能独立分析乳腺钼靶筛查影像时机已到。 相关链接 JAMA Oncol. 2020 Aug 27. Online ahead of print. External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms. Mattie Salim, Erik Wahlin, Karin Dembrower, Edward Azavedo, Theodoros Foukakis, Yue Liu, Kevin Smith, Martin Eklund, Fredrik Strand. Karolinska Institute, Stockholm, Sweden; Karolinska University Hospital, Stockholm, Sweden; Capio Sankt Gorans Hospital, Stockholm, Sweden; KTH Royal Institute of Technology, Science for Life Laboratory, Solna, Sweden. This case-control study of women screened at an academic hospital in Stockholm, Sweden, evaluates 3 commercially available artificial intelligence algorithms to assess whether they perform independently as well or better than radiologists in mammography screening assessment or improve the performance of radiologists. QUESTION: Are there currently commercially available artificial intelligence (AI) algorithms that perform as well as or above the level of radiologists in mammography screening assessment? FINDINGS: In this case-control study that included 8805 women, 1 of the 3 externally evaluated AI computer-aided detection algorithms was more accurate than first-reader radiologists in assessing screening mammograms. However, the highest number of cases positive for breast cancer was detected by combining this best algorithm with first-reader radiologists. MEANING: One commercially available AI algorithm performed independent reading of screening mammograms with sufficient diagnostic performance to act as an independent reader in prospective clinical studies. IMPORTANCE: A computer algorithm that performs at or above the level of radiologists in mammography screening assessment could improve the effectiveness of breast cancer screening. OBJECTIVE: To perform an external evaluation of 3 commercially available artificial intelligence (AI) computer-aided detection algorithms as independent mammography readers and to assess the screening performance when combined with radiologists. DESIGN, SETTING, AND PARTICIPANTS: This retrospective case-control study was based on a double-reader population-based mammography screening cohort of women screened at an academic hospital in Stockholm, Sweden, from 2008 to 2015. The study included 8805 women aged 40 to 74 years who underwent mammography screening and who did not have implants or prior breast cancer. The study sample included 739 women who were diagnosed as having breast cancer (positive) and a random sample of 8066 healthy controls (negative for breast cancer). MAIN OUTCOMES AND MEASURES: Positive follow-up findings were determined by pathology-verified diagnosis at screening or within 12 months thereafter. Negative follow-up findings were determined by a 2-year cancer-free follow-up. Three AI computer-aided detection algorithms (AI-1, AI-2, and AI-3), sourced from different vendors, yielded a continuous score for the suspicion of cancer in each mammography examination. For a decision of normal or abnormal, the cut point was defined by the mean specificity of the first-reader radiologists (96.6%). RESULTS: The median age of study participants was 60 years (interquartile range, 50-66 years) for 739 women who received a diagnosis of breast cancer and 54 years (interquartile range, 47-63 years) for 8066 healthy controls. The cases positive for cancer comprised 618 (84%) screen detected and 121 (16%) clinically detected within 12 months of the screening examination. The area under the receiver operating curve for cancer detection was 0.956 (95% CI, 0.948-0.965) for AI-1, 0.922 (95% CI, 0.910-0.934) for AI-2, and 0.920 (95% CI, 0.909-0.931) for AI-3. At the specificity of the radiologists, the sensitivities were 81.9% for AI-1, 67.0% for AI-2, 67.4% for AI-3, 77.4% for first-reader radiologist, and 80.1% for second-reader radiologist. Combining AI-1 with first-reader radiologists achieved 88.6% sensitivity at 93.0% specificity (abnormal defined by either of the 2 making an abnormal assessment). No other examined combination of AI algorithms and radiologists surpassed this sensitivity level. CONCLUSIONS AND RELEVANCE: To our knowledge, this study is the first independent evaluation of several AI computer-aided detection algorithms for screening mammography. The results of this study indicated that a commercially available AI computer-aided detection algorithm can assess screening mammograms with a sufficient diagnostic performance to be further evaluated as an independent reader in prospective clinical trials. Combining the first readers with the best algorithm identified more cases positive for cancer than combining the first readers with second readers. DOI: 10.1001/jamaoncol.2020.3321  JAMA Oncol. 2020 Aug 27. Online ahead of print. Artificial Intelligence to Support Independent Assessment of Screening Mammograms—The Time Has Come. Constance Dobbins Lehman. Massachusetts General Hospital, Harvard Medical School, Boston. DOI: 10.1001/jamaoncol.2020.3186
|
|
|
