目的：探讨应用乳腺磁共振计算机辅助系统（MRI-CAD）对于不同经验的医师鉴别乳腺小肿块良恶性的价值。方法：回顾性分析行 MRI 检查的肿块型乳腺病灶235个（≤2．0 cm），均经病理证实或随诊2年以上。比较4名医师（2名经验缺乏者和2名经验丰富者）使用 CAD 系统前后的诊断敏感度、特异度。采用 ROC 曲线评价并比较4名医师使用 CAD 系统前后的诊断符合率。采用 Kappa 检验评价使用 CAD 系统前后医师间的一致性。结果：235个病灶中，155个良性病灶，80个恶性病灶。4位医师均检出了所有病灶。应用 CAD 系统前，4名医师诊断乳腺癌的特异度分别为55．5％、58．1％、72．3％、74．8％，使用 CAD 后分别为72．3％、76．1％、75．5％、70．3％；医师一、医师二（两名低年资医师）的诊断特异度前后差异具有统计学意义（P ＜0．001），医师三及医师四差异无统计学意义（P 3＝0．404，P 4＝0．265）。四位医师在使用 CAD 系统后诊断敏感度均略有提高，但差异均无统计学意义（P 1＝1．000，P 2＝1．000，P 3＝1．000，P 4＝0．480）。医师一、医师二及医师三在应用 CAD 系统后，总体诊断符合率均有明显提高，ROC 曲线下面积分别由0．899（95％CI：0．853～0．934）、0．839（95％CI：0．785～0．883）、0．929（95％CI：0．888～0．958）提高至0．947（95％CI：0．910～0．972）、0．987（95％CI：0．962～0．997）、0．971（95％CI：0．940～0．988），且差异具有统计学意义（P 1＝0．002，P 2＜0．001，P 3＜0．001）。医师四尽管在使用 CAD 系统后总体诊断符合率亦有提高，ROC 曲线下面积由0．940（95％CI：0．901～0．966）提高至0．960（95％CI：0．927～0．981），但差异无统计学意义（P ＝0．11）。四位医师在应用 CAD 系统后诊断一致性提高（P ＝0．004）。结论：MRI-CAD 系统的应用有助于提高医师诊断乳腺小肿块的准确度及特异度，使得不同经验程度医师的诊断一致性提高，减少了不必要的活检，可作为提高缺乏经验医师诊断符合率的有力工具。%Objective:To investigate the value of MRI in addition with computer-aided diagnostic (CAD)system in the evaluation of contrast-enhanced breast MRI for readers with different level of experience.Methods:A total of 235 small breast lesions(≤2.0cm)assessed on MRI were reviewed retrospectively.All had either pathology diagnosis or follow-up for 2 years.The diagnosis sensitivity,specificity by 4 readers (experienced and inexperienced)before and after using CAD sys-tem were compared.ROC was used to evaluate the diagnosis accuracy before and after using CAD of the 4 readers.Interob-server variations were evaluated using kappa statistics.Results:Of the 235 breast lesions,there were 155 benign and 80 ma-lignant masses.All lesions were detected by four readers.Before CAD was used,the specificity of these 4 readers was 55.5%、58.1%、72.3%、74.8%,respectively;which was 72.3%、76.1%、75.5%、70.3% respectively after using CAD.Sta-tistic difference (P <0.001)was existed between the 2 inexperienced readers before and after using CAD;whereas no statis-tic difference (P =0.404 for reader 3,P =0.265 for reader 4)was existed in the 2 experienced readers before and after u-sing CAD.Diagnostic sensitivity in all four readers increased slightly by the use of CAD,yet there was no statistical signifi-cance (P 1 =1.000,P 2 =1.000,P 3 =1.000,P 4 =0.480).The overall performance found in both inexperienced and one expe-rienced readers (reader 3)improved significantly after using CAD (ROC,0.899,95%CI:0.853~0.934 vs 0.947,95% CI:0.910~0.972,P =0.002 in reader 1;ROC,0.839,95% CI:0.785 ~0.883 vs 0.987,95%CI:0.962 ~0.997,P <0.001 in reader 2;ROC,0.929,95% CI:0.888 ~0.958 vs 0.971,95% CI:0.940 ~0.988,P <0.001 in reader 3),with significant statistic differences.Although there was improvement of overall accuracy after using CAD in reader 4,ROC 0.940,95%CI:0.901~0.966 vs 0.960,95% CI:0.927~0.981,no significant statistic difference was found (P =0.11).The level of agree-ment between the readers improved significantly when using the CAD (P =0.004).Conclusion:The accuracy and specificity in diagnosing small breast mass lesion with MRI could be improved after using CAD system in readers with different level of experience,unnecessary biopsy could be avoided,therefore,which is a helpful modality to improve the diagnosis accuracy, and is recommended for inexperienced readers.
展开▼
