基于级联深度学习算法在双参数MRI中检测前列腺病变的评估| 文献速递-AI辅助的放射影像疾病诊断

Title

题目

Evaluation of a Cascaded Deep Learning–based Algorithm  for Prostate Lesion Detection at Biparametric MRI

基于级联深度学习算法在双参数MRI中检测前列腺病变的评估

Background

背景

Multiparametric MRI (mpMRI) improves prostate cancer (PCa) detection compared with systematic biopsy, but its interpretation is prone to interreader variation, which results in performance inconsistency. Artificial intelligence (AI) models can assist in mpMRI interpretation, but large training data sets and extensive model testing are required.

系统性活检相比，多参数MRI（mpMRI）在前列腺癌（PCa）检测方面具有优势，但其解读容易受阅片者之间的差异影响，从而导致性能不一致。人工智能（AI）模型可以辅助mpMRI的解读，但需要大量的训练数据集和广泛的模型测试。

Method

方法

This secondary analysis of a prospective registry included consecutive patients with suspected or known PCa who underwent mpMRI, US-guided systematic biopsy, or combined systematic and MRI/US fusion–guided biopsy between April 2019 and September 2022. All lesions were prospectively evaluated using Prostate Imaging Reporting and Data System version 2.1. The lesion- and participant-level performance of a previously developed cascaded deep learning algorithm was compared with histopathologic outcomes and radiologist readings using sensitivity, positive predictive value (PPV), and Dice similarity coefficient (DSC).

这项前瞻性配准的二次分析包括在2019年4月至2022年9月期间进行mpMRI、超声引导的系统性活检或系统性和MRI/超声融合引导活检的连续前列腺癌（PCa）疑似或已确诊患者。所有病变均使用前列腺成像报告和数据系统（PI-RADS）2.1版进行前瞻性评估。将先前开发的级联深度学习算法在病变和参与者层面的表现与组织病理学结果和放射科医生的解读结果进行比较，使用的评价指标包括敏感性、阳性预测值（PPV）和Dice相似系数（DSC）。

Conclusion

结论

The AI algorithm detected cancer-suspicious lesions on biparametric MRI scans with a performance comparable to that of an experienced radiologist. Moreover, the algorithm reliably predicted clinically significant lesions at histopathologic examination.

该人工智能算法在双参数MRI扫描中检测可疑癌变病灶的表现与经验丰富的放射科医生相当。此外，该算法在组织病理学检查中可靠地预测了具有临床意义的病灶。

Results

结果

A total of 658 male participants (median age, 67 years [IQR, 61–71 years]) with 1029 MRI-visible lesions were included. At histopathologic analysis, 45% (294 of 658) of participants had lesions of International Society of Urological Pathology (ISUP) grade group (GG) 2 or higher. The algorithm identified 96% (282 of 294; 95% CI: 94%, 98%) of all participants with clinically significant PCa, whereas the radiologist identified 98% (287 of 294; 95% CI: 96%, 99%; P = .23). The algorithm identified 84% (103 of 122), 96% (152 of 159), 96% (47 of 49), 95% (38 of 40), and 98% (45 of 46) of participants with ISUP GG 1, 2, 3, 4, and 5 lesions, respectively. In the lesion-level analysis using radiologist ground truth, the detection sensitivity was 55% (569 of 1029; 95% CI: 52%, 58%), and the PPV was 57% (535 of 934; 95% CI: 54%, 61%). The mean number of false-positive lesions per participant was 0.61 (range, 0–3). The lesion segmentation DSC was 0.29.

共纳入658名男性参与者（中位年龄67岁[IQR, 61-71岁]），其中有1029个在MRI中可见的病变。在组织病理学分析中，45%的参与者（658人中的294人）具有国际泌尿病理学会（ISUP）2级或更高级别的病变。算法识别出96%的具有临床意义前列腺癌（PCa）的参与者（294人中的282人；95%CI: 94%, 98%），而放射科医生识别出98%（294人中的287人；95%CI: 96%, 99%；P = .23）。算法分别识别出84%（122人中的103人）、96%（159人中的152人）、96%（49人中的47人）、95%（40人中的38人）和98%（46人中的45人）的ISUP 1、2、3、4和5级病变参与者。在基于放射科医生标准的病变级别分析中，检测敏感性为55%（1029个病变中的569个；95%CI: 52%, 58%），阳性预测值（PPV）为57%（934个病变中的535个；95%CI: 54%, 61%）。每名参与者的平均假阳性病变数为0.61（范围：0-3）。病变分割的Dice相似系数（DSC）为0.29。

Figure

图

Figure 1: Participant flow diagram. mpMRI = multiparametric MRI, PI-RADS = Prostate Imaging Reporting and Data System.

图1：参与者流程图。mpMRI = 多参数MRI，PI-RADS = 前列腺成像报告和数据系统。

Figure 2: Distribution of combined biopsy outcomes (percentage) based on highest International Society of Urological Pathology (ISUP) grade group per participant (PT). AI = artificial intelligence, PI-RADS = Prostate Imaging Reporting and Data System.

图2：基于每位参与者（PT）最高国际泌尿病理学会（ISUP）分级组的综合活检结果分布（百分比）。AI = 人工智能，PI-RADS = 前列腺成像报告和数据系统。

Figure 3: Axial multiparametric MRI scans in a 72-year-old male participant with a serum prostate-specific antigen level of 9.1 ng/mL: (A) T2-weighted image, (B)apparent diffusion coefficient map, (C) high-b-value diffusion-weighted image (b = 1500 sec/mm2 ), (D) dynamic contrast-enhanced image (frame 17 of 54 acquired at 5.6-second intervals), (E) T2-weighted image with radiologist-segmented lesions (green contours) overlaid, (F) T2-weighted image with artificial intelligence (AI) prediction map overlaid (red contour is positive prediction; blue contour is AI prostate organ segmentation), and (G) T2-weighted image with AI probability map overlaid (red indicates higher probability). Two distinct lesions were detected by the radiologist and represented the ground truth. Lesion 1 (1.6 cm; arrow in A–D) was in the right midgland transition zone and was designated Prostate Imaging Reporting and Data System (PI-RADS) category 4. Lesion 2 (1.5 cm; arrowhead in A–D) was in the left midgland transition zone and was designated PI-RADS category 3. Lesion 1 was correctly detected (true positive), while lesion 2 was missed by the AI algorithm (false negative). Based on targeted biopsy samples, lesion 1 was positive for Gleason score 7 (3 + 4) prostate adenocarcinoma, and lesion 2 was benign.

图3：72岁男性参与者的轴向多参数MRI扫描，血清前列腺特异性抗原水平为9.1 ng/mL：(A) T2加权图像，(B) 表观扩散系数图，(C) 高b值扩散加权图像(b = 1500 sec/mm²)，(D) 动态对比增强图像（以5.6秒间隔获取的54帧中的第17帧），(E) 叠加放射科医生分割病变的T2加权图像（绿色轮廓），(F) 叠加人工智能（AI）预测图的T2加权图像（红色轮廓为阳性预测；蓝色轮廓为AI前列腺器官分割），(G) 叠加AI概率图的T2加权图像（红色表示较高概率）。放射科医生检测到两个不同的病变并作为标准。病变1（1.6 cm；A-D中的箭头）位于右侧中腺移行区，被指定为前列腺成像报告和数据系统（PI-RADS）类别4。病变2（1.5 cm；A-D中的箭头）位于左侧中腺移行区，被指定为PI-RADS类别3。病变1被正确检测（真阳性），而病变2被AI算法遗漏（假阴性）。根据靶向活检样本，病变1为Gleason评分7（3+4）的前列腺腺癌阳性，病变2为良性。

Figure 4: Axial multiparametric MRI scans in a 64-year-old male participant with a serum prostate-specific antigen level of 8.1 ng/mL: (A)T2-weighted image, (B) apparent diffusion coefficient map, (C) high-b-value diffusion-weighted image (b = 1500 sec/mm2 ), (D) dynamic contrastenhanced image (frame 45 of 54 acquired at 5.6-second intervals), (E) T2-weighted image with artificial intelligence (AI) prediction map overlaid (red contour is positive prediction; blue contour is AI prostate organ segmentation), and (F) T2-weighted image with AI probability map overlaid (red indicates higher probability). No distinct lesion was detected by the radiologist (Prostate Imaging Reporting and Data System category 1). One lesion was called by the AI algorithm in the left midgland peripheral zone (arrow in E and F), representing a false positive based on the radiologist ground truth. Systematic biopsy obtained from this site (left midgland lateral) was positive for Gleason score 7 (3 + 4) prostate adenocarcinoma.

图4：64岁男性参与者的轴向多参数MRI扫描，血清前列腺特异性抗原水平为8.1 ng/mL：(A) T2加权图像，(B) 表观扩散系数图，(C) 高b值扩散加权图像(b = 1500 sec/mm²)，(D) 动态对比增强图像（以5.6秒间隔获取的54帧中的第45帧），(E) 叠加人工智能（AI）预测图的T2加权图像（红色轮廓为阳性预测；蓝色轮廓为AI前列腺器官分割），(F) 叠加AI概率图的T2加权图像（红色表示较高概率）。放射科医生未检测到明显病变（前列腺成像报告和数据系统类别1）。AI算法在左侧中腺周围区检测到一个病变（E和F中的箭头），根据放射科医生的标准，这是一个假阳性。系统性活检从该部位（左侧中腺侧面）获取的样本显示为Gleason评分7（3+4）的前列腺腺癌阳性。

Figure 5: Axial multiparametric MRI scans in a 69-year-old male participant with a serum prostate-specific antigen level of 7.3 ng/mL: (A)T2-weighted image, (B) apparent diffusion coefficient map, (C) high-b-value diffusion-weighted image (b = 1500 sec/mm2 ), (D) dynamic contrastenhanced image (frame 25 of 54 acquired at 5.6-second intervals), (E) T2-weighted image with artificial intelligence (AI) prediction map overlaid (red contour is positive prediction; blue contour is AI prostate organ segmentation), and (F) T2-weighted image with AI probability map overlaid (red indicates higher probability). One lesion was called by the AI algorithm in the left midgland anterior transition zone (arrow in E and F), representing a false positive based on the radiologist ground truth. A systematic biopsy sample obtained from this site (left midgland medial) was benign.

图5：69岁男性参与者的轴向多参数MRI扫描，血清前列腺特异性抗原水平为7.3 ng/mL：(A) T2加权图像，(B) 表观扩散系数图，(C) 高b值扩散加权图像(b = 1500 sec/mm²)，(D) 动态对比增强图像（以5.6秒间隔获取的54帧中的第25帧），(E) 叠加人工智能（AI）预测图的T2加权图像（红色轮廓为阳性预测；蓝色轮廓为AI前列腺器官分割），(F) 叠加AI概率图的T2加权图像（红色表示较高概率）。AI算法在左侧中腺前部移行区检测到一个病变（E和F中的箭头），根据放射科医生的标准，这是一个假阳性。从该部位（左侧中腺内侧）获取的系统性活检样本为良性。

Figure 6: Axial multiparametric MRI scans in a 74-year-old male participant with a serum prostate-specific antigen level of 12.9 ng/mL: (A)** T2-weighted image, (B) apparent diffusion coefficient map, (C) high-b-value diffusion-weighted image (b* = 1500 sec/mm2 ), (D) dynamic contrast-enhanced image (frame 16 of 54 acquired at 5.6-second intervals), (E) T2-weighted image with radiologist-segmented lesion (green contour) overlaid, and (F) T2-weighted image with artificial intelligence (AI) prediction map overlaid (no positive prediction; blue contour is AI prostate organ segmentation). One lesion was detected by the radiologist and represented the ground truth. The lesion (1.9 cm; arrow in A–D) was in the right apical midgland peripheral zone and was designated Prostate Imaging Reporting and Data System category 4. This lesion was missed by the AI algorithm, representing a false negative. A targeted biopsy sample obtained from the lesion was positive for Gleason score 7 (3 + 4) prostate adenocarcinoma.

图6：74岁男性参与者的轴向多参数MRI扫描，血清前列腺特异性抗原水平为12.9 ng/mL：(A) T2加权图像，(B) 表观扩散系数图，(C) 高b值扩散加权图像(b = 1500 sec/mm²)，(D) 动态对比增强图像（以5.6秒间隔获取的54帧中的第16帧），(E) 叠加放射科医生分割病变的T2加权图像（绿色轮廓），(F) 叠加人工智能（AI）预测图的T2加权图像（无阳性预测；蓝色轮廓为AI前列腺器官分割）。放射科医生检测到一个病变并作为标准。病变（1.9 cm；A-D中的箭头）位于右侧尖端中腺周围区，被指定为前列腺成像报告和数据系统类别4。该病变被AI算法遗漏，属于假阴性。从该病变获取的靶向活检样本显示为Gleason评分7（3+4）的前列腺腺癌阳性。

Table

表

Table 1: Participant and Lesion Characteristics (n = 658 Participants)

表1：参与者和病变特征（n = 658名参与者）

Table 2: Lesion-Level Comparisons of Radiologist and AI Cancer Detection Rates Based on Histopathologic Ground Truth

表2：基于组织病理学标准的放射科医生和人工智能癌症检测率的病变级别比较

Table 3: Participant-Level Sensitivity and PPV of AI versus Radiologist Detection of Prostate Cancer Based on Combined Biopsy Results

表3：基于综合活检结果的人工智能与放射科医生在前列腺癌检测中的参与者级别敏感性和阳性预测值（PPV）比较

Table 4: Participant-Level Sensitivity and PPV of AI versus Radiologist Detection of Clinically Significant Prostate Cancer Based on Combined Biopsy Results

表4：基于综合活检结果的人工智能与放射科医生在检测临床意义前列腺癌中的参与者级别敏感性和阳性预测值（PPV）比较

Table 5: Lesion- and Participant-Level Detection Performance Metrics Based on Radiologist Ground Truth

表5：基于放射科医生标准的病变和参与者级别检测性能指标