Our objective was to compare the diagnostic performance and diagnostic confidence of convolutional neural networks (CNN) to radiologists in characterizing small hypoattenuating hepatic nodules (SHHN) in colorectal carcinoma (CRC) on CT scans. Retrospective review of CRC CT scans over 6-years yielded 199 patients (550 SHHN) defined as < 1 cm in diameter. The reference standard was established through 1-year stability/MRI for benign or nodule evolution for malignant nodules. Five CNNs underwent supervised training on 150 patients (412 SHHN). The remaining 49 patients (138 SHHN) were used as testing-set to compare performance of 3 radiologists to CNN, measured through ROC AUC analysis of confidence rating assigned to each nodule by the radiologists. Multivariable modeling was used to compensate for radiologist bias from visible findings other than SHHN. In characterizing SHHN as benign or malignant, the radiologists’ mean AUC ROC (0.96) was significantly higher than CNN (0.84, p = 0.0004) but equivalent to CNN adjusted through multivariable modeling for presence of synchronous ≥ 1 cm liver metastases (0.95, p = 0.9). The diagnostic confidence of radiologists and CNN were analyzed. There were significantly lower number of nodules rated with low confidence by CNN (19.6%) and CNN with liver metastatic status (18.1%) than two (38.4%, 44.2%, p < 0.0001) but not a third radiologist (11.1%, p = 0.09). We conclude that in CRC, CNN in combination with liver metastatic status equaled expert radiologists in characterizing SHHN but with better diagnostic confidence.

我们的目标是比较卷积神经网络 (CNN) 与放射科医师在 CT 扫描中表征结直肠癌 (CRC) 中的小低密度肝结节 (SHHN) 的诊断性能和诊断信心。对 6 年的 CRC CT 扫描进行回顾性审查，发现 199 名患者 (550 SHHN) 定义为直径 < 1 cm。参考标准是通过1年稳定性/MRI对恶性结节的良性或结节演变建立的。五个 CNN 对 150 名患者（412 SHHN）进行了监督训练。其余 49 名患者 (138 SHHN) 用作测试集，以比较 3 位放射科医生与 CNN 的表现，通过对放射科医生分配给每个结节的置信度进行 ROC AUC 分析来衡量。多变量建模用于补偿来自除 SHHN 以外的可见发现的放射科医师偏见。在将 SHHN 表征为良性或恶性时，放射科医师的平均 AUC ROC (0.96) 显着高于 CNN (0.84,p  = 0.0004），但相当于通过多变量建模调整的 CNN 同步≥ 1 cm 肝转移的存在（0.95，p  = 0.9）。分析了放射科医生和CNN的诊断信心。CNN (19.6%) 和 CNN 具有肝转移状态 (18.1%) 的低置信度结节数量明显低于两个 (38.4%, 44.2%, p  < 0.0001) 但不是第三位放射科医生 (11.1%, p  = 0.09）。我们得出的结论是，在 CRC 中，CNN 与肝转移状态相结合，在表征 SHHN 方面与专家放射科医生相当，但具有更好的诊断信心。