PURPOSE:To develop a radiomic nomogram based on multiparametric magnetic resonance imaging for the preoperative prediction of lymph node metastasis (LNM) in rectal cancer. METHODS:This retrospective study included 318 patients with pathologically proven rectal adenocarcinoma from two hospitals. Radiomic features were extracted from T2-weighted imaging, diffusion-weighted imaging, and contrast-enhanced T1-weighted imaging scans of the training cohort, and the radsore model was then constructed. The combined model was obtained by integrating the Radscore and clinical models. The area under the receiver operating characteristic curve (AUC) was used to assess the diagnostic effectiveness of each model, and the best-performing model was used to develop the nomogram. RESULTS:The Radscore and clinical models exhibited similar diagnostic efficacy (DeLong's test, P > 0.05). The AUC of the combined model was significantly higher than those of the clinical and Radscore models in the training cohort (AUC: 0.837 vs. 0.763 and 0.787, P: 0.02120 and 0.02309) and the external validation cohort (AUC: 0.880 vs. 0.797 and 0.779, P: 0.02310 and 0.02471). However, the diagnostic performance of the three models was comparable in the internal validation cohort (P > 0.05). Thus, among the three models, the combined model exhibited the highest diagnostic efficiency. The calibration curve exhibited satisfactory consistency between the nomogram predictions and the actual results. DCA confirmed the considerable clinical usefulness of the nomogram. CONCLUSION:The radiomics nomogram can accurately and noninvasively predict LNM in rectal cancer before surgery, serving as a convenient visualization tool for informing treatment decisions, including the choice of surgical approach and the need for neoadjuvant therapy.

Abstract Purpose To compare the effects of different annotation strategies on the performance of Radiomics models in identifying COVID-19. Methods A total of 775 CT scans were retrospectively collected from 5 hospitals in China between Jan 19 and Mar 26, 2020, including 310 COVID-19 scans and 465 other community-acquired pneumonia (CAP) scans. Coarse annotation which labels the major lesions on certain CT slides and fine annotation which delineates the contour of lesions on each slide was performed on CT images. Four feature selection methods and four machine learning algorithms were then applied in combinations to develop Radiomics models on different sizes of datasets, including small (56 CT scans) and large (56 + 489 CT scans). Model performance was evaluated by ROC curve, PR curve, and other diagnostic metrics on an external test set. Statistical analyses were performed with Chi-square tests and DeLong Test; P < 0.05 was considered statistically significant. Results Differences between coarse and fine annotated data were quantitatively analyzed by a Dice index of 0.689, an average Hausdorff distance of 3.7%, and an average volume difference of 5.8%. Inaccurate segmentations were observed in coarse annotated images, including relatively smaller ROI and missed delineation of ground-glass opacity. In addition, more abundant features were extracted from fine annotated images in categories of FirstOrder, GLSZM, and GLCM features. With regard to model performance, fine annotation enabled an over better performance of Radiomics models while enlarged dataset size could remedy the influence of coarse annotation. Meanwhile, models trained on large datasets displayed more stable performance on all selection methods and algorithm combinations. Among them, L1-LR-MLP was selected as the optimal combination for modeling. In particular, SDFine, SDRough, LDFine, and LDRough datasets developed L1-LR-MLP models achieved the AUROC of 0.864,0.707, 0.904, and 0.899, and the AUPR of 0.888, 0.714, 0.934 and 0.896, respectively, on the external dataset. Conclusions Fine annotation generally enables a better model performance in the identification of COVID-19 while the efficient coarse annotation strategy could also be applied to achieve the equivalent diagnostic performance by expanding the training dataset, especially in urgent scenarios. L1-LR-MLP displayed great potential to be applied for establishing COVID-19 identification models.

Abstract Objectives Artificial intelligence (AI) has been proved to be a highly efficient tool for COVID‐19 diagnosis, but the large data size and heavy label force required for algorithm development and the poor generalizability of AI algorithms, to some extent, limit the application of AI technology in clinical practice. The aim of this study is to develop an AI algorithm with high robustness using limited chest CT data for COVID‐19 discrimination. Methods A three dimensional algorithm that combined multi‐instance learning with the LSTM architecture (3DMTM) was developed for differentiating COVID‐19 from community acquired pneumonia (CAP) while logistic regression (LR), k‐nearest neighbor (KNN), support vector machine (SVM), and a three dimensional convolutional neural network set for comparison. Totally, 515 patients with or without COVID‐19 between December 2019 and March 2020 from five different hospitals were recruited and divided into relatively large (150 COVID‐19 and 183 CAP cases) and relatively small datasets (17 COVID‐19 and 35 CAP cases) for either training or validation and another independent dataset (37 COVID‐19 and 93 CAP cases) for external test. Area under the receiver operating characteristic curve (AUC), sensitivity, specificity, precision, accuracy, F1 score, and G‐mean were utilized for performance evaluation. Results In the external test cohort, the relatively large data‐based 3DMTM‐LD achieved an AUC of 0.956 (95% confidence interval, 95% CI, 0.929∼0.982) with 86.2% and 98.0% for its sensitivity and specificity. 3DMTM‐SD got an AUC of 0.937 (95% CI, 0.909∼0.965), while the AUC of 3DCM‐SD decreased dramatically to 0.714 (95% CI, 0.649∼0.780) with training data reduction. KNN‐MMSD, LR‐MMSD, SVM‐MMSD, and 3DCM‐MMSD benefited significantly from the inclusion of clinical information while models trained with relatively large dataset got slight performance improvement in COVID‐19 discrimination. 3DMTM, trained with either CT or multi‐modal data, presented comparably excellent performance in COVID‐19 discrimination. Conclusions The 3DMTM algorithm presented excellent robustness for COVID‐19 discrimination with limited CT data. 3DMTM based on CT data performed comparably in COVID‐19 discrimination with that trained with multi‐modal information. Clinical information could improve the performance of KNN, LR, SVM, and 3DCM in COVID‐19 discrimination, especially in the scenario with limited data for training.

目的 探讨脑灌注相对参数在预测急性前循环大血管闭塞性脑卒中机械取栓后出血转化的价值.方法 回顾性分析2021年1至11月台州市第一人民医院就诊的急性前循环大血管闭塞性脑卒中患者86例的临床及影像资料,通过纳入标准及排除标准,最终纳入患者51例,根据机械取栓治疗后复查是否发生出血转化分为出血转化组25例,非出血转化组26例,应用MIStar软件测量患侧低灌注区及梗死核心区的脑血容量(cerebral blood volume,CBV)、脑血流量(cerebral blood flow,CBF)、平均通过时间(mean transit time,MTT)、延迟时间(delay time,DT)参数,经中线镜像到健侧获取健侧相对应的灌注参数,并通过计算患侧与健侧的灌注参数比值得到相对脑血容量(relative cerebral blood volume,rCBV)、相对脑血流量(relative cerebral blood flow,rCBF)、相对平均通过时间(relative mean transit time,rMTT)、相对延迟时间(relative delay time,rDT).分析两组患者的一般资料与灌注参数,采用受试者工作特征(receiver operating characteristic curve,ROC)曲线评估机械取栓治疗后出血转化的诊断效能.结果 出血转化组和非出血转化组在年龄、性别、吸烟史、高血压、糖尿病、心房颤动、心肌梗死病史、高脂血症方面比较,差异无统计学意义(P>0.05).出血转化组和非出血转化组在低灌注区的rCBV、rCBF和梗死核心区的rCBV、rCBF比较,差异有统计学意义(P<0.05).低灌注区的rCBV、rCBF的曲线下面积(area under curve,AUC)分别为0.865和0.840,梗死核心区的rCBV、rCBF的AUC分别为0.737和0.709.结论 脑灌注相对参数中的rCBV、rCBF可以用来预测急性前循环大血管闭塞性脑卒中患者经机械取栓后出血转化,对临床进行机械取栓治疗后出血转化的预测提供影像学指导.

目的 探讨CT扫描定量分析鉴别诊断惰性肺腺癌与浸润性肺腺癌的价值.方法 回顾性分析2017年8月-2021年5月浙江省台州市第一人民医院经手术病理证实的98例长径小于30mm的T1期肺腺癌患者,对其胸部CT平扫薄层图像进行主观形态学分析,并利用LIFEx软件通过人工分割,定量提取强度特征、形态特征及纹理特征等CT定量分析特征后进行比较分析.结果 病灶的体积、直方图的均匀性、峰度差异具有统计学意义(P＜0.05),偏度差异无统计学意义(P＞0.05),而CT衰减值中的均值、标准差、最大值差异均有统计学意义(P＜0.05).结论 CT扫描的定量分析特征有助于区分惰性和浸润性肺腺癌,为肺结节患者提供选择干预措施的机会.

背景 肾上腺偶发瘤中,肾上腺转移瘤需要与肾上腺最常见的良性肿瘤(肾上腺腺瘤)进行鉴别,推荐延迟15 min的扫描方式计算绝对廓清率与相对廓清率,然而扫描时间过长.目的 探讨简化计算CT增强廓清率鉴别小于4 cm的肾上腺转移瘤与肾上腺腺瘤的价值.方法 选取2014年1月—2019年12月台州市第一人民医院经临床随访证实或拟诊非肾上腺腺瘤病变后手术病理证实并行CT增强扫描的肾上腺转移瘤患者78例和肾上腺腺瘤患者50例.依据纳入和排除标准最终本研究纳入肾上腺转移瘤患者37例(肾上腺转移瘤组)和肾上腺腺瘤患者47例(肾上腺腺瘤组);其中肾上腺转移瘤包含原发灶为肺癌患者16例、原发灶为其他肿瘤患者21例(肝癌患者4例、胃肠道肿瘤患者14例、胰腺癌患者1例、膀胱癌患者1例、涎腺癌患者1例),肾上腺腺瘤包含肾上腺乏脂腺瘤患者15例、肾上腺富脂腺瘤患者32例.收集患者年龄、性别、高血压发生情况、病灶部位(左侧/右侧)、肿瘤大小,并测量平扫、动脉期及静脉期的CT值,计算简化绝对廓清率及相对廓清率.采用受试者工作特征曲线(ROC曲线)分别分析肾上腺转移瘤与肾上腺腺瘤组、肾上腺转移瘤与肾上腺乏脂腺瘤组、肾上腺转移瘤与肾上腺富脂腺瘤组、肺癌肾上腺转移瘤与肾上腺乏脂腺瘤组中差异有统计学意义的变量的效能.结果 肾上腺转移瘤组与肾上腺腺瘤组患者、肾上腺转移瘤组与肾上腺乏脂腺瘤组患者、肾上腺转移瘤组与肾上腺富脂腺瘤组患者、肺癌肾上腺转移瘤组与肾上腺乏脂腺瘤组患者年龄、性别、高血压发生率、病灶部位及肿瘤大小比较,差异均无统计学意义(P>0.05).肾上腺转移瘤组患者的平扫CT值高于肾上腺腺瘤组(P<0.001).肾上腺转移瘤组平扫CT值高于肾上腺乏脂腺瘤组,绝对廓清率和相对廓清率低于肾上腺乏脂腺瘤组(P<0.05).肾上腺转移瘤组平扫CT值及相对廓清率高于肾上腺富脂腺瘤组(P<0.05);肾上腺转移瘤组与肾上腺富脂腺瘤组患者的绝对廓清率比较,差异无统计学意义(P>0.05).肺癌肾上腺转移瘤组平扫CT值高于肾上腺乏脂腺瘤组,绝对廓清率和相对廓清率低于肾上腺乏脂腺瘤组(P<0.05).在肾上腺转移瘤与肾上腺腺瘤ROC曲线分析中,平扫CT值的截断值为21.00 HU,ROC曲线下面积(AUC)、灵敏度、特异度分别为0.894、81.1％、89.4％.在肾上腺转移瘤与肾上腺乏脂腺瘤ROC曲线分析中,平扫CT值的截断值为28.50 HU,AUC、灵敏度、特异度分别为0.746、64.9％、86.7％;绝对廓清率的截断值为-21.54％,AUC、灵敏度、特异度分别为0.733、80.0％、83.8％;相对廓清率的截断值为-9.65％,AUC、灵敏度、特异度分别为0.760、73.3％、89.2％.在肾上腺转移瘤与肾上腺富脂腺瘤ROC曲线分析中,平扫CT值的截断值为11.50 HU,AUC、灵敏度、特异度分别为0.964、91.9％、100％;相对廓清率的截断值为-64.10％,AUC、灵敏度、特异度分别为0.677、89.2％、53.1％.在肺癌肾上腺转移瘤与肾上腺乏脂腺瘤ROC曲线分析中,平扫CT值的截断值为29.50 HU,AUC、灵敏度、特异度分别为0.881、81.3％、93.3％;绝对廓清率的截断值为-24.89％,AUC、灵敏度、特异度分别为0.721、80.0％、81.3％;相对廓清率的截断值为-10.58％,AUC、灵敏度、特异度分别为0.733、73.3％、87.5％.结论 简化计算CT增强绝对廓清率及相对廓清率在鉴别小于4 cm的肾上腺转移瘤与肾上腺腺瘤间有重要价值.