Radiomics model based on preoperative gadoxetic acid-enhanced MRI for predicting liver failure

BACKGROUND Postoperative liver failure is the most severe complication in cirrhotic patients with hepatocellular carcinoma(HCC) after major hepatectomy. Current available clinical indexes predicting postoperative residual liver function are not sufficiently accurate.AIM To determine a radiomics model based on preoperative gadoxetic acid-enhanced magnetic resonance imaging for predicting liver failure in cirrhotic patients with HCC after major hepatectomy.METHODS For this retrospective study, a radiomics-based model was developed based on preoperative hepatobiliary phase gadoxetic acid-enhanced magnetic resonance images in 101 patients with HCC between June 2012 and June 2018. Sixty-one radiomic features were extracted from hepatobiliary phase images and selected by the least absolute shrinkage and selection operator method to construct a radiomics signature. A clinical prediction model, and radiomics-based model incorporating significant clinical indexes and radiomics signature were built using multivariable logistic regression analysis. The integrated radiomics-based model was presented as a radiomics nomogram. The performances of clinical prediction model, radiomics signature, and radiomics-based model for predicting post-operative liver failure were determined using receiver operating characteristics curve, calibration curve, and decision curve analyses.RESULTS Five radiomics features from hepatobiliary phase images were selected to construct the radiomics signature. The clinical prediction model, radiomics signature, and radiomics-based model incorporating indocyanine green clearance rate at 15 min and radiomics signature showed favorable performance for predicting postoperative liver failure(area under the curve: 0.809-0.894). The radiomics-based model achieved the highest performance for predicting liver failure(area under the curve: 0.894; 95%CI: 0.823-0.964). The integrated discrimination improvement analysis showed a significant improvement in the accuracy of liver failure prediction when radiomics signature was added to the clinical prediction model(integrated discrimination improvement = 0.117, P =0.002). The calibration curve and an insignificant Hosmer-Lemeshow test statistic(P = 0.841) demonstrated good calibration of the radiomics-based model. The decision curve analysis showed that patients would benefit more from a radiomics-based prediction model than from a clinical prediction model and radiomics signature alone.CONCLUSION A radiomics-based model of preoperative gadoxetic acid–enhanced MRI can be used to predict liver failure in cirrhotic patients with HCC after major hepatectomy.     

Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features

PurposeThe purpose of this study was to determine whether computed tomography (CT)-based machine learning of radiomics features could help distinguish autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC).Materials and MethodsEighty-nine patients with AIP (65 men, 24 women; mean age, 59.7 ± 13.9 [SD] years; range: 21–83 years) and 93 patients with PDAC (68 men, 25 women; mean age, 60.1 ± 12.3 [SD] years; range: 36–86 years) were retrospectively included. All patients had dedicated dual-phase pancreatic protocol CT between 2004 and 2018. Thin-slice images (0.75/0.5 mm thickness/increment) were compared with thick-slices images (3 or 5 mm thickness/increment). Pancreatic regions involved by PDAC or AIP (areas of enlargement, altered enhancement, effacement of pancreatic duct) as well as uninvolved parenchyma were segmented as three-dimensional volumes. Four hundred and thirty-one radiomics features were extracted and a random forest was used to distinguish AIP from PDAC. CT data of 60 AIP and 60 PDAC patients were used for training and those of 29 AIP and 33 PDAC independent patients were used for testing.ResultsThe pancreas was diffusely involved in 37 (37/89; 41.6%) patients with AIP and not diffusely in 52 (52/89; 58.4%) patients. Using machine learning, 95.2% (59/62; 95% confidence interval [CI]: 89.8–100%), 83.9% (52:67; 95% CI: 74.7–93.0%) and 77.4% (48/62; 95% CI: 67.0–87.8%) of the 62 test patients were correctly classified as either having PDAC or AIP with thin-slice venous phase, thin-slice arterial phase, and thick-slice venous phase CT, respectively. Three of the 29 patients with AIP (3/29; 10.3%) were incorrectly classified as having PDAC but all 33 patients with PDAC (33/33; 100%) were correctly classified with thin-slice venous phase with 89.7% sensitivity (26/29; 95% CI: 78.6–100%) and 100% specificity (33/33; 95% CI: 93–100%) for the diagnosis of AIP, 95.2% accuracy (59/62; 95% CI: 89.8–100%) and area under the curve of 0.975 (95% CI: 0.936–1.0).ConclusionsRadiomic features help differentiate AIP from PDAC with an overall accuracy of 95.2%.     

Artificial intelligence in liver ultrasound

Artificial intelligence (AI) is playing an increasingly important role in medicine, especially in the field of medical imaging. It can be used to diagnose diseases and predict certain statuses and possible events that may happen. Recently, more and more studies have confirmed the value of AI based on ultrasound in the evaluation of diffuse liver diseases and focal liver lesions. It can assess the severity of liver fibrosis and nonalcoholic fatty liver, differentially diagnose benign and malignant liver lesions, distinguish primary from secondary liver cancers, predict the curative effect of liver cancer treatment and recurrence after treatment, and predict microvascular invasion in hepatocellular carcinoma. The findings from these studies have great clinical application potential in the near future. The purpose of this review is to comprehensively introduce the current status and future perspectives of AI in liver ultrasound.     

基于动态增强MRI影像组学评分和激素受体的列线图预测乳腺癌新辅助化疗不敏感的价值

目的 探讨基于动态增强MRI（DCE-MRI）影像组学评分（Radscore）和激素受体状态的列线图预测乳腺癌新辅助化疗（NAC）疗效不敏感的价值。 方法 回顾性收集128例行乳腺癌NAC治疗的女性病人,平均年龄（49.2±10.0）岁。128例病人按照7∶3比例随机分为训练集90例（疗效敏感者47例,疗效不敏感者43例）和测试集38例（疗效敏感者15例,疗效不敏感者23例）。基于DCE-MRI影像提取并筛选影像组学特征,采用多因素逻辑回归构建影像组学模型并计算模型的Radscore。采用t检验、χ²检验或Fisher确切概率检验比较训练集和测试集中临床病理指标[年龄、雌激素受体（ER）、孕激素受体（PR）、人表皮生长因子受体-2（HER-2）和肿瘤增殖细胞核抗原-67（Ki-67）],将差异有统计学意义的临床病理指标和Radscore纳入多因素逻辑回归,建立联合模型和列线图。应用受试者操作特征（ROC）曲线下面积（AUC）评价影像组学模型和联合模型的预测效能。应用决策曲线评估影像组学模型和联合模型的临床应用价值。 结果 在训练集中,ER和PR在疗效敏感与不敏感组间的差异均有统计学意义（均P<0.05）,但未得到测试集的验证（均P>0.05）。在训练集中,联合模型预测NAC不敏感的AUC值和准确度分别高于影像组学模型约3.8%和3.1%。在测试集中,联合模型预测NAC不敏感的AUC值高于影像组学模型,其较后者提高了约2.3%,但两者的准确度相同。在基于ER、PR和Radscore构建的联合模型列线图中,Radscore得分最高,其次是ER和PR。决策曲线分析显示联合模型的临床获益高于影像组学模型。 结论 基于DCE-MRI的Radscore和ER、PR构建的联合模型列线图能够较好地预测NAC疗效不敏感。     

基于增强CT影像组学列线图预测单发肝细胞癌GPC3表达状态

目的 探讨增强CT影像组学列线图在鉴别单发肝细胞癌（HCC）磷脂酰肌醇蛋白聚糖3（GPC3）表达中的价值。方法 回顾性收集来自2个医疗机构共152例单发HCC病人的临床及影像资料,所有病人均行上腹部增强CT扫描并记录GPC3表达水平。天津市第一中心医院的106例病人资料作为训练集（GPC3阳性83例、阴性23例）,天津医科大学肿瘤医院的46例病人资料作为验证集（GPC3阳性35例、阴性11例）。对所有病人术前1个月内增强CT影像进行影像组学特征提取。在训练集中,对所有影像组学特征进行降维并得到最优子集,计算影像组学评分（Radscore）;比较GPC3阳性组和阴性组间临床资料[包括血清甲胎蛋白（AFP）、糖类抗原199（CA199）等]的差异,将差异有统计学意义的指标进行二元logistic回归分析,获得GPC3阳性的独立预测因素。将获得的临床信息及Radscore分别建立临床列线图、影像组学列线图及联合列线图。采用受试者操作特征曲线下面积（AUC）分析各列线图对GPC3表达状态的预测能力,采用DeLong检验比较各列线图间的诊断效能,并用决策曲线分析评估列线图的临床价值。使用验证集数据对列线图预测效能进行验证。结果 二元logistic回归显示血清AFP、CA199、Radscore是GPC3阳性的独立危险因素[优势比（OR）分别为8.503、1.090、13 300.044,均P<0.05]。校准曲线显示联合列线图对GPC3阳性表达的预测概率与实际概率一致性良好。训练集中,联合列线图的AUC（0.918）高于影像组学列线图（0.842）和临床列线图（0.787）（均P<0.05）,联合列线图的敏感度最高,而临床列线图的特异度最高;验证集中,联合列线图的AUC（0.896）高于影像组学列线图（0.726）和临床列线图（0.803）（均P<0.05）,联合列线图的敏感度和特异度均最高。决策曲线分析显示当阈值概率处于16%~86%时,联合列线图的临床净获益高于临床列线图和影像组学列线图。结论 基于增强CT的影像组学列线图可以术前鉴别单发HCC GPC3阳性和阴性表达,联合列线图进一步提高了预测效能。     

Changes in ADC and T2-weighted MRI-derived radiomic features in patients treated with focal salvage HDR prostate brachytherapy for local recurrence after previous external-beam radiotherapy

PurposeTo explore the changes in T2-weighted (T2w) and apparent diffusion coefficient (ADC) magnetic resonance imaging -derived radiomic features of the gross tumor volume (GTV) from focal salvage high-dose-rate prostate brachytherapy (HDRB) and to correlate with clinical parameters.Materials and MethodsEligible patients included those with biopsy-confirmed local recurrence that correlated with MRI (T2w, ADC). Patients received 27 Gy in 2 fractions separated by 1 week to a quadrant consisting of the GTV. The MRI was repeated 1 year after HDRB. GTVs, planning target volumes, and normal prostate tissue control volumes were identified on the pre- and post-HDRB MRIs. Radiomic features from each GTV were extracted, and principle component analysis identified features with the highest variance.ResultsPre- and post-HDRB MRIs were obtained from 14 trial patients. Principle component analysis showed that 18 and 17 features contributed to 93% and 86% of the variance observed in the T2w and ADC data, respectively. Sixteen T2w features and 1 ADC GTV feature were different from the control volumes in the pre-HDRB images (p < 0.05). Ten T2w and 7 ADC GTV post-HDRB features were different from those of pre-HDRB (p < 0.05).ConclusionsExploratory analysis reveals several radiomic features in the T2w and ADC image GTVs that distinguish the GTV from healthy prostate tissue and change significantly after salvage HDRB.     

La radiómica mejora la utilidad del ADC en la diferenciación entre el oncocitoma renal y el carcinoma cromófobo de células renales: resultados preliminares

ObjectiveDifferentiation between renal oncocytoma (RON) and chromophobe renal cell carcinoma (chRCC) remains challenging. We aimed to assess the accurate apparent diffusion coefficient (ADC) radiomics features in differentiating these tumors.Materials and methodsThis single-center retrospective study included 14 patients with histopathologically proven RON (n=6) and chRCC (n=8) who underwent magnetic resonance imaging. Features were extracted from ADC maps. Features with an intraclass correlation coefficient >0.90, an intergroup p<0.01 and interrater differences with normal distribution underwent agreement and receiver operating characteristic curve analyses.ResultsOverall, 6 features qualified for further analysis and Bland-Altman plots revealed acceptable agreement for all. Only 1 first order feature and 5 high order texture features successfully predicted RON with more than 90% sensitivities and specificities more than 80%.ConclusionSquared mean ADC and certain gray level run length matrix features extracted by radiomics of ADC mapping provide quite high diagnostic precision in terms of distinguishing between RON and chRCC.