This study aimed to identify radiomic features of primary tumor and develop a model for indicating extrahepatic metastasis of hepatocellular carcinoma (HCC). Contrast-enhanced computed tomographic (CT) images of 177 HCC cases, including 26 metastatic (MET) and 151 non-metastatic (non-MET), were retrospectively collected and analyzed. For each case, 851 radiomic features, which quantify shape, intensity, texture, and heterogeneity within the segmented volume of the largest HCC tumor in arterial phase, were extracted using Pyradiomics. The dataset was randomly split into training and test sets. Synthetic Minority Oversampling Technique (SMOTE) was performed to augment the training set to 145 MET and 145 non-MET cases. The test set consists of six MET and six non-MET cases. The external validation set is comprised of 20 MET and 25 non-MET cases collected from an independent clinical unit. Logistic regression and support vector machine (SVM) models were identified based on the features selected using the stepwise forward method while the deep convolution neural network, visual geometry group 16 (VGG16), was trained using CT images directly. Grey-level size zone matrix (GLSZM) features constitute four of eight selected predictors of metastasis due to their perceptiveness to the tumor heterogeneity. The radiomic logistic regression model yielded an area under receiver operating characteristic curve (AUROC) of 0.944 on the test set and an AUROC of 0.744 on the external validation set. Logistic regression revealed no significant difference with SVM in the performance and outperformed VGG16 significantly. As extrahepatic metastasis workups, such as chest CT and bone scintigraphy, are standard but exhaustive, radiomic model facilitates a cost-effective method for stratifying HCC patients into eligibility groups of these workups.

Background Single‐shot diffusion‐weighted imaging (ssDWI) has been shown useful for detecting active bowel inflammation in Crohn's disease (CD) without MRI contrast. However, ssDWI suffers from geometric distortion and low spatial resolution. Purpose To compare conventional ssDWI with higher‐resolution ssDWI (HR‐ssDWI) and multi‐shot DWI based on multiplexed sensitivity encoding (MUSE‐DWI) for evaluating bowel inflammation in CD, using contrast‐enhanced MR imaging (CE‐MRI) as the reference standard. Study Type Prospective. Subjects Eighty nine patients with histological diagnosis of CD from previous endoscopy (55 male/34 female, age: 17–69 years). Field Strength/Sequences ssDWI (2.7 mm × 2.7 mm), HR‐ssDWI (1.8 mm × 1.8 mm), MUSE‐DWI (1.8 mm × 1.8 mm) based on echo‐planar imaging, T2‐weighted imaging, and CE‐MRI sequences, all at 1.5 T. Assessment Five raters independently evaluated the tissue texture conspicuity, geometry accuracy, minimization of artifacts, diagnostic confidence, and overall image quality using 5‐point Likert scales. The diagnostic performance (sensitivity, specificity and accuracy) of each DWI sequences was assessed on per‐bowel‐segment basis. Statistical Tests Inter‐rater agreement for qualitative evaluation of each parameter was measured by the intra‐class correlation coefficient (ICC). Paired Wilcoxon signed‐rank tests were performed to evaluate the statistical significance of differences in qualitative scoring between DWI sequences. A P value <0.05 was considered to be statistically significant. Results Tissue texture conspicuity, geometric distortions, and overall image quality were significantly better for MUSE‐DWI than for ssDWI and HR‐ssDWI with good agreement among five raters (ICC: 0.70–0.89). HR‐ssDWI showed significantly poorer performance to ssDWI and MUSE‐DWI for all qualitative scores and had the worst diagnostic performance (sensitivity of 57.0% and accuracy of 87.3%, with 36 undiagnosable cases due to severe artifacts). MUSE‐DWI showed significantly higher sensitivity (97.5% vs. 86.1%) and accuracy (98.9% vs. 95.1%) than ssDWI for detecting bowel inflammation. Data Conclusion MUSE‐DWI was advantageous in assessing bowel inflammation in CD, resulting in improved spatial resolution and image quality. Level of Evidence 2 Technical Efficacy Stage 2

While chest radiograph (CXR) is the first-line imaging investigation in patients with respiratory symptoms, differentiating COVID-19 from other respiratory infections on CXR remains challenging. We developed and validated an AI system for COVID-19 detection on presenting CXR. A deep learning model (RadGenX), trained on 168,850 CXRs, was validated on a large international test set of presenting CXRs of symptomatic patients from 9 study sites (US, Italy, and Hong Kong SAR) and 2 public datasets from the US and Europe. Performance was measured by area under the receiver operator characteristic curve (AUC). Bootstrapped simulations were performed to assess performance across a range of potential COVID-19 disease prevalence values (3.33 to 33.3 • An AI model developed using CXRs to detect COVID-19 was validated in a large multi-center cohort of 5,894 patients from 9 prospectively recruited sites and 2 public datasets. • Differences in AI model performance were seen across region, disease severity, gender, and age. • Prevalence simulations on the international test set demonstrate the model’s NPV is greater than 98.5

Reverse Transcription-Polymerase Chain Reaction (RT-PCR) is the gold standard for diagnosis of SARS-CoV-2 infection, but requires specialized equipment and reagents and suffers from long turnaround times. While valuable, chest imaging currently only detects COVID-19 pneumonia, but if it can predict actual RT-PCR SARS-CoV-2 status is unknown. Radiogenomics may provide an effective and accurate RT-PCR-based surrogate. We describe a deep learning radiogenomics (DLR) model (RadGen) that predicts a patient's RT-PCR SARS-CoV-2 status solely from their frontal chest radiograph (CXR).

Purpose: To evaluate the performance of a deep learning (DL) algorithm for the detection of COVID-19 on chest radiographs (CXR). Materials and Methods: In this retrospective study, a DL model was trained on 112,120 CXR images with 14 labeled classifiers (ChestX-ray14) and fine-tuned using initial CXR on hospital admission of 509 patients, who had undergone COVID-19 reverse transcriptase-polymerase chain reaction (RT-PCR). The test set consisted of a CXR on presentation of 248 individuals suspected of COVID-19 pneumonia between February 16 and March 3, 2020 from 4 centers (72 RT-PCR positives and 176 RT-PCR negatives). The CXR were independently reviewed by 3 radiologists and using the DL algorithm. Diagnostic performance was compared with radiologists’ performance and was assessed by area under the receiver operating characteristics (AUC). Results: The median age of the subjects in the test set was 61 (interquartile range: 39 to 79) years (51% male). The DL algorithm achieved an AUC of 0.81, sensitivity of 0.85, and specificity of 0.72 in detecting COVID-19 using RT-PCR as the reference standard. On subgroup analyses, the model achieved an AUC of 0.79, sensitivity of 0.80, and specificity of 0.74 in detecting COVID-19 in patients presented with fever or respiratory systems and an AUC of 0.87, sensitivity of 0.85, and specificity of 0.81 in distinguishing COVID-19 from other forms of pneumonia. The algorithm significantly outperforms human readers ( P <0.001 using DeLong test) with higher sensitivity ( P =0.01 using McNemar test). Conclusions: A DL algorithm (COV19NET) for the detection of COVID-19 on chest radiographs can potentially be an effective tool in triaging patients, particularly in resource-stretched health-care systems.

Outbreaks due to emergent pathogens like Covid-19 are difficult to contain as the time to gather sufficient information to develop a detection system is outpaced by the speed of transmission. Here we develop a general pneumonia (PNA) CXR Deep Learning (DL) model (MAIL1.0) follow by a second-generation DL model (MAIL2.0) for detection of Covid-19 on chest radiographs (CXR). We validate the models on two prospective cohorts of high-risks patients screened for Covid-19 reverse transcriptase-polymerase chain reaction (RT-PCR). MAIL1.0 has an Area Under the Receiver Operating Characteristics (AUC) of 0.93, sensitivity and specificity of 90.5% and 76.7% in detection of visible pneumonia and MAIL2.0 has an AUC of 0.81, sensitivity and specificity of 84.7% and 71.6%, significantly outperforming radiologists, especially amongst asymptomatic and patients presenting with early symptoms. Nowcast DL models may be an effective tool in helping to constrain the outbreak, particularly in resource-stretched healthcare systems.

To describe the clinical outcome of advanced HCC patients treated according to our individualized hypo-fractionated radiotherapy (IHRT) protocol. We analyzed the prospective collected data of 172 patients who received palliative IHRT from May-2006 to Apr-2017. All patients had advanced HCC > 5cm ineligible for curative interventions. Out of 172 patients, 100 (58.1%) were refractory to loco-regional therapy and received RT alone, and 72 (41.9%) received single dose of TACE at 4 weeks before RT. IHRT was delivered by stereotactic body radiation therapy (SBRT) techniques at 4 Gy/fractions (fr) daily for 5 to 10 fr, which was determined by tumor size/volume, V30/mean dose of uninvolved liver, and proximity of bowel. No scheduled treatment was given unless disease progression. Median age was 61 years (interquartile range: 29 – 90 years). HCC was related to hepatitis B virus in 79.1%, hepatitis C virus in 5.8%, and alcoholism in 5.8%. There were 80.8% CP A, 19.2% B. There were 34.9% who had portal vein or IVC thrombosis, 27.3% had extra-hepatic metastasis. Median tumor size was 12.2 cm (interquartile range: 8.5 – 16.0 cm) and median volume was 718.2 ml (interquartile range: 249.6 – 1577.9 ml). The median total equivalent dose in 2Gy per fraction (EQD2, a/b=10) was 32.7 Gy (4Gy x 7) (Range: 23.3 – 46.7 Gy). The median follow-up time was 11.2 months (Range: 0.2 – 134.3 months). One hundred fifty-six patients had died at the time of analysis. Of the surviving 16 patients, the median follow-up time was 34.6 months (Range: 13.6 – 131.7 months). The best response (RECIST) was 2.6% CR, 46.1 % PR, 40.1% SD, and 11.2% PD. The 1-year and 2-year local control rate was 78.8 % (95% Cl, 70.4 – 84.9%) and 63.8 % (95% Cl, 51.8 – 72.7%) respectively. The overall median OS was 11.1 months (95% Cl, 9.3 – 13.0 months). Patients received TACE + RT had significantly better local control and overall survival than RT alone (Table 1). Treatment related death occurred in 4 patients (2.3%). Two patients did not complete IHRT. The commonest ≥ grade 3 toxicities were anemia (8.7%), thrombocytopenia (4.1%). There were 17.9% of patients without disease progression had decline of CP class in 3 months. One patient developed non-classical radiation-induced liver injury (RILD). IHRT with low to moderate dose achieves effective local control with manageable toxicity in advanced HCC patients. The survival outcome compared favorably to historical results in similar population. Patients received TACE + RT had better outcome than RT alone. Randomized trial to evaluate adding IHRT to the standard of care is warranted.Abstract 1095; Table 1Comparison of clinical outcome between TACE + RT vs. RT aloneTACE + RT (N=72) (2012-2017)RT alone (N=100) (2006-2012)P value1-year local control rate (%)88.4 (76.6 – 94.2)71.3 (58.3 – 80.3)0.0382- year local control rate (%)75.5 (57.1 – 86.0)53.9 (36.4 – 66.5)1-year overall survival rate (%)50.0 (38.5 – 61.6)40.0 (30.4 – 49.6)0.0422-year overall survival rate (%)31.6 (20.8 – 42.4)21.6 (13.5 – 29.7)Median OS (months)11.8 (9.5 – 14.0)9.9 (6.9 – 12.9) Open table in a new tab