Search

Abstract Triaging and prioritising patients for RT-PCR test had been essential in the management of COVID-19 in resource-scarce countries. In this study, we applied machine learning (ML) to the task of detection of SARS-CoV-2 infection using basic laboratory markers. We performed the statistical analysis and trained an ML model on a retrospective cohort of 5148 patients from 24 hospitals in Hong Kong to classify COVID-19 and other aetiology of pneumonia. We validated the model on three temporal validation sets from different waves of infection in Hong Kong. For predicting SARS-CoV-2 infection, the ML model achieved high AUCs and specificity but low sensitivity in all three validation sets (AUC: 89.9–95.8%; Sensitivity: 55.5–77.8%; Specificity: 91.5–98.3%). When used in adjunction with radiologist interpretations of chest radiographs, the sensitivity was over 90% while keeping moderate specificity. Our study showed that machine learning model based on readily available laboratory markers could achieve high accuracy in predicting SARS-CoV-2 infection.

Abstract Rationale and objectives To evaluate the impact of metabolic parameters in the peritoneal cavity on the likelihood of achieving complete tumor debulking in patients with ovarian and peritoneal cancers. Materials and methods Forty-nine patients with ovarian and peritoneal cancers were included, who underwent pre-operative 18F-fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (18F-FDG PET/CT). The immediate surgical outcome was dichotomized into complete and incomplete tumor debulking. 18F-FDG PET/CT was qualitatively and quantitatively assessed by scrutinizing 15 anatomical sites for the presence of peritoneal carcinomatosis (PC). Patient-based and site-based diagnostic characteristics were described. Metabolic parameters (SUVmax, metabolic tumor volume and total lesion glycolysis) and the number of 18F-FDG avid peritoneal sites were evaluated between the two groups. Receiver operating curve (ROC) analysis was performed to determine the optimal cut-off value in predicting incomplete tumor debulking. Results Twenty-seven out of the 49 patients had PC and 11 had incomplete debulking. Patient-based and site-based accuracies for detection of PC were 87.8 and 97.6%, respectively. The number of 18F-FDG avid peritoneal sites was significantly different between complete and incomplete debulking groups (0.6 ± 0.8 versus 2.3 ± 1.7 sites respectively, p = 0.001), and the only independent significant risk factor among other metabolic parameters tested (odd ratio = 2.983, 95% CI 1.104–8.062) for incomplete tumor debulking with an optimal cut-off value of ≥4 (AUC = 0.816). Conclusion The number of 18F-FDG avid peritoneal sites increased the risk of incomplete tumor debulking after surgery and potentially useful in assisting treatment stratification in patients with ovarian and peritoneal cancers.

Abstract Background 18F-FDG PET-CT is commonly used to monitor treatment response in patients with metastatic colorectal cancer (mCRC). With improvement in systemic therapy, complete metabolic response (CMR) is increasingly encountered but its clinical significance is undefined. The study examined the long-term outcomes and recurrence patterns in these patients. Methods Consecutive patients with mCRC who achieved CMR on PET-CT during first-line systemic therapy were retrospectively analysed. Measurable and non-measurable lesions identified on baseline PET-CT were compared with Response Criteria in Solid Tumors (RECIST) on CT on a per-lesion basis. Progression free (PFS) and Overall Survival (OS) were compared with clinical parameters and treatment characteristics on a per-patient basis. Results Between 2008 and 2011, 40 patients with 192 serial PET-CT scans were eligible for analysis involving 44 measurable and 38 non-measurable lesions in 59 metastatic sites. On a per-lesion basis, 46% also achieved Complete Response (CR) on RECIST criteria and sustained CMR was more frequent in these lesions (OR 1.727, p = 0.0031). Progressive metabolic disease (PMD) was seen in 12% of lesions, with liver metastasis the most common. Receiver operating characteristics (ROC) curve analysis revealed the optimal value of SUVmax for predicting PMD of a lesion was 4.4 (AUC 0.734, p = 0.004). On a per-patient basis, 14 patients achieved sustained CMR and their outcomes were better than those with PMD (median OS not reached vs 37.7 months p = 0.0001). No statistical difference was seen in OS between patients who achieved PR or CR (median OS 51.4 vs 44.2 months p = 0.766). Conclusion Our results provided additional information of long-term outcomes and recurrence patterns of patients with mCRC after achieving CMR. They had improved survival and sustained CMR using systemic therapy alone is possible. Discordance between morphological and metabolic response was consistent with reported literature but in the presence of CMR the two groups had comparable outcomes.

Background: Current treatments of unresectable hepatocellular carcinoma (HCC) are trans-arterial chemo-embolization (TACE), stereotactic body radiotherapy (SBRT), and targeted therapy. However, these treatments are limited in efficacy and safety for patients with large tumor sizes. Here, we report a case series of combined SBRT and anti-PD-1 therapy in patients with unresectable HCC of large tumors.Methods: This is a retrospective case series of five patients with unresectable hepatocellular carcinoma who were treated with SBRT followed by anti-PD1 antibodies. Four patients (80%) received a single dose of TACE prior to SBRT. All patients had advanced HCC ineligible of curative intervention. In this study, we report their treatment responses according to modified RECIST (response evaluation criteria in solid tumor) criteria, 1-year local control (LC), progression-free survival (PFS), 1-year overall survival (OS) rate, and toxicities.Results: Among the five evaluated patients, three patients had underlying diseases of hepatitis B and four patients had Barcelona clinic liver cancer stage C. The median size of their tumors was 9.8 cm (range: 9–16.1 cm). In addition, two patients had tumor vascular thrombosis and one had extra-hepatic disease. Five out of five patients (100%) responded to treatment, with two complete responses (CR) and three partial responses (PR). Among the partial responders, one had a down-staged tumor that became amenable for radiofrequency ablation for tumor clearance. No patient developed tumor progression at the time of analysis during the median follow-up of 14.9 months (range 8.6–19 months). The median PFS was 14.9 months (range: 8.6–19 months); 1-year LC and OS rate were both 100%. One patient had grade ≥ 3 toxicities (pneumonitis and skin reaction). There was no classical radiation-induced liver disease.Conclusions: The results obtained from these 5 cases demonstrate impressive tumor control from the combination of SBRT and checkpoint inhibitors in patients with large tumors of advanced HCC. Further prospective trials are warranted.

Objectives: 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. Methods: 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%). Comparison against international radiologists was performed on an independent test set of 852 cases. Results: RadGenX achieved an AUC of 0.89 on 4-fold cross-validation and an AUC of 0.79 (95%CI 0.78–0.80) on an independent test cohort of 5,894 patients. Delong's test showed statistical differences in model performance across patients from different regions (p < 0.01), disease severity (p < 0.001), gender (p < 0.001), and age (p = 0.03). Prevalence simulations showed the negative predictive value increases from 86.1% at 33.3% prevalence, to greater than 98.5% at any prevalence below 4.5%. Compared with radiologists, McNemar's test showed the model has higher sensitivity (p < 0.001) but lower specificity (p < 0.001). Conclusion: An AI model that predicts COVID-19 infection on CXR in symptomatic patients was validated on a large international cohort providing valuable context on testing and performance expectations for AI systems that perform COVID-19 prediction on CXR. Key Points: • 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% at any prevalence below 4.5%. [ABSTRACT FROM AUTHOR]

Objectives: To investigate the predictive value of peritoneal carcinomatosis (PC) quantification by DWI in determining incomplete tumour debulking in ovarian carcinoma (OC). Methods: Prospective patients with suspected stage III–IV or recurrent OC were recruited for DWI before surgery. PC on DWI was segmented semi-automatically by k-means clustering, retaining voxels with intermediate apparent diffusion coefficient (ADC) to quantify PC burden. A scoring system, functional peritoneal cancer index (fPCI), was proposed based on the segmentation of tumour volume in 13 abdominopelvic regions with additional point given to involvement of critical sites. ADC of the largest PC was recorded. The surgical complexity and outcomes (complete vs. incomplete tumour debulking) were documented. fPCI was correlated with surgical PCI (sPCI), surgical complexity, and its ability to predict incomplete tumour debulking. Results: Fifty-three patients with stage III–IV or recurrent OC were included with a mean age of 56.1 ± 11.8 years old. Complete tumour debulking was achieved in 38/53 patients (71.7%). Significant correlation was found between fPCI and sPCI (r > 0.757, p < 0.001). Patients with high-fPCI (fPCI ≥ 6) had a high surgical complexity score (p = 0.043) with 84.2% received radical or supra-radical surgery. The mean fPCI was significantly higher in patients with incomplete tumour debulking than in those with complete debulking (10.27 vs. 4.71, p < 0.001). fPCI/ADC combined with The International Federation of Gynecology and Obstetrics stage achieved 92.5% accuracy in predicting incomplete tumour debulking (AUC 0.947). Conclusions: DWI-derived fPCI offered a semi-automated estimation of PC burden. fPCI/ADC could predict the likelihood of incomplete tumour debulking with high accuracy. Key Points: • Functional peritoneal cancer index (fPCI) derived from DWI offered a semi-automated estimation of tumour burden in ovarian carcinoma. • fPCI was highly correlated with surgical PCI (sPCI). • fPCI/ADC could predict the likelihood of incomplete tumour debulking with high accuracy. [ABSTRACT FROM AUTHOR]

Rationale and objectives: To evaluate the impact of metabolic parameters in the peritoneal cavity on the likelihood of achieving complete tumor debulking in patients with ovarian and peritoneal cancers. Materials and methods: Forty-nine patients with ovarian and peritoneal cancers were included, who underwent pre-operative 18F-fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (18F-FDG PET/CT). The immediate surgical outcome was dichotomized into complete and incomplete tumor debulking. 18F-FDG PET/CT was qualitatively and quantitatively assessed by scrutinizing 15 anatomical sites for the presence of peritoneal carcinomatosis (PC). Patient-based and site-based diagnostic characteristics were described. Metabolic parameters (SUVmax, metabolic tumor volume and total lesion glycolysis) and the number of 18F-FDG avid peritoneal sites were evaluated between the two groups. Receiver operating curve (ROC) analysis was performed to determine the optimal cut-off value in predicting incomplete tumor debulking. Results: Twenty-seven out of the 49 patients had PC and 11 had incomplete debulking. Patient-based and site-based accuracies for detection of PC were 87.8 and 97.6%, respectively. The number of 18F-FDG avid peritoneal sites was significantly different between complete and incomplete debulking groups (0.6 ± 0.8 versus 2.3 ± 1.7 sites respectively, p = 0.001), and the only independent significant risk factor among other metabolic parameters tested (odd ratio = 2.983, 95% CI 1.104–8.062) for incomplete tumor debulking with an optimal cut-off value of ≥4 (AUC = 0.816). Conclusion: The number of 18F-FDG avid peritoneal sites increased the risk of incomplete tumor debulking after surgery and potentially useful in assisting treatment stratification in patients with ovarian and peritoneal cancers. [ABSTRACT FROM AUTHOR]

Background: Current treatments of unresectable hepatocellular carcinoma (HCC) are trans-arterial chemo-embolization (TACE), stereotactic body radiotherapy (SBRT), and targeted therapy. However, these treatments are limited in efficacy and safety for patients with large tumor sizes. Here, we report a case series of combined SBRT and anti-PD-1 therapy in patients with unresectable HCC of large tumors. Methods: This is a retrospective case series of five patients with unresectable hepatocellular carcinoma who were treated with SBRT followed by anti-PD1 antibodies. Four patients (80%) received a single dose of TACE prior to SBRT. All patients had advanced HCC ineligible of curative intervention. In this study, we report their treatment responses according to modified RECIST (response evaluation criteria in solid tumor) criteria, 1-year local control (LC), progression-free survival (PFS), 1-year overall survival (OS) rate, and toxicities. Results: Among the five evaluated patients, three patients had underlying diseases of hepatitis B and four patients had Barcelona clinic liver cancer stage C. The median size of their tumors was 9.8 cm (range: 9–16.1 cm). In addition, two patients had tumor vascular thrombosis and one had extra-hepatic disease. Five out of five patients (100%) responded to treatment, with two complete responses (CR) and three partial responses (PR). Among the partial responders, one had a down-staged tumor that became amenable for radiofrequency ablation for tumor clearance. No patient developed tumor progression at the time of analysis during the median follow-up of 14.9 months (range 8.6–19 months). The median PFS was 14.9 months (range: 8.6–19 months); 1-year LC and OS rate were both 100%. One patient had grade ≥ 3 toxicities (pneumonitis and skin reaction). There was no classical radiation-induced liver disease. Conclusions: The results obtained from these 5 cases demonstrate impressive tumor control from the combination of SBRT and checkpoint inhibitors in patients with large tumors of advanced HCC. Further prospective trials are warranted. [ABSTRACT FROM AUTHOR]

Background: 18F-FDG PET-CT is commonly used to monitor treatment response in patients with metastatic colorectal cancer (mCRC). With improvement in systemic therapy, complete metabolic response (CMR) is increasingly encountered but its clinical significance is undefined. The study examined the long-term outcomes and recurrence patterns in these patients.Methods: Consecutive patients with mCRC who achieved CMR on PET-CT during first-line systemic therapy were retrospectively analysed. Measurable and non-measurable lesions identified on baseline PET-CT were compared with Response Criteria in Solid Tumors (RECIST) on CT on a per-lesion basis. Progression free (PFS) and Overall Survival (OS) were compared with clinical parameters and treatment characteristics on a per-patient basis.Results: Between 2008 and 2011, 40 patients with 192 serial PET-CT scans were eligible for analysis involving 44 measurable and 38 non-measurable lesions in 59 metastatic sites. On a per-lesion basis, 46% also achieved Complete Response (CR) on RECIST criteria and sustained CMR was more frequent in these lesions (OR 1.727, p = 0.0031). Progressive metabolic disease (PMD) was seen in 12% of lesions, with liver metastasis the most common. Receiver operating characteristics (ROC) curve analysis revealed the optimal value of SUVmax for predicting PMD of a lesion was 4.4 (AUC 0.734, p = 0.004). On a per-patient basis, 14 patients achieved sustained CMR and their outcomes were better than those with PMD (median OS not reached vs 37.7 months p = 0.0001). No statistical difference was seen in OS between patients who achieved PR or CR (median OS 51.4 vs 44.2 months p = 0.766).Conclusion: Our results provided additional information of long-term outcomes and recurrence patterns of patients with mCRC after achieving CMR. They had improved survival and sustained CMR using systemic therapy alone is possible. Discordance between morphological and metabolic response was consistent with reported literature but in the presence of CMR the two groups had comparable outcomes. [ABSTRACT FROM AUTHOR]

Background:Given that high-intensity focussed ultrasound (HIFU) of benign thyroid nodules often causes a massive release of thyroglobulin (Tg) into the circulation, we hypothesised a greater initial Tg rise may result in a greater nodule shrinkage 6 months after ablation. Methods:One hundred and five patients who underwent HIFU for symptomatic benign thyroid nodule from 2015 to 2016 were analysed. Serum Tg and anti-Tg autoantibody were checked on treatment day (baseline) and 4 d after treatment. The % of Tg rise = [serum Tg on day-4 – baseline serum Tg]/[baseline serum Tg] * 100 while the nodule shrinkage as measured by volume reduction ratio (VRR) = [baseline volume – volume at 6-month]/[baseline volume] * 100. Treatment success was defined as VRR >50%. Results:At 6-month, the mean VRR was 62.2 ± 25.0% and 59 (76.6%) patients had treatment success. The mean baseline Tg level increased from 292.8 ± 672.7 ng/mL to 2022.7 ± 1759.8 ng/mL in the first-week. The % of Tg rise did not significantly correlate with either 3-month or 6-month VRR (p = 0.920 andp = 0.699, respectively). The mean % of Tg rise in the first week was not different between those with and without 6-month treatment success (368.2% vs. 1068.7%,p = 0.381). No clinical factors significantly correlated with treatment success. Conclusions:There was an almost seven-fold increase in the mean Tg level 4 d after HIFU ablation. The % of Tg rise in the first week did not appear to correlate with the 6-month nodule shrinkage or treatment success. [ABSTRACT FROM PUBLISHER]