Routine CT Imaging Research Articles

600 Acute Appendicitis as an Early Manifestation of Colorectal Cancer for Patients Aged 40 Years and Above

Abstract Aim Presence of underlying colorectal cancer with acute appendicitis is not unfamiliar in medical literature. However, there remains no clear guidance in the follow-up care post-appendicectomy. This study aims to investigate whether acute appendicitis can be an early manifestation of colorectal cancer in older adults and determine the need of routine pre-operative CT imaging and post-operative colonoscopy as a follow-up screen for early detection of colorectal cancer. Method This is a retrospective study comprising 1236 patients, aged 40 years and above, who underwent appendicectomy between January 2006 to September 2021. Results of radiological investigation pre-appendicectomy and colonoscopy post-appendicectomy were reviewed. Patients who were diagnosed immediately and subsequently following appendicectomy were recorded and analysed. Results Of the 1236 patients underwent appendicectomy, 636 (51.5%) were male and 600 (48.5%) were female (Median age 53 years; range 40–96 years). Out of 412 (33.3%) patients who had CT imaging, only one revealed sigmoid tumour which was later confirmed as moderately differentiated adenocarcinoma. 71 (5.7%) patients had colonoscopy post-appendicectomy. Among these, two were diagnosed with caecal cancer. A total of 22 (1.8%) patients were diagnosed with colorectal cancer: 13 adenocarcinoma, 5 carcinoid tumours, 3 low-grade mucinous carcinoma peritonei and 1 lymphoma. 15 (1.2%) were diagnosed at the time of appendicectomy, whereas the remaining 7 (0.6%) were diagnosed between 6 months to 11 years post-appendicectomy. Conclusion Preliminary finding suggests this is an area that warrant further study. Patients aged 40 years and above may benefit from colonoscopy following appendicectomy to exclude the possibility of underlying colorectal cancer.

Is routine CT scan after pancreaticoduodenectomy a useful tool in the early detection of complications? A single center retrospective analysis.

The clinical impact of routine CT imaging after pancreaticoduodenectomy (PD) has not been properly investigated. The aim of this study was to investigate the role of routine CT scan after PD for the detection of postoperative complications. Prospectively collected data of consecutive patients undergoing PD and receiving routine postoperative CT imaging were retrospectively analyzed. The primary endpoint was accuracy of CT imaging in identifying major complications. The secondary endpoint was identification of preoperative and intraoperative factors associated with severe complications. A subgroup analysis of CT scan accuracy in identifying severe complications in patients stratified by fistula risk score (FRS) and presence of early clinical alterations was also performed. A total of 145 patients were included. Routine CT scan had low specificity (Sp = 0.36) and high sensitivity (Sn = 0.98) for predicting major complications, with an accuracy of 0.57. At multivariate logistic regression analysis, only fistula moderate-high FRS (p = 0.029) was independently associated with severe complications. In patients with negligible-low FRS, CT scan showed a Sp of 0.63 and a Sn of 1.0 with an accuracy of 0.69. In patients with moderate-high FRS, CT scan had a Sp of 0.19, a Sn of 0.97 and an accuracy of 0.5. In the 20 (14%) patients with negligible-low FRS and no clinical alterations, no deaths or readmissions occurred regardless of CT findings, while one severe complication occurred in the positive CT scan group. In all other groups, no deaths or readmissions occurred in case of negative CT, with only one severe complication in the moderate-high FRS group with clinical alterations. In case of positive CT, the rate of severe complications was 47% in case of negligible-low FRS and clinical alterations, 40% in case of moderate-high FRS with no clinical alterations, and 45% in case of moderate-high FRS and clinical alterations. Routine postoperative CT scan after PD should not be performed in patients with negligible-low FRS and no clinical alterations. In all other patients, a negative CT scan appears to be highly accurate in identifying patients who will have an uneventful course and who could benefit from early discharge.

Additional clinical value of routine CT imaging in fragility fractures of the pelvis: a prospective cohort study (ARTIFACT).

Additional CT imaging for fragility fractures of the pelvis (FFP) has a high detection rate for concomitant posterior ring fractures (cPRFs). However, the clinical value of routine additional CT imaging is unknown. This study aimed to determine the additional clinical value of routine CT imaging by changes in treatment policy and to establish the predictive value of pain localized around the sacroiliac joint (SIJ) for cPRFs. A prospective cohort study was conducted in a single teaching hospital in the Netherlands between November 2019 and November 2020. Patients were included if they were ≥ 65years and had a (suspected) FFP on the pelvic radiograph. All patients underwent additional CT imaging. Changes in treatment policies ((possible) surgery, restrictive weight-bearing, hospital admission and outpatient follow-up) after CT imaging were registered. Fifty-one patients (44 female) were included with a mean age of 80.6years. Routine CT imaging revealed an additional cPRF in 27 patients (53%). A change in treatment occurred in 29 patients (57%), of which 7 (12%) were managed either surgical or with restrictive weight-bearing. The presence of pain around the SIJ had a sensitivity of 89% and specificity of 61% for detecting a cPRF. Routine additional CT imaging has few direct therapeutic consequences with regards to surgical management or restrictive weight-bearing. These findings may be altered when considering a lower threshold for surgical intervention. The presence of pain around the SIJ was highly predictive for a clinically relevant cPRF. NL8011 on 02-09-2019.

Multi-center evaluation of artificial intelligent imaging and clinical models for predicting neoadjuvant chemotherapy response in breast cancer.

Neoadjuvant chemotherapy (NAC) plays an important role in the management of locally advanced breast cancer. It allows for downstaging of tumors, potentially allowing for breast conservation. NAC also allows for in-vivo testing of the tumors' response to chemotherapy and provides important prognostic information. There are currently no clearly defined clinical models that incorporate imaging with clinical data to predict response to NAC. Thus, the aim of this work is to develop a predictive AI model based on routine CT imaging and clinical parameters to predict response to NAC. The CT scans of 324 patients with NAC from multiple centers in Singapore were used in this study. Four different radiomics models were built for predicting pathological complete response (pCR): first two were based on textural features extracted from peri-tumoral and tumoral regions, the third model based on novel space-resolved radiomics which extract feature maps using voxel-based radiomics and the fourth model based on deep learning (DL). Clinical parameters were included to build a final prognostic model. The best performing models were based on space-resolved and DL approaches. Space-resolved radiomics improves the clinical AUCs of pCR prediction from 0.743 (0.650 to 0.831) to 0.775 (0.685 to 0.860) and our DL model improved it from 0.743 (0.650 to 0.831) to 0.772 (0.685 to 0.853). The tumoral radiomics model performs the worst with no improvement of the AUC from the clinical model. The peri-tumoral combined model gives moderate performance with an AUC of 0.765 (0.671 to 0.855). Radiomics features extracted from diagnostic CT augment the predictive ability of pCR when combined with clinical features. The novel space-resolved radiomics and DL radiomics approaches outperformed conventional radiomics techniques.

Radiomics biopsy signature for predicting survival in patients with spinal bone metastases (SBMs)

Study designRetrospective analysis of a registered cohort of patients treated and irradiated for metastases in the spinal column in a single institute. ObjectiveThis is the first study to develop and internally validate radiomics features for predicting six-month survival probability for patients with spinal bone metastases (SBM). Background dataExtracted radiomics features from routine clinical CT images can be used to identify textural and intensity-based features unperceivable to human observers and associate them with a patient survival probability or disease progression. MethodsA study was conducted on 250 patients treated for metastases in the spinal column irradiated for the first time between 2014 and 2016, at the MAASTRO clinic in Maastricht, the Netherlands. The first 150 available patients were used to develop the model and the subsequent 100 patient were considered as a test set for the model. A bootstrap (B = 400) stepwise model selection, which combines both the forward and backward variable elimination procedure, was used to select the most useful predictive features from the training data based on the Akaike information criterion (AIC). The stepwise selection procedure was applied to the 400 bootstrap samples, and the results were plotted as a histogram to visualize how often each variable was selected. Only variables selected more than 90 % of the time over the bootstrap runs were used to build the final model.A prognostic index (PI) called radiomics score (radscore) and clinical score (clinscore) was calculated for each patient. The prognostic index was not scaled, the original values were used which can be extracted from the model directly or calculated as a linear combination of the variables in the model multiplied by the respective beta value for each patient. ResultsThe clinical model had a good discrimination power. The radiomics model, on the other hand, had an inferior performance with no added predictive power to the clinical model. The internal imaging characteristics do not seem to have a value in the prediction of survival. However, the Shape features were excluded from further analyses in our study since all biopsies had a standard shape hence no variability.

Impact of Muscle Mass Depletion on Surgical Outcomes in Patients with Primary High-grade Serous Ovarian Cancer Undergoing CRS and HIPEC.

To investigate the effect of sarcopenia on surgical outcomes in patients with primary high-grade serous ovarian cancer undergoing cytoreductive surgery and hyperthermic intraperitoneal chemotherapy (CRS and HIPEC). Descriptive study. Department of Surgical Oncology, Faculty of Medicine, Ankara University Ankara, Turkey, from January 2013 to January 2020. Forty patients, who underwent CRS and HIPEC with the diagnosis of primary high-grade serous ovarian cancer and peritoneal carcinomatosis were included in the study. Preoperative staging CT images were used to determine total psoas ındex values by measuring psoas muscle area at the level of L3 vertebra. Patients with total psoas ındex values below the cut-off levels were considered sarcopenic. Demographic, clinicopathological and perioperative results were compared between sarcopenic and non-sarcopenic patients. Serious postoperative complications (36.4% vs. 6.9%, p=0.039) and infective (54.5% vs. 17.2%, p=0.042) and pulmonary (72.7% vs. 34.5%, p=0.040 complications were significantly higher in sarcopenic patients. Hospital stay [20(12-25) vs. 12(9-16.5) days, p=0.017] and ICU stay [4(2-6) vs. 2(1-2.5) days, p=0.013)] were found to be longer in sarcopenic patients. In univariate analysis, advanced age (OR: 1.40 95% CI: 1.07-1.84; p=0.021) and sarcopenia (OR: 7.71% 95 CI: 1.17-51.06; p=0.039) were significantly associated with serious postoperative complications. The presence of sarcopenia (OR: 0.050 95% CI: 0.004-0.675; p=0.024) was found to be independent predictor of serious postoperative complications. Sarcopenia can easily be diagnosed without additional cost or radiation exposure with routine preoperative staging CT images. Identification of sarcopenic ovarian cancer patients in preoperative period may affect patient selection, predictability of possible serious complications, elective operation preparation process with a combination of nutrition and exercise therapy, thus postoperative complication rates may be reduced and short-term results may be improved. Key Words: Cytoreductive surgery, Ovarian cancer, Sarcopenia.

Epidemiology and reporting of osteoporotic vertebral fractures in patients with long-term hospital records based on routine clinical CT imaging

SummaryOsteoporotic vertebral fractures signify an increased risk of future fractures and mortality and can manifest the diagnosis of osteoporosis. We investigated the prevalence of vertebral fractures in routine CT of patients with long-term hospital records. Three out of ten patients showed osteoporotic vertebral fractures (VFs) corresponding to the highest rates reported in European population-based studies.IntroductionVFs are a common manifestation of osteoporosis, which influences future fracture risk. Their epidemiology has been investigated in population-based studies. However, few studies report the prevalence of osteoporotic VF in patients seen in clinical routine and include all common fracture levels of the thoracolumbar spine. The purpose of this study was to investigate the prevalence of osteoporotic VF in patients with CT scans and long-term hospital records and identify clinical factors associated with prevalent VFs.MethodsAll patients aged 45 years and older with a CT scan and prior hospital record of at least 5 years that were seen in the study period between September 2008 and May 2017 were reviewed. Imaging requirements were a CT scan with sagittal reformations including at least T6-L4. Patients with multiple myeloma were excluded. Fracture reading was performed using the Genant semi-quantitative method. Medical notes were reviewed for established diagnoses of osteoporosis and clinical information. Clinical factors (e.g. drug intake, chemotherapy, and mobility level) associated with prevalent VF were identified in logistic regression.ResultsThe study population consisted of 718 patients (228 women and 490 men; mean age 69.3 ± 10.1 years) with mainly cancer staging and angiography CT imaging. The overall prevalence of VFs was 30.5%, with non-significantly more men showing a fracture (32.5%) compared to women (26.3%; p > 0.05). Intake of metamizole for ≥ 3 months was significantly associated with a prevalent VF. Medical records did not include information about bone health in 90% of all patients. CT reports did mention a VF in only 24.7% of patients with a prevalent VF on CT review.ConclusionApproximately 30% of elderly patients with CT imaging and long-term hospital records showed VFs. Only one-quarter of these patients had VFs mentioned in CT reports. Osteoporosis management could be improved by consequent reporting of VFs in CT, opportunistic bone density measurements, and early involvement of fracture liaison services.

Overview of imaging choices for thrombectomy patients

Neuroimaging Predictors for the Outcome of Acute Interventions-Marc Fisher, M.D. Boston MA USA Brain imaging plays a key role in the diagnosis and management of acute ischemic stroke. All patients are imaged with either CT or MRI to exclude a hemorrhage and vessel imaging is necessary to identify patients with large vessel occlusion that are candidates for thrombectomy. The extent of ischemic injury early after stroke onset can also be estimated by various CT and MRI approaches. On routine CT imaging, the ASPECTS score provides information about the extent of ischemic injury and is widely used to identify thrombectomy candidates in the early time window after stroke onset.

Usefulness of advanced monoenergetic reconstruction technique in dual-energy computed tomography for detecting bladder cancer

PurposeDetecting bladder cancer (BC) in routine CT images is important but is sometimes difficult when cancer is small. We evaluated the ability of 40-keV advanced monoenergetic images to depict BC.Materials and methodsFifty-two patients with a median age of 74 years (range 45–92) who were diagnosed as BC with transurethral resection or cystectomy, were included. They were examined with contrast-enhanced dual-energy CT (DE-CT) and advanced virtual monoenergetic images (40 keV) were reconstructed. For evaluating depictability of BC on 40-keV or virtual-120-kVp images, the difference in CT number between the cancer and bladder wall (BC–BW value) were calculated. We also subjectively assessed depictability of BC in virtual-120-kVp and 40-keV images using a 4-grade Likert scale (3: clear, 0: not visualized).ResultsIn 42 of 52 patients, BC–BW values could be calculated because BC was detected on CT images. The mean BC–BW value at 40 keV was significantly higher than that of virtual 120 kVp [80.5 ± 54 (SD) vs. 11.4 ± 12.5 HU, P < 0.01]. Average scores of subjective evaluations in the virtual-120-kVp and 40-keV images were 1.7 ± 1.2 and 2.1 ± 1.2, respectively (P < 0.001).ConclusionThe advanced monoenergetic reconstruction technique reconstructed using DE-CT image is useful to depict BC.

Influence of reduced muscle mass and quality on ventilator weaning and complications during intensive care unit stay in COVID-19 patients

Background & aimsSarcopenia, a loss of muscle mass, quality and function, which is particularly evident in respiratory muscles, has been associated with many clinical adverse outcomes. In this study, we aimed at evaluating the role of reduced muscle mass and quality in predicting ventilation weaning, complications, length of intensive care unit (ICU) and of hospital stay and mortality in patients admitted to ICU for SARS-CoV-2-related pneumonia.MethodsThis was an observational study based on a review of medical records of all adult patients admitted to the ICU of a tertiary hospital in Milan and intubated for SARS-CoV-2-related pneumonia during the first wave of the COVID-19 pandemic. Muscle mass and quality measurement were retrieved from routine thoracic CT scans, when sections passing through the first, second or third lumbar vertebra were available.ResultsA total of 81 patients were enrolled. Muscle mass was associated with successful extubation (OR 1.02, 95% C.I. 1.00–1.03, p = 0.017), shorter ICU stay (OR 0.97, 95% C.I. 0.95–0.99, p = 0.03) and decreased hospital mortality (HR 0.98, 95% C.I. 0.96–0.99, p = 0.02). Muscle density was associated with successful extubation (OR 1.07, 95% C.I. 1.01–1.14; p = 0.02) and had an inverse association with the number of complications in ICU (Β −0.07, 95% C.I. −0.13 - −0.002, p = 0.03), length of hospitalization (Β −1.36, 95% C.I. −2.21 - −0.51, p = 0.002) and in-hospital mortality (HR 0.88, 95% C.I. 0.78–0.99, p = 0.046).ConclusionsLeveraging routine CT imaging to measure muscle mass and quality might constitute a simple, inexpensive and powerful tool to predict survival and disease course in patients with COVID-19. Preserving muscle mass during hospitalisation might have an adjuvant role in facilitating remission from COVID-19.

Applied machine learning for liver surgery

Abstract Background and objectives: Both hepatic functional reserve and the underlying histology are important determinants in the preoperative risk evaluation before major hepatectomies. In this project we developed a new approach that implements cutting-edge research in machine learning and nevertheless is cheap and easily applicable in a routine clinical setting is needed. Methods: After splitting the study population into a training and test set we trained a convolutional neural network to predict the liver function as determined by hepatobiliary mebrofenin scintigraphy and single photon emission computer tomography (SPECT) imaging. Results: We developed a workflow for predicting liver function from routine CT imaging data using convolutional neural networks. We also evaluated in how far transfer learning and data augmentation can help to solve remaining manual data pre-processing steps and implemented the developed workflow in a clinical routine setting. Conclusion: We propose a robust semiautomatic end-to-end classification workflow for abdominal CT scans for the prediction of liver function based on a deep convolutional neural network model that shows reliable and accurate results even with limited computational resources.

Chest CT Has Higher Yield for Infection than CT Sinus in Febrile Neutropenic Patients

ObjectiveChest and sinus CT imaging among cancer patients undergoing chemotherapy and bone marrow transplant in the setting of neutropenic fever is not uncommon, yet the utility of routine imaging surveillance remains unclear. We aim to compare the rates of acute infection detected on CT chest and CT sinus exams performed in this clinical setting. MethodsReports of 1059 consecutive CT chest and sinus examinations for the clinical indication of neutropenic fever on 262 patients performed between January through June 2017 were retrospectively reviewed. Infection as reported was characterized as acute or worsening, improving, stable, indeterminate or negative. Results were tabulated and Pearson's chi-square test was used for comparison analysis. ResultsAbsence of infection on CT sinus was significantly higher than CT chest (86.1% vs. 58.5%; P<0.001). Conversely, CT chest had significantly higher incidence of acute or worsening infection than CT sinus (28.7% vs. 11.6%; P<0.001). CT chest also showed significantly higher incidence of improving infection compared to CT sinus (6.2% vs. 1.1%; P<0.001). There was no significant difference between incidence of stable infection on CT chest and CT sinus (1.1% vs. 0.2%; P=0.059). Infection was indeterminate in 5.5% of CT chest vs. 1% on CT sinus (P<0.001). ConclusionsCT chest showed significantly higher diagnostic yield for acute infection than CT sinus, suggesting that sinusitis is less likely to be the source of fever than chest infections in febrile neutropenic patients. The majority of CT studies showed absence of infection, raising the question of the overall utility of routine surveillance CT imaging among this subset of patients.

The utility of routine post-hospitalization CT imaging in patients with non-operative mild to moderate traumatic brain injury

ABSTRACT Primary Objective: The purpose of this study was to determine the utility of CT imaging in patients with non-operative mild–moderate TBI with respect to changes in management. Methods: We conducted a retrospective analysis for 191 patients over a 5-year interval to examine whether follow-up CT initiated a change in management. We created a logistic regression model to incorporate different variables contributing to change in management. Results: Of 191 patients, 31 (16.2%) underwent a change in management. Change in management was associated with older age (65 yo vs. 55 yo, p = .011), diagnosis of subdural hematoma (p = .041), antiplatelet/anticoagulant therapy (p = .009), imaging performed (p = .16), and increased blood products on CT (p = <0.0001). For patients on antiplatelet/anticoagulant therapy, only those with worsening findings on CT required a change in management (p = .0002, 0.039). Surgical intervention was indicated in two patients. Conclusions: Limited clinical value exists in repeat CT scans for patients with mild TBI. Most patients with traumatic SAH, contusions, or asymptomatic patients should not have repeat imaging, as our study revealed only 2% of patients with positive CT finding and 0.6% requiring surgical intervention.

3D-printed models for periacetabular osteotomy surgical planning.

The purpose of this study was to determine the feasibility and clinical benefits of using 3D-printed hemipelvis models for periacetabular osteotomy preoperative planning in the treatment of hip dysplasia. This retrospective study included 28 consecutive cases in 26 patients, with two bilateral cases, who underwent periacetabular osteotomy between January 2017 and February 2020 and had routine radiographs, CT and MR imaging. Of these, 14 cases [mean patient age 30.7 (SD 8.4) years, 11 female] had routine preoperative imaging, and 14 cases [mean patient age 28.0 (SD 8.7) years, 13 female] had routine preoperative imaging and creation of a full-scale 3D-printed hemipelvis model from the CT data. The expected surgical cuts were performed on the 3D-printed models. All patients underwent Bernese periacetabular osteotomy. Operative times, including time to achieve proper acetabular position and total periacetabular osteotomy time, fluoroscopy radiation dose and estimated total blood loss were compiled. ANOVA compared outcome variables between the two patient groups, controlling for possible confounders. On average, patients who had additional preoperative planning using the 3D-printed model had a 5.5-min reduction in time to achieve proper acetabular position and a 14.5-min reduction in total periacetabular osteotomy time; however, these changes were not statistically significant (P = 0.526 and 0.151, respectively). No significant difference was identified in fluoroscopy radiation dose or total blood loss. Detailed surgical planning for periacetabular osteotomy using 3D-printed models is feasible using widely available and affordable technology and shows promise to improve surgical efficiency.

Evaluation of Ultra-Low-Dose Chest CT Images to Detect Lung Lesions

Background: The present study was conducted to examine the possibility of detecting different types of lung lesions, such as cancer, using ultra-low dose (ULD) chest CT images. Method: In this basic (experimental) study with computed tomography (CT images), 20 patients with different lung disease indications were scanned with ULD and routine dose chest CT protocols. ULD and routine dose CT images were reconstructed utilizing iDose and iterative model reconstruction. CT images were evaluated by two expert radiologists. Volume CT dose index (CTDIvol), dose length product, and effective dose were used for dose assessment in both protocols. Results: CTDIvol and dose length product for ULD protocol were 98% less compared to those for routine chest CT. The chest CT images for ULD and routine dose were diagnosed as normal in three patients with lung lesions, such as nodules, masses, plural effusion, fibrosis, diffuse ground glass opacities, bronchiectasis, and infiltration, in 17 patients. Patient dose of ULD chest CT (0.11mSv) is comparable to Poster-Anterior plus Lateral (0.1 mSv) chest radiograph while the effective dose due to routine chest CT is about 5.1 mSv. Conclusion: Diagnostic findings regarding ULD chest CT images with 98% of dose reduction were compared to those for routine dose. We concluded that it may be utilized as a very useful tool for screening and the follow-up of different lung diseases, malignancy for instance. ULD chest CT with 98% of dose reduction could be a suitable substitute for chest radiograph, with higher diagnostic values.

Motion correction for routine X-ray lung CT imaging

A novel motion correction algorithm for X-ray lung CT imaging has been developed recently. It was designed to perform for routine chest or thorax CT scans without gating, namely axial or helical scans with pitch around 1.0. The algorithm makes use of two conjugate partial angle reconstruction images for motion estimation via non-rigid registration which is followed by a motion compensated reconstruction. Differently from other conventional approaches, no segmentation is adopted in motion estimation. This makes motion estimation of various fine lung structures possible. The aim of this study is to explore the performance of the proposed method in correcting the lung motion artifacts which arise even under routine CT scans with breath-hold. The artifacts are known to mimic various lung diseases, so it is of great interest to address the problem. For that purpose, a moving phantom experiment and clinical study (seven cases) were conducted. We selected the entropy and positivity as figure of merits to compare the reconstructed images before and after the motion correction. Results of both phantom and clinical studies showed a statistically significant improvement by the proposed method, namely up to 53.6% (p < 0.05) and up to 35.5% (p < 0.05) improvement by means of the positivity measure, respectively. Images of the proposed method show significantly reduced motion artifacts of various lung structures such as lung parenchyma, pulmonary vessels, and airways which are prominent in FBP images. Results of two exemplary cases also showed great potential of the proposed method in correcting motion artifacts of the aorta which is known to mimic aortic dissection. Compared to other approaches, the proposed method provides an excellent performance and a fully automatic workflow. In addition, it has a great potential to handle motions in wide range of organs such as lung structures and the aorta. We expect that this would pave a way toward innovations in chest and thorax CT imaging.

CT-Based Radiomics Analysis Before Thermal Ablation to Predict Local Tumor Progression for Colorectal Liver Metastases

Predicting early local tumor progression after thermal ablation treatment for colorectal liver metastases patients is critical for the decision of subsequent follow-up and treatment. Radiomics features derived from medical images show great potential for prediction and prognosis. The aim is to develop and validate a machine learning radiomics model to predict local tumor progression based on the pre-ablation CT scan of colorectal liver metastases patients. Ninety patients with colorectal liver metastases (140 lesions) treated by ablation were included in the study and were randomly divided into a training (n = 63 patients/n = 94 lesions) and validation (n = 27 patients/n = 46 lesions) cohort. After manual lesion volume segmentation and preprocessing, 1593 radiomics features were extracted for each lesion. Three machine learning survival models were constructed based on (1) radiomics features, (2) clinical features and (3) a combination of clinical and radiomics features to predict local tumor progression free survival. Feature reduction and machine learning modeling were performed and optimized with sequential model-based optimization. Median follow-up was 24months (range 6-115). Thirty-one (22%) lesions developed local tumor progression. The concordance index in the validation set to predict local tumor progression free survival was 0.78 (95% confidence interval [CI]: 0.77-0.79) for the radiomics model, 0.56 (95%CI: 0.55-0.57) for the clinical model and 0.79 (95%CI: 0.78-0.80) for the combined model. A machine learning-based radiomics analysis of routine clinical CT imaging pre-ablation could act as a valuable biomarker model to predict local tumor progression with curative intent for colorectal liver metastases patients.

Serial Optic Nerve Sheath Diameter via Radiographic Imaging: Correlation With ICP and Outcomes.

Evaluation of optic nerve sheath diameter (ONSD) is a suggested correlation of intracranial pressure (ICP) and potential predictor of outcome after neurologic injury. Studies have evaluated sonographic measurement of ONSD; however, clinical limitations to this approach persist. Evaluation of ONSD measurements via routine brain CT imaging is less studied but offers potential for detection of increased ICP in the absence of invasive monitoring. Previous studies have used cross-sectional approaches to ONSD measurements via CT scan among patients with traumatic brain injury (TBI). No studies have evaluated serial correlations between CT ONSD measurements and ICP throughout hospitalization and across diagnosis types. The objective of this study was to investigate correlations between ONSD via serial CT imaging, ICP, and outcome at discharge among patients with neurologic injury. This is a retrospective cohort study of all adult patients admitted during a 12-month period with acute neurologic injury requiring ICP monitoring and critical care admission. N = 48. There was a strong, positive correlation between right/left ONSD across time points (r = 0.7-9, p < 0.001), suggesting a consistent bilateral response. Correlations were strongest between initial inpatient CT scan ONSD readings and ICP (r = 0.5, p < 0.05), but decreased over time. Patients with increased ICP across all diagnosis types experienced higher ONSD values on presentation to the emergency department (ED) and throughout hospitalization (range 5.7-6.4 mm, p < 0.05). Findings contribute to the utility of CT ONSD measurements as a potential indicator of increased ICP. Measurement of ONSD during serial CT brain imaging may inform clinical decisions regarding need for more invasive monitoring after neurologic injury.

Radiological society of North America: 106th annual meeting, November 29 to December 5, 2020

Radiological society of North America: 106th annual meeting, November 29 to December 5, 2020

Antiplatelet therapy is associated with a high rate of intracranial hemorrhage in patients with head injuries

BackgroundAntiplatelet agents are increasingly used in cardiovascular treatment. Limited research has been performed into risks of acute and delayed traumatic intracranial hemorrhage (ICH) in these patients who sustain head injuries....