Sorafenib induces pigmentation via the regulation of ß-catenin signalling pathway in melanoma cells.

We conducted large-scale screening test on drugs that were already approved for other diseases to find pigmentation-modulating agents. Among drugs with potential for pigmentation control, we selected sorafenib and further investigated the effect on pigmentation using HM3KO melanoma cells. As a result of treating melanoma cells with sorafenib, pigmentation was promoted in terms of melanin content and tyrosinase activity. Sorafenib increased mRNA and protein levels of pigmentation-related genes such as MITF, tyrosinase and TRP1. To uncover the action mechanism, we investigated the effect of sorafenib on the intracellular signalling pathways. Sorafenib reduced phosphorylation of AKT and ERK, suggesting that sorafenib induces pigmentation through inhibition of the AKT and ERK pathways. In addition, sorafenib significantly increased the level of active ß-catenin, together with activation of ß-catenin signalling. Mechanistic study revealed that sorafenib decreased phosphorylation of serine 9 (S9) of GSK3ß, while it increased phosphorylation of tyrosine 216 (Y216) of GSK3ß. These results suggest that sorafenib activates the ß-catenin signalling through the regulation of GSK3ß phosphorylation, thereby affecting the pigmentation process.

Development and validation of an ensemble artificial intelligence model for comprehensive imaging quality check to classify body parts and contrast enhancement.

BACKGROUND: Despite the dramatic increase in the use of medical imaging in various therapeutic fields of clinical trials, the first step of image quality check (image QC), which aims to check whether images are uploaded appropriately according to the predefined rules, is still performed manually by image analysts, which requires a lot of manpower and time. METHODS: In this retrospective study, 1669 computed tomography (CT) images with five specific anatomical locations were collected from Asan Medical Center and Kangdong Sacred Heart Hospital. To generate the ground truth, two radiologists reviewed the anatomical locations and presence of contrast enhancement using the collected data. The individual deep learning model is developed through InceptionResNetv2 and transfer learning, and we propose Image Quality Check-Net (Image QC-Net), an ensemble AI model that utilizes it. To evaluate their clinical effectiveness, the overall accuracy and time spent on image quality check of a conventional model and ImageQC-net were compared. RESULTS: ImageQC-net body part classification showed excellent performance in both internal (precision, 100%; recall, 100% accuracy, 100%) and external verification sets (precision, 99.8%; recovery rate, 99.8%, accuracy, 99.8%). In addition, contrast enhancement classification performance achieved 100% precision, recall, and accuracy in the internal verification set and achieved (precision, 100%; recall, 100%; accuracy 100%) in the external dataset. In the case of clinical effects, the reduction of time by checking the quality of artificial intelligence (AI) support by analysts 1 and 2 (49.7% and 48.3%, respectively) was statistically significant (p < 0.001). CONCLUSIONS: Comprehensive AI techniques to identify body parts and contrast enhancement on CT images are highly accurate and can significantly reduce the time spent on image quality checks.

A reliable and robust method for the upper thigh muscle quantification on computed tomography: toward a quantitative biomarker for sarcopenia.

BACKGROUND: We aimed to evaluate the feasibility of the upper thigh level as a landmark to measure muscle area for sarcopenia assessment on computed tomography (CT). METHODS: In the 116 healthy subjects who performed CT scans covering from mid-abdomen to feet, the skeletal muscle area in the upper thigh level at the inferior tip of ischial tuberosity (SMAUT), the mid-thigh level (SMAMT), and L3 inferior endplate level (SMAL3) were measured by two independent readers. Pearson correlation coefficients between SMAUT, SMAMT, and SMAL3 were calculated. Inter-reader agreement between the two readers were evaluated using intraclass correlation coefficient (ICC) and Bland-Altman plots with 95% limit of agreement (LOA). RESULTS: In readers 1 and 2, very high positive correlations were observed between SMAUT and SMAMT (r = 0.91 and 0.92, respectively) and between SMAUT and SMAL3 (r = 0.90 and 0.91, respectively), while high positive correlation were observed between SMAMT and SMAL3 (r = 0.87 and 0.87, respectively). Based on ICC values, the inter-reader agreement was the best in the SMAUT (0.999), followed by the SMAL3 (0.990) and SMAMT (0.956). The 95% LOAs in the Bland-Altman plots indicated that the inter-reader agreement of the SMAUT (- 0.462 to 1.513) was the best, followed by the SMAL3 (- 9.949 to 7.636) and SMAMT (- 12.105 to 14.605). CONCLUSION: Muscle area measurement at the upper thigh level correlates well with those with the mid-thigh and L3 inferior endpoint level and shows the highest inter-reader agreement. Thus, the upper thigh level might be an excellent landmark enabling SMAUT as a reliable and robust biomarker for muscle area measurement for sarcopenia assessment.

CDISC-compliant clinical trial imaging management system with automatic verification and data Transformation: Focusing on tumor response assessment data in clinical trials.

OBJECTIVE: Major issues in imaging data management of tumor response assessment in clinical trials include high human errors in data input and unstandardized data structures, warranting a new breakthrough IT solution. Thus, we aim to develop a Clinical Data Interchange Standards Consortium (CDISC)-compliant clinical trial imaging management system (CTIMS) with automatic verification and transformation modules for implementing the CDISC Study Data Tabulation Model (SDTM) in the tumor response assessment dataset of clinical trials. MATERIALS AND METHODS: In accordance with various CDISC standards guides and Response Evaluation Criteria in Solid Tumors (RECIST) guidelines, the overall system architecture of CDISC-compliant CTIMS was designed. Modules for standard-compliant electronic case report form (eCRF) to verify data conformance and transform into SDTM data format were developed by experts in diverse fields such as medical informatics, medical, and clinical trial. External validation of the CDISC-compliant CTIMS was performed by comparing it with our previous CTIMS based on real-world data and CDISC validation rules by Pinnacle 21 Community Software. RESULTS: The architecture of CDISC-compliant CTIMS included the standard-compliant eCRF module of RECIST, the automatic verification module of the input data, and the SDTM transformation module from the eCRF input data to the SDTM datasets based on CDISC Define-XML. This new system was incorporated into our previous CTIMS. External validation demonstrated that all 176 human input errors occurred in the previous CTIMS filtered by a new system yielding zero error and CDISC-compliant dataset. The verified eCRF input data were automatically transformed into the SDTM dataset, which satisfied the CDISC validation rules by Pinnacle 21 Community Software. CONCLUSIONS: To assure data consistency and high quality of the tumor response assessment data, our new CTIMS can minimize human input error by using standard-compliant eCRF with an automatic verification module and automatically transform the datasets into CDISC SDTM format.

COVID-19 Pneumonia Diagnosis Using a Simple 2D Deep Learning Framework With a Single Chest CT Image: Model Development and Validation.

BACKGROUND: Coronavirus disease (COVID-19) has spread explosively worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) is a relevant screening tool due to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely occupied fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. OBJECTIVE: We aimed to rapidly develop an AI technique to diagnose COVID-19 pneumonia in CT images and differentiate it from non-COVID-19 pneumonia and nonpneumonia diseases. METHODS: A simple 2D deep learning framework, named the fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning using one of four state-of-the-art pretrained deep learning models (VGG16, ResNet-50, Inception-v3, or Xception) as a backbone. For training and testing of FCONet, we collected 3993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and nonpneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training set and a testing set at a ratio of 8:2. For the testing data set, the diagnostic performance of the four pretrained FCONet models to diagnose COVID-19 pneumonia was compared. In addition, we tested the FCONet models on an external testing data set extracted from embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. RESULTS: Among the four pretrained models of FCONet, ResNet-50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100.00%, and accuracy 99.87%) and outperformed the other three pretrained models in the testing data set. In the additional external testing data set using low-quality CT images, the detection accuracy of the ResNet-50 model was the highest (96.97%), followed by Xception, Inception-v3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). CONCLUSIONS: FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing data set, the FCONet model based on ResNet-50 appears to be the best model, as it outperformed other FCONet models based on VGG16, Xception, and Inception-v3.

CT indices for the diagnosis of hepatic steatosis using non-enhanced CT images: development and validation of diagnostic cut-off values in a large cohort with pathological reference standard.

OBJECTIVES: To compare the performances of CT indices for diagnosing hepatic steatosis (HS) and to determine and validate the CT index cut-off values. METHODS: Three indices were measured on non-enhanced CT images of 4413 living liver donor candidates (2939 men, 1474 women; mean age, 31.4 years): hepatic attenuation (CTL), hepatic attenuation minus splenic attenuation (CTL-S), and hepatic attenuation divided by splenic attenuation (CTL/S). The performances of these CT indices in diagnosing HS, relative to pathologic diagnosis, were compared in the development cohort of 3312 subjects by receiver operating characteristic (ROC) analysis. The cut-off values for diagnosing HS > 33% in the development cohort were determined at 95% specificity and 95% sensitivity using bootstrap ROC analysis, and the diagnostic performance of these cut-off values was validated in the test cohort of 1101 subjects. RESULTS: CTL-S showed the highest performance for diagnosing HS ≥ 5% and HS > 33% (areas under the curve (AUCs) = 0.737 and 0.926, respectively), followed by CTL/S (AUCs = 0.732 and 0.925, respectively) and CTL (AUCs = 0.707 and 0.880, respectively). For CT scans using 120 kVp, the CTL-S cut-off values for highly specific (i.e., - 2.1) and highly sensitive (i.e., 7.6) diagnosis of HS > 33% resulted in a specificity of 96.4% with a sensitivity of 64.0% and a sensitivity of 97.3% with a specificity of 54.9%, respectively, in the test cohort. CONCLUSION: CT indices using liver and spleen attenuations have higher performance for diagnosing HS than indices using liver attenuation alone. The CTL-S cut-off values in this study may have utility for diagnosing HS in clinical practice and research. KEY POINTS: • CT indices based on both liver attenuation and spleen attenuation (CTL-Sand CTL/S) have higher diagnostic performance than CTLbased on liver attenuation alone in diagnosing HS using various CT techniques. • The CT index cut-off values determined in this study can be utilized for reliable diagnosis or to rule out subjects with moderate to severe HS in clinical practice and research, including the selection of living liver donors and the development of cohorts with HS or healthy controls.

Radiation-induced cutaneous angiosarcoma of the abdomen in a patient with cervical cancer: A case report.

Cutaneous angiosarcoma (CA) is a rare and aggressive malignant tumor that develops from vascular endothelium. Secondary CAs are often caused by radiotherapy and chronic lymphedema. Most radiation-induced CAs are associated with breast or gynecologic cancer. The prognosis of CA is extremely poor, with a 5-year survival rate ranging from 12% to 34%. Therapeutic options are limited, and surgical excision with negative margins remains the mainstay of treatment. We report a case of a 63-year-old woman who developed secondary CA at an irradiated site 7 years after receiving radiotherapy for cervical cancer.

Comprehensive Analysis for Anti-Cancer Target-Indication Prioritization of Placental Growth Factor Inhibitor (PGF) by Use of Omics and Patient Survival Data.

The expression of the placental growth factor (PGF) in cancer cells and the tumor microenvironment can contribute to the induction of angiogenesis, supporting cancer cell metabolism by ensuring an adequate blood supply. Angiogenesis is a key component of cancer metabolism as it facilitates the delivery of nutrients and oxygen to rapidly growing tumor cells. PGF is recognized as a novel target for anti-cancer treatment due to its ability to overcome resistance to existing angiogenesis inhibitors and its impact on the tumor microenvironment. We aimed to integrate bioinformatics evidence using various data sources and analytic tools for target-indication identification of the PGF target and prioritize the indication across various cancer types as an initial step of drug development. The data analysis included PGF gene function, molecular pathway, protein interaction, gene expression and mutation across cancer type, survival prognosis and tumor immune infiltration association with PGF. The overall evaluation was conducted given the totality of evidence, to target the PGF gene to treat the cancer where the PGF level was highly expressed in a certain tumor type with poor survival prognosis as well as possibly associated with poor tumor infiltration level. PGF showed a significant impact on overall survival in several cancers through univariate or multivariate survival analysis. The cancers considered as target diseases for PGF inhibitors, due to their potential effects on PGF, are adrenocortical carcinoma, kidney cancers, liver hepatocellular carcinoma, stomach adenocarcinoma, and uveal melanoma.

Sequence-Type Classification of Brain MRI for Acute Stroke Using a Self-Supervised Machine Learning Algorithm.

We propose a self-supervised machine learning (ML) algorithm for sequence-type classification of brain MRI using a supervisory signal from DICOM metadata (i.e., a rule-based virtual label). A total of 1787 brain MRI datasets were constructed, including 1531 from hospitals and 256 from multi-center trial datasets. The ground truth (GT) was generated by two experienced image analysts and checked by a radiologist. An ML framework called ImageSort-net was developed using various features related to MRI acquisition parameters and used for training virtual labels and ML algorithms derived from rule-based labeling systems that act as labels for supervised learning. For the performance evaluation of ImageSort-net (MLvirtual), we compare and analyze the performances of models trained with human expert labels (MLhumans), using as a test set blank data that the rule-based labeling system failed to infer from each dataset. The performance of ImageSort-net (MLvirtual) was comparable to that of MLhuman (98.5% and 99%, respectively) in terms of overall accuracy when trained with hospital datasets. When trained with a relatively small multi-center trial dataset, the overall accuracy was relatively lower than that of MLhuman (95.6% and 99.4%, respectively). After integrating the two datasets and re-training them, MLvirtual showed higher accuracy than MLvirtual trained only on multi-center datasets (95.6% and 99.7%, respectively). Additionally, the multi-center dataset inference performances after the re-training of MLvirtual and MLhumans were identical (99.7%). Training of ML algorithms based on rule-based virtual labels achieved high accuracy for sequence-type classification of brain MRI and enabled us to build a sustainable self-learning system.

Evolution of Radiological Treatment Response Assessments for Cancer Immunotherapy: From iRECIST to Radiomics and Artificial Intelligence.

Immunotherapy has revolutionized and opened a new paradigm for cancer treatment. In the era of immunotherapy and molecular targeted therapy, precision medicine has gained emphasis, and an early response assessment is a key element of this approach. Treatment response assessment for immunotherapy is challenging for radiologists because of the rapid development of immunotherapeutic agents, from immune checkpoint inhibitors to chimeric antigen receptor-T cells, with which many radiologists may not be familiar, and the atypical responses to therapy, such as pseudoprogression and hyperprogression. Therefore, new response assessment methods such as immune response assessment, functional/molecular imaging biomarkers, and artificial intelligence (including radiomics and machine learning approaches) have been developed and investigated. Radiologists should be aware of recent trends in immunotherapy development and new response assessment methods.

Alternative splicing of human height-related zinc finger and BTB domain-containing 38 gene through Alu exonization.

Recently, genome-wide association studies have identified a strong association between the ZBTB38 locus and human height. In a functional study, we detected two RT-PCR products of ZBTB38, amplified with primers in exons 7 and 8 from a chondrocyte cell line, C-28/I2. Sequencing revealed that the longer product contained an Alu segment in intron 7 of ZBTB38, which contained a potential splicing acceptor site that likely was used to generate the alternative transcript. Insertion of the Alu segment changed the consensus Kozak sequence of the ZBTB38 transcript, potentially altering translational efficiency. We performed RT-PCR using 16 tissue samples from humans and 8 tissue samples from primates to determine any tissue specificity or evolutionary conservation of the alternative splicing. Although we failed to identify any difference among the tissues, all primate samples expressed only the shorter Alu segment (lacking the transcript), suggesting that the alternative splicing event is hominid primate-specific.

Palisaded Neutrophilic and Granulomatous Dermatitis in a Patient with Behçet's Disease: A Case Report.

Palisaded neutrophilic and granulomatous dermatitis (PNGD) is an uncommon skin eruption and characterized histopathologically by the presence of granulomatous inflammation with or without leukocytoclastic vasculitis. PNGD is known to be associated with various immune-mediated connective tissue diseases such as rheumatoid arthritis and lupus erythematosus. However, to our knowledge, a case of PNGD in a patient with Behçet's disease is extremely rare and only one case has been reported in foreign literature to date. Herein, we report an unusual case of a 60-year-old female with Behçet's disease who presented multiple erythematous to flesh-colored papules on the extremities, buttocks, and ear lobes and was diagnosed with PNGD. After the treatment of systemic corticosteroids, colchicine and azathioprine, the skin lesions and oral ulcers improved. The patient is under observation without recurrence of skin lesions for 6 months.

Incidence of Immune-Mediated Pseudoprogression of Lymphoma Treated with Immune Checkpoint Inhibitors: Systematic Review and Meta-Analysis.

We evaluated the incidence of pseudoprogression and indeterminate response (IR) in patients with lymphoma treated with immune checkpoint inhibitors (ICIs). A systematic search of PubMed and EMBASE was performed up to 6 February 2021, using the keywords "lymphoma," "immunotherapy," and "pseudoprogression." Random-effects models were used to calculate both pooled incidence of pseudoprogression patients with lymphoma and an IR according to LYRIC criteria, while the Higgins inconsistency index (I2) test and Cochran's Q test were used for heterogeneity. Eight original articles were included, in which the number of patients ranged from 7 to 243. Among the lymphoma patients with ICIs, the pooled incidence of pseudoprogression was 10% (95% confidence interval [CI]: 0.06-0.17). There was no publication bias in Begg's test (p = 0.14). Three articles were analyzed to determine the pooled incidence of pseudoprogression in patients with IR according to LYRIC criteria in a subgroup analysis, which was shown to be 19% (95% CI: 0.08-0.40). A significant proportion (10%) of patients with lymphoma treated with ICIs showed pseudoprogression, and 19% of patients with an IR response showed pseudoprogression and a delayed response. Immune-related response criteria such as LYRIC may be used for patients with lymphoma treated with ICIs.

Test-retest repeatability of ultrasonographic shear wave elastography in a rat liver fibrosis model: toward a quantitative biomarker for preclinical trials.

PURPOSE: This study evaluated the test-retest repeatability and measurement variability of ultrasonographic shear wave elastography (SWE) for liver stiffness in a rat liver fibrosis model. METHODS: In 31 Sprague-Dawley rats divided into three groups (high-dose, low-dose, and control), liver fibrosis was induced by intraperitoneal administration of thioacetamide for 8 weeks. A dedicated radiographer performed SWE to measure liver stiffness in kilopascals in two sessions at a 3-day interval. We calculated correlations between liver stiffness and histopathologic results, measurement variability in each session using coefficients of variation (CoVs) and interquartile/median (IQR/M), and test-retest repeatability between both sessions using the repeatability coefficient. RESULTS: Different levels of liver fibrosis in each group were successfully induced in the animal model. The mean liver stiffness values were 8.88±1.48 kPa in the control group, 11.62±1.70 kPa in the low-dose group, and 11.91±1.73 kPa in the high-dose group. The correlation between collagen areas and liver stiffness values was moderate (r=0.6). In all groups, the second session yielded lower CoVs (i.e., more reliable results) for liver stiffness than the first session, suggesting a training effect for the operator. The mean IQR/M values were also lower in the second session than in the first session, which had four outliers (0.21 vs. 0.12, P<0.001). The test-retest repeatability coefficient was 3.75 kPa and decreased to 2.82 kPa after removing the four outliers. CONCLUSION: The use of ultrasonographic SWE was confirmed to be feasible and repeatable for evaluating liver fibrosis in preclinical trials. Operator training might reduce variability in liver stiffness measurements.

Development of a fully automatic deep learning system for L3 selection and body composition assessment on computed tomography.

As sarcopenia research has been gaining emphasis, the need for quantification of abdominal muscle on computed tomography (CT) is increasing. Thus, a fully automated system to select L3 slice and segment muscle in an end-to-end manner is demanded. We aimed to develop a deep learning model (DLM) to select the L3 slice with consideration of anatomic variations and to segment cross-sectional areas (CSAs) of abdominal muscle and fat. Our DLM, named L3SEG-net, was composed of a YOLOv3-based algorithm for selecting the L3 slice and a fully convolutional network (FCN)-based algorithm for segmentation. The YOLOv3-based algorithm was developed via supervised learning using a training dataset (n = 922), and the FCN-based algorithm was transferred from prior work. Our L3SEG-net was validated with internal (n = 496) and external validation (n = 586) datasets. Ground truth L3 level CT slice and anatomic variation were identified by a board-certified radiologist. L3 slice selection accuracy was evaluated by the distance difference between ground truths and DLM-derived results. Technical success for L3 slice selection was defined when the distance difference was < 10 mm. Overall segmentation accuracy was evaluated by CSA error and DSC value. The influence of anatomic variations on DLM performance was evaluated. In the internal and external validation datasets, the accuracy of automatic L3 slice selection was high, with mean distance differences of 3.7 ± 8.4 mm and 4.1 ± 8.3 mm, respectively, and with technical success rates of 93.1% and 92.3%, respectively. However, in the subgroup analysis of anatomic variations, the L3 slice selection accuracy decreased, with distance differences of 12.4 ± 15.4 mm and 12.1 ± 14.6 mm, respectively, and with technical success rates of 67.2% and 67.9%, respectively. The overall segmentation accuracy of abdominal muscle areas was excellent regardless of anatomic variation, with CSA errors of 1.38-3.10 cm2. A fully automatic system was developed for the selection of an exact axial CT slice at the L3 vertebral level and the segmentation of abdominal muscle areas.

Assessment of Myosteatosis on Computed Tomography by Automatic Generation of a Muscle Quality Map Using a Web-Based Toolkit: Feasibility Study.

BACKGROUND: Muscle quality is associated with fatty degeneration or infiltration of the muscle, which may be associated with decreased muscle function and increased disability. OBJECTIVE: The aim of this study is to evaluate the feasibility of automated quantitative measurements of the skeletal muscle on computed tomography (CT) images to assess normal-attenuation muscle and myosteatosis. METHODS: We developed a web-based toolkit to generate a muscle quality map by categorizing muscle components. First, automatic segmentation of the total abdominal muscle area (TAMA), visceral fat area, and subcutaneous fat area was performed using a predeveloped deep learning model on a single axial CT image at the L3 vertebral level. Second, the Hounsfield unit of each pixel in the TAMA was measured and categorized into 3 components: normal-attenuation muscle area (NAMA), low-attenuation muscle area (LAMA), and inter/intramuscular adipose tissue (IMAT) area. The myosteatosis area was derived by adding the LAMA and IMAT area. We tested the feasibility of the toolkit using randomly selected healthy participants, comprising 6 different age groups (20 to 79 years). With stratification by sex, these indices were compared between age groups using 1-way analysis of variance (ANOVA). Correlations between the myosteatosis area or muscle densities and fat areas were analyzed using Pearson correlation coefficient r. RESULTS: A total of 240 healthy participants (135 men and 105 women) with 40 participants per age group were included in the study. In the 1-way ANOVA, the NAMA, LAMA, and IMAT were significantly different between the age groups in both male and female participants (P≤.004), whereas the TAMA showed a significant difference only in male participants (male, P<.001; female, P=.88). The myosteatosis area had a strong negative correlation with muscle densities (r=-0.833 to -0.894), a moderate positive correlation with visceral fat areas (r=0.607 to 0.669), and a weak positive correlation with the subcutaneous fat areas (r=0.305 to 0.441). CONCLUSIONS: The automated web-based toolkit is feasible and enables quantitative CT assessment of myosteatosis, which can be a potential quantitative biomarker for evaluating structural and functional changes brought on by aging in the skeletal muscle.

Design Characteristics of Studies Reporting the Performance of Artificial Intelligence Algorithms for Diagnostic Analysis of Medical Images: Results from Recently Published Papers.

OBJECTIVE: To evaluate the design characteristics of studies that evaluated the performance of artificial intelligence (AI) algorithms for the diagnostic analysis of medical images. MATERIALS AND METHODS: PubMed MEDLINE and Embase databases were searched to identify original research articles published between January 1, 2018 and August 17, 2018 that investigated the performance of AI algorithms that analyze medical images to provide diagnostic decisions. Eligible articles were evaluated to determine 1) whether the study used external validation rather than internal validation, and in case of external validation, whether the data for validation were collected, 2) with diagnostic cohort design instead of diagnostic case-control design, 3) from multiple institutions, and 4) in a prospective manner. These are fundamental methodologic features recommended for clinical validation of AI performance in real-world practice. The studies that fulfilled the above criteria were identified. We classified the publishing journals into medical vs. non-medical journal groups. Then, the results were compared between medical and non-medical journals. RESULTS: Of 516 eligible published studies, only 6% (31 studies) performed external validation. None of the 31 studies adopted all three design features: diagnostic cohort design, the inclusion of multiple institutions, and prospective data collection for external validation. No significant difference was found between medical and non-medical journals. CONCLUSION: Nearly all of the studies published in the study period that evaluated the performance of AI algorithms for diagnostic analysis of medical images were designed as proof-of-concept technical feasibility studies and did not have the design features that are recommended for robust validation of the real-world clinical performance of AI algorithms.

Feasibility of non-enhanced CT for assessing longitudinal changes in hepatic steatosis.

To evaluate the feasibility of computed tomography (CT) in the assessment of the change in hepatic steatosis (HS) in longitudinal follow-up by employing pathological HS as the reference standard.We retrospectively evaluated 38 living liver donor candidates (27 men and 11 women; mean age, 29.5 years) who underwent liver biopsy twice and had liver CT scans within 1 week of each biopsy. Four readers independently calculated CTL-S index by subtracting spleen attenuation from liver attenuation on non-enhanced CT images. The changes in pathological HS (ΔHS) and CTL-S (ΔCTL-S) between the 1st and 2nd examinations were assessed. The correlation between ΔHS and ΔCTL-S was assessed using the linear regression analysis. Inter-observer measurement error for ΔCTL-S among the 4 readers was assessed using the repeatability coefficient.ΔCTL-S showed a significant correlation with ΔHS in all readers (r = 0.571-0.65, P < .001). The inter-observer measurement error for ΔCTL-S was ±8.9. The ΔCTL-S values beyond the measurement error were associated with a consistent change in HS in 83.3% (13/15) to 100% (15/15), with sensitivities of 47.8 to 79.9% and specificities of 86.7 to 100% for detecting an absolute change of ≥10% in HS among the 4 readers. However, ΔCTL-S values within the measurement error were associated with a consistent change in HS in 43.5% (8/19) to 61.5% (16/26).The change in CTL-S roughly reflects the change in HS during longitudinal follow-up. A small change in CTL-S should not be considered meaningful, while a larger change in CTL-S beyond the measurement error strongly indicates a true change in HS.

Reliable and robust method for abdominal muscle mass quantification using CT/MRI: An explorative study in healthy subjects.

BACKGROUND: Quantification of abdominal muscle mass by cross-sectional imaging has been increasingly used to diagnose sarcopenia; however, the technical method for quantification has not been standardized yet. We aimed to determine an optimal method to measure the abdominal muscle area. METHODS: Among 50 consecutive subjects who underwent abdominal CT and MRI for possible liver donation, total abdominal muscle area (TAMA) and total psoas muscle area (TPA) at the L3 inferior endplate level were measured by two blinded readers. Inter-scan agreement between CT and MRI and inter-reader agreement between the two readers were evaluated using intraclass correlation coefficient (ICC) and within-subject coefficient of variation (WSCV). To evaluate the effect of measurement level, one reader measured TAMA and TPA at six levels from the L2 to L4 vertebral bodies. RESULTS: TAMA was a more reliable biomarker than TPA in terms of inter-scan agreement (ICC: 0.928 vs. 0.788 for reader 1 and 0.853 vs. 0.821 for reader 2, respectively; WSCV: 8.3% vs. 23.4% for reader 1 and 10.4% vs. 22.3% for reader 2, respectively) and inter-reader agreement (ICC: 0.986 vs. 0.886 for CT and 0.865 vs. 0.669 for MRI, respectively; WSCV: 8.2% vs. 16.0% for CT and 11.6% vs. 29.7% for MRI, respectively). In terms of the measurement level, TAMA did not differ from the L2inf to L4inf levels, whereas TPA increased with a decrease in measurement level. CONCLUSIONS: TAMA is a better biomarker than TPA in terms of inter-scan and inter-reader agreement and robustness to the measurement level. CT was a more reliable imaging modality than MRI. Our results support the use of TAMA measured by CT as a standard biomarker for abdominal muscle area measurement.

A Good Practice-Compliant Clinical Trial Imaging Management System for Multicenter Clinical Trials: Development and Validation Study.

BACKGROUND: With the rapid increase in utilization of imaging endpoints in multicenter clinical trials, the amount of data and workflow complexity have also increased. A Clinical Trial Imaging Management System (CTIMS) is required to comprehensively support imaging processes in clinical trials. The US Food and Drug Administration (FDA) issued a guidance protocol in 2018 for appropriate use of medical imaging in accordance with many regulations including the Good Clinical Practice (GCP) guidelines. Existing research on CTIMS, however, has mainly focused on functions and structures of systems rather than regulation and compliance. OBJECTIVE: We aimed to develop a comprehensive CTIMS to meet the current regulatory guidelines and various required functions. We also aimed to perform computerized system validation focusing on the regulatory compliance of our CTIMS. METHODS: Key regulatory requirements of CTIMS were extracted thorough review of many related regulations and guidelines including International Conference on Harmonization-GCP E6, FDA 21 Code of Federal Regulations parts 11 and 820, Good Automated Manufacturing Practice, and Clinical Data Interchange Standards Consortium. The system architecture was designed in accordance with these regulations by a multidisciplinary team including radiologists, engineers, clinical trial specialists, and regulatory medicine professionals. Computerized system validation of the developed CTIMS was performed internally and externally. RESULTS: Our CTIMS (AiCRO) was developed based on a two-layer design composed of the server system and the client system, which is efficient at meeting the regulatory and functional requirements. The server system manages system security, data archive, backup, and audit trail. The client system provides various functions including deidentification, image transfer, image viewer, image quality control, and electronic record. Computerized system validation was performed internally using a V-model and externally by a global quality assurance company to demonstrate that AiCRO meets all regulatory and functional requirements. CONCLUSIONS: We developed a Good Practice-compliant CTIMS-AiCRO system-to manage large amounts of image data and complexity of imaging management processes in clinical trials. Our CTIMS adopts and adheres to all regulatory and functional requirements and has been thoroughly validated.