A multicenter clinical AI system study for detection and diagnosis of focal liver lesions.

Early and accurate diagnosis of focal liver lesions is crucial for effective treatment and prognosis. We developed and validated a fully automated diagnostic system named Liver Artificial Intelligence Diagnosis System (LiAIDS) based on a diverse sample of 12,610 patients from 18 hospitals, both retrospectively and prospectively. In this study, LiAIDS achieved an F1-score of 0.940 for benign and 0.692 for malignant lesions, outperforming junior radiologists (benign: 0.830-0.890, malignant: 0.230-0.360) and being on par with senior radiologists (benign: 0.920-0.950, malignant: 0.550-0.650). Furthermore, with the assistance of LiAIDS, the diagnostic accuracy of all radiologists improved. For benign and malignant lesions, junior radiologists' F1-scores improved to 0.936-0.946 and 0.667-0.680 respectively, while seniors improved to 0.950-0.961 and 0.679-0.753. Additionally, in a triage study of 13,192 consecutive patients, LiAIDS automatically classified 76.46% of patients as low risk with a high NPV of 99.0%. The evidence suggests that LiAIDS can serve as a routine diagnostic tool and enhance the diagnostic capabilities of radiologists for liver lesions.

Higher Levels of Tumour-Infiltrating Lymphocytes (TILs) are Associated with a Better Prognosis, While CDK5 Plays a Different Role Between Nonmetastatic and Metastatic Colonic Carcinoma.

OBJECTIVE: We investigated the prognostic value of cyclin-dependent kinase 5 (CDK5) in a true population-based cohort of patients with colon cancer. METHODS: 1. Immunohistochemical (IHC) staining was used to retrospectively analyse the expression of CDK5 in colon cancer tissue samples of 296 patients. The χ2 test, Kaplan-Meier method and Cox proportional regression model were used to analyse the difference between the patients with differential expression of CDK5 and with different stages (metastatic and nonmetastatic); 2. The number of tumour-infiltrating lymphocytes (TILs) in tumour sections was determined, and its relationship with prognosis was explored. RESULTS: 1. Among 296 patients stained for CDK5, 18 cases (6.09%) showed negative expression, 77 cases (26.01%) showed weak expression (+1), 124 cases (41.89%) showed medium positive expression (2+), and 77 cases (26.01%) showed strong positive expression (3+). The expression of CDK5 was neither related to mismatch repair nor TILs (p > .05). In non-metastatic patients, longer progression-free survival (PFS) and cancer-specific survival (CSS) were observed in patients with high CDK5 expression (2+ or 3+) than low CDK5 expression (- or 1+), while in metastatic disease, the opposite was true (p < .001). 2. TILs in 226 patients were detected in the study. Among them, 115 cases (50.88%) showed a low number of TILs (TILs-L), and 111 cases (49.12%) showed a high number of TILs (TILs-H). Patients with a TIL ratio greater than .2 had a significantly better CSS (p < .001) or PFS (p = .008) than patients with a lower TIL ratio. By multivariate analysis, TILs-H was a protective factor for CSS, however failed to reach a significant difference (hazard ratio: .59, 95% CI: .33∼1.06, p = .079), and so was the PFS (HR: .65, 95% CI: .29∼1.43, p = .279). CONCLUSION: High expression of CDK5 indicates a good prognosis in nonmetastatic colon cancer, while it is the opposite in metastatic colon cancer, and the expression of CDK5 is unrelated to TILs. Patients with TIL-H have a better prognosis, with a proper cut-off value of 20% for colon cancer.

Resection of primary lesion with chemotherapy improves the survival of patients with metastatic colorectal neuroendocrine carcinoma.

OBJECTIVE: To evaluate the effect of resection of primary lesion and chemotherapy on survival of patients with metastatic colorectal neuroendocrine carcinoma (CRNEC). METHODS: Clinical data of 393 patients with metastatic CRNECs between January 2010 and December 2016 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database, including 171 patients who received resection of primary lesion and 221 patients who did not undergo surgery. With the propensity score matching method 172 non-operated patients were selected as controls. Kaplan-Meier method and Log-rank test were used to evaluate the survival differences, while the prognostic factors were analyzed by Cox proportional-hazards model. Metastatic CRNEC patients from January 2001 to December 2021 in Affiliated Jinhua Hospital, Zhejiang University School of Medicine were selected for validation. RESULTS: Compared with non-operated patients, patients who received resection had longer cause-specific survival ( P<0.05). Patients with resected positive lymph nodes>8 had a poorer prognosis compared to those with resected positive lymph nodes≤8 ( P<0.05). Multivariate analysis showed that gender, location of primary lesion and treatments were independent risk factors for cause-specific survival in patients with metastatic CRNEC (all P<0.05). For metastatic CRNEC patients with resection of primary lesion, rectal neuroendocrine carcinoma, positive resected lymph nodes≤8 and resection of primary lesion combined with chemotherapy were associated with better cause-specific survival (all P<0.05). CONCLUSIONS: Patients with metastatic CRNEC may benefit from resection of primary lesion, and resection of primary lesion combined with chemotherapy might be the better strategy for metastatic CRNECs. The number of positive lymph nodes resected is correlated with the prognosis of patients.

Chordoma of petrosal mastoid region: A case report.

BACKGROUND: Chordoma is a rare low-grade malignant tumor originating from embryonic notochordal tissue mainly occurring in the axial bone, mostly in the spheno-occipital junction and sacrococcyx, which accounts for approximately 1% of all malignant bone tumors and 0.1%-0.2% of intracranial tumors. Chordoma in the petrous mastoid region is rare. CASE SUMMARY: We describe a 36-year-old male patient with chordoma in the left petrous mastoid region. The main clinical manifestations were pain and discomfort, which lasted for 2 years. Magnetic resonance imaging showed a lobulated mass in the left petrous mastoid with an unclear boundary and obvious enhancement. The tumor was completely removed after surgical treatment, and a histological examination confirmed that the tumor was a chordoma. During 5 years of follow-up, no clinical or radiological evidence of recurrence or metastasis was found. CONCLUSION: Chordoma in the petrosal mastoid region is rare but should be included in differential diagnosis of petrosal mastoid tumors.

Sinus Disease Grading on Computed Tomography Before and After Modulating Therapy in Adult Patients with Cystic Fibrosis.

Objectives: Cystic fibrosis transmembrane conductance regulator (CFTR) modulator therapy effects on respiratory function, pulmonary exacerbations and quality of life have been well documented. However, CFTR modulator therapy effects on sinus disease have not been so well reported. A previous study reported that ivacaftor improves appearance of sinus disease on Computed Tomography (CT) in cystic fibrosis (CF) patients with G551D mutation. The aim of this study was to evaluate the effect of CFTR modulator therapy in sinus disease using CT scores in a wider CF patient population. Materials and Methods: Forty-eight adult patients with CF underwent at least one CT sinus examination before CFTR modulator therapy (ivacaftor, lumacaftor, ivacaftor/lumacaftor or elexcaftor/tezacaftor/ivacaftor) and one CT sinus examination one year after CFTR modulator therapy initiation. Two radiologists assessed the images in consensus. The Lund-Mackay score (LM score) and the Sheikh-Lind CT sinus disease severity scoring system (SL score) were used. The 22-item SinoNasal Outcome Test (SNOT-22) questionnaire was evaluated before CFTR modulator therapy and one year after CFTR modulator therapy initiation. Results: CT sinus examination after CFTR modulator therapy showed statistically significant lower mean LM, SL and SNOT-22 scores than CT sinus examination before CFTR modulator therapy (p < 0.001). Conclusion: Evolution of imaging findings on CT during follow-up closely correlate with improved SNOT-22 score one year after CFTR modulator therapy initiation, indicating that CT may be a useful adjunct during follow-up of CF patients under this treatment as an objective measure of sinonasal disease improvement.

Development and validation of a radiomics-based nomogram for the preoperative prediction of microsatellite instability in colorectal cancer.

BACKGROUND: Preoperative prediction of microsatellite instability (MSI) status in colorectal cancer (CRC) patients is of great significance for clinicians to perform further treatment strategies and prognostic evaluation. Our aims were to develop and validate a non-invasive, cost-effective reproducible and individualized clinic-radiomics nomogram method for preoperative MSI status prediction based on contrast-enhanced CT (CECT)images. METHODS: A total of 76 MSI CRC patients and 200 microsatellite stability (MSS) CRC patients with pathologically confirmed (194 in the training set and 82 in the validation set) were identified and enrolled in our retrospective study. We included six significant clinical risk factors and four qualitative imaging data extracted from CECT images to build the clinics model. We applied the intra-and inter-class correlation coefficient (ICC), minimal-redundancy-maximal-relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) for feature reduction and selection. The selected independent prediction clinical risk factors, qualitative imaging data and radiomics features were performed to develop a predictive nomogram model for MSI status on the basis of multivariable logistic regression by tenfold cross-validation. The area under the receiver operating characteristic (ROC) curve (AUC), calibration plots and Hosmer-Lemeshow test were performed to assess the nomogram model. Finally, decision curve analysis (DCA) was performed to determine the clinical utility of the nomogram model by quantifying the net benefits of threshold probabilities. RESULTS: Twelve top-ranked radiomics features, three clinical risk factors (location, WBC and histological grade) and CT-reported IFS were finally selected to construct the radiomics, clinics and combined clinic-radiomics nomogram model. The clinic-radiomics nomogram model with the highest AUC value of 0.87 (95% CI, 0.81-0.93) and 0.90 (95% CI, 0.83-0.96), as well as good calibration and clinical utility observed using the calibration plots and DCA in the training and validation sets respectively, was regarded as the candidate model for identification of MSI status in CRC patients. CONCLUSION: The proposed clinic-radiomics nomogram model with a combination of clinical risk factors, qualitative imaging data and radiomics features can potentially be effective in the individualized preoperative prediction of MSI status in CRC patients and may help performing further treatment strategies.

Deep Learning Radiomics to Predict Regional Lymph Node Staging for Hilar Cholangiocarcinoma.

BACKGROUND: Our aim was to establish a deep learning radiomics method to preoperatively evaluate regional lymph node (LN) staging for hilar cholangiocarcinoma (HC) patients. METHODS AND MATERIALS: Of the 179 enrolled HC patients, 90 were pathologically diagnosed with lymph node metastasis. Quantitative radiomic features and deep learning features were extracted. An LN metastasis status classifier was developed through integrating support vector machine, high-performance deep learning radiomics signature, and three clinical characteristics. An LN metastasis stratification classifier (N1 vs. N2) was also proposed with subgroup analysis. RESULTS: The average areas under the receiver operating characteristic curve (AUCs) of the LN metastasis status classifier reached 0.866 in the training cohort and 0.870 in the external test cohorts. Meanwhile, the LN metastasis stratification classifier performed well in predicting the risk of LN metastasis, with an average AUC of 0.946. CONCLUSIONS: Two classifiers derived from computed tomography images performed well in predicting LN staging in HC and will be reliable evaluation tools to improve decision-making.

Efficacy and safety of low-dose glucocorticoids combined with methotrexate and hydroxychloroquine in the treatment of early rheumatoid arthritis: A single-center, randomized, double-blind clinical trial.

INTRODUCTION: Glucocorticoids (GCs), especially low-dose GCs, are commonly prescribed for rheumatoid arthritis (RA), although the risk/benefit ratio is controversial. A randomized, double-blind clinical trial was performed to evaluate the efficacy and safety of low-dose oral GCs combined with methotrexate (MTX) and hydroxychloroquine (HCQ) in early RA (ERA). METHODS: Eighty untreated ERA patients were randomized into the trial (GCs + MTX + HCQ) and control (placebo + MTX + HCQ) groups, for 1-year treatment. Therapeutic evaluation indices were American College of Rheumatology (ACR) 20 of ACR, disease activity score (DAS) 28- erythrocyte sedimentation rate (ESR), visual analog scale scores, joint function, health assessment questionnaire-disability index score, morning stiffness duration, C-reaction protein and ESR. The clinical indicators were evaluated pre-treatment and at 1st, 3th, 6th and 12th month of treatment. The MRI data of single joint (ie, the most swollen joint) for each patient were acquired with a revised OMERACT RAMRIS Scoring System before and after treatment. The correlation analysis was adopted to confirm whether the efficacy of GC treatment is related to the time of RA onset. The side effects (eg, gastrointestinal reactions, liver dysfunction, upper respiratory tract infection, leukocyte reduction) were also monitored. RESULTS: At 1st month, 55% and 20% cases in the experimental and control groups achieved ACR20 response, respectively, indicating a significant difference (χ = 16.157, P < .001). This trend continued until 6th month. At 12th month, the number of patients achieved ACR20 response was similar in both groups. At 1st to 6th month, DAS28- ESR scores in the experimental group were significantly lower than control values (all p < .05). The experimental group showed improved inflammation, quality of life and radiological symptoms. Bone erosion remained unchanged in the experimental group, while worsening in control group. Correlation coefficients between RA duration and DAS28-ESR score were 0.496, 0.464, 0.509, and 0.550 at 1st, 3th, 6th, and 12th month, respectively. No differences were found in adverse events between the 2 groups. CONCLUSIONS: Low-dose GCs combined with MTX and HCQ significantly achieves disease remission indexed by ACR20 and DAS28-ESR, and improves clinical and radiological outcomes in ERA patients at the early stage, with superiority over placebo + MTX + HCQ, without enhancing adverse reactions.

COVID-19 with acute cholecystitis: a case report.

BACKGROUND: The 2019 novel coronavirus (COVID-19) presents a major threat to public health and has rapidly spread worldwide since the outbreak in Wuhan, Hubei Province, China in 2019. To date, there have been few reports of the varying degrees of illness caused by the COVID-19. CASE PRESENTATION: A case of 68-year-old female with COVID-19 pneumonia who had constant pain in the right upper quadrant of her abdomen during her hospitalization that was finally diagnosed as acute cholecystitis. Ultrasound-guided percutaneous transhepatic gallbladder drainage (PTGD) was performed, and the real-time fluorescence polymerase chain reaction (RT-PCR) COVID-19 nucleic acid assay of the bile was found to be negative. PTGD, antibacterial and anti-virus combined with interferon inhalation treatment were successful. CONCLUSION: The time course of chest CT findings is typical for COVID-19 pneumonia. PTGD is useful for acute cholecystitis in COVID-19 patients. Acute cholecystitis is likely to be caused by COVID-19 .

Young-onset breast cancer: a poor prognosis only exists in low-risk patients.

The number of reported young breast cancer cases has increased dramatically recently. The impact of age on the outcomes of breast cancers remains controversial. Our study aimed to explore the factors that can stratify the impact of young age on the prognosis of early breast cancer patients. In total, 244,324 patients with early breast cancer in the Surveillance, Epidemiology, and End Results database were identified from 1990 to 2007. Survival curves were generated using the Kaplan-Meier method. The 5- and 10-year cancer-specific survival (CSS) rates were calculated using the Life-Table method. Multivariable analyses were used to identify prognosti c variables (without age) to construct the nomograms. The risk score developed from the nomogram was used to classify the cohort into three subgroups (low-, medium- and high-risk subgroup). Approximately 8.89% of women were diagnosed with breast cancer at a young age (≤ 40 years). Clinical nomogram had the potential ability to predict CSS accurately with a well C-index (0.785). Subgroup analysis indicated that the risk score as the sole factor can stratify the impact of young age on the prognosis of early breast cancer patients. Young breast cancer patients had a worse prognosis in the low-risk (HR=0.61; 95% CI: 0.57-0.65; P<0.001) or medium-risk subgroup (HR=0.89; 95% CI: 0.85-0.93; P<0.01) than in the high-risk subgroup (P=0.431). In conclusion, the worse prognosis of young women only appeared in the low- and medium-risk subgroups rather than in the high-risk subgroup. The risk score yielded from the nomogram model can assist clinical decision making for young breast cancer patients.

Author Correction: Influences of scan-position on clinical ultra-high-resolution CT scanning: a preliminary study.

A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has not been fixed in the paper.

Influences of scan-position on clinical ultra-high-resolution CT scanning: a preliminary study.

The aim of this study is to access influences of scan-position on clinical ultra-high-resolution CT scanning. We proposed a breath-hold assisted ultra-high-resolution scanning technology (scan scheme G) and compared with scan scheme A (regular CT plain scan) and scheme B (1024 ultra-high-resolution scan with patients stay in supine position). A total of 30 patients with fGGO were included in this study. Three highly experienced chest imaging doctors were employed to score the image and to select regions of interest (ROIs) for CT value and signal-to-noise ratio (SNR) calculation. In comparison with scan A and B, this new scan scheme G shows more clear CT images and higher SNRs at overall lung field (the p-values of A versus G and B versus G are 0.041 and 0.065, respectively). These findings suggest that scan-G provides a better image quality and contributes significantly to clinical detection accuracy of fGGO.

Morphological classification of intraductal papillary neoplasm of the bile duct.

OBJECTIVES: To investigate the morphological classification of intraductal papillary neoplasm of the bile duct (IPNB), as well as morphological differences between IPNB without mucin secretion (IPNB-NM) and IPNB with mucin secretion (IPMN-B). METHODS: Eighty-one patients with IPNB were retrospectively analysed. Imaging examinations included computed tomography (CT), magnetic resonance imaging (MRI), gadolinium-ethoxybenzyl-diethylenetriaminepentaacetic acid (Gd-EOB-DTPA)-enhanced MRI and positron emission tomography-computed tomography (PET-CT). According to the morphology of tumours and extent of bile duct dilations, IPNB was classified into seven types: I, upstream-ductectatic type; II, typical type; III, superficial-spreading type; IV, no-mass-forming type; V, intrahepatic-cystic type; VI, extrahepatic-cystic type; and VII, infiltrating type. RESULTS: Thirteen IPNB-NM patients comprised type I (11 cases), type II (1 case) and type VII (1 case); 68 IPMN-B patients comprised type I (2 cases), type II (30 cases), type III (6 cases), type IV (11 cases), type V (13 cases), type VI (2 cases) and type VII (4 cases). Bile duct dilations were more severe in IPMN-B than in IPNB-NM. PET-CT and Gd-EOB-DTPA-enhanced MRI clearly demonstrated the extension of infiltrating IPNB. CONCLUSIONS: IPNB can be classified into seven morphological types. IPNB-NM and IPMN-B have different morphological features. KEY POINTS: • IPNB can be classified into seven morphological types. • IPNB-NM and IPMN-B have different morphological features. • Enhanced CT and MRI can display different types of IPNB. • Morphological classification of IPNB facilitates management of the disease.

Prognostic value of high-resolution magnetic resonance imaging in evaluating carotid atherosclerotic plaque in patients with ischemic stroke.

BACKGROUND: Ischemic stroke (IS) is a devastating occurrence affecting millions worldwide. This study aimed to evaluate the prognostic value of high-resolution magnetic resonance imaging (HRMRI) in assessing carotid atherosclerotic plaque in IS patients. METHODS: Between January 2013 and March 2015, 338 IS patients were recruited for the investigative purposes of the study. All participants of the study underwent an HRMRI inspection procedure after being admitted into the hospital. During this study, we systematically analyzed and measured various types of fibrous caps, lipid compositions, and plaque lipid ratios. Univariate and multivariate logistic regression analyses were performed for predicting prognosis of IS patients. A receiver-operating characteristic (ROC) curve was employed to determine the accuracy of the IS prognosis. RESULTS: The percentage of type I fibrous caps exhibited significant decrease, while the percentage of type III fibrous caps, lipid compositions, and lipid ratios all displayed increase. The results of the univariate analysis indicated that age, hypertension, hyperlipidemia, treatment regimens, fibrous cap type, plaque type, lipid composition, and lipid ratio shared a correlation in regards to the poor prognosis of IS patients. Multivariate logistic regression analysis demonstrated that the prognosis of IS patients was not necessarily dependent on fibrous cap type, plaque type, or age. ROC curves revealed that the HRMRI possessed a strong predicative ability in relation to the identification of the prognosis of IS patients through factors such as type of plaque and fibrous caps determination. CONCLUSION: Our study conclusively intimated the promise of HRMRI as an evaluative tool for the determination of carotid atherosclerotic plaques in patients with IS.