Machine learning for differentiation of lipid-poor adrenal adenoma and subclinical pheochromocytoma based on multiphase CT imaging radiomics.

BACKGROUND: There is a paucity of research investigating the application of machine learning techniques for distinguishing between lipid-poor adrenal adenoma (LPA) and subclinical pheochromocytoma (sPHEO) based on radiomic features extracted from non-contrast and dynamic contrast-enhanced computed tomography (CT) scans of the abdomen. METHODS: We conducted a retrospective analysis of multiphase spiral CT scans, including non-contrast, arterial, venous, and delayed phases, as well as thin- and thick-thickness images from 134 patients with surgically and pathologically confirmed. A total of 52 patients with LPA and 44 patients with sPHEO were randomly assigned to training/testing sets in a 7:3 ratio. Additionally, a validation set was comprised of 22 LPA cases and 16 sPHEO cases from two other hospitals. We used 3D Slicer and PyRadiomics to segment tumors and extract radiomic features, respectively. We then applied T-test and least absolute shrinkage and selection operator (LASSO) to select features. Six binary classifiers, including K-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP), were employed to differentiate LPA from sPHEO. Receiver operating characteristic (ROC) curves and area under the curve (AUC) values were compared using DeLong's method. RESULTS: All six classifiers showed good diagnostic performance for each phase and slice thickness, as well as for the entire CT data, with AUC values ranging from 0.706 to 1. Non-contrast CT densities of LPA were significantly lower than those of sPHEO (P < 0.001). However, using the optimal threshold for non-contrast CT density, sensitivity was only 0.743, specificity 0.744, and AUC 0.828. Delayed phase CT density yielded a sensitivity of 0.971, specificity of 0.641, and AUC of 0.814. In radiomics, AUC values for the testing set using non-contrast CT images were: KNN 0.919, LR 0.979, DT 0.835, RF 0.967, SVM 0.979, and MLP 0.981. In the validation set, AUC values were: KNN 0.891, LR 0.974, DT 0.891, RF 0.964, SVM 0.949, and MLP 0.979. CONCLUSIONS: The machine learning model based on CT radiomics can accurately differentiate LPA from sPHEO, even using non-contrast CT data alone, making contrast-enhanced CT unnecessary for diagnosing LPA and sPHEO.

Acute septic thrombophlebitis of the lower extremities due to foreign body injury and infection: a case report.

BACKGROUND: Septic thrombophlebitis (STP) of the lower extremities caused by foreign bodies is rare in the clinic, and the symptoms are serious. If the correct treatment is not implemented as soon as possible, the patient may progress to sepsis. CASE PRESENTATION: We report the case of a 51-year-old normally healthy male who developed fever 3 days after field work. When he was weeding with a lawn mower in the field, a metal foreign body from the grass flew into his left lower abdomen, resulting in an eschar on his left lower abdomen. He was diagnosed with scrub typhus but did not respond well to anti-infective treatment. After a detailed inquiry of his medical history and an auxiliary examination, the diagnosis was confirmed as STP of the left lower limb caused by a foreign body. After surgery, anticoagulation and anti-infection treatment, the infection and thrombosis were controlled, and the patient was cured and discharged. CONCLUSIONS: STP caused by foreign bodies is rare. Early detection of the aetiology of sepsis and early adoption of the correct measures can effectively block the progression of the disease and reduce the patient's pain. Clinicians should identify the source of sepsis through a medical history and clinical examination.

Clinical and Imaging Characteristics of Cerebral Infarction in Patients with Nonvalvular Atrial Fibrillation Combined with Cerebral Artery Stenosis.

AIMS: Nonvalvular atrial fibrillation often occurs in combination with carotid atherosclerosis, but less is known about it in combination with cerebral artery stenosis. This study investigated the characteristics of cerebral infarction in patients with nonvalvular atrial fibrillation with or without cerebral artery stenosis. METHODS: A retrospective analysis was conducted on 172 cerebral infarction patients with nonvalvular atrial fibrillation hospitalized at the Affiliated Ganzhou Hospital of Nanchang University between December 2011 and January 2016. The patients were divided into two groups (stenosis and non-stenosis groups) based on whether the cerebral infarction was combined with cerebral artery stenosis or not. Clinical characteristics, related supplementary examination, and the imaging characteristics of cerebral infarction lesions were compared between the groups. RESULTS: Mean age [(75.73±8.46) years vs. (63.44±9.95) years], National Institute of Health stroke scale (NIHSS) score [(8.66±6.73) vs. (4.59±3.51)], CHA2DS2-VASc score [(2.93±1.40) vs. (0.96±0.98)], history of hypertension (74.4% vs. 30.0%), and history of stroke/ transient ischemic attack (TIA) (55.8% vs. 13.3%) were higher in the stenosis group (n=107) than in the non-stenosis group (n=65) (P＜0.01). In the stenosis group, there were different types of cerebral infarction lesions, including multiple infarction (multifocal type), massive infarction, watershed infarction, and lacunar infarction; in the non-stenosis group, the 60.0% lesions were multiple infarction (multifocal type), a significantly higher proportion than the stenosis group (26.2%, P＜0.05). NIHSS score was an independent risk factor for worse prognosis at follow-up (OR (95%CI) 1.251-1.674, P＜0.001). CONCLUSIONS: Advanced age, hypertension, and stroke/TIA were increased in patients with cerebral infarction with nonvalvular atrial fibrillation combined with cerebral artery stenosis.