Deep learning algorithm applied to plain CT images to identify superior mesenteric artery abnormalities.

OBJECTIVES: Atypical presentations, lack of biomarkers, and low sensitivity of plain CT can delay the diagnosis of superior mesenteric artery (SMA) abnormalities, resulting in poor clinical outcomes. Our study aims to develop a deep learning (DL) model for detecting SMA abnormalities in plain CT and evaluate its performance in comparison with a clinical model and radiologist assessment. MATERIALS AND METHODS: A total of 1048 patients comprised the internal (474 patients with SMA abnormalities, 474 controls) and external testing (50 patients with SMA abnormalities, 50 controls) cohorts. The internal cohort was divided into the training cohort (n = 776), validation cohort (n = 86), and internal testing cohort (n = 86). A total of 5 You Only Look Once version 8 (YOLOv8)-based DL submodels were developed, and the performance of the optimal submodel was compared with that of a clinical model and of experienced radiologists. RESULTS: Of the submodels, YOLOv8x had the best performance. The area under the curve (AUC) of the YOLOv8x submodel was higher than that of the clinical model (internal test set: 0.990 vs 0.878, P =.002; external test set: 0.967 vs 0.912, P =.140) and that of all radiologists (P <.001). The YOLOv8x submodel, when compared with radiologist assessment, demonstrated higher sensitivity (internal test set: 100.0 % vs 70.7 %, P =.002; external test set: 96.0 % vs 68.8 %, P <.001) and specificity (internal test set: 90.7 % vs 66.0 %, P =.025; external test set: = 88.0 % vs 66.0 %, P <.001). CONCLUSION: Using plain CT images, YOLOv8x was able to efficiently identify cases of SMA abnormalities. This could potentially improve early diagnosis accuracy and thus improve clinical outcomes.

Application of dual-source computed tomography in the diagnosis of thyroid cancer and evaluation of biological behaviors.

OBJECTIVE: Thyroid cancer (TC) is an extremely prevailing malignant endocrine tumor. Therefore, effective diagnostic tools are necessary. This study explored the application value of dual-source computed tomography (DSCT) in TC diagnosis and biological behavior assessment. METHODS: This study retrospectively selected 68 TC patients and another 74 benign patients with thyroid adenoma, nodular goiter, or adenomatous hyperplasia. All patients were confirmed by pathological examination and underwent DSCT examination. The iodine concentration (IC) obtained from plain computed tomography (CT) scanning and normalized iodine concentration (NIC) in the arterial phase and venous phase were recorded. The positive expression rates of estrogen receptor alpha (ERα), estrogen receptors beta (ERß), and Ki67 in pathological tissues were determined by immunohistochemistry, and their correlation with IC in plain CT was assessed by Pearson correlation analysis, respectively. The diagnostic values of IC in plain CT and venous phase NIC in TC patients were evaluated using the receiver operating characteristic curve. RESULTS: Malignant patients had lower IC in plain DSCT scanning, venous phase NIC, and ERß, and higher ERα and Ki67 than benign patients. IC level in plain DSCT scanning was inversely-correlated with ERα and Ki-67 positive expression rates, but positively-related to ERß to different degrees. For the diagnosis of TC patients, the AUC of IC level in plain DSCT was 0.771, with a cut-off value of 1.250 (97.06% sensitivity and 41.89% specificity), and the AUC of venous phase NIC was 0.738, with a cut-off value of 0.825 (100% sensitivity and 43.24% specificity). CONCLUSION: The IC level obtained from DSCT scanning could assist in the differential diagnosis of malignant and benign thyroid nodules and evaluation of biological behaviors.

Prevalence of coronary calcification on preoperative computed tomography and its management in thoracic surgery.

PURPOSE: We investigated the preoperative assessment of coronary artery calcification using computed tomography for appropriate intraoperative management to reduce the risk of perioperative cardiac complications during pulmonary resection. METHODS: Patients (n = 665) who underwent anatomical lung resection were examined. The extent of preoperative asymptomatic coronary artery stenosis or cardiac complications in patients with coronary artery calcification was assessed. In addition, the risk factors for perioperative cardiac complications were determined. RESULTS: Coronary artery calcification was detected in 233 (35.0%) asymptomatic patients. Nineteen (8.2%) patients with coronary artery calcification had coronary artery stenosis ≥ 75%. Percutaneous coronary intervention was performed preoperatively (n = 3) and postoperatively (n = 10), and preoperative drug intervention was performed in 10 cases. One case of severe postoperative cardiac complications and 20 cases of mild postoperative cardiac complications, including those without coronary artery calcification, occurred. Patients with calcified coronary arteries were at risk of cardiovascular complications in the perioperative period. However, patients with coronary artery calcification who underwent preoperative cardiology intervention had no significant perioperative cardiovascular complications. CONCLUSIONS: Coronary artery calcification detected on preoperative computed tomography is a risk factor for perioperative cardiovascular complications. Early intervention may reduce the risk of such complications.

Usefulness of Routine Plain CT the Day After an Interventional EUS Procedure.

BACKGROUND: Interventional endoscopic ultrasound-guided procedures (I-EUS) are widely accepted as salvage procedures in ERCP-failed cases, and to drain fluid collected in the abdominal cavity. Although I-EUS has a relatively high incidence of complications and is severe/fatal in some cases, no follow-up strategy has been established. In our institution, plain computed tomography (P-CT) is performed routinely the day after I-EUS. In this study, we evaluated the usefulness of routine P-CT the day after I-EUS, as a follow-up method, and propose an algorithm. METHODS: We retrospectively reviewed 81 patients who underwent I-EUS and evaluated the usefulness of P-CT, abdominal X-ray, laboratory data, and symptoms as a follow-up method. An adverse event (AE) was defined as an event requiring any treatment. RESULTS: Technical success, clinical success, and AE rates were 96.3%, 90.1%, and 18.9%, respectively. In total, 30 patients had abnormal findings among the follow-up methods: 6 cases underwent additional procedures, 8 underwent medical treatments, and 16 were observed. The sensitivity, specificity, and accuracy for detecting AEs were assessed based on P-CT (85.7%, 100%, and 97.5%), X-ray (7.1%, 100%, and 83.5%), laboratory data (71.4%, 83.0%, and 81.0%), and symptoms (92.9%, 86.2%, and 87.3%). The sensitivity and accuracy of the latter two items were as high as those for X-ray, but specificity was lower than those for X-ray and P-CT. CONCLUSIONS: Routine P-CT the day after I-EUS was useful for detecting complications and deciding to perform an invasive salvage procedure. Symptoms and laboratory data were useful to supplement routine P-CT.

Attempt to delineate occluded arteries with initial plain computed tomography in acute cerebral arterial occlusion.

BACKGROUND: We used initial plain computed tomography to delineate acutely occluded internal carotid arteries or horizontal segments of middle cerebral arteries. If affected arteries could be delineated using initial plain computed tomography, useful information might be obtained that could support endovascular thrombectomies. METHODS: In 15 patients with occluded internal carotid arteries or horizontal segments of middle cerebral arteries, the affected middle cerebral artery was automatically traced using the extender function for blood vessel tracing with reference to the default value (window setting, 40; window width, 90) on Ziostation 2 (Ziosoft Inc., Tokyo, Japan) based on initial plain computed tomography data. RESULTS: The horizontal and sylvian segments of the middle cerebral artery were delineated in 15 and nine patients, respectively, based on plain computed tomography volume data. Images of occluded vessels delineated by plain computed tomography closely correlated with digital subtraction angiography. CONCLUSIONS: Initial plain computed tomography combined with a new generation workstation enabled the rapid delineation of occluded segments of intracranial vessels and could provide useful information that might improve the safety of endovascular thrombectomy.