Preoperative Contrast-Enhanced CT-Based Deep Learning Radiomics Model for Distinguishing Retroperitoneal Lipomas and Well­Differentiated Liposarcomas.

RATIONALE AND OBJECTIVES: To assess the efficacy of a preoperative contrast-enhanced CT (CECT)-based deep learning radiomics nomogram (DLRN) for predicting murine double minute 2 (MDM2) gene amplification as a means of distinguishing between retroperitoneal well-differentiated liposarcomas (WDLPS) and lipomas. METHODS: This retrospective multi-center study included 167 patients (training/external test cohort, 104/63) with MDM2-positive WDLPS or MDM2-negative lipomas. Clinical data and CECT features were independently measured and analyzed by two radiologists. A clinico-radiological model, radiomics signature (RS), deep learning and radiomics signature (DLRS), and a DLRN incorporating radiomics and deep learning features were developed to differentiate between WDLPS and lipoma. The model utility was evaluated based on the area under the receiver operating characteristic curve (AUC), accuracy, calibration curve, and decision curve analysis (DCA). RESULTS: The DLRN showed good performance for distinguishing retroperitoneal lipomas and WDLPS in the training (AUC, 0.981; accuracy, 0.933) and external validation group (AUC, 0.861; accuracy, 0.810). The DeLong test revealed the DLRN was noticeably better than clinico-radiological and RS models (training: 0.981 vs. 0.890 vs. 0.751; validation: 0.861 vs. 0.724 vs. 0.700; both P < 0.05); however, no discernible difference in performance was seen between the DLRN and DLRS (training: 0.981 vs. 0.969; validation: 0.861 vs. 0.837; both P > 0.05). The calibration curve analysis and DCA demonstrated that the nomogram exhibited good calibration and offered substantial clinical advantages. CONCLUSION: The DLRN exhibited strong predictive capability in predicting WDLPS and retroperitoneal lipomas preoperatively, making it a promising imaging biomarker that can facilitate personalized management and precision medicine.

Changes in ocular surface status and dry eye symptoms following femtosecond laser-assisted cataract surgery.

AIM: To observe the changes in ocular surface and the dry eye symptoms following femtosecond laser-assisted cataract surgery (FLACS). METHODS: Patients with no eye signs or symptoms in Guangzhou Aier Eye Hospital between October 2017 and September 2018, who underwent FLACS and intraocular lens (IOL) implantation for age-related cataract were enrolled. Tear film stability assessed with OCULUS Keratograph 5M, Schirmer's I test (SIT), and corneal fluorescein staining (CFS) were evaluated before and after surgery at 1d, 1wk, 1, and 3mo in order. Ocular Surface Disease Index scores (OSDI) and Subjective Symptom Questionnaires (SSQs) were recorded at the same time point. RESULTS: Thirty-eight eyes of 38 patients were enrolled. The noninvasive tear film break-up time (first break-up time and average break-up time) decreased in a peak at the 1wk visit, and then increased to basic levels at 1mo. The tear meniscus height (TMH) increased transiently at 1d, and declined in the following 3mo visits. The SIT had a transient increase at 1d (P=0.357) and a decrease at 1wk and 1mo (both P<0.05) but returned to the preoperative levels at 3mo after surgery (P=0.062). CFS scores were significantly improved compared with those before surgery, and had a statistical difference (P<0.05). OSDI scores and SSQs after surgery were obviously higher, and had a statistical difference (P<0.001) but didn't return to the basic level by 3mo. CONCLUSION: Dry eye signs and symptoms can occur immediately following FLACS and have a peak severity on day 7 postoperatively. Most signs of dry eye can return to preoperative basic levels within 3mo postoperatively. However, all cases can not recover from CFS and dry eye symptoms at 3mo postoperatively.

Computed tomography and magnetic resonance imaging features of cervical chordoma.

Computed tomography (CT) and magnetic resonance imaging (MRI) scans of 11 patients with histologically proven cervical chordoma were retrospectively evaluated. Imaging features assessed included location, morphology, association with adjacent structures, vertebral destruction, status of cortical bone, periosteal reaction, attenuation and calcification by CT, and signal intensity and enhancement pattern by MRI. Of 7 cases with CT, 6 exhibited lytic-sclerotic bone destruction. A total of 5 cases exhibited pressure erosion of outer cortex, 3 of which had spiculated periosteal reaction. Calcification was observed in 3 cases. All cases were heterogeneous and hypodense. MRI T2-weighted images (n=10) revealed heterogeneous hyperintense (n=5), intermediate (n=2) and intermediate-hyperintense signal intensity (n=3). Hypointense septa between lobules (n=5) and stripes (n=3) were observed on T2-weighted images. Post-contrast magnetic resonance images (n=6) demonstrated marked heterogeneous (n=3) and ring-like (n=3) enhancement. CT scanning is valuable in revealing the lytic-sclerotic bone destruction, pressure erosion of outer cortex and calcification. MRI is useful in demonstrating the results of soft tissue mass. The two examinations are necessary for differential diagnosis of patients with suspected cervical chordoma.

Magnetic Resonance Features and Characteristic Vascular Pattern of Alveolar Soft-Part Sarcoma.

OBJECTIVE: The aim of this study was to investigate the magnetic resonance (MR) features of alveolar soft-part sarcoma (ASPS). METHODS: We studied 12 patients with ASPS confirmed by pathology in this retrospective study. MR features were analyzed, especially for the location, morphology, signals, and related enhanced features of the tumor vessels. RESULTS: Flow voids were shown in the central part of the tumor on T2-weighted imaging (T2WI) in all patients; they were arrayed in a radiating mode gathered toward the center (8 cases), designated by us as vascular center-gathered syndrome (VCGS), or scattered like twigs (4 cases). The flow voids were accompanied by high signals in all patients, including tubular (6 cases) and platy (6 cases) signals. Slightly higher signals were shown in the peripheral part of the tumor in all patients. Flow voids in the peripheral part were shown in all patients, and the majority of the flow voids surrounded the tumor (8 cases). The vessels around the tumor in 9 patients showed high signals, and the majority of the vessels were located at the superior and inferior poles (8 cases). 6 patients underwent enhanced scanning, including moderate (5 cases) and significant enhancement (1 case). CONCLUSION: Low signals of radiating flow voids accompanied by high signals of slow blood flow or blood sinuses in the center part have high significance for the diagnosis of ASPS.

Clinical application of 64-slice spiral CT in the diagnosis of the Tetralogy of Fallot.

OBJECTIVE: To explore the clinical application of 64-slice spiral CT in the diagnosis of the Tetralogy of Fallot. METHODS: Eighteen patients with diagnosed Tetralogy of Fallot underwent cardiac CT angiography with 64-slice CT (CTA). Two- and three-dimensional images were used for diagnosing in all cases by means of MPR (coronal, sagital and oblique), cMPR, MIP and VRT. RESULTS: All patients had ventricular septal defect, pulmonary stenosis and hypertrophy of right ventricle. The morphologic features of Tetralogy of Fallot were equal to echocardiography. Patent ductus arteriosus (PDA) were detected on eight patients. Main coronary artery branches and partial sub-branches were visualized in all patients. Abnormal coronary arteries were found in seven cases: both left and right main coronary artery arising from the right aortic sinus one case, right main coronary artery and circumflex (CX) arising from the right aortic sinus one case, left anterior descending (LAD) and CX arising from left aortic sinus directly one case, left and right coronary artery arising from back and front of the aortic sinus, respectively, three cases. Pulmonary artery branch stenosis was found in 12 cases and branch pulmonary artery dilation noticed in 1 case. Double superior vena cava was also found in one case. According to the surgery the diagnostic accuracy of CT and Echocardiography was 95.45 and 83.33%, respectively. CONCLUSION: Two- and three-dimensional 64-slice CTA not only show the overall anatomical structure of the heart, but also show coronary and pulmonary arteries. With these results, evaluation of coronary anomalies and pulmonary artery stenosis with 64-MSCT is extremely valuable for planning the operative procedure on the patients with Tetralogy of Fallot.