Oral squamous cell carcinoma (OSCC) is a subset of head and neck squamous cell carcinoma (HNSCC), the 7th most common cancer worldwide, and accounts for more than 90% of oral malignancies. Early detection of OSCC is essential for effective treatment and reducing the mortality rate. However, the gold standard method of microscopy-based histopathological investigation is often challenging, time-consuming and relies on human expertise. Automated analysis of oral biopsy images can aid the histopathologists in performing a rapid and arguably more accurate diagnosis of OSCC. In this study, we present deep learning (DL) based auto- mated classification of 290 normal and 934 cancerous oral histopathological images published by Tabassum et al (Data in Brief, 2020). We utilized transfer learning approach by adapt- ing three pre-trained DL models to OSCC detection. VGG16, InceptionV3, and Resnet50 were fine-tuned individually and then used in concatenation as feature extractors. The con- catenated model outperformed the individual models and achieved 96.66% accuracy (95.16% precision, 98.33% recall, and 95.00% specificity) compared to 89.16% (VGG16), 94.16% (In- ceptionV3) and 90.83% (ResNet50). These results demonstrate that the concatenated model can effectively replace the use of a single DL architecture.
Background Cardiac imaging is the cornerstone of the pretranscatheter aortic valve replacement (TAVR) assessment. Multi‐detector computed tomography (MDCT) is considered the conventional imaging modality. However, there is still no definitive gold standard. Targeted cohort of inoperable high‐risk patients with underlying comorbidities, particularly renal impairment, makes apparent the need for MDCT alternative. We aimed to demonstrate the correlation extent between MDCT and three‐dimensional transesophageal echocardiography (3DTEE) aortic annular area measures and to answer the question: Is 3DTEE a good alternative to MDCT? Methods A systematic literature search and meta‐analysis were conducted to evaluate the degree of correlation and agreement between 3DTEE and MDCT aortic annular sizing. A thorough assessment of EMBASE, PubMed, and Cochrane Central Register of Controlled Trials (CENTRAL) was performed. All studies comparing 3DTEE and MDCT in relation to aortic annular sizing were included. Results Thirteen studies were included (N = 1228 patients). A strong linear correlation was found between 3DTEE and MDCT measurements of aortic annulus area (r = 0.84, P < 0.001), mean perimeter (r = 0. 0.85, P < 0.001), and mean diameter (r = 0.80, P < 0.001). Bland–Altman plots revealed smaller mean 3DTEE values in comparison to MDCT for aortic annular area, the mean difference being −2.22 mm2 with 95% limits of agreement −12.79 to 8.36. Conclusion Aortic annulus measurements obtained by 3DTEE demonstrated a high level of correlation with those evaluated by MDCT. This makes 3DTEE a feasible choice for aortic annulus assessment, with advantage of real time assessment, lack of contrast, and no radiation exposure.
Renocolic fistula is a rare clinical finding that is most commonly iatrogenic after surgical intervention. Herein, we present a case of renocolic fistula secondary to xanthogranulomatous pyelonephritis (XGP) with a subtle presentation as anemia. A 40-year-old female was found to have a hemoglobin of 6.5 g/dL after presenting for worsening fatigue. A urinalysis was remarkable for numerous white blood cell (WBC), positive bacteria, and nitrite. As part of her anemia workup, an esophagogastroduodenoscopy (EGD) was done which was normal while a colonoscopy showed a fistula opening with surrounding nodularity close to the splenic flexure of the colon. A computed tomography (CT) scan of the abdomen and pelvis with contrast showed chronic left kidney pyelonephritis with multiple contiguous abscesses in the inferior left kidney in addition to a staghorn calculus concerning for XGP. The patient was started on antibiotics and underwent laparotomy with repair of the renocolic fistula, partial omentectomy, and left nephrectomy. She tolerated the surgery well and was discharged with a stable hemoglobin. XGP is a rare type of chronic pyelonephritis that is usually a result of chronic obstruction by an infected stone. Spontaneous renocolic fistulas are rare nowadays with the advancement in antibiotics and renal stones treatment.
Isolation of Shigella in the bloodstream is a rare sequela of Shigella infections. Shigellemia typically occurs in patients with immature immune responses or in immunocompromised adults. Herein, we present a case of shigellemia in a 40-year-old male who presented with diabetic ketoacidosis (DKA), severe diarrhea, hypovolemic hyponatremia, and altered mental status. Stool cultures were found to be positive for Shigella , and broad-spectrum antibiotic therapy was initiated. Because of the patient’s reported sexual exposures, a rapid HIV point of care test was done and returned negative. In spite of intervention, the patient’s vitals, labs, and symptoms failed to improve, and he developed septic shock requiring pressor support in the intensive care unit. Further workup for the etiology of the patient’s sepsis included a CT abdomen and pelvis which showed findings concerning infectious colitis. Blood cultures later returned positive for Shigella , which was found to be resistant to multiple antibiotics. The patient was started on IV ceftriaxone with an improvement of and eventual resolution of symptoms. Shigellemia is a rare complication of infection with Shigella and necessitates further workup to avoid overlooking potential predisposing factors such as HIV or other immunocompromising conditions. Its susceptibilities should also be evaluated, as Shigella strains are more frequently becoming resistant to antibiotics that had previously been the therapies of choice.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.