Individualized Scan Protocols in Abdominal Computed Tomography

2021 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Bibi Martens ◽  
Gregor Jost ◽  
Casper Mihl ◽  
Estelle C. Nijssen ◽  
Joachim E. Wildberger ◽  
...  
2017 ◽  
Vol 35 (1) ◽  
pp. 21-25 ◽  
Author(s):  
Hyung Soo Kim ◽  
Chang Hee Lee ◽  
Seong Hyun Kim ◽  
Jeong Woo Kim ◽  
Cheol Min Park ◽  
...  

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Kwang-Hyun Uhm ◽  
Seung-Won Jung ◽  
Moon Hyung Choi ◽  
Hong-Kyu Shin ◽  
Jae-Ik Yoo ◽  
...  

AbstractIn 2020, it is estimated that 73,750 kidney cancer cases were diagnosed, and 14,830 people died from cancer in the United States. Preoperative multi-phase abdominal computed tomography (CT) is often used for detecting lesions and classifying histologic subtypes of renal tumor to avoid unnecessary biopsy or surgery. However, there exists inter-observer variability due to subtle differences in the imaging features of tumor subtypes, which makes decisions on treatment challenging. While deep learning has been recently applied to the automated diagnosis of renal tumor, classification of a wide range of subtype classes has not been sufficiently studied yet. In this paper, we propose an end-to-end deep learning model for the differential diagnosis of five major histologic subtypes of renal tumors including both benign and malignant tumors on multi-phase CT. Our model is a unified framework to simultaneously identify lesions and classify subtypes for the diagnosis without manual intervention. We trained and tested the model using CT data from 308 patients who underwent nephrectomy for renal tumors. The model achieved an area under the curve (AUC) of 0.889, and outperformed radiologists for most subtypes. We further validated the model on an independent dataset of 184 patients from The Cancer Imaging Archive (TCIA). The AUC for this dataset was 0.855, and the model performed comparably to the radiologists. These results indicate that our model can achieve similar or better diagnostic performance than radiologists in differentiating a wide range of renal tumors on multi-phase CT.


2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 1818.1-1818
Author(s):  
J. Razanamahery ◽  
S. Humbert ◽  
A. Malakhia ◽  
J. F. Emile ◽  
F. Cohen ◽  
...  

Background:Sclerosing Mesenteritis (SM) refers to an entire spectrum of digestive inflammatory disorders. Diagnosis is based on imaging showing an increase of fat attenuation displacing bowel loops and is in most cases non-symptomatic. Several conditions (abdominal trauma/surgery, neoplasia, infectious and inflammatory diseases) are responsible for SM (1). Among neoplasia, Erdheim-Chester disease (ECD) is a rare clonal histiocytosis characterized by long bone involvement, peri-nephric fat infiltration and cardio-vascular involvement associated with compatible histology (2). Biopsy is mandatory to confirm tissue infiltration by histiocytes and detect somatic mutation. Almost 80% of ECDpatients harbor mutation in mitogen activated protein(MAP) kinase pathway especiallyBRAFV600Egene mutation in about 60% of cases(3). No series of patients presenting both pathologies has been reported. Furthermore, no correlation withBRAFmutation status has been described in patient harboring SM and ECD.Objectives:To describe the clinical, radiological and mutational status of patients harboring SM and ECD.Methods:We reviewed the database of patients with histiocytic disorders in Besancon University Hospital. Patient required one abdominal computed tomography showing sclerosing mesenteritis and clinical/histological features of ECD to fulfill the inclusion criteria. All biopsy samples were investigated for mutation ofMAPkinase pathway gene.Results:Four patients suffered from SM and ECD. The median age at the diagnosis of ECD was 68 years old (61-72). All patients described abdominal pain and the mean duration between first symptoms and diagnosis of ECD was 12 months (4-19). The mean CRP level at diagnosis was 40.75 mg/L (5-117). Two patients were found to have myeloid neoplasms (chronic myelomonocytic leukemia (#2) and essential thrombocythemia (#4)) concurrent with ECD diagnosis.Regarding abdominal computed tomography, all patients had a mesenteric mass associated with hyper-attenuated mesenteric fat and a “fat halo sign”. One patient (#2) had ascites and one had splenomegaly (#4) but no patient had enlarged lymph nodes. CT also demonstrated peri-nephric fat infiltration (“hairy kidney”) (4/4), vascular sheathing of aortic branches (3/4), adrenal hypertrophy (1/4) or ureter dilation (1/4). The mean SUVmaxof the mesentery was 7.5 (4.1-10.9) at diagnosis on (18F)- fluorodeoxyglucose-PET. Three patients underwent mesentery fat biopsy and all samples exhibited ECD histology. Regarding mutational status, 75% (3/4) patients hadBRAFV600Emutation.After initiation of therapies for ECD (targeted therapies for ¾ patients), all patients had improvement of digestive symptoms and decreased of SUVmaxon evaluation18FDG-PET during the follow up.Conclusion:ECD should be investigated in patient with symptomatic SM especially if it is associated with peri-nephric fat infiltration. This condition is rare and might be driven by BRAF gene.TABLE 2.Full term pregnancyMultiple gestationPreconception CZP exposureLabor complicationsMaternal infectionsNeonatal infections (< 6 m after birth)Congenital malformationsBreast-feedingNeonates, n/N15/152/155/150/151/150/150/156/15References:[1]Danford CJ, Lin SC, Wolf JL. Sclerosing Mesenteritis. Am J Gastroenterol. 2019 Jun;114(6):867–73.[2]Diamond EL, Dagna L, Hyman DM, Cavalli G, Janku F, Estrada-Veras J, et al. Consensus guidelines for the diagnosis and clinical management of Erdheim-Chester disease. Blood. 2014 Jul 24;124(4):483–92.[3]Haroche J, Cohen-Aubart F, Rollins BJ, Donadieu J, Charlotte F, Idbaih A, et al. Histiocytoses: emerging neoplasia behind inflammation. Lancet Oncol. 2017 Feb;18(2):e113–25.Disclosure of Interests:None declared


2007 ◽  
Vol 21 (4) ◽  
pp. 612-614
Author(s):  
Gianluca Santise ◽  
Giuseppe D’Ancona ◽  
Sergio Sciacca ◽  
Francesco Pirone ◽  
Salvatore Gruttadauria ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document