A5005807339- Hepatocellular Carcinoma Treatment and Prognosis
- Vascular Procedures and Complications
- Venous Thromboembolism Diagnosis and Management
- Central Venous Catheters and Hemodialysis
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Liver Disease Diagnosis and Treatment
- Renal cell carcinoma treatment
- Liver Disease and Transplantation
- Hepatitis B Virus Studies
- Renal and Vascular Pathologies
- Topic Modeling
- Machine Learning in Healthcare
- Radiomics and Machine Learning in Medical Imaging
- Abdominal vascular conditions and treatments
- Organ Transplantation Techniques and Outcomes
- MRI in cancer diagnosis
- Prostate Cancer Diagnosis and Treatment
- Esophageal and GI Pathology
- Gastrointestinal Bleeding Diagnosis and Treatment
- Urinary Bladder and Prostate Research
- Peripheral Artery Disease Management
- Glioma Diagnosis and Treatment
- COVID-19 and healthcare impacts
- Transplantation: Methods and Outcomes
- COVID-19 diagnosis using AI
Mount Sinai Medical Center
2015-2024
Icahn School of Medicine at Mount Sinai
2014-2021
Mount Sinai Health System
2017-2020
Mount Sinai Hospital
2018-2020
Neurological Surgery
2019
California Pacific Medical Center
2019
Boston University
2018
Abington Memorial Hospital
2014
Early results in using convolutional neural networks (CNNs) on x-rays to diagnose disease have been promising, but it has not yet shown that models trained from one hospital or group of hospitals will work equally well at different hospitals. Before these tools are used for computer-aided diagnosis real-world clinical settings, we must verify their ability generalize across a variety systems. A cross-sectional design was train and evaluate pneumonia screening CNNs 158,323 chest NIH...
Purpose To compare different methods for generating features from radiology reports and to develop a method automatically identify findings in these reports. Materials Methods In this study, 96 303 head computed tomography (CT) were obtained. The linguistic complexity of was compared with that alternative corpora. Head CT preprocessed, machine-analyzable constructed by using bag-of-words (BOW), word embedding, Latent Dirichlet allocation-based approaches. Ultimately, 1004 manually labeled...
Purpose To compare the outcomes of radiation segmentectomy (RS) and transarterial chemoembolization (TACE) combined with microwave ablation (MWA) in treatment unresectable solitary hepatocellular carcinoma (HCC) up to 3 cm. Materials Methods This retrospective study was approved by institutional review board, requirement obtain informed consent waived. From January 2010 June 2015, a total 417 235 consecutive patients HCC underwent RS TACE MWA, respectively. A cohort 121 who had not...
Background: Differentiating glioblastoma, brain metastasis, and central nervous system lymphoma (CNSL) on conventional magnetic resonance imaging (MRI) can present a diagnostic dilemma due to the potential for overlapping features. We investigate whether machine learning evaluation of multimodal MRI reliably differentiate these entities. Methods: Preoperative including diffusion weighted (DWI), dynamic contrast enhanced (DCE), susceptibility (DSC) perfusion in patients with lymphoma, or...
In this study we analyze the different types of endovascular interventions (EVIs) in de novo transplant renal artery stenosis (TRAS) and its anatomical subtypes to examine any variation recovery allograft function, blood pressure control, EVI patency survival with respect type (DES: drug-eluting stent, BMS: bare-metal PTA: percutaneous transluminal angioplasty). Forty-five patients underwent a total 50 primary EVIs 18, 26, 6). Patients were stratified according medical co-morbidities, graft...
PurposeTransradial access (TRA) has been shown to lower morbidity and bleeding complications compared transfemoral in percutaneous coronary interventions. Morbid obesity, commonly defined as a body mass index (BMI) ≥40 kg/m2, be risk factor for site irrespective of site. This study evaluates the safety feasibility performing visceral endovascular interventions morbidly obese patients via TRA. MethodsProcedural details, technical success, 30-day major minor site, bleeding, neurological...
Abstract Background There is a lack of registry studies about transradial access (TRA) outcomes. This prospective evaluated the TRA and procedure outcomes visceral embolizations performed via with 30-day follow-up. Material & methods Prospective, multicenter included uterine fibroids (UFE), prostate artery (PAE), liver tumors (LT), other hypervascular (OHT) embolization in six US hospitals. Between February 2020 January 2022, 99 patients underwent one radial intervention (RAVI); 70 had...
Purpose To determine if weakly supervised learning with surrogate metrics and active transfer can hasten clinical deployment of deep models. Materials Methods By leveraging Liver Tumor Segmentation (LiTS) challenge 2017 public data (n = 131 studies), natural language processing reports, an method, a model was trained to segment livers on 239 retrospectively collected portal venous phase abdominal CT studies obtained between January 1, 2014, December 31, 2016. Absolute volume differences...
Vertical sleeve gastrectomy (VSG) was originally performed as the first-stage of biliopancreatic diversion with duodenal switch (BPD/DS) for superobesity a strategy to reduce perioperative complications and morbidity. VSG is now considered definitive procedure because its technical simplicity promising outcomes.To analyze outcomes laparoscopic compare them those single-stage BPD/DS.A retrospective review 200 consecutive patients who underwent BPD/DS between 2008 2011.A total 100 BPD/DS. The...
Pre-transplant locoregional therapy for hepatocellular carcinoma (HCC) during bridge-to-transplant impacts recurrence and survival rates following liver transplantation. Optimizing the effectiveness of transarterial chemoembolization (TACE) in this population is imperative, microvalve infusion catheters offer a means such improvement. All treatment-naive patients with solitary HCC tumors < 6.5 cm who underwent drug-eluting microspheres (DEM) TACE between 04/2015 08/2017 were retrospectively...
Background: Errors in grammar, spelling, and usage radiology reports are common. To automatically detect inappropriate insertions, deletions, substitutions of words reports, we proposed using a neural sequence-to-sequence (seq2seq) model. Methods: Head CT chest radiograph from Mount Sinai Hospital (MSH) (n=61,722 818,978, respectively), Queens (MSQ) (n=30,145 194,309, respectively) MIMIC-III (n=32,259 54,685) were converted into sentences. Insertions, substitutions, deletions randomly...
The purpose of this study is to analyze the efficacy transfer learning techniques and transformer-based models as applied medical natural language processing (NLP) tasks, specifically radiological text classification. We used 1,977 labeled head CT reports, from a corpus 96,303 total evaluate pretraining using general domain corpora combined with bidirectional representations transformers (BERT) model for Model performance was benchmarked logistic regression bag-of-words vectorization long...