PubMed Kapalı Erişimli Yayınlar

Permanent URI for this collectionhttps://hdl.handle.net/11727/10764

Browse

Filters

2021 - 20222

Settings

Subject: search.filters.subject.deep learning

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Use Of Deep Learning Methods For Hand Fracture Detection From Plain Hand Radiographs
    (2022) Ureten, Kemal; Sevinc, Huseyin Fatih; Igdeli, Ufuk; Onay, Aslihan; Maras, Yuksel; https://orcid.org/0000-0003-4213-9126; 35099027
    BACKGROUND: Patients with hand trauma are usually examined in emergency departments of hospitals. Hand fractures are frequently observed in patients with hand trauma. Here, we aim to develop a computer-aided diagnosis (CAD) method to assist physicians in the diagnosis of hand fractures using deep learning methods. METHODS: In this study, Convolutional Neural Networks (CNN) were used and the transfer learning method was applied. There were 275 fractured wrists, 257 fractured phalanx, and 270 normal hand radiographs in the raw dataset. CNN, a deep learning method, were used in this study. In order to increase the performance of the model, transfer learning was applied with the pre-trained VGG-16, GoogLeNet, and ResNet-50 networks. RESULTS: The accuracy, sensitivity, specificity, and precision results in Group 1 (wrist fracture and normal hand) dataset were 93.3%, 96.8%, 90.3%, and 89.7% , respectively, with VGG-16, were 88.9%, 94.9%, 84.2%, and 82.4%, respectively, with Resnet-50, and were 88.1%, 90.6%, 85.9%, and 85.3%, respectively, with GoogLeNet. The accuracy, sensitivity, specificity, and precision results in Group 2 (phalanx fracture and normal hand) dataset were 84.0%, 84.1%, 83.8%, and 82.8%, respectively, with VGG-16, were 79.4%, 78.5%, 80.3%, and 79.7%, respectively, with Resnet-50, and were 81.7%, 81.3%, 82.1%, and 81.3%, respectively, with GoogLeNet. CONCLUSION: We achieved promising results in this CAD method, which we developed by applying methods such as transfer learning, data augmentation, which are state-of-the-art practices in deep learning applications. This CAD method can assist physicians working in the emergency departments of small hospitals when interpreting hand radiographs, especially when it is difficult to reach qualified colleagues, such as night shifts and weekends.
  • No Thumbnail Available
    Item
    A deep learning approach for sepsis monitoring via severity score estimation
    (2021) Asuroglu, Tunc; Ogul, Hasan; 33157471
    Background and objective: Sepsis occurs in response to an infection in the body and can progress to a fatal stage. Detection and monitoring of sepsis require multi-step analysis, which is time-consuming, costly and requires medically trained personnel. A metric called Sequential Organ Failure Assessment (SOFA) score is used to determine the severity of sepsis. This score depends heavily on laboratory measurements. In this study, we offer a computational solution for quantitatively monitoring sepsis symptoms and organ systems state without laboratory test. To this end, we propose to employ a regression-based analysis by using only seven vital signs that can be acquired from bedside in Intensive Care Unit (ICU) to predict the exact value of SOFA score of patients before sepsis occurrence. Methods: A model called Deep SOFA-Sepsis Prediction Algorithm (DSPA) is introduced. In this model, we combined Convolutional Neural Networks (CNN) features with Random Forest (RF) algorithm to predict SOFA scores of sepsis patients. A subset of Medical Information Mart in Intensive Care (MIMIC) III dataset is used in experiments. 5154 samples are extracted as input. Ten-fold cross validation test are carried out for experiments. Results: We demonstrated that our model has achieved a Correlation Coefficient (CC) of 0.863, a Mean Absolute Error (MAE) of 0.659, a Root Mean Square Error (RMSE) of 1.23 for predictions at sepsis onset. The accuracies of SOFA score predictions for 6 hours before sepsis onset were 0.842, 0.697, and 1.308, in terms of CC, MAE and RMSE, respectively. Our model outperformed traditional machine learning and deep learning models in regression analysis. We also evaluated our model's prediction performance for identifying sepsis patients in a binary classification setup. Our model achieved up to 0.982 AUC (Area Under Curve) for sepsis onset and 0.972 AUC for 6 hours before sepsis, which are higher than those reported by previous studies. Conclusions: By utilizing SOFA scores, our framework facilitates the prognose of sepsis and infected organ systems state. While previous studies focused only on predicting presence of sepsis, our model aims at providing a prognosis solution for sepsis. SOFA score estimation process in ICU depends on laboratory environment. This dependence causes delays in treating patients, which in turn may increase the risk of complications. By using easily accessible non-invasive vital signs that are routinely collected in ICU, our framework can eliminate this delay. We believe that the estimation of the SOFA score will also help health professionals to monitor organ states. (C) 2020 Elsevier B.V. All rights reserved.