Deep Learning in Dynamic Modeling of Medical Imaging: A Review Study

Swarna, Srinivasa Rao; Boyapati, Sumati; Dutt, Vishal; Bajaj, Karan

doi:10.1109/iciss49785.2020.9315990

Cited by 10 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the intersection of EHR data and the progress of ML, is an opportunity to develop tools for personalised medicine. Currently, the most common ML applications in medicine are in imaging [2, 3]. An upcoming frontier is surgical risk prediction [4].…”

Section: Introductionmentioning

confidence: 99%

Development and Validation of ‘Patient Optimizer’ (POP) Algorithms for Predicting Surgical Risk with Machine Learning

Kowadlo¹,

Mittelberg²,

Ghomlaghi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Background Pre-operative risk assessment can help clinicians prepare patients for surgery, reducing the risk of perioperative complications, length of hospital stay, readmission and mortality. Further, it can facilitate collaborative decision-making and operational planning. Objective To develop effective pre-operative risk assessment algorithms (referred to as Patient Optimizer or POP) using Machine Learning (ML) that predicts the development of post-operative complications and provides pilot data to inform the design of a larger prospective study. Methods After institutional ethics approval, we developed a baseline model that encapsulates the standard manual approach of combining patient-risk and procedure-risk. In an automated process, additional variables were included and tested with 10-fold cross-validation, and the best performing features were selected. The models were evaluated and confidence intervals calculated using bootstrapping. Clinical expertise was used to restrict the cardinality of categorical variables (e.g. pathology results) by including the most clinically relevant values. The models were created with extreme gradient-boosted trees using XGBoost (Chen et al. 2016). We evaluated performance using the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). Data was obtained from a metropolitan university teaching hospital from January 2015 to July 2020. Data collection was restricted to adult patients undergoing elective surgery. Results A total of 11,475 adult admissions were included. For predicting the risk of any post-operative complication, kidney failure and length-of-stay (LOS), POP achieved an AUROC (95%CI) of 0.755 (0.744, 0.767), 0.869 (0.846, 0.891) and 0.841 (0.833, 0.847) respectively and AUPRC of 0.651 (0.632, 0.669), 0.326 (0.293, 0.359) and 0.741 (0.729, 0.753) respectively. For 30-day readmission and in-patient mortality, POP achieved an AUROC (95%CI) of 0.61 (0.587, 0.635) and 0.866 (0.777, 0.943) respectively and AUPRC of 0.116 (0.104, 0.132) and 0.031 (0.015, 0.072) respectively. Conclusion The POP algorithms effectively predicted any post-operative complications, kidney failure and LOS in the sample population. A larger study is justified to improve the algorithm to better predict complications and length of hospital stay. A larger dataset may also improve the prediction of additional specific complications, readmissions and mortality.

show abstract

Section: Introductionmentioning

confidence: 99%

Development and Validation of ‘Patient Optimizer’ (POP) Algorithms for Predicting Surgical Risk with Machine Learning

Kowadlo¹,

Mittelberg²,

Ghomlaghi³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Additionally, diagnosis of potential endodontic pathosis may be time-consuming for dentists in daily dental practice. With the rapid growth of technology, big data analytics, and machine learning techniques have been widely used in medicine, such as in autism [11], detection of pneumonia [12], risk of falls [13], classification of cancers [14], application of disease detection [15], predicting severe retinopathy of prematurity [16], dynamic modeling of medical imaging [17], and lung and pancreatic tumor characterization [18]. In response to this problem, this article combines big data analysis and machine learning technology to improve.…”

Section: Introductionmentioning

confidence: 99%

Detection of Dental Apical Lesions Using CNNs on Periapical Radiograph

Lin

Chou

et al. 2021

Sensors

View full text Add to dashboard Cite

Apical lesions, the general term for chronic infectious diseases, are very common dental diseases in modern life, and are caused by various factors. The current prevailing endodontic treatment makes use of X-ray photography taken from patients where the lesion area is marked manually, which is therefore time consuming. Additionally, for some images the significant details might not be recognizable due to the different shooting angles or doses. To make the diagnosis process shorter and efficient, repetitive tasks should be performed automatically to allow the dentists to focus more on the technical and medical diagnosis, such as treatment, tooth cleaning, or medical communication. To realize the automatic diagnosis, this article proposes and establishes a lesion area analysis model based on convolutional neural networks (CNN). For establishing a standardized database for clinical application, the Institutional Review Board (IRB) with application number 202002030B0 has been approved with the database established by dentists who provided the practical clinical data. In this study, the image data is preprocessed by a Gaussian high-pass filter. Then, an iterative thresholding is applied to slice the X-ray image into several individual tooth sample images. The collection of individual tooth images that comprises the image database are used as input into the CNN migration learning model for training. Seventy percent (70%) of the image database is used for training and validating the model while the remaining 30% is used for testing and estimating the accuracy of the model. The practical diagnosis accuracy of the proposed CNN model is 92.5%. The proposed model successfully facilitated the automatic diagnosis of the apical lesion.

show abstract

“…Blockchain, the core technology behind Bitcoin (Nakamoto, 2008) has gained an extensive attention in the recent years and it has revolutionized the digital world. Blockchain is a distributed open ledger that contains data that is immutable in a secure and encrypted mode and ensures that the transactions can never be altered.…”

Section: Introductionmentioning

confidence: 99%

Blockchain-based Framework for Online Entrance Examination and Score Card Verification System

Thilagavathi¹

2021

TURCOMAT

View full text Add to dashboard Cite

Entrance examinations are a means through which universities select prospective students for admission. Most of the entrance exams are conducted using pen-paper in an offline mode where the number of students appearing is also very high. The current entrance examination system with centralized servers to prone to single point of failure and faces threats with respect to leaks in question papers, copying by students during the exam, impersonation, manipulation of the answers, forging the score cards, difficulty in verifying the authenticity and reliability of score cards by the university, etc. To overcome these issues and to conduct entrance exams online in a secure manner and to make the process of verifying the score card easier, a framework based on private blockchain is proposed in this paper.

show abstract

Deep Learning in Dynamic Modeling of Medical Imaging: A Review Study

Cited by 10 publications

References 13 publications

Development and Validation of ‘Patient Optimizer’ (POP) Algorithms for Predicting Surgical Risk with Machine Learning

Development and Validation of ‘Patient Optimizer’ (POP) Algorithms for Predicting Surgical Risk with Machine Learning

Detection of Dental Apical Lesions Using CNNs on Periapical Radiograph

Blockchain-based Framework for Online Entrance Examination and Score Card Verification System

Contact Info

Product

Resources

About