Fellow in a Box: Combining AI and Domain Knowledge with Bayesian Networks for Differential Diagnosis in Neuroimaging

A comparative analysis of meta-heuristic optimization algorithms for feature selection on ML-based classification of heart-related diseases

This study aims to use a machine learning (ML)-based enhanced diagnosis and survival model to predict heart disease and survival in heart failure by combining the cuckoo search (CS), flower pollination algorithm (FPA), whale optimization algorithm (WOA), and Harris hawks optimization (HHO) algorithms, which are meta-heuristic feature selection algorithms. To achieve this, experiments are conducted on the Cleveland heart disease dataset and the heart failure dataset collected from the Faisalabad Institute of Cardiology published at UCI. CS, FPA, WOA, and HHO algorithms for feature selection are applied for different population sizes and are realized based on the best fitness values. For the original dataset of heart disease, the maximum prediction F-score of 88% is obtained using K-nearest neighbour (KNN) when compared to logistic regression (LR), support vector machine (SVM), Gaussian Naive Bayes (GNB), and random forest (RF). With the proposed approach, the heart disease prediction F-score of 99.72% is obtained using KNN for population sizes 60 with FPA by selecting eight features. For the original dataset of heart failure, the maximum prediction F-score of 70% is obtained using LR and RF compared to SVM, GNB, and KNN. With the proposed approach, the heart failure prediction F-score of 97.45% is obtained using KNN for population sizes 10 with HHO by selecting five features. Experimental findings show that the applied meta-heuristic algorithms with ML algorithms significantly improve prediction performances compared to performances obtained from the original datasets. The motivation of this paper is to select the most critical and informative feature subset through meta-heuristic algorithms to improve classification accuracy.

Deep Learning-driven classification of external DICOM studies for PACS archiving

OBJECTIVES

Over the course of their treatment, patients often switch hospitals, requiring staff at the new hospital to import external imaging studies to their local database. In this study, the authors present MOdality Mapping and Orchestration (MOMO), a Deep Learning-based approach to automate this mapping process by combining metadata analysis and a neural network ensemble.

METHODS

A set of 11,934 imaging series with existing anatomical labels was retrieved from the PACS database of the local hospital to train an ensemble of neural networks (DenseNet-161 and ResNet-152), which process radiological images and predict the type of study they belong to. We developed an algorithm that automatically extracts relevant metadata from imaging studies, regardless of their structure, and combines it with the neural network ensemble, forming a powerful classifier. A set of 843 anonymized external studies from 321 hospitals was hand-labeled to assess performance. We tested several variations of this algorithm.

RESULTS

MOMO achieves 92.71% accuracy and 2.63% minor errors (at 99.29% predictive power) on the external study classification task, outperforming both a commercial product (82.86% accuracy, 1.36% minor errors, 96.20% predictive power) and a pure neural network ensemble (72.69% accuracy, 10.3% minor errors, 99.05% predictive power) performing the same task. We find that the highest performance is achieved by an algorithm that combines all information into one vote-based classifier.

CONCLUSION

Deep Learning combined with metadata matching is a promising and flexible approach for the automated classification of external DICOM studies for PACS archiving.

KEY POINTS

• The algorithm can successfully identify 76 medical study types across seven modalities (CT, X-ray angiography, radiographs, MRI, PET (+CT/MRI), ultrasound, and mammograms). • The algorithm outperforms a commercial product performing the same task by a significant margin (> 9% accuracy gain). • The performance of the algorithm increases through the application of Deep Learning techniques.

Toward Generalizability in the Deployment of Artificial Intelligence in Radiology: Role of Computation Stress Testing to Overcome Underspecification

The clinical deployment of artificial intelligence (AI) applications in medical imaging is perhaps the greatest challenge facing radiology in the next decade. One of the main obstacles to the incorporation of automated AI-based decision-making tools in medicine is the failure of models to generalize when deployed across institutions with heterogeneous populations and imaging protocols. The most well-understood pitfall in developing these AI models is overfitting, which has, in part, been overcome by optimizing training protocols. However, overfitting is not the only obstacle to the success and generalizability of AI. Underspecification is also a serious impediment that requires conceptual understanding and correction. It is well known that a single AI pipeline, with prescribed training and testing sets, can produce several models with various levels of generalizability. Underspecification defines the inability of the pipeline to identify whether these models have embedded the structure of the underlying system by using a test set independent of, but distributed identically, to the training set. An underspecified pipeline is unable to assess the degree to which the models will be generalizable. Stress testing is a known tool in AI that can limit underspecification and, importantly, assure broad generalizability of AI models. However, the application of stress tests is new in radiologic applications. This report describes the concept of underspecification from a radiologist perspective, discusses stress testing as a specific strategy to overcome underspecification, and explains how stress tests could be designed in radiology-by modifying medical images or stratifying testing datasets. In the upcoming years, stress tests should become in radiology the standard that crash tests have become in the automotive industry. Keywords: Computer Applications-General, Informatics, Computer-aided Diagnosis © RSNA, 2021.

Applying artificial intelligence for cancer immunotherapy

Artificial intelligence (AI) is a general term that refers to the use of a machine to imitate intelligent behavior for performing complex tasks with minimal human intervention, such as machine learning; this technology is revolutionizing and reshaping medicine. AI has considerable potential to perfect health-care systems in areas such as diagnostics, risk analysis, health information administration, lifestyle supervision, and virtual health assistance. In terms of immunotherapy, AI has been applied to the prediction of immunotherapy responses based on immune signatures, medical imaging and histological analysis. These features could also be highly useful in the management of cancer immunotherapy given their ever-increasing performance in improving diagnostic accuracy, optimizing treatment planning, predicting outcomes of care and reducing human resource costs. In this review, we present the details of AI and the current progression and state of the art in employing AI for cancer immunotherapy. Furthermore, we discuss the challenges, opportunities and corresponding strategies in applying the technology for widespread clinical deployment. Finally, we summarize the impact of AI on cancer immunotherapy and provide our perspectives about underlying applications of AI in the future.