Performance analysis of texture characterization techniques for lung nodule classification

Lung cancer ranks very high on a global index for cancer-related casualties. With early detection of lung cancer, the rate of survival increases to 80-90%. The standard method for diagnosing lung cancer from Computed Tomography (CT) scans is by manual annotation and detection of the cancerous regions, which is a tedious task for radiologists. This paper proposes a machine learning approach for multi-class classification of the lung nodules into solid, semi-solid, and Ground Glass Object texture classes. We employ feature extraction techniques, such as gray-level co-occurrence matrix, Gabor filters, and local binary pattern, and validate the performance on the LNDb dataset. The best performing classifier displays an accuracy of 94% and an F1-score of 0.92. The proposed approach was compared with related work using the same dataset. The results are promising, and the proposed method can be used to diagnose lung cancer accurately.

Novel loss functions for ensemble-based medical image classification

Medical images commonly exhibit multiple abnormalities. Predicting them requires multi-class classifiers whose training and desired reliable performance can be affected by a combination of factors, such as, dataset size, data source, distribution, and the loss function used to train deep neural networks. Currently, the cross-entropy loss remains the de-facto loss function for training deep learning classifiers. This loss function, however, asserts equal learning from all classes, leading to a bias toward the majority class. Although the choice of the loss function impacts model performance, to the best of our knowledge, we observed that no literature exists that performs a comprehensive analysis and selection of an appropriate loss function toward the classification task under study. In this work, we benchmark various state-of-the-art loss functions, critically analyze model performance, and propose improved loss functions for a multi-class classification task. We select a pediatric chest X-ray (CXR) dataset that includes images with no abnormality (normal), and those exhibiting manifestations consistent with bacterial and viral pneumonia. We construct prediction-level and model-level ensembles to improve classification performance. Our results show that compared to the individual models and the state-of-the-art literature, the weighted averaging of the predictions for top-3 and top-5 model-level ensembles delivered significantly superior classification performance (p < 0.05) in terms of MCC (0.9068, 95% confidence interval (0.8839, 0.9297)) metric. Finally, we performed localization studies to interpret model behavior and confirm that the individual models and ensembles learned task-specific features and highlighted disease-specific regions of interest. The code is available at https://github.com/sivaramakrishnan-rajaraman/multiloss_ensemble_models.

The SAMME.C2 Algorithm for Severely Imbalanced Multi-class Classification

Classification predictive modeling involves the accurate assignment of observations in a dataset to target classes or categories. There is an increasing growth of real-world classification problems with severely imbalanced class distributions. In this case, minority classes have much fewer observations to learn from than those from majority classes. Despite this sparsity, a minority class is often considered the more interesting class yet developing a scientific learning algorithm suitable for the observations presents countless challenges. In this article, we suggest a novel multi-class classification algorithm specialized to handle severely imbalanced classes based on the method we refer to as SAMME.C2. It blends the flexible mechanics of the boosting techniques from SAMME algorithm, a multi-class classifier, and Ada.C2 algorithm, a cost-sensitive binary classifier designed to address highly class imbalances. Not only do we provide the resulting algorithm but we also establish scientific and statistical formulation of our proposed SAMME.C2 algorithm. Through numerical experiments examining various degrees of classifier difficulty, we demonstrate consistent superior performance of our proposed model.

AI_COVID: AUTOMATIC DIAGNOSIS OF COVID-19 USING FRONTAL CHEST X-RAY IMAGE

With the continued growth of confirmed cases of COVID-19, a highly infectious disease caused by a newly discovered coronavirus called Severe Acute Respiratory Syndrome Coronavirus 2, or SARS-CoV-2, there is an urgent need to find ways to help clinicians fight the virus by reducing the workload and speeding up the diagnosis of COVID-19. In this work, we propose an artificial intelligence solution “AI_COVID” which can help radiologists to know if the lungs are infected with the virus in just a few seconds.AI_COVID is based on a pre-trained DenseNet-121 model that detects subtle changes in the lungs and an SVM classifier that decides whether these changes are caused by COVID-19 or other diseases. AI_COVID is trained on thousands of frontal chest x-rays of people who have contracted COVID-19, healthy people, and people with viral or bacterial pneumonia. The experimental study is tested on 781 chest x-rays from two publicly available chest x-ray datasets COVID-19 radiography database and COVIDx Dataset. The performance results showed that our proposed model (DenseNet-121 + SVM) demonstrated high performance and yielded excellent results compared to the current methods in the literature, with a total accuracy of 99.74% and 98.85% for binary classification (COVID-19 vs. No COVID-19) and multi-class classification (COVID-19 vs. Normal vs. Pneumonia), respectively.

Automated detection of skeletal metastasis of lung cancer with bone scans using convolutional nuclear network

Bone scan is widely used for surveying bone metastases caused by various solid tumors. Scintigraphic images are characterized by inferior spatial resolution, bringing a significant challenge to manual analysis of images by nuclear medicine physicians. We present in this work a new framework for automatically classifying scintigraphic images collected from patients clinically diagnosed with lung cancer. The framework consists of data preparation and image classification. In the data preparation stage, data augmentation is used to enlarge the dataset, followed by image fusion and thoracic region extraction. In the image classification stage, we use a self-defined convolutional neural network consisting of feature extraction, feature aggregation, and feature classification sub-networks. The developed multi-class classification network can not only predict whether a bone scan image contains bone metastasis but also tell which subcategory of lung cancer that a bone metastasis metastasized from is present in the image. Experimental evaluations on a set of clinical bone scan images have shown that the proposed multi-class classification network is workable for automated classification of metastatic images, with achieving average scores of 0.7392, 0.7592, 0.7242, and 0.7292 for accuracy, precision, recall, and F-1 score, respectively.