A new method for pulmonary nodule detection using decision trees

Automated lung cancer diagnosis using three-dimensional convolutional neural networks

Lung cancer is the deadliest cancer worldwide. It has been shown that early detection using low-dose computer tomography (LDCT) scans can reduce deaths caused by this disease. We present a general framework for the detection of lung cancer in chest LDCT images. Our method consists of a nodule detector trained on the LIDC-IDRI dataset followed by a cancer predictor trained on the Kaggle DSB 2017 dataset and evaluated on the IEEE International Symposium on Biomedical Imaging (ISBI) 2018 Lung Nodule Malignancy Prediction test set. Our candidate extraction approach is effective to produce accurate candidates with a recall of 99.6%. In addition, our false positive reduction stage classifies successfully the candidates and increases precision by a factor of 2000. Our cancer predictor obtained a ROC AUC of 0.913 and was ranked 1st place at the ISBI 2018 Lung Nodule Malignancy Prediction challenge. Graphical abstract.

Predicting Unnecessary Nodule Biopsies from a Small, Unbalanced, and Pathologically Proven Dataset by Transfer Learning

This study explores an automatic diagnosis method to predict unnecessary nodule biopsy from a small, unbalanced, and pathologically proven database. The automatic diagnosis method is based on a convolutional neural network (CNN) model. Because of the small and unbalanced samples, the presented method aims to improve the transfer learning capability via the VGG16 architecture and optimize the related transfer learning parameters. For comparison purpose, a traditional machine learning method is implemented, which extracts the texture features and classifies the features by support vector machine (SVM). The database includes 68 biopsied nodules, 16 are pathologically proven benign and the remaining 52 are malignant. To consider the volumetric data by the CNN model, each image slice from each nodule volume is selected randomly until all image slices of each nodule are utilized. The leave-one-out and 10-folder cross validations are applied to train and test the randomly selected 68 image slices (one image slice from one nodule) in each experiment, respectively. The averages over all the experimental outcomes are the final results. The experiments revealed that the features from both the medical and the natural images share the similarity of focusing on simpler and less-abstract objects, leading to the conclusion that not the more the transfer convolutional layers, the better the classification results. Transfer learning from other larger datasets can supply additional information to small and unbalanced datasets to improve the classification performance. The presented method has shown the potential to adapt CNN architecture to improve the prediction of unnecessary nodule biopsy from small, unbalanced, and pathologically proven volumetric dataset.

PISIoT: A Machine Learning and IoT-Based Smart Health Platform for Overweight and Obesity Control

Overweight and obesity are affecting productivity and quality of life worldwide. The Internet of Things (IoT) makes it possible to interconnect, detect, identify, and process data between objects or services to fulfill a common objective. The main advantages of IoT in healthcare are the monitoring, analysis, diagnosis, and control of conditions such as overweight and obesity and the generation of recommendations to prevent them. However, the objects used in the IoT have limited resources, so it has become necessary to consider other alternatives to analyze the data generated from monitoring, analysis, diagnosis, control, and the generation of recommendations, such as machine learning. This work presents PISIoT: a machine learning and IoT-based smart health platform for the prevention, detection, treatment, and control of overweight and obesity, and other associated conditions or health problems. Weka API and the J48 machine learning algorithm were used to identify critical variables and classify patients, while Apache Mahout and RuleML were used to generate medical recommendations. Finally, to validate the PISIoT platform, we present a case study on the prevention of myocardial infarction in elderly patients with obesity by monitoring biomedical variables.

Gastric precancerous diseases classification using CNN with a concise model

Gastric precancerous diseases (GPD) may deteriorate into early gastric cancer if misdiagnosed, so it is important to help doctors recognize GPD accurately and quickly. In this paper, we realize the classification of 3-class GPD, namely, polyp, erosion, and ulcer using convolutional neural networks (CNN) with a concise model called the Gastric Precancerous Disease Network (GPDNet). GPDNet introduces fire modules from SqueezeNet to reduce the model size and parameters about 10 times while improving speed for quick classification. To maintain classification accuracy with fewer parameters, we propose an innovative method called iterative reinforced learning (IRL). After training GPDNet from scratch, we apply IRL to fine-tune the parameters whose values are close to 0, and then we take the modified model as a pretrained model for the next training. The result shows that IRL can improve the accuracy about 9% after 6 iterations. The final classification accuracy of our GPDNet was 88.90%, which is promising for clinical GPD recognition.

Development and Evaluation of an Educational E-Tool to Help Patients With Non-Hodgkin's Lymphoma Manage Their Personal Care Pathway

BACKGROUND

An overload of health-related information is available for patients on numerous websites, guidelines, and information leaflets. However, the increasing need for personalized health-related information is currently unmet.

OBJECTIVE

This study evaluates an educational e-tool for patients with non-Hodgkin's lymphoma (NHL) designed to meet patient needs with respect to personalized and complete health-related information provision. The e-tool aims to help NHL patients manage and understand their personal care pathway, by providing them with insight into their own care pathway, the possibility to keep a diary, and structured health-related information.

METHODS

Together with a multidisciplinary NHL expert panel, we developed an e-tool consisting of two sections: (1) a personal section for patients' own care pathway and their experiences, and (2) an informative section including information on NHL. We developed an ideal NHL care pathway based on the available (inter)national guidelines. The ideal care pathway, including date of first consultation, diagnosis, and therapy start, was used to set up the personal care pathway. The informative section was developed in collaboration with the patient association, Hematon. Regarding participants, 14 patients and 6 laymen were asked to evaluate the e-tool. The 24-item questionnaire used discussed issues concerning layout (6 questions), user convenience (3 questions), menu clarity (3 questions), information clarity (5 questions), and general impression (7 questions). In addition, the panel members were asked to give their feedback by email.

RESULTS

A comprehensive overview of diagnostics, treatments, and aftercare can be established by patients completing the questions from the personal section. The informative section consisted of NHL information regarding NHL in general, diagnostics, therapy, aftercare, and waiting times. Regarding participants, 6 patients and 6 laymen completed the questionnaire. Overall, the feedback was positive, with at least 75% satisfaction on each feedback item. Important strengths mentioned were the use of a low health-literacy level, the opportunity to document the personal care pathway and experiences, and the clear overview of the information provided. The added value of the e-tool in general was pointed out as very useful for preparing the consultation with one's doctor and for providing all information on one website, including the opportunity for a personalized care pathway and diary. The majority of the revisions concerned wording and clarity. In addition, more explicit information on immunotherapy, experimental therapy, and psychosocial support was added.

CONCLUSIONS

We have developed a personal care management e-tool for NHL patients. This tool contains a unique way to help patients manage their personal care pathway and give them insight into their NHL by providing health-related information and a personal diary. This evaluation showed that our e-tool meets patients' needs concerning personalized health-related information, which might serve as a good example for other oncologic diseases. Future research should focus on the possible impact of the e-tool on doctor-patient communication during consultations.

Ant colony optimization approaches to clustering of lung nodules from CT images

Lung cancer is becoming a threat to mankind. Applying machine learning algorithms for detection and segmentation of irregular shaped lung nodules remains a remarkable milestone in CT scan image analysis research. In this paper, we apply ACO algorithm for lung nodule detection. We have compared the performance against three other algorithms, namely, Otsu algorithm, watershed algorithm, and global region based segmentation. In addition, we suggest a novel approach which involves variations of ACO, namely, refined ACO, logical ACO, and variant ACO. Variant ACO shows better reduction in false positives. In addition we propose black circular neighborhood approach to detect nodule centers from the edge detected image. Genetic algorithm based clustering is performed to cluster the nodules based on intensity, shape, and size. The performance of the overall approach is compared with hierarchical clustering to establish the improvisation in the proposed approach.