A multitarget training method for artificial neural network with application to computer-aided diagnosis.
Ontology highlight
ABSTRACT:
SUBMITTER: Liu B
PROVIDER: S-EPMC3543375 | biostudies-other | 2013 Jan
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Training deep Convolutional Neural Networks (CNNs) presents challenges in terms of memory requirements and computational resources, often resulting in issues such as model overfitting and lack of generalization. These challenges can only be mitigated by using an excessive number of training images. However, medical image datasets commonly suffer from data scarcity due to the complexities involved in their acquisition, preparation, and curation. To address this issue, we propose a compact and hybrid machine learning architecture based on the Morphological and Convolutional Neural Network (MCNN), followed by a Random Forest classifier. Unlike deep CNN architectures, the MCNN was specifically designed to achieve effective performance with medical image datasets limited to a few hundred samples. It incorporates various morphological operations into a single layer and uses independent neural networks to extract information from each signal channel. The final classification is obtained by utilizing a Random Forest classifier on the outputs of the last neural network layer. We compare the classification performance of our proposed method with three popular deep CNN architectures (ResNet-18, ShuffleNet-V2, and MobileNet-V2) using two training approaches: full training and transfer learning. The evaluation was conducted on two distinct medical image datasets: the ISIC dataset for melanoma classification and the ORIGA dataset for glaucoma classification. Results demonstrate that the MCNN method exhibits reliable performance in melanoma classification, achieving an AUC of 0.94 (95% CI: 0.91 to 0.97), outperforming the popular CNN architectures. For the glaucoma dataset, the MCNN achieved an AUC of 0.65 (95% CI: 0.53 to 0.74), which was similar to the performance of the popular CNN architectures. This study contributes to the understanding of mathematical morphology in shallow neural networks for medical image classification and highlights the potential of hybrid architectures in effectively learning from medical image datasets that are limited by a small number of case samples.
| S-EPMC10546173 | biostudies-literature
Project description:The current multiphase, invitro study developed and validated a 3-dimensional convolutional neural network (3D-CNN) to generate partial dental crowns (PDC) for use in restorative dentistry. The effectiveness of desktop laser and intraoral scanners in generating data for the purpose of 3D-CNN was first evaluated (phase 1). There were no significant differences in surface area [t-stat(df) = - 0.01 (10), mean difference = - 0.058, P > 0.99] and volume [t-stat(df) = 0.357(10)]. However, the intraoral scans were chosen for phase 2 as they produced a greater level of volumetric details (343.83 ± 43.52 mm3) compared to desktop laser scanning (322.70 ± 40.15 mm3). In phase 2, 120 tooth preparations were digitally synthesized from intraoral scans, and two clinicians designed the respective PDCs using computer-aided design (CAD) workflows on a personal computer setup. Statistical comparison by 3-factor ANOVA demonstrated significant differences in surface area (P < 0.001), volume (P < 0.001), and spatial overlap (P < 0.001), and therefore only the most accurate PDCs (n = 30) were picked to train the neural network (Phase 3). The current 3D-CNN produced a validation accuracy of 60%, validation loss of 0.68-0.87, sensitivity of 1.00, precision of 0.50-0.83, and serves as a proof-of-concept that 3D-CNN can predict and generate PDC prostheses in CAD for restorative dentistry.
| S-EPMC9884213 | biostudies-literature
Project description:Introduction Chronic lymphocytic leukemia (CLL) is one of the most common types of leukemia, and the early diagnosis of patients coincides with their proper treatment and survival. If patients are diagnosed late or proper treatment is not applied, it may lead to harmful results. Several methods could be used for the diagnosis of leukemia; some of these include complete blood count (CBC), immunophenotyping, lymph node biopsy, chest X-ray, computerized tomography (CT) scan, and ultrasound. Most of these methods are time-consuming and an application of more than one method will result as intended. This acknowledgment stresses the necessity of rapid and proper diagnosis for leukemia based on clinical and medical findings, inasmuch as it was decided to apply the artificial neural network (ANN) in order to identify a molecular biomarker for rapid leukemia diagnosis from blood samples and evaluate its potential for the detection of cancer. Materials & methods The independent sample t-test was applied with the Statistical Package for the Social Sciences (SPSS; IBM Corp, Armonk, NY, US) software on the microarray gene expression data of Gene Expression Omnibus (GEO) datasets (GSE22529); 12 genes that had shown the highest differences (among parameters whose p-value was less than 0.01) were selected for further ANN analysis. The selected genes of 53 patients were applied to the training network algorithm, with a learning rate of 0.1. Results The results showed a high accuracy of the relationship between the output of the trained network and the test data. The area under the receiver operating characteristic (ROC) curve was 0.991, which provides proof of the precision and the relationship with identifying Gelsolin as a potential biomarker for this research. Conclusions With these results, it was concluded that the training process of the ANN could be applied to rapid CLL diagnosis and finding a potential biomarker. Besides, it is suggested that this method could be performed to diagnose other forms of cancer in order to get a rapid and reliable outcome.
| S-EPMC6450593 | biostudies-literature
Project description:Background and Purpose- Computed tomography perfusion (CTP) is a useful tool in the evaluation of acute ischemic stroke, where it can provide an estimate of the ischemic core and the ischemic penumbra. The optimal CTP parameters to identify the ischemic core remain undetermined. Methods- We used artificial neural networks (ANNs) to optimally predict the ischemic core in acute stroke patients, using diffusion-weighted imaging as the gold standard. We first designed an ANN based on CTP data alone and next designed an ANN based on clinical and CTP data. Results- The ANN based on CTP data predicted the ischemic core with a mean absolute error of 13.8 mL (SD, 13.6 mL) compared with diffusion-weighted imaging. The area under the receiver operator characteristic curve was 0.85. At the optimal threshold, the sensitivity for predicting the ischemic core was 0.90 and the specificity was 0.62. Combining CTP data with clinical data available at time of presentation resulted in the same mean absolute error (13.8 mL) but lower SD (12.4 mL). The area under the curve, sensitivity, and specificity were 0.87, 0.91, and 0.65, respectively. The maximal Dice coefficient was 0.48 in the ANN based on CTP data exclusively. Conclusions- An ANN that integrates clinical and CTP data predicts the ischemic core with accuracy.
| S-EPMC6538437 | biostudies-literature
Project description:BackgroundThe early diagnosis of colorectal cancer (CRC) is associated with improved survival rates, and development of novel non-invasive, sensitive, and specific diagnostic tests is highly demanded. The objective of this paper was to identify commonly circulating microRNA (miRNA) biomarkers for use in CRC diagnosis.MethodsAn artificial neural network (ANN) model was proposed in this work. Among miRNAs retrieved from the Gene Expression Omnibus dataset, four miRNAs with the best miRNA score were selected by ANN units.ResultsThe simulation results showed that the designed ANN model could accurately classify the sample data into cancerous or non-cancerous. Furthermore, based on the results of evaluated ANN model, the area under the ROC curve (AUC) of the designed ANN model as well as the regression coefficient between the output of the ANN and the expected output was one. The confusion matrix of the ANN model indicated that all non-cancerous patients were predicted as normal, and the cancerous patients as cancerous.ConclusionOur findings suggest that the improved model can be used as a robust prediction toolbox for cancer diagnosis. In conclusion, by using ANN, circulatory miRNAs can be used as a non-invasive, sensitive and specific diagnostic marker.
| S-EPMC6462295 | biostudies-literature
Project description:Arrhythmias can pose a significant threat to cardiac health, potentially leading to serious consequences such as stroke, heart failure, cardiac arrest, shock, and sudden death. In computer-aided electrocardiogram interpretation systems, the inclusion of certain classes of arrhythmias, which we term "aggressive" or "bullying," can lead to the underdiagnosis of other "vulnerable" classes. To address this issue, a method for arrhythmia diagnosis is proposed in this study. This method combines morphological-characteristic-based waveform clustering with Bayesian theory, drawing inspiration from the diagnostic reasoning of experienced cardiologists. The proposed method achieved optimal performance in macro-recall and macro-precision through hyperparameter optimization, including spliced heartbeats and clusters. In addition, with increasing bullying by aggressive arrhythmias, our model obtained the highest average recall and the lowest average drop in recall on the nine vulnerable arrhythmias. Furthermore, the maximum cluster characteristics were found to be consistent with established arrhythmia diagnostic criteria, lending interpretability to the proposed method.
| S-EPMC10499877 | biostudies-literature
Project description:ObjectiveOur aim was to propose a preoperative computer-aided diagnosis scheme to differentiate pancreatic serous cystic neoplasms from other pancreatic cystic neoplasms, providing supportive opinions for clinicians and avoiding overtreatment.Materials and methodsIn this retrospective study, 260 patients with pancreatic cystic neoplasm were included. Each patient underwent a multidetector row computed tomography scan and pancreatic resection. In all, 200 patients constituted a cross-validation cohort, and 60 patients formed an independent validation cohort. Demographic information, clinical information, and multidetector row computed tomography images were obtained from Picture Archiving and Communication Systems. The peripheral margin of each neoplasm was manually outlined by experienced radiologists. A radiomics system containing 24 guideline-based features and 385 radiomics high-throughput features was designed. After the feature extraction, least absolute shrinkage selection operator regression was used to select the most important features. A support vector machine classifier with 5-fold cross-validation was applied to build the diagnostic model. The independent validation cohort was used to validate the performance.ResultsOnly 31 of 102 serous cystic neoplasm cases in this study were recognized correctly by clinicians before the surgery. Twenty-two features were selected from the radiomics system after 100 bootstrapping repetitions of the least absolute shrinkage selection operator regression. The diagnostic scheme performed accurately and robustly, showing the area under the receiver operating characteristic curve = 0.767, sensitivity = 0.686, and specificity = 0.709. In the independent validation cohort, we acquired similar results with receiver operating characteristic curve = 0.837, sensitivity = 0.667, and specificity = 0.818.ConclusionThe proposed radiomics-based computer-aided diagnosis scheme could increase preoperative diagnostic accuracy and assist clinicians in making accurate management decisions.
| S-EPMC6374001 | biostudies-literature
Project description:Generally, the decision rule for classifying unstructured data in an artificial neural network system depends on the sequence results of an activation function determined by vector-matrix multiplication between the input bias signal and the analog synaptic weight quantity of each node in a matrix array. Although a sequence-based decision rule can efficiently extract a common feature in a large data set in a short time, it can occasionally fail to classify similar species because it does not intrinsically consider other quantitative configurations of the activation function that affect the synaptic weight update. In this work, we implemented a simple run-off election-based decision rule via an additional filter evaluation to mitigate the confusion from proximity of output activation functions, enabling the improved training and inference performance of artificial neural network system. Using the filter evaluation selected via the difference among common features of classified images, the recognition accuracy achieved for three types of shoe image data sets reached ~ 82.03%, outperforming the maximum accuracy of ~ 79.23% obtained via the sequence-based decision rule in a fully connected single layer network. This training algorithm with an independent filter can precisely supply the output class in the decision step of the fully connected network.
| S-EPMC7806707 | biostudies-literature
Project description:The digitalization of clinical workflows and the increasing performance of deep learning algorithms are paving the way towards new methods for tackling cancer diagnosis. However, the availability of medical specialists to annotate digitized images and free-text diagnostic reports does not scale with the need for large datasets required to train robust computer-aided diagnosis methods that can target the high variability of clinical cases and data produced. This work proposes and evaluates an approach to eliminate the need for manual annotations to train computer-aided diagnosis tools in digital pathology. The approach includes two components, to automatically extract semantically meaningful concepts from diagnostic reports and use them as weak labels to train convolutional neural networks (CNNs) for histopathology diagnosis. The approach is trained (through 10-fold cross-validation) on 3'769 clinical images and reports, provided by two hospitals and tested on over 11'000 images from private and publicly available datasets. The CNN, trained with automatically generated labels, is compared with the same architecture trained with manual labels. Results show that combining text analysis and end-to-end deep neural networks allows building computer-aided diagnosis tools that reach solid performance (micro-accuracy = 0.908 at image-level) based only on existing clinical data without the need for manual annotations.
| S-EPMC9307641 | biostudies-literature
Project description:BackgroundComputer-aided diagnosis (CAD) systems can help reduce radiologists' workload. This study assessed the value of a CAD system for the detection of lung nodules on chest computed tomography (CT) images.MethodsThe study retrospectively analyzed the CT images of patients who underwent routine health checkups between August 2019 and November 2019 at 3 hospitals in China. All images were first assessed by 2 radiologists manually in a blinded manner, which was followed by assessment with the CAD system. The location and classification of the lung nodules were determined. The final diagnosis was made by a panel of experts, including 2 associate chief radiologists and 1 chief radiologist at the radiology department. The sensitivity for nodule detection and false-positive nodules per case were calculated.ResultsA total of 1,002 CT images were included in the study, and the process was completed for 999 images. The sensitivity of the CAD system and manual detection was 90.19% and 49.88% (P<0.001), respectively. Similar sensitivity was observed between manual detection and the CAD system in lung nodules >15 mm (P=0.08). The false-positive nodules per case for the CAD system were 0.30±0.84 and those for manual detection were 0.24±0.68 (P=0.12). The sensitivity of the CAD system was higher than that of the radiologists, but the increase in the false-positive rate was only slight.ConclusionsIn addition to reducing the workload for medical professionals, a CAD system developed using a deep-learning model was highly effective and accurate in detecting lung nodules and did not demonstrate a meaningfully higher the false-positive rate.
| S-EPMC10585542 | biostudies-literature