Differentiation of thyroid nodules on US using features learned and extracted from various convolutional neural networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Lee E
PROVIDER: S-EPMC6934479 | biostudies-literature | 2019 Dec
REPOSITORIES: biostudies-literature
Publications
Differentiation of thyroid nodules on US using features learned and extracted from various convolutional neural networks.
Lee Eunjung E Ha Heonkyu H Kim Hye Jung HJ Moon Hee Jung HJ Byon Jung Hee JH Huh Sun S Son Jinwoo J Yoon Jiyoung J Han Kyunghwa K Kwak Jin Young JY
Scientific reports 20191227 1
Thyroid nodules are a common clinical problem. Ultrasonography (US) is the main tool used to sensitively diagnose thyroid cancer. Although US is non-invasive and can accurately differentiate benign and malignant thyroid nodules, it is subjective and its results inevitably lack reproducibility. Therefore, to provide objective and reliable information for US assessment, we developed a CADx system that utilizes convolutional neural networks and the machine learning technique. The diagnostic perform ...[more]
Similar Datasets
Project description:The tumor-stroma ratio (TSR) reflected on hematoxylin and eosin (H&E)-stained histological images is a potential prognostic factor for survival. Automatic image processing techniques that allow for high-throughput and precise discrimination of tumor epithelium and stroma are required to elevate the prognostic significance of the TSR. As a variant of deep learning techniques, transfer learning leverages nature-images features learned by deep convolutional neural networks (CNNs) to relieve the requirement of deep CNNs for immense sample size when handling biomedical classification problems. Herein we studied different transfer learning strategies for accurately distinguishing epithelial and stromal regions of H&E-stained histological images acquired from either breast or ovarian cancer tissue. We compared the performance of important deep CNNs as either a feature extractor or as an architecture for fine-tuning with target images. Moreover, we addressed the current contradictory issue about whether the higher-level features would generalize worse than lower-level ones because they are more specific to the source-image domain. Under our experimental setting, the transfer learning approach achieved an accuracy of 90.2 (vs. 91.1 for fine tuning) with GoogLeNet, suggesting the feasibility of using it in assisting pathology-based binary classification problems. Our results also show that the superiority of the lower-level or the higher-level features over the other ones was determined by the architecture of deep CNNs.
| S-EPMC6286645 | biostudies-literature
Project description:Objective:The incidence of superficial organ diseases has increased rapidly in recent years. New methods such as computer-aided diagnosis (CAD) are widely used to improve diagnostic efficiency. Convolutional neural networks (CNNs) are one of the most popular methods, and further improvements of CNNs should be considered. This paper aims to develop a multiorgan CAD system based on CNNs for classifying both thyroid and breast nodules and investigate the impact of this system on the diagnostic efficiency of different preprocessing approaches. Methods:The training and validation sets comprised randomly selected thyroid and breast nodule images. The data were subgrouped into 4 models according to the different preprocessing methods (depending on segmentation and the classification method). A prospective data set was selected to verify the clinical value of the CNN model by comparison with ultrasound guidelines. Diagnostic efficiency was assessed based on receiver operating characteristic (ROC) curves. Results:Among the 4 models, the CNN model using segmented images for classification achieved the best result. For the validation set, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and area under the curve (AUC) of our CNN model were 84.9%, 69.0%, 62.5%, 88.2%, 75.0%, and 0.769, respectively. There was no statistically significant difference between the CNN model and the ultrasound guidelines. The combination of the two methods achieved superior diagnostic efficiency compared with their use individually. Conclusions:The study demonstrates the probability, feasibility, and clinical value of CAD in the ultrasound diagnosis of multiple organs. The use of segmented images and classification by the nature of the disease are the main factors responsible for the improvement of the CNN model. Moreover, the combination of the CNN model and ultrasound guidelines results in better diagnostic performance, which will contribute to the improved diagnostic efficiency of CAD systems.
| S-EPMC7199615 | biostudies-literature
Project description:The purpose of this study was to evaluate and compare the diagnostic performances of the deep convolutional neural network (CNN) and expert radiologists for differentiating thyroid nodules on ultrasonography (US), and to validate the results in multicenter data sets. This multicenter retrospective study collected 15,375 US images of thyroid nodules for algorithm development (n = 13,560, Severance Hospital, SH training set), the internal test (n = 634, SH test set), and the external test (n = 781, Samsung Medical Center, SMC set; n = 200, CHA Bundang Medical Center, CBMC set; n = 200, Kyung Hee University Hospital, KUH set). Two individual CNNs and two classification ensembles (CNNE1 and CNNE2) were tested to differentiate malignant and benign thyroid nodules. CNNs demonstrated high area under the curves (AUCs) to diagnose malignant thyroid nodules (0.898-0.937 for the internal test set and 0.821-0.885 for the external test sets). AUC was significantly higher for CNNE2 than radiologists in the SH test set (0.932 vs. 0.840, P < 0.001). AUC was not significantly different between CNNE2 and radiologists in the external test sets (P = 0.113, 0.126, and 0.690). CNN showed diagnostic performances comparable to expert radiologists for differentiating thyroid nodules on US in both the internal and external test sets.
| S-EPMC7498581 | biostudies-literature
Project description:Computer-aided diagnosis (CAD) systems hold potential to improve the diagnostic accuracy of thyroid ultrasound (US). We aimed to develop a deep learning-based US CAD system (dCAD) for the diagnosis of thyroid nodules and compare its performance with those of a support vector machine (SVM)-based US CAD system (sCAD) and radiologists. dCAD was developed by using US images of 4919 thyroid nodules from three institutions. Its diagnostic performance was prospectively evaluated between June 2016 and February 2017 in 286 nodules, and was compared with those of sCAD and radiologists, using logistic regression with the generalized estimating equation. Subgroup analyses were performed according to experience level and separately for small thyroid nodules 1-2?cm. There was no difference in overall sensitivity, specificity, positive predictive value (PPV), negative predictive value and accuracy (all p?>?0.05) between radiologists and dCAD. Radiologists and dCAD showed higher specificity, PPV, and accuracy than sCAD (all p?<?0.001). In small nodules, experienced radiologists showed higher specificity, PPV and accuracy than sCAD (all p?<?0.05). In conclusion, dCAD showed overall comparable diagnostic performance with radiologists and assessed thyroid nodules more effectively than sCAD, without loss of sensitivity.
| S-EPMC6882804 | biostudies-literature
Project description:We have developed a deep learning-based computer algorithm to recognize and predict retinal differentiation in stem cell-derived organoids based on bright-field imaging. The three-dimensional "organoid" approach for the differentiation of pluripotent stem cells (PSC) into retinal and other neural tissues has become a major in vitro strategy to recapitulate development. We decided to develop a universal, robust, and non-invasive method to assess retinal differentiation that would not require chemical probes or reporter gene expression. We hypothesized that basic-contrast bright-field (BF) images contain sufficient information on tissue specification, and it is possible to extract this data using convolutional neural networks (CNNs). Retina-specific Rx-green fluorescent protein mouse embryonic reporter stem cells have been used for all of the differentiation experiments in this work. The BF images of organoids have been taken on day 5 and fluorescent on day 9. To train the CNN, we utilized a transfer learning approach: ImageNet pre-trained ResNet50v2, VGG19, Xception, and DenseNet121 CNNs had been trained on labeled BF images of the organoids, divided into two categories (retina and non-retina), based on the fluorescent reporter gene expression. The best-performing classifier with ResNet50v2 architecture showed a receiver operating characteristic-area under the curve score of 0.91 on a test dataset. A comparison of the best-performing CNN with the human-based classifier showed that the CNN algorithm performs better than the expert in predicting organoid fate (84% vs. 67 ± 6% of correct predictions, respectively), confirming our original hypothesis. Overall, we have demonstrated that the computer algorithm can successfully recognize and predict retinal differentiation in organoids before the onset of reporter gene expression. This is the first demonstration of CNN's ability to classify stem cell-derived tissue in vitro.
| S-EPMC7350982 | biostudies-literature
Project description:Computer aided diagnosis systems based on brain imaging are an important tool to assist in the diagnosis of Parkinson's disease, whose ultimate goal is the detection by automatic recognizing of patterns that characterize the disease. In recent times Convolutional Neural Networks (CNN) have proved to be amazingly useful for that task. The drawback, however, is that 3D brain images contain a huge amount of information that leads to complex CNN architectures. When these architectures become too complex, classification performances often degrades because the limitations of the training algorithm and overfitting. Thus, this paper proposes the use of isosurfaces as a way to reduce such amount of data while keeping the most relevant information. These isosurfaces are then used to implement a classification system which uses two of the most well-known CNN architectures, LeNet and AlexNet, to classify DaTScan images with an average accuracy of 95.1% and AUC = 97%, obtaining comparable (slightly better) values to those obtained for most of the recently proposed systems. It can be concluded therefore that the computation of isosurfaces reduces the complexity of the inputs significantly, resulting in high classification accuracies with reduced computational burden.
| S-EPMC6614282 | biostudies-literature
Project description:New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.
| S-EPMC5679649 | biostudies-literature
Project description:Differentiated thyroid cancer (DTC) from follicular epithelial cells is the most common form of thyroid cancer. Beyond the common papillary thyroid carcinoma (PTC), there are a number of rare but difficult-to-diagnose pathological classifications, such as follicular thyroid carcinoma (FTC). We employed deep convolutional neural networks (CNNs) to facilitate the clinical diagnosis of differentiated thyroid cancers. An image dataset with thyroid ultrasound images of 421 DTCs and 391 benign patients was collected. Three CNNs (InceptionV3, ResNet101, and VGG19) were retrained and tested after undergoing transfer learning to classify malignant and benign thyroid tumors. The enrolled cases were classified as PTC, FTC, follicular variant of PTC (FVPTC), Hürthle cell carcinoma (HCC), or benign. The accuracy of the CNNs was as follows: InceptionV3 (76.5%), ResNet101 (77.6%), and VGG19 (76.1%). The sensitivity was as follows: InceptionV3 (83.7%), ResNet101 (72.5%), and VGG19 (66.2%). The specificity was as follows: InceptionV3 (83.7%), ResNet101 (81.4%), and VGG19 (76.9%). The area under the curve was as follows: Incep-tionV3 (0.82), ResNet101 (0.83), and VGG19 (0.83). A comparison between performance of physicians and CNNs was assessed and showed significantly better outcomes in the latter. Our results demonstrate that retrained deep CNNs can enhance diagnostic accuracy in most DTCs, including follicular cancers.
| S-EPMC8698578 | biostudies-literature
Project description:Motivation:In addition to substitution frequency data from protein sequence alignments, many state-of-the-art methods for contact prediction rely on additional sources of information, or features, of protein sequences in order to predict residue-residue contacts, such as solvent accessibility, predicted secondary structure, and scores from other contact prediction methods. It is unclear how much of this information is needed to achieve state-of-the-art results. Here, we show that using deep neural network models, simple alignment statistics contain sufficient information to achieve state-of-the-art precision. Our prediction method, DeepCov, uses fully convolutional neural networks operating on amino-acid pair frequency or covariance data derived directly from sequence alignments, without using global statistical methods such as sparse inverse covariance or pseudolikelihood estimation. Results:Comparisons against CCMpred and MetaPSICOV2 show that using pairwise covariance data calculated from raw alignments as input allows us to match or exceed the performance of both of these methods. Almost all of the achieved precision is obtained when considering relatively local windows (around 15 residues) around any member of a given residue pairing; larger window sizes have comparable performance. Assessment on a set of shallow sequence alignments (fewer than 160 effective sequences) indicates that the new method is substantially more precise than CCMpred and MetaPSICOV2 in this regime, suggesting that improved precision is attainable on smaller sequence families. Overall, the performance of DeepCov is competitive with the state of the art, and our results demonstrate that global models, which employ features from all parts of the input alignment when predicting individual contacts, are not strictly needed in order to attain precise contact predictions. Availability and implementation:DeepCov is freely available at https://github.com/psipred/DeepCov. Supplementary information:Supplementary data are available at Bioinformatics online.
| S-EPMC6157083 | biostudies-other
Project description:PurposeDevelop computer vision models for image-based differentiation of bacterial and fungal corneal ulcers and compare their performance against human experts.DesignCross-sectional comparison of diagnostic performance.ParticipantsPatients with acute, culture-proven bacterial or fungal keratitis from 4 centers in South India.MethodsFive convolutional neural networks (CNNs) were trained using images from handheld cameras collected from patients with culture-proven corneal ulcers in South India recruited as part of clinical trials conducted between 2006 and 2015. Their performance was evaluated on 2 hold-out test sets (1 single center and 1 multicenter) from South India. Twelve local expert cornea specialists performed remote interpretation of the images in the multicenter test set to enable direct comparison against CNN performance.Main outcome measuresArea under the receiver operating characteristic curve (AUC) individually and for each group collectively (i.e., CNN ensemble and human ensemble).ResultsThe best-performing CNN architecture was MobileNet, which attained an AUC of 0.86 on the single-center test set (other CNNs range, 0.68-0.84) and 0.83 on the multicenter test set (other CNNs range, 0.75-0.83). Expert human AUCs on the multicenter test set ranged from 0.42 to 0.79. The CNN ensemble achieved a statistically significantly higher AUC (0.84) than the human ensemble (0.76; P < 0.01). CNNs showed relatively higher accuracy for fungal (81%) versus bacterial (75%) ulcers, whereas humans showed relatively higher accuracy for bacterial (88%) versus fungal (56%) ulcers. An ensemble of the best-performing CNN and best-performing human achieved the highest AUC of 0.87, although this was not statistically significantly higher than the best CNN (0.83; P = 0.17) or best human (0.79; P = 0.09).ConclusionsComputer vision models achieved superhuman performance in identifying the underlying infectious cause of corneal ulcers compared with cornea specialists. The best-performing model, MobileNet, attained an AUC of 0.83 to 0.86 without any additional clinical or historical information. These findings suggest the potential for future implementation of these models to enable earlier directed antimicrobial therapy in the management of infectious keratitis, which may improve visual outcomes. Additional studies are ongoing to incorporate clinical history and expert opinion into predictive models.
| S-EPMC9560557 | biostudies-literature