Journal of imaging informatics in medicine最新文献

Periodontal disease is a significant global oral health problem. Radiographic staging is critical in determining periodontitis severity and treatment requirements. This study aims to automatically stage periodontal bone loss using a deep learning approach using bite-wing images. A total of 1752 bite-wing images were used for the study. Radiological examinations were classified into 4 groups. Healthy (normal), no bone loss; stage I (mild destruction), bone loss in the coronal third (< 15%); stage II (moderate destruction), bone loss is in the coronal third and from 15 to 33% (15-33%); stage III-IV (severe destruction), bone loss extending from the middle third to the apical third with furcation destruction (> 33%). All images were converted to 512 × 400 dimensions using bilinear interpolation. The data was divided into 80% training validation and 20% testing. The classification module of the YOLOv8 deep learning model was used for the artificial intelligence-based classification of the images. Based on four class results, it was trained using fivefold cross-validation after transfer learning and fine tuning. After the training, 20% of test data, which the system had never seen, were analyzed using the artificial intelligence weights obtained in each cross-validation. Training and test results were calculated with average accuracy, precision, recall, and F1-score performance metrics. Test images were analyzed with Eigen-CAM explainability heat maps. In the classification of bite-wing images as healthy, mild destruction, moderate destruction, and severe destruction, training performance results were 86.100% accuracy, 84.790% precision, 82.350% recall, and 84.411% F1-score, and test performance results were 83.446% accuracy, 81.742% precision, 80.883% recall, and 81.090% F1-score. The deep learning model gave successful results in staging periodontal bone loss in bite-wing images. Classification scores were relatively high for normal (no bone loss) and severe bone loss in bite-wing images, as they are more clearly visible than mild and moderate damage.

In the field of deep learning for medical image analysis, training models from scratch are often used and sometimes, transfer learning from pretrained parameters on ImageNet models is also adopted. However, there is no universally accepted medical image dataset specifically designed for pretraining models currently. The purpose of this study is to construct such a general dataset and validate its effectiveness on downstream medical imaging tasks, including classification and segmentation. In this work, we first build a medical image dataset by collecting several public medical image datasets (CPMID). And then, some pretrained models used for transfer learning are obtained based on CPMID. Various-complexity Resnet and the Vision Transformer network are used as the backbone architectures. In the tasks of classification and segmentation on three other datasets, we compared the experimental results of training from scratch, from the pretrained parameters on ImageNet, and from the pretrained parameters on CPMID. Accuracy, the area under the receiver operating characteristic curve, and class activation map are used as metrics for classification performance. Intersection over Union as the metric is for segmentation evaluation. Utilizing the pretrained parameters on the constructed dataset CPMID, we achieved the best classification accuracy, weighted accuracy, and ROC-AUC values on three validation datasets. Notably, the average classification accuracy outperformed ImageNet-based results by 4.30%, 8.86%, and 3.85% respectively. Furthermore, we achieved the optimal balanced outcome of performance and efficiency in both classification and segmentation tasks. The pretrained parameters on the proposed dataset CPMID are very effective for common tasks in medical image analysis such as classification and segmentation.

The objective of this study was to develop and evaluate a model for predicting post-treatment survival in hepatocellular carcinoma (HCC) patients using their CT images and clinical information, including various treatment information. We collected pre-treatment contrast-enhanced CT images and clinical information including patient-related factors, initial treatment options, and survival status from 692 patients. The patient cohort was divided into a training cohort (n = 507), a testing cohort (n = 146), and an external CT cohort (n = 39), which included patients who underwent CT scans at other institutions. After model training using fivefold cross-validation, model validation was performed on both the testing cohort and the external CT cohort. Our cascaded model employed a 3D convolutional neural network (CNN) to extract features from CT images and derive final survival probabilities. These probabilities were obtained by concatenating previously predicted probabilities for each interval with the patient-related factors and treatment options. We utilized two consecutive fully connected layers for this process, resulting in a number of final outputs corresponding to the number of time intervals, with values representing conditional survival probabilities for each interval. Performance was assessed using the concordance index (C-index), the mean cumulative/dynamic area under the receiver operating characteristics curve (mC/D AUC), and the mean Brier score (mBS), calculated every 3 months. Through an ablation study, we found that using DenseNet-121 as the backbone network and setting the prediction interval to 6 months optimized the model's performance. The integration of multimodal data resulted in superior predictive capabilities compared to models using only CT images or clinical information (C index 0.824 [95% CI 0.822-0.826], mC/D AUC 0.893 [95% CI 0.891-0.895], and mBS 0.121 [95% CI 0.120-0.123] for internal test cohort; C index 0.750 [95% CI 0.747-0.753], mC/D AUC 0.819 [95% CI 0.816-0.823], and mBS 0.159 [95% CI 0.158-0.161] for external CT cohort, respectively). Our CNN-based discrete-time survival prediction model with CT images and clinical information demonstrated promising results in predicting post-treatment survival of patients with HCC.

Pneumonia is a severe health concern, particularly for vulnerable groups, needing early and correct classification for optimal treatment. This study addresses the use of deep learning combined with machine learning classifiers (DLxMLCs) for pneumonia classification from chest X-ray (CXR) images. We deployed modified VGG19, ResNet50V2, and DenseNet121 models for feature extraction, followed by five machine learning classifiers (logistic regression, support vector machine, decision tree, random forest, artificial neural network). The approach we suggested displayed remarkable accuracy, with VGG19 and DenseNet121 models obtaining 99.98% accuracy when combined with random forest or decision tree classifiers. ResNet50V2 achieved 99.25% accuracy with random forest. These results illustrate the advantages of merging deep learning models with machine learning classifiers in boosting the speedy and accurate identification of pneumonia. The study underlines the potential of DLxMLC systems in enhancing diagnostic accuracy and efficiency. By integrating these models into clinical practice, healthcare practitioners could greatly boost patient care and results. Future research should focus on refining these models and exploring their application to other medical imaging tasks, as well as including explainability methodologies to better understand their decision-making processes and build trust in their clinical use. This technique promises promising breakthroughs in medical imaging and patient management.

Segmentation of infarcts is clinically important in ischemic stroke management and prognostication. It is unclear what role the combination of DWI, ADC, and FLAIR MRI sequences provide for deep learning in infarct segmentation. Recent technologies in model self-configuration have promised greater performance and generalizability through automated optimization. We assessed the utility of DWI, ADC, and FLAIR sequences on ischemic stroke segmentation, compared self-configuring nnU-Net models to conventional U-Net models without manual optimization, and evaluated the generalizability of results on an external clinical dataset. 3D self-configuring nnU-Net models and standard 3D U-Net models with MONAI were trained on 200 infarcts using DWI, ADC, and FLAIR sequences separately and in all combinations. Segmentation results were compared between models using paired t-test comparison on a hold-out test set of 50 cases. The highest performing model was externally validated on a clinical dataset of 50 MRIs. nnU-Net with DWI sequences attained a Dice score of 0.810 ± 0.155. There was no statistically significant difference when DWI sequences were supplemented with ADC and FLAIR images (Dice score of 0.813 ± 0.150; p = 0.15). nnU-Net models significantly outperformed standard U-Net models for all sequence combinations (p < 0.001). On the external dataset, Dice scores measured 0.704 ± 0.199 for positive cases with false positives with intracranial hemorrhage. Highly optimized neural networks such as nnU-Net provide excellent stroke segmentation even when only provided DWI images, without significant improvement from other sequences. This differs from-and significantly outperforms-standard U-Net architectures. Results translated well to the external clinical environment and provide the groundwork for optimized acute stroke segmentation on MRI.

The diagnosis and treatment of pulmonary hypertension have changed dramatically through the re-defined diagnostic criteria and advanced drug development in the past decade. The application of Artificial Intelligence for the detection of elevated pulmonary arterial pressure (ePAP) was reported recently. Artificial Intelligence (AI) has demonstrated the capability to identify ePAP and its association with hospitalization due to heart failure when analyzing chest X-rays (CXR). An AI model based on electrocardiograms (ECG) has shown promise in not only detecting ePAP but also in predicting future risks related to cardiovascular mortality. We aimed to develop an AI model integrating ECG and CXR to detect ePAP and evaluate their performance. We developed a deep-learning model (DLM) using paired ECG and CXR to detect ePAP (systolic pulmonary artery pressure > 50 mmHg in transthoracic echocardiography). This model was further validated in a community hospital. Additionally, our DLM was evaluated for its ability to predict future occurrences of left ventricular dysfunction (LVD, ejection fraction < 35%) and cardiovascular mortality. The AUCs for detecting ePAP were as follows: 0.8261 with ECG (sensitivity 76.6%, specificity 74.5%), 0.8525 with CXR (sensitivity 82.8%, specificity 72.7%), and 0.8644 with a combination of both (sensitivity 78.6%, specificity 79.2%) in the internal dataset. In the external validation dataset, the AUCs for ePAP detection were 0.8348 with ECG, 0.8605 with CXR, and 0.8734 with the combination. Furthermore, using the combination of ECGs and CXR, the negative predictive value (NPV) was 98% in the internal dataset and 98.1% in the external dataset. Patients with ePAP detected by the DLM using combination had a higher risk of new-onset LVD with a hazard ratio (HR) of 4.51 (95% CI: 3.54-5.76) in the internal dataset and cardiovascular mortality with a HR of 6.08 (95% CI: 4.66-7.95). Similar results were seen in the external validation dataset. The DLM, integrating ECG and CXR, effectively detected ePAP with a strong NPV and forecasted future risks of developing LVD and cardiovascular mortality. This model has the potential to expedite the early identification of pulmonary hypertension in patients, prompting further evaluation through echocardiography and, when necessary, right heart catheterization (RHC), potentially resulting in enhanced cardiovascular outcomes.

To evaluate the usefulness of low-keV multiphasic computed tomography (CT) with deep learning image reconstruction (DLIR) in improving the delineation of pancreatic ductal adenocarcinoma (PDAC) compared to conventional hybrid iterative reconstruction (HIR). Thirty-five patients with PDAC who underwent multiphasic CT were retrospectively evaluated. Raw data were reconstructed with two energy levels (40 keV and 70 keV) of virtual monochromatic imaging (VMI) using HIR (ASiR-V50%) and DLIR (TrueFidelity-H). Contrast-to-noise ratio (CNR_tumor) was calculated from the CT values within regions of interest in tumor and normal pancreas in the pancreatic parenchymal phase images. Lesion conspicuity of PDAC in pancreatic parenchymal phase on 40-keV HIR, 40-keV DLIR, and 70-keV DLIR images was qualitatively rated on a 5-point scale, using 70-keV HIR images as reference (score 1 = poor; score 3 = equivalent to reference; score 5 = excellent) by two radiologists. CNR_tumor of 40-keV DLIR images (median 10.4, interquartile range (IQR) 7.8-14.9) was significantly higher than that of the other VMIs (40 keV HIR, median 6.2, IQR 4.4-8.5, P < 0.0001; 70-keV DLIR, median 6.3, IQR 5.1-9.9, P = 0.0002; 70-keV HIR, median 4.2, IQR 3.1-6.1, P < 0.0001). CNR_tumor of 40-keV DLIR images were significantly better than those of the 40-keV HIR and 70-keV HIR images by 72 ± 22% and 211 ± 340%, respectively. Lesion conspicuity scores on 40-keV DLIR images (observer 1, 4.5 ± 0.7; observer 2, 3.4 ± 0.5) were significantly higher than on 40-keV HIR (observer 1, 3.3 ± 0.9, P < 0.0001; observer 2, 3.1 ± 0.4, P = 0.013). DLIR is a promising reconstruction method to improve PDAC delineation in 40-keV VMI at the pancreatic parenchymal phase compared to conventional HIR.

Time-of-flight magnetic resonance angiography (TOF-MRA) is a non-contrast technique used to visualize neurovascular. However, manual reconstruction of the volume render (VR) by radiologists is time-consuming and labor-intensive. Deep learning-based (DL-based) vessel segmentation technology may provide intelligent automation workflow. To evaluate the image quality of DL vessel segmentation for automatically acquiring intracranial arteries in TOF-MRA. A total of 394 TOF-MRA scans were selected, which included cerebral vascular health, aneurysms, or stenoses. Both our proposed method and two state-of-the-art DL methods are evaluated on external datasets for generalization ability. For qualitative assessment, two experienced clinical radiologists evaluated the image quality of cerebrovascular diagnostic and visualization (scoring 0-5 as unacceptable to excellent) obtained by manual VR reconstruction or automatic convolutional neural network (CNN) segmentation. The proposed CNN outperforms the other two DL-based methods in clinical scoring on external datasets, and its visualization was evaluated by readers as having the appearance of the radiologists' manual reconstructions. Scoring of proposed CNN and VR of intracranial arteries demonstrated good to excellent agreement with no significant differences (median, 5.0 and 5.0, P ≥ 12) at healthy-type scans. All proposed CNN image quality were considered to have adequate diagnostic quality (median scores > 2). Quantitative analysis demonstrated a superior dice similarity coefficient of cerebrovascular overlap (training sets and validation sets; 0.947 and 0.927). Automatic cerebrovascular segmentation using DL is feasible and the image quality in terms of vessel integrity, collateral circulation and lesion morphology is comparable to expert manual VR without significant differences.

Deep learning techniques offer improvements in computer-aided diagnosis systems. However, acquiring image domain annotations is challenging due to the knowledge and commitment required of expert pathologists. Pathologists often identify regions in whole slide images with diagnostic relevance rather than examining the entire slide, with a positive correlation between the time spent on these critical image regions and diagnostic accuracy. In this paper, a heatmap is generated to represent pathologists' viewing patterns during diagnosis and used to guide a deep learning architecture during training. The proposed system outperforms traditional approaches based on color and texture image characteristics, integrating pathologists' domain expertise to enhance region of interest detection without needing individual case annotations. Evaluating our best model, a U-Net model with a pre-trained ResNet-18 encoder, on a skin biopsy whole slide image dataset for melanoma diagnosis, shows its potential in detecting regions of interest, surpassing conventional methods with an increase of 20%, 11%, 22%, and 12% in precision, recall, F1-score, and Intersection over Union, respectively. In a clinical evaluation, three dermatopathologists agreed on the model's effectiveness in replicating pathologists' diagnostic viewing behavior and accurately identifying critical regions. Finally, our study demonstrates that incorporating heatmaps as supplementary signals can enhance the performance of computer-aided diagnosis systems. Without the availability of eye tracking data, identifying precise focus areas is challenging, but our approach shows promise in assisting pathologists in improving diagnostic accuracy and efficiency, streamlining annotation processes, and aiding the training of new pathologists.

The skin prick test (SPT) is a key tool for identifying sensitized allergens associated with immunoglobulin E-mediated allergic diseases such as asthma, allergic rhinitis, atopic dermatitis, urticaria, angioedema, and anaphylaxis. However, the SPT is labor-intensive and time-consuming due to the necessity of measuring the sizes of the erythema and wheals induced by allergens on the skin. In this study, we used an image preprocessing method and a deep learning model to segment wheals and erythema in SPT images captured by a smartphone camera. Subsequently, we assessed the deep learning model's performance by comparing the results with ground-truth data. Using contrast-limited adaptive histogram equalization (CLAHE), an image preprocessing technique designed to enhance image contrast, we augmented the chromatic contrast in 46 SPT images from 33 participants. We established a deep learning model for wheal and erythema segmentation using 144 and 150 training datasets, respectively. The wheal segmentation model achieved an accuracy of 0.9985, a sensitivity of 0.5621, a specificity of 0.9995, and a Dice similarity coefficient of 0.7079, whereas the erythema segmentation model achieved an accuracy of 0.9660, a sensitivity of 0.5787, a specificity of 0.97977, and a Dice similarity coefficient of 0.6636. The use of image preprocessing and deep learning technology in SPT is expected to have a significant positive impact on medical practice by ensuring the accurate segmentation of wheals and erythema, producing consistent evaluation results, and simplifying diagnostic processes.