Journal of imaging informatics in medicine最新文献

Deep learning can exceed dermatologists' diagnostic accuracy in experimental image environments. However, inaccurate segmentation of images with multiple skin lesions can be seen with current methods. Thus, information present in multiple-lesion images, available to specialists, is not retrievable by machine learning. While skin lesion images generally capture a single lesion, there may be cases in which a patient's skin variation may be identified as skin lesions, leading to multiple false positive segmentations in a single image. Conversely, image segmentation methods may find only one region and may not capture multiple lesions in an image. To remedy these problems, we propose a novel and effective data augmentation technique for skin lesion segmentation in dermoscopic images with multiple lesions. The lesion-aware mixup augmentation (LAMA) method generates a synthetic multi-lesion image by mixing two or more lesion images from the training set. We used the publicly available International Skin Imaging Collaboration (ISIC) 2017 Challenge skin lesion segmentation dataset to train the deep neural network with the proposed LAMA method. As none of the previous skin lesion datasets (including ISIC 2017) has considered multiple lesions per image, we created a new multi-lesion (MuLe) segmentation dataset utilizing publicly available ISIC 2020 skin lesion images with multiple lesions per image. MuLe was used as a test set to evaluate the effectiveness of the proposed method. Our test results show that the proposed method improved the Jaccard score 8.3% from 0.687 to 0.744 and the Dice score 5% from 0.7923 to 0.8321 over a baseline model on MuLe test images. On the single-lesion ISIC 2017 test images, LAMA improved the baseline model's segmentation performance by 0.08%, raising the Jaccard score from 0.7947 to 0.8013 and the Dice score 0.6% from 0.8714 to 0.8766. The experimental results showed that LAMA improved the segmentation accuracy on both single-lesion and multi-lesion dermoscopic images. The proposed LAMA technique warrants further study.

Breast cancer holds the highest diagnosis rate among female tumors and is the leading cause of death among women. Quantitative analysis of radiological images shows the potential to address several medical challenges, including the early detection and classification of breast tumors. In the P.I.N.K study, 66 women were enrolled. Their paired Automated Breast Volume Scanner (ABVS) and Digital Breast Tomosynthesis (DBT) images, annotated with cancerous lesions, populated the first ABVS+DBT dataset. This enabled not only a radiomic analysis for the malignant vs. benign breast cancer classification, but also the comparison of the two modalities. For this purpose, the models were trained using a leave-one-out nested cross-validation strategy combined with a proper threshold selection approach. This approach provides statistically significant results even with medium-sized data sets. Additionally it provides distributional variables of importance, thus identifying the most informative radiomic features. The analysis proved the predictive capacity of radiomic models even using a reduced number of features. Indeed, from tomography we achieved AUC-ROC $89.9\%$ using 19 features and $92.1\%$ using 7 of them; while from ABVS we attained an AUC-ROC of $72.3\%$ using 22 features and $85.8\%$ using only 3 features. Although the predictive power of DBT outperforms ABVS, when comparing the predictions at the patient level, only 8.7% of lesions are misclassified by both methods, suggesting a partial complementarity. Notably, promising results (AUC-ROC ABVS-DBT $71.8\%$ - $74.1\%$ ) were achieved using non-geometric features, thus opening the way to the integration of virtual biopsy in medical routine.

Lung diseases represent a significant global health threat, impacting both well-being and mortality rates. Diagnostic procedures such as Computed Tomography (CT) scans and X-ray imaging play a pivotal role in identifying these conditions. X-rays, due to their easy accessibility and affordability, serve as a convenient and cost-effective option for diagnosing lung diseases. Our proposed method utilized the Contrast-Limited Adaptive Histogram Equalization (CLAHE) enhancement technique on X-ray images to highlight the key feature maps related to lung diseases using DenseNet201. We have augmented the existing Densenet201 model with a hybrid pooling and channel attention mechanism. The experimental results demonstrate the superiority of our model over well-known pre-trained models, such as VGG16, VGG19, InceptionV3, Xception, ResNet50, ResNet152, ResNet50V2, ResNet152V2, MobileNetV2, DenseNet121, DenseNet169, and DenseNet201. Our model achieves impressive accuracy, precision, recall, and F1-scores of 95.34%, 97%, 96%, and 96%, respectively. We also provide visual insights into our model's decision-making process using Gradient-weighted Class Activation Mapping (Grad-CAM) to identify normal, pneumothorax, and atelectasis cases. The experimental results of our model in terms of heatmap may help radiologists improve their diagnostic abilities and labelling processes.

This study aimed to construct an imaging genomics nomogram based on intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) to predict the status of the alpha thalassemia/mental retardation syndrome X-linked (ATRX) gene in patients with brain gliomas. We retrospectively analyzed routine MR and IVIM-DWI data from 85 patients with pathologically confirmed brain gliomas from January 2017 to May 2023. The data were divided into a training set (N=61) and a test set (N=24) in a 7:3 ratio. Regions of interest (ROIs) of brain gliomas, including the solid tumor region (rCET), edema region (rE), and necrotic region (rNec), were delineated using 3D-Slicer software and projected onto the D, D*, and f sequences. A total of 1037 features were extracted from each ROI, resulting in 3111 features per patient. Age was incorporated in the calculation of the Radscore, and a clinical-imaging genomics combined model was constructed, from which a nomogram graph was generated. Separate models were built for the D, D*, and f parameters. The AUC value of the D parameter model was 0.97 (95% CI: 0.93-1.00) in the training set and 0.91 (95% CI: 0.79-1.00) in the validation set, which was significantly higher than that of the D* parameter model (0.90, 0.82) and the f parameter model (0.89, 0.91). The imaging genomics nomogram based on IVIM-DWI can effectively predict the ATRX gene status of patients with brain gliomas, with the D parameter showing the highest efficacy.

Forkhead box P3 (FOXP3) has been identified as a novel molecular marker in various types of cancer. The present study assessed the expression of FOXP3 in patients with head and neck squamous cell carcinoma (HNSCC) and its potential as a clinical prognostic indicator, and developed a radiomics model based on enhanced computed tomography (CT) imaging. Data from 483 patients with HNSCC were downloaded from the Cancer Genome Atlas for FOXP3 prognostic analysis and enhanced CT images from 139 patients included in the Cancer Imaging Archives, which were subjected to the maximum relevance and minimum redundancy and recursive feature elimination algorithms for radiomics feature extraction and processing. Logistic regression was used to build a model for predicting FOXP3 expression. A prognostic scoring system for radiomics score (RS), FOXP3, and patient clinicopathological factors was established to predict patient survival. The area under the receiver operating characteristic (ROC) curve (AUC) and calibration curve and decision curve analysis (DCA) were used to evaluate model performance. Furthermore, the relationship between FOXP3 and the immune microenvironment, as well as the association between RS and immune checkpoint-related genes, was analyzed. Results of analysis revealed that patients with HNSCC and high FOXP3 mRNA expression exhibited better overall survival. Immune infiltration analysis revealed that FOXP3 had a positive correlation with CD4⁺ and CD8⁺ T cells and other immune cells. The 8 best radiomics features were selected to construct the radiomics model. In the FOXP3 expression prediction model, the AUC values were 0.707 and 0.702 for the training and validation sets, respectively. Additionally, the calibration curve and DCA demonstrated the positive diagnostic utility of the model. RS was correlated with immune checkpoint-related genes such as ICOS, CTLA4, and PDCD1. A predictive nomogram was established, the AUCs were 0.87, 0.787, and 0.801 at 12, 24, and 36 months, respectively, and DCA demonstrated the high clinical applicability of the nomogram. The enhanced CT radiomics model can predict expression of FOXP3 and prognosis in patients with HNSCC. As such, FOXP3 may be used as a novel prognostic marker to improve individualized clinical diagnosis and treatment decisions.

Image segmentation is a crucial task in computer vision and image processing, with numerous segmentation algorithms being found in the literature. It has important applications in scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, image compression, among others. In light of this, the widespread popularity of deep learning (DL) and machine learning has inspired the creation of fresh methods for segmenting images using DL and ML models respectively. We offer a thorough analysis of this recent literature, encompassing the range of ground-breaking initiatives in semantic and instance segmentation, including convolutional pixel-labeling networks, encoder-decoder architectures, multi-scale and pyramid-based methods, recurrent networks, visual attention models, and generative models in adversarial settings. We study the connections, benefits, and importance of various DL- and ML-based segmentation models; look at the most popular datasets; and evaluate results in this Literature.

Identifying indolent and aggressive prostate cancers is a critical problem for optimal treatment. The existing approaches of prostate cancer detection are facing challenges as the techniques rely on ground truth labels with limited accuracy, and histological similarity, and do not consider the disease pathology characteristics, and indefinite differences in appearance between the cancerous and healthy tissue lead to many false positive and false negative interpretations. Hence, this research introduces a comprehensive framework designed to achieve accurate identification and localization of prostate cancers, irrespective of their aggressiveness. This is accomplished through the utilization of a sophisticated multilevel bidirectional long short-term memory (Bi-LSTM) model. The pre-processed images are subjected to multilevel feature map-based U-Net segmentation, bolstered by ResNet-101 and a channel-based attention module that improves the performance. Subsequently, segmented images undergo feature extraction, encompassing various feature types, including statistical features, a global hybrid-based feature map, and a ResNet-101 feature map that enhances the detection accuracy. The extracted features are fed to the multilevel Bi-LSTM model, further optimized through channel and spatial attention mechanisms that offer the effective localization and recognition of complex structures of cancer. Further, the framework represents a promising approach for enhancing the diagnosis and localization of prostate cancers, encompassing both indolent and aggressive cases. Rigorous testing on a distinct dataset demonstrates the model's effectiveness, with performance evaluated through key metrics which are reported as 96.72%, 96.17%, and 96.17% for accuracy, sensitivity, and specificity respectively utilizing the dataset 1. For dataset 2, the model achieves the accuracy, sensitivity, and specificity values of 94.41%, 93.10%, and 94.96% respectively. These results surpass the efficiency of alternative methods.

A neural network was developed to detect and characterize bowel obstruction, a common cause of acute abdominal pain. In this retrospective study, 202 CT scans of 165 patients with bowel obstruction from March to June 2022 were included and partitioned into training and test data sets. A multi-channel neural network was trained to segment the gastrointestinal tract, and to predict the diameter and the longitudinal position ("longitude") along the gastrointestinal tract using a novel embedding. Its performance was compared to manual segmentations using the Dice score, and to manual measurements of the diameter and longitude using intraclass correlation coefficients (ICC). ROC curves as well as sensitivity and specificity were calculated for diameters above a clinical threshold for obstruction, and for longitudes corresponding to small bowel. In the test data set, Dice score for segmentation of the gastrointestinal tract was 78 ± 8%. ICC between measured and predicted diameters was 0.72, indicating moderate agreement. ICC between measured and predicted longitude was 0.85, indicating good agreement. AUROC was 0.90 for detection of dilated bowel, and was 0.95 and 0.90 for differentiation of the proximal and distal gastrointestinal tract respectively. Overall sensitivity and specificity for dilated small bowel were 0.83 and 0.90. Since obstruction is diagnosed based on the diameter and longitude of the bowel, this neural network and embedding may enable detection and characterization of this important disease on CT.

The diaphragm is the main inspiratory muscle and separates the thorax and the abdomen. In COPD, the evaluation of the diaphragm shape is clinically important, especially in the case of hyperinflation. However, delineating the diaphragm remains a challenge as it cannot be seen entirely on CT scans. Therefore, the lungs, ribs, sternum, and lumbar vertebrae are used as surrogate landmarks to delineate the diaphragm. We herein describe a CT-based method for evaluating the shape of the diaphragm using 3D Slicer-a free software that allows delineation of the diaphragm landmarks-in ten COPD patients. Using the segmentation performed with 3D Slicer, the diaphragm shape was reconstructed with open-source Free Pascal Compiler. From this graduated model, the length of the muscle fibers, the radius of curvature, and the area of the diaphragm-the main determinants of its function-can be measured. Inter- and intra-user variabilities were evaluated with Bland and Altman plots and linear mixed models. Except for the coronal length (p = 0.049), there were not statistically significant inter- or intra-user differences (p values ranging from 0.326 to 0.910) suggesting that this method is reproducible and repeatable. In conclusion, 3D Slicer can be applied to CT scans for determining the shape of the diaphragm in COPD patients.

The introduction of three-dimensional (3D) printed anatomical models has garnered interest in pre-operative planning, especially in orthopedic and trauma surgery. Identifying potential error sources and quantifying their effect on the model dimensional accuracy are crucial for the applicability and reliability of such models. In this study, twenty radii were extracted from anatomic forearm specimens and subjected to osteotomy to simulate a defined fracture of the distal radius (Colles' fracture). Various factors, including two different computed tomography (CT) technologies (energy-integrating detector (EID) and photon-counting detector (PCD)), four different CT scanners, two scan protocols (i.e., routine and high dosage), two different scan orientations, as well as two segmentation algorithms were considered to determine their effect on 3D model accuracy. Ground truth was established using 3D reconstructions of surface scans of the physical specimens. Results indicated that all investigated variables significantly impacted the 3D model accuracy (p < 0.001). However, the mean absolute deviation fell within the range of 0.03 ± 0.20 to 0.32 ± 0.23 mm, well below the 0.5 mm threshold necessary for pre-operative planning. Intra- and inter-operator variability demonstrated fair to excellent agreement for 3D model accuracy, with an intra-class correlation (ICC) of 0.43 to 0.92. This systematic investigation displayed dimensional deviations in the magnitude of sub-voxel imaging resolution for all variables. Major pitfalls included missed or overestimated bone regions during the segmentation process, necessitating additional manual editing of 3D models. In conclusion, this study demonstrates that 3D bone fracture models can be obtained with clinical routine scanners and scan protocols, utilizing a simple global segmentation threshold, thereby providing an accurate and reliable tool for pre-operative planning.