Journal Of Digital Imaging[JOURNAL]
Sun
200 papers
Cascading Affine and B-spline Registration Method for Large Deformation Registration of Lung X-rays.
Chang Q, Lu C, Li M
J Digit Imaging · 2023 Jun · PMID 36788195 · Full text
Accurate registration of lung X-rays is an important task in medical image analysis. However, the conventional methods usually cost a lot in running time, and the existing deep learning methods are hard to deal with the...
Accurate registration of lung X-rays is an important task in medical image analysis. However, the conventional methods usually cost a lot in running time, and the existing deep learning methods are hard to deal with the large deformation caused by respiratory and cardiac motion. In this paper, we attempt to use deep learning methods to deal with large deformation and enable it to achieve the accuracy of conventional methods. We proposed the cascading affine and B-spline network (CABN), which consists of convolutional cross-stitch affine block (CCAB) and B-splines U-net-like block (BUB) for large lung motion. CCAB makes use of the convolutional cross-stitch model to learn global features among images. And BUB adopts the idea of cubic B-splines which is suitable for large deformation. We separately demonstrated CCAB, BUB, and CABN on two chest X-ray datasets. The experimental results indicate that our methods are highly competitive both in accuracy and runtime when compared to both other deep learning methods and iterative conventional approaches. Moreover, CCAB also can be used for the preprocessing of non-rigid registration methods, replacing affine in conventional methods.
Prognostic Prediction of Cancer Based on Radiomics Features of Diagnostic Imaging: The Performance of Machine Learning Strategies.
Tang FH, Xue C, Law MY … +3 more , Wong CY, Cho TH, Lai CK
J Digit Imaging · 2023 Jun · PMID 36781589 · Full text
Tumor phenotypes can be characterized by radiomics features extracted from images. However, the prediction accuracy is challenged by difficulties such as small sample size and data imbalance. The purpose of the study was...
Tumor phenotypes can be characterized by radiomics features extracted from images. However, the prediction accuracy is challenged by difficulties such as small sample size and data imbalance. The purpose of the study was to evaluate the performance of machine learning strategies for the prediction of cancer prognosis. A total of 422 patients diagnosed with non-small cell lung carcinoma (NSCLC) were selected from The Cancer Imaging Archive (TCIA). The gross tumor volume (GTV) of each case was delineated from the respective CT images for radiomic features extraction. The samples were divided into 4 groups with survival endpoints of 1 year, 3 years, 5 years, and 7 years. The radiomic image features were analyzed with 6 different machine learning methods: decision tree (DT), boosted tree (BT), random forests (RF), support vector machine (SVM), generalized linear model (GLM), and deep learning artificial neural networks (DL-ANNs) with 70:30 cross-validation. The overall average prediction performance of the BT, RF, DT, SVM, GLM and DL-ANNs was AUC with 0.912, 0.938, 0.793, 0.746, 0.789 and 0.705 respectively. The RF and BT gave the best and second performance in the prediction. The DL-ANN did not show obvious advantage in predicting prognostic outcomes. Deep learning artificial neural networks did not show a significant improvement than traditional machine learning methods such as random forest and boosted trees. On the whole, the accurate outcome prediction using radiomics serves as a supportive reference for formulating treatment strategy for cancer patients.
A Deep Learning Approach for Automated Bone Removal from Computed Tomography Angiography of the Brain.
Isikbay M, Caton MT, Calabrese E
J Digit Imaging · 2023 Jun · PMID 36781588 · Full text
Advanced visualization techniques such as maximum intensity projection (MIP) and volume rendering (VR) are useful for evaluating neurovascular anatomy on CT angiography (CTA) of the brain; however, interference from surr...
Advanced visualization techniques such as maximum intensity projection (MIP) and volume rendering (VR) are useful for evaluating neurovascular anatomy on CT angiography (CTA) of the brain; however, interference from surrounding osseous anatomy is common. Existing methods for removing bone from CTA images are limited in scope and/or accuracy, particularly at the skull base. We present a new brain CTA bone removal tool, which addresses many of these limitations. A deep convolutional neural network was designed and trained for bone removal using 72 brain CTAs. The model was tested on 15 CTAs from the same data source and 17 CTAs from an independent external dataset. Bone removal accuracy was assessed quantitatively, by comparing automated segmentation results to manual segmentations, and qualitatively by evaluating VR visualization of the carotid siphons compared to an existing method for automated bone removal. Average Dice overlap between automated and manual segmentations from the internal and external test datasets were 0.986 and 0.979 respectively. This was superior compared to a publicly available noncontrast head CT bone removal algorithm which had a Dice overlap of 0.947 (internal dataset) and 0.938 (external dataset). Our algorithm yielded better VR visualization of the carotid siphons than the publicly available bone removal tool in 14 out of 15 CTAs (93%, chi-square statistic of 22.5, p-value of < 0.00001) from the internal test dataset and 15 out of 17 CTAs (88%, chi-square statistic of 23.1, p-value of < 0.00001) from the external test dataset. Bone removal allowed subjectively superior MIP and VR visualization of vascular anatomy/pathology. The proposed brain CTA bone removal algorithm is rapid, accurate, and allows superior visualization of vascular anatomy and pathology compared to other available techniques and was validated on an independent external dataset.
The FIND Program: Improving Follow-up of Incidental Imaging Findings.
Zaki-Metias KM, MacLean JJ, Satei AM … +4 more , Medvedev S, Wang H, Zarour CC, Arpasi PJ
J Digit Imaging · 2023 Jun · PMID 36759382 · Full text
Incidental findings are findings identified on imaging which are unrelated to the original reason for examination and require follow-up. The Radiology Finding Incidental Disease (FIND) Program was designed to track and i...
Incidental findings are findings identified on imaging which are unrelated to the original reason for examination and require follow-up. The Radiology Finding Incidental Disease (FIND) Program was designed to track and improve follow-up of incidental imaging findings. The purpose of this study was to determine the frequency of incidental findings on cross-sectional imaging and the adherence to suggested follow-up of incidental findings prior to and after implementation of a structured reporting and tracking system. A retrospective analysis of 2000 patients with computed tomographic cross-sectional imaging was performed: 1000 patients prior to implementation of the FIND Program and 1000 patients 1 year after establishment of the program. Data collected included the frequency of incidental findings, inclusion of follow-up recommendations in the radiology report, and adherence to suggested follow-up. There was a higher rate of completion of recommended follow-up imaging in the post-implementation group (34/67, 50.7%) compared to the pre-implementation (16/52, 30.8%) (p = 0.03). Implementation of an incidental findings tracking program resulted in improved follow-up of incidental imaging findings. This has the potential to reduce the burden of clinically significant incidental findings possibly resulting in later presentation of advanced disease.
Automatic Segmentation of Hyperreflective Foci in OCT Images Based on Lightweight DBR Network.
Wei J, Yu S, Du Y … +3 more , Liu K, Xu Y, Xu X
J Digit Imaging · 2023 Jun · PMID 36749455 · Full text
Hyperreflective foci (HF) reflects inflammatory responses for fundus diseases such as diabetic macular edema (DME), retina vein occlusion (RVO), and central serous chorioretinopathy (CSC). Shown as high contrast and refl...
Hyperreflective foci (HF) reflects inflammatory responses for fundus diseases such as diabetic macular edema (DME), retina vein occlusion (RVO), and central serous chorioretinopathy (CSC). Shown as high contrast and reflectivity in optical coherence tomography (OCT) images, automatic segmentation of HF in OCT images is helpful for the prognosis of fundus diseases. Previous traditional methods were time-consuming and required high computing power. Hence, we proposed a lightweight network to segment HF (with a speed of 57 ms per OCT image, at least 150 ms faster than other methods). Our framework consists of two stages: an NLM filter and patch-based split to preprocess images and a lightweight DBR neural network to segment HF automatically. Experimental results from 3000 OCT images of 300 patients (100 DME,100 RVO, and 100 CSC) revealed that our method achieved HF segmentation successfully. The DBR network had the area under curves dice similarity coefficient (DSC) of 83.65%, 76.43%, and 82.20% in segmenting HF in DME, RVO, and CSC on the test cohort respectively. Our DBR network achieves at least 5% higher DSC than previous methods. HF in DME was more easily segmented compared with the other two types. In addition, our DBR network is universally applicable to clinical practice with the ability to segment HF in a wide range of fundus diseases.
Ultrasound Prostate Segmentation Using Adaptive Selection Principal Curve and Smooth Mathematical Model.
Peng T, Wu Y, Zhao J … +3 more , Wang C, Wang J, Cai J
J Digit Imaging · 2023 Jun · PMID 36729258 · Full text
Accurate prostate segmentation in ultrasound images is crucial for the clinical diagnosis of prostate cancer and for performing image-guided prostate surgery. However, it is challenging to accurately segment the prostate...
Accurate prostate segmentation in ultrasound images is crucial for the clinical diagnosis of prostate cancer and for performing image-guided prostate surgery. However, it is challenging to accurately segment the prostate in ultrasound images due to their low signal-to-noise ratio, the low contrast between the prostate and neighboring tissues, and the diffuse or invisible boundaries of the prostate. In this paper, we develop a novel hybrid method for segmentation of the prostate in ultrasound images that generates accurate contours of the prostate from a range of datasets. Our method involves three key steps: (1) application of a principal curve-based method to obtain a data sequence comprising data coordinates and their corresponding projection index; (2) use of the projection index as training input for a fractional-order-based neural network that increases the accuracy of results; and (3) generation of a smooth mathematical map (expressed via the parameters of the neural network) that affords a smooth prostate boundary, which represents the output of the neural network (i.e., optimized vertices) and matches the ground truth contour. Experimental evaluation of our method and several other state-of-the-art segmentation methods on datasets of prostate ultrasound images generated at multiple institutions demonstrated that our method exhibited the best capability. Furthermore, our method is robust as it can be applied to segment prostate ultrasound images obtained at multiple institutions based on various evaluation metrics.
Creating a Medical Imaging Workflow Based on FHIR, DICOMweb, and SVG.
Tang ST, Tjia V, Noga T … +5 more , Febri J, Lien CY, Chu WC, Chen CY, Hsiao CH
J Digit Imaging · 2023 Jun · PMID 36729257 · Full text
This paper proposes a web-based workflow scheme for the organization of medical images using FHIR and DICOM servers equipped with standard RESTful APIs. In our integrated workflow, the client systems (including order pla...
This paper proposes a web-based workflow scheme for the organization of medical images using FHIR and DICOM servers equipped with standard RESTful APIs. In our integrated workflow, the client systems (including order placer, scheduler, imaging modality, viewer, and report creator) use standard FHIR and DICOMweb APIs. The proposed scheme also facilitates the creation of reports formatted as standard FHIR resources. This paper leverages W3C Scalable Vector Graphics (SVG) to record the image graphic annotations, and encapsulates the SVG image annotation in FHIR observation. FHIR DiagnosticReports and Observations are used to encapsulate reports, findings, and annotations, thereby facilitating the implementation and integration of the scheme within existing structures. The proposed scheme also provides the potential to make it possible to convert results of Computer Aided Detection/Diagnosis from medical images into FHIR DiagnosticReports and Observations to be stored on a FHIR server. The resulting web-based solution uses FHIR XML and/or JSON data to record and exchange information related to imaging workflow. It can also be used to store imaging reports, findings, and annotations linked to the images using the DICOM WADO-RS protocol. As a result, it is possible to integrate all information that is created in medical imaging workflow. Finally, the proposed scheme is easily integrated with other FHIR systems.
Breast Tumor Classification in Ultrasound Images by Fusion of Deep Convolutional Neural Network and Shallow LBP Feature.
Chen H, Ma M, Liu G … +3 more , Wang Y, Jin Z, Liu C
J Digit Imaging · 2023 Jun · PMID 36720840 · Full text
Breast cancer is one of the most dangerous and common cancers in women which leads to a major research topic in medical science. To assist physicians in pre-screening for breast cancer to reduce unnecessary biopsies, bre...
Breast cancer is one of the most dangerous and common cancers in women which leads to a major research topic in medical science. To assist physicians in pre-screening for breast cancer to reduce unnecessary biopsies, breast ultrasound and computer-aided diagnosis (CAD) have been used to distinguish between benign and malignant tumors. In this study, we proposed a CAD system for tumor diagnosis using a multi-channel fusion method and feature extraction structure based on multi-feature fusion on breast ultrasound (BUS) images. In the pre-processing stage, the multi-channel fusion method completed the color conversion of the BUS image to make it contain richer information. In the feature extraction stage, the pre-trained ResNet50 network was selected as the basic network, and three levels of features were combined based on adaptive spatial feature fusion (ASFF), and finally, the shallow local binary pattern (LBP) texture features were fused. Support vector machine (SVM) was used for comparative analysis. A retrospective analysis was carried out, and 1615 breast tumor images (572 benign and 1043 malignant) confirmed by pathological examinations were collected. After data processing and augmentation, for an independent test set consisting of 874 breast ultrasound images (457 benign and 417 malignant), the accuracy, precision, recall, specificity, F1 score, and AUC of our method were 96.91%, 98.75%, 94.72%, 98.91%, 0.97, and 0.991, respectively. The results show that the integration of shallow LBP texture features and multi-level depth features can more effectively improve the comprehensive performance of breast tumor diagnosis, and has strong clinical application value. Compared with the past methods, our proposed method is expected to realize the automatic diagnosis of breast tumors and provide an auxiliary tool for radiologists to accurately diagnose breast diseases.
An Unsupervised Learning-Based Regional Deformable Model for Automated Multi-Organ Contour Propagation.
Liang X, Dai J, Zhou X … +8 more , Liu L, Zhang C, Jiang Y, Li N, Niu T, Xie Y, Dai Z, Wang X
J Digit Imaging · 2023 Jun · PMID 36717520 · Full text
The aim of this study is to evaluate a regional deformable model based on a deep unsupervised learning model for automatic contour propagation in breast cone-beam computed tomography-guided adaptive radiation therapy. A...
The aim of this study is to evaluate a regional deformable model based on a deep unsupervised learning model for automatic contour propagation in breast cone-beam computed tomography-guided adaptive radiation therapy. A deep unsupervised learning model was introduced to map breast's tumor bed, clinical target volume, heart, left lung, right lung, and spinal cord from planning computed tomography to cone-beam CT. To improve the traditional image registration method's performance, we used a regional deformable framework based on the narrow-band mapping, which can mitigate the effect of the image artifacts on the cone-beam CT. We retrospectively selected 373 anonymized cone-beam CT volumes from 111 patients with breast cancer. The cone-beam CTs are divided into three sets. 311 / 20 / 42 cone-beam CT images were used for training, validating, and testing. The manual contour was used as reference for the testing set. We compared the results between the reference and the model prediction for evaluating the performance. The mean Dice between manual reference segmentations and the model predicted segmentations for breast tumor bed, clinical target volume, heart, left lung, right lung, and spinal cord were 0.78 ± 0.09, 0.90 ± 0.03, 0.88 ± 0.04, 0.94 ± 0.03, 0.95 ± 0.02, and 0.77 ± 0.07, respectively. The results demonstrated a good agreement between the reference and the proposed contours. The proposed deep learning-based regional deformable model technique can automatically propagate contours for breast cancer adaptive radiotherapy. Deep learning in contour propagation was promising, but further investigation was warranted.
The Use of Virtual Reality in Teaching Three-Dimensional Anatomy and Pathology on CT.
Banerjee S, Pham T, Eastaway A … +2 more , Auffermann WF, Quigley EP
J Digit Imaging · 2023 Jun · PMID 36717519 · Full text
While radiological imaging is presented as two-dimensional images either on radiography or cross-sectional imaging, it is important for interpreters to understand three-dimensional anatomy and pathology. We hypothesized...
While radiological imaging is presented as two-dimensional images either on radiography or cross-sectional imaging, it is important for interpreters to understand three-dimensional anatomy and pathology. We hypothesized that virtual reality (VR) may serve as an engaging and effective way for trainees to learn to extrapolate from two-dimensional images to an understanding of these three-dimensional structures. We created a Google Cardboard Virtual Reality application that depicts intracranial vasculature and aneurysms. We then recruited 12 medical students to voluntarily participate in our study. The performance of the students in identifying intracranial aneurysms before and after the virtual reality training was evaluated and compared to a control group. While the experimental group's performance in correctly identifying aneurysms after virtual reality educational intervention was better than the control's (experimental increased by 5.3%, control decreased by 2.1%), the difference was not statistically significant (p-value of 0.06). Significantly, survey data from the medical students was very positive with students noting they preferred the immersive virtual reality training over conventional education and believed that VR would be a helpful educational tool for them in the future. We believe virtual reality can serve as an important tool to help radiology trainees better understand three-dimensional anatomy and pathology.
Development and Validation of CT-Based Radiomics Signature for Overall Survival Prediction in Multi-organ Cancer.
Le VH, Kha QH, Minh TNT … +3 more , Nguyen VH, Le VL, Le NQK
J Digit Imaging · 2023 Jun · PMID 36717518 · Full text
The malignant tumors in nature share some common morphological characteristics. Radiomics is not only images but also data; we think that a probability exists in a set of radiomics signatures extracted from CT scan image...
The malignant tumors in nature share some common morphological characteristics. Radiomics is not only images but also data; we think that a probability exists in a set of radiomics signatures extracted from CT scan images of one cancer tumor in one specific organ also be utilized for overall survival prediction in different types of cancers in different organs. The retrospective study enrolled four data sets of cancer patients in three different organs (420, 157, 137, and 191 patients for lung 1 training, lung 2 testing, and two external validation set: kidney and head and neck, respectively). In the training set, radiomics features were obtained from CT scan images, and essential features were chosen by LASSO algorithm. Univariable and multivariable analyses were then conducted to find a radiomics signature via Cox proportional hazard regression. The Kaplan-Meier curve was performed based on the risk score. The integrated time-dependent area under the ROC curve (iAUC) was calculated for each predictive model. In the training set, Kaplan-Meier curve classified patients as high or low-risk groups (p-value < 0.001; log-rank test). The risk score of radiomics signature was locked and independently evaluated in the testing set, and two external validation sets showed significant differences (p-value < 0.05; log-rank test). A combined model (radiomics + clinical) showed improved iAUC in lung 1, lung 2, head and neck, and kidney data set are 0.621 (95% CI 0.588, 0.654), 0.736 (95% CI 0.654, 0.819), 0.732 (95% CI 0.655, 0.809), and 0.834 (95% CI 0.722, 0.946), respectively. We believe that CT-based radiomics signatures for predicting overall survival in various cancer sites may exist.
CheSS: Chest X-Ray Pre-trained Model via Self-supervised Contrastive Learning.
Cho K, Kim KD, Nam Y … +9 more , Jeong J, Kim J, Choi C, Lee S, Lee JS, Woo S, Hong GS, Seo JB, Kim N
J Digit Imaging · 2023 Jun · PMID 36702988 · Full text
Training deep learning models on medical images heavily depends on experts' expensive and laborious manual labels. In addition, these images, labels, and even models themselves are not widely publicly accessible and suff...
Training deep learning models on medical images heavily depends on experts' expensive and laborious manual labels. In addition, these images, labels, and even models themselves are not widely publicly accessible and suffer from various kinds of bias and imbalances. In this paper, chest X-ray pre-trained model via self-supervised contrastive learning (CheSS) was proposed to learn models with various representations in chest radiographs (CXRs). Our contribution is a publicly accessible pretrained model trained with a 4.8-M CXR dataset using self-supervised learning with a contrastive learning and its validation with various kinds of downstream tasks including classification on the 6-class diseases in internal dataset, diseases classification in CheXpert, bone suppression, and nodule generation. When compared to a scratch model, on the 6-class classification test dataset, we achieved 28.5% increase in accuracy. On the CheXpert dataset, we achieved 1.3% increase in mean area under the receiver operating characteristic curve on the full dataset and 11.4% increase only using 1% data in stress test manner. On bone suppression with perceptual loss, we achieved improvement in peak signal to noise ratio from 34.99 to 37.77, structural similarity index measure from 0.976 to 0.977, and root-square-mean error from 4.410 to 3.301 when compared to ImageNet pretrained model. Finally, on nodule generation, we achieved improvement in Fréchet inception distance from 24.06 to 17.07. Our study showed the decent transferability of CheSS weights. CheSS weights can help researchers overcome data imbalance, data shortage, and inaccessibility of medical image datasets. CheSS weight is available at https://github.com/mi2rl/CheSS .
RbQE: An Efficient Method for Content-Based Medical Image Retrieval Based on Query Expansion.
Rashad M, Afifi I, Abdelfatah M
J Digit Imaging · 2023 Jun · PMID 36702987 · Full text
Systems for retrieving and managing content-based medical images are becoming more important, especially as medical imaging technology advances and the medical image database grows. In addition, these systems can also us...
Systems for retrieving and managing content-based medical images are becoming more important, especially as medical imaging technology advances and the medical image database grows. In addition, these systems can also use medical images to better grasp and gain a deeper understanding of the causes and treatments of different diseases, not just for diagnostic purposes. For achieving all these purposes, there is a critical need for an efficient and accurate content-based medical image retrieval (CBMIR) method. This paper proposes an efficient method (RbQE) for the retrieval of computed tomography (CT) and magnetic resonance (MR) images. RbQE is based on expanding the features of querying and exploiting the pre-trained learning models AlexNet and VGG-19 to extract compact, deep, and high-level features from medical images. There are two searching procedures in RbQE: a rapid search and a final search. In the rapid search, the original query is expanded by retrieving the top-ranked images from each class and is used to reformulate the query by calculating the mean values for deep features of the top-ranked images, resulting in a new query for each class. In the final search, the new query that is most similar to the original query will be used for retrieval from the database. The performance of the proposed method has been compared to state-of-the-art methods on four publicly available standard databases, namely, TCIA-CT, EXACT09-CT, NEMA-CT, and OASIS-MRI. Experimental results show that the proposed method exceeds the compared methods by 0.84%, 4.86%, 1.24%, and 14.34% in average retrieval precision (ARP) for the TCIA-CT, EXACT09-CT, NEMA-CT, and OASIS-MRI databases, respectively.
MRI-Based Radiomics Approach Predicts Tumor Recurrence in ER + /HER2 - Early Breast Cancer Patients.
Chiacchiaretta P, Mastrodicasa D, Chiarelli AM … +17 more , Luberti R, Croce P, Sguera M, Torrione C, Marinelli C, Marchetti C, Domenico A, Cocco G, Di Credico A, Russo A, D'Eramo C, Corvino A, Colasurdo M, Sensi SL, Muzi M, Caulo M, Delli Pizzi A
J Digit Imaging · 2023 Jun · PMID 36698037 · Full text
Oncotype Dx Recurrence Score (RS) has been validated in patients with ER + /HER2 - invasive breast carcinoma to estimate patient risk of recurrence and guide the use of adjuvant chemotherapy. We investigated the role of...
Oncotype Dx Recurrence Score (RS) has been validated in patients with ER + /HER2 - invasive breast carcinoma to estimate patient risk of recurrence and guide the use of adjuvant chemotherapy. We investigated the role of MRI-based radiomics features extracted from the tumor and the peritumoral tissues to predict the risk of tumor recurrence. A total of 62 patients with biopsy-proved ER + /HER2 - breast cancer who underwent pre-treatment MRI and Oncotype Dx were included. An RS > 25 was considered discriminant between low-intermediate and high risk of tumor recurrence. Two readers segmented each tumor. Radiomics features were extracted from the tumor and the peritumoral tissues. Partial least square (PLS) regression was used as the multivariate machine learning algorithm. PLS β-weights of radiomics features included the 5% features with the largest β-weights in magnitude (top 5%). Leave-one-out nested cross-validation (nCV) was used to achieve hyperparameter optimization and evaluate the generalizable performance of the procedure. The diagnostic performance of the radiomics model was assessed through receiver operating characteristic (ROC) analysis. A null hypothesis probability threshold of 5% was chosen (p < 0.05). The exploratory analysis for the complete dataset revealed an average absolute correlation among features of 0.51. The nCV framework delivered an AUC of 0.76 (p = 1.1∙10). When combining "early" and "peak" DCE images of only T or TST, a tendency toward statistical significance was obtained for TST with an AUC of 0.61 (p = 0.05). The 47 features included in the top 5% were balanced between T and TST (23 and 24, respectively). Moreover, 33/47 (70%) were texture-related, and 25/47 (53%) were derived from high-resolution images (1 mm). A radiomics-based machine learning approach shows the potential to accurately predict the recurrence risk in early ER + /HER2 - breast cancer patients.
The Virtual Radiology Reading Room: Initial Perceptions of Referring Providers and Radiologists.
Yacoub JH, Bourne MD, Krishnan P
J Digit Imaging · 2023 Jun · PMID 36698036 · Full text
The objective of this study is to assess the initial perception of referring providers and radiologists to a virtual consultation solution (the Virtual Radiology Reading Room, VR3). VR3 is specifically designed to replac...
The objective of this study is to assess the initial perception of referring providers and radiologists to a virtual consultation solution (the Virtual Radiology Reading Room, VR3). VR3 is specifically designed to replace the radiology reading room phone and enable the radiologist to continue to work as part of the clinical care team fielding radiology consults without being confined to the same physical space. Surveys of providers' and radiologists' initial experience were conducted approximately 6 months after initial deployment. Users were asked about their overall impression, and how well the solution integrates with their workflow as well as how it compares to traditional phone calls to the reading room. Forty of 71 referring providers and 27 of 44 radiologists responded to our survey. VR3 was rated 4.7 out of 5 stars by referrers and 4.1 by radiologists. Seventy percent of referrers and radiologists preferred VR3 to the phone while 4.5% of referrers and 11% of radiologists preferred the phone. Referring providers and radiologists expressed a positive initial perception of the Virtual Radiology Reading Room and prefer it to traditional phone calls to the reading room.
Effect of Contrast Level and Image Format on a Deep Learning Algorithm for the Detection of Pneumothorax with Chest Radiography.
Yoon MS, Kwon G, Oh J … +5 more , Ryu J, Lim J, Kang BK, Lee J, Han DK
J Digit Imaging · 2023 Jun · PMID 36698035 · Full text
Under the black-box nature in the deep learning model, it is uncertain how the change in contrast level and format affects the performance. We aimed to investigate the effect of contrast level and image format on the eff...
Under the black-box nature in the deep learning model, it is uncertain how the change in contrast level and format affects the performance. We aimed to investigate the effect of contrast level and image format on the effectiveness of deep learning for diagnosing pneumothorax on chest radiographs. We collected 3316 images (1016 pneumothorax and 2300 normal images), and all images were set to the standard contrast level (100%) and stored in the Digital Imaging and Communication in Medicine and Joint Photographic Experts Group (JPEG) formats. Data were randomly separated into 80% of training and 20% of test sets, and the contrast of images in the test set was changed to 5 levels (50%, 75%, 100%, 125%, and 150%). We trained the model to detect pneumothorax using ResNet-50 with 100% level images and tested with 5-level images in the two formats. While comparing the overall performance between each contrast level in the two formats, the area under the receiver-operating characteristic curve (AUC) was significantly different (all p < 0.001) except between 125 and 150% in JPEG format (p = 0.382). When comparing the two formats at same contrast levels, AUC was significantly different (all p < 0.001) except 50% and 100% (p = 0.079 and p = 0.082, respectively). The contrast level and format of medical images could influence the performance of the deep learning model. It is required to train with various contrast levels and formats of image, and further image processing for improvement and maintenance of the performance.
Skin Cancer Classification Using Deep Spiking Neural Network.
Qasim Gilani S, Syed T, Umair M … +1 more , Marques O
J Digit Imaging · 2023 Jun · PMID 36690775 · Full text
Skin cancer is one of the primary causes of death globally, and experts diagnose it by visual inspection, which can be inaccurate. The need for developing a computer-aided method to aid dermatologists in diagnosing skin...
Skin cancer is one of the primary causes of death globally, and experts diagnose it by visual inspection, which can be inaccurate. The need for developing a computer-aided method to aid dermatologists in diagnosing skin cancer is highlighted by the fact that early identification can lower the number of deaths caused by skin malignancies. Among computer-aided techniques, deep learning is the most popular for identifying cancer from skin lesion images. Due to their power-efficient behavior, spiking neural networks are attractive deep neural networks for hardware implementation. We employed deep spiking neural networks using the surrogate gradient descent method to classify 3670 melanoma and 3323 non-melanoma images from the ISIC 2019 dataset. We achieved an accuracy of 89.57% and an F1 score of 90.07% using the proposed spiking VGG-13 model, which is higher than the VGG-13 and AlexNet using less trainable parameters.
Using Transfer Learning of Convolutional Neural Network on Neck Radiographs to Identify Acute Epiglottitis.
Lin YT, Shia BC, Chang CJ … +3 more , Wu Y, Yang JD, Kang JH
J Digit Imaging · 2023 Jun · PMID 36658377 · Full text
Acute epiglottitis (AE) is a life-threatening condition and needs to be recognized timely. Diagnosis of AE with a lateral neck radiograph yields poor reliability and sensitivity. Convolutional neural networks (CNN) are p...
Acute epiglottitis (AE) is a life-threatening condition and needs to be recognized timely. Diagnosis of AE with a lateral neck radiograph yields poor reliability and sensitivity. Convolutional neural networks (CNN) are powerful tools to assist the analysis of medical images. This study aimed to develop an artificial intelligence model using CNN-based transfer learning to identify AE in lateral neck radiographs. All cases in this study are from two hospitals, a medical center, and a local teaching hospital in Taiwan. In this retrospective study, we collected 251 lateral neck radiographs of patients with AE and 936 individuals without AE. Neck radiographs obtained from patients without and with AE were used as the input for model transfer learning in a pre-trained CNN including Inception V3, Densenet201, Resnet101, VGG19, and Inception V2 to select the optimal model. We used five-fold cross-validation to estimate the performance of the selected model. The confusion matrix of the final model was analyzed. We found that Inception V3 yielded the best results as the optimal model among all pre-train models. Based on the average value of the fivefold cross-validation, the confusion metrics were obtained: accuracy = 0.92, precision = 0.94, recall = 0.90, and area under the curve (AUC) = 0.96. Using the Inception V3-based model can provide an excellent performance to identify AE based on radiographic images. We suggest using the CNN-based model which can offer a non-invasive, accurate, and fast diagnostic method for AE in the future.
Automated Adrenal Gland Disease Classes Using Patch-Based Center Symmetric Local Binary Pattern Technique with CT Images.
Sut SK, Koc M, Zorlu G … +7 more , Serhatlioglu I, Barua PD, Dogan S, Baygin M, Tuncer T, Tan RS, Acharya UR
J Digit Imaging · 2023 Jun · PMID 36658376 · Full text
Incidental adrenal masses are seen in 5% of abdominal computed tomography (CT) examinations. Accurate discrimination of the possible differential diagnoses has important therapeutic and prognostic significance. A new han...
Incidental adrenal masses are seen in 5% of abdominal computed tomography (CT) examinations. Accurate discrimination of the possible differential diagnoses has important therapeutic and prognostic significance. A new handcrafted machine learning method has been developed for the automated and accurate classification of adrenal gland CT images. A new dataset comprising 759 adrenal gland CT image slices from 96 subjects were analyzed. Experts had labeled the collected images into four classes: normal, pheochromocytoma, lipid-poor adenoma, and metastasis. The images were preprocessed, resized, and the image features were extracted using the center symmetric local binary pattern (CS-LBP) method. CT images were next divided into 16 × 16 fixed-size patches, and further feature extraction using CS-LBP was performed on these patches. Next, extracted features were selected using neighborhood component analysis (NCA) to obtain the most meaningful ones for downstream classification. Finally, the selected features were classified using k-nearest neighbor (kNN), support vector machine (SVM), and neural network (NN) classifiers to obtain the optimum performing model. Our proposed method obtained an accuracy of 99.87%, 99.21%, and 98.81% with kNN, SVM, and NN classifiers, respectively. Hence, the kNN classifier yielded the highest classification results with no pathological image misclassified as normal. Our developed fixed patch CS-LBP-based automatic classification of adrenal gland pathologies on CT images is highly accurate and has low time complexity [Formula: see text]. It has the potential to be used for screening of adrenal gland disease classes with CT images.
Optimal Deep CNN-Based Vectorial Variation Filter for Medical Image Denoising.
Atal DK
J Digit Imaging · 2023 Jun · PMID 36650303 · Full text
Medical imaging has acquired more attention due to the emerging design of wireless technologies, the internet, and data storage. The reflection of these technologies has gained attraction in medicine and medical sciences...
Medical imaging has acquired more attention due to the emerging design of wireless technologies, the internet, and data storage. The reflection of these technologies has gained attraction in medicine and medical sciences facilitating the diagnosis and treatment of different diseases in an effective manner. However, medical images are vulnerable to noise, which can make the image unclear and perplex the identification. Thus, denoising of medical images is imperative for processing medical images. This paper devises a novel optimal deep convolution neural network-based vectorial variation (ODVV) filter for denoising medical computed tomography (CT) images and Lena images. Here, the input medical images are fed to a noisy pixel map identification module wherein the deep convolutional neural network (Deep CNN) is adapted for discovering noisy pixel maps. Here, Deep CNN training is done with the Adam algorithm. Once noisy pixels are identified, it is further given to noise removal module which is performed using the proposed optimization algorithm, namely Feedback Artificial Lion (FAL). Here, the FAL is devised by combining the FAT and Lion algorithm. After noise removal, the pixel enhancement is performed using the vectorial total variation norm to get final pixel-enhanced image. The proposed FAL algorithm offered enhanced performance in contrast to other techniques with the highest peak signal-to-noise ratio (PSNR) of 24.149 dB, highest second-derivative-like measure of enhancement (SDME) of 32.142 dB, highest structural index similarity (SSIM) of 0.800, and Edge Preserve Index (EPI) of 0.9267.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe