Journal of Medical Imaging最新文献

{"title":"Stain SAN: simultaneous augmentation and normalization for histopathology images.","authors":"Taebin Kim, Yao Li, Benjamin C Calhoun, Aatish Thennavan, Lisa A Carey, W Fraser Symmans, Melissa A Troester, Charles M Perou, J S Marron","doi":"10.1117/1.JMI.11.4.044006","DOIUrl":"10.1117/1.JMI.11.4.044006","url":null,"abstract":"<p><strong>Purpose: </strong>We address the need for effective stain domain adaptation methods in histopathology to enhance the performance of downstream computational tasks, particularly classification. Existing methods exhibit varying strengths and weaknesses, prompting the exploration of a different approach. The focus is on improving stain color consistency, expanding the stain domain scope, and minimizing the domain gap between image batches.</p><p><strong>Approach: </strong>We introduce a new domain adaptation method, Stain simultaneous augmentation and normalization (SAN), designed to adjust the distribution of stain colors to align with a target distribution. Stain SAN combines the merits of established methods, such as stain normalization, stain augmentation, and stain mix-up, while mitigating their inherent limitations. Stain SAN adapts stain domains by resampling stain color matrices from a well-structured target distribution.</p><p><strong>Results: </strong>Experimental evaluations of cross-dataset clinical estrogen receptor status classification demonstrate the efficacy of Stain SAN and its superior performance compared with existing stain adaptation methods. In one case, the area under the curve (AUC) increased by 11.4%. Overall, our results clearly show the improvements made over the history of the development of these methods culminating with substantial enhancement provided by Stain SAN. Furthermore, we show that Stain SAN achieves results comparable with the state-of-the-art generative adversarial network-based approach without requiring separate training for stain adaptation or access to the target domain during training. Stain SAN's performance is on par with HistAuGAN, proving its effectiveness and computational efficiency.</p><p><strong>Conclusions: </strong>Stain SAN emerges as a promising solution, addressing the potential shortcomings of contemporary stain adaptation methods. Its effectiveness is underscored by notable improvements in the context of clinical estrogen receptor status classification, where it achieves the best AUC performance. The findings endorse Stain SAN as a robust approach for stain domain adaptation in histopathology images, with implications for advancing computational tasks in the field.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11342968/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142056923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Examining feature extraction and classification modules in machine learning for diagnosis of low-dose computed tomographic screening-detected <i>in vivo</i> lesions.","authors":"Daniel D Liang, David D Liang, Marc J Pomeroy, Yongfeng Gao, Licheng R Kuo, Lihong C Li","doi":"10.1117/1.JMI.11.4.044501","DOIUrl":"10.1117/1.JMI.11.4.044501","url":null,"abstract":"<p><strong>Purpose: </strong>Medical imaging-based machine learning (ML) for computer-aided diagnosis of <i>in vivo</i> lesions consists of two basic components or modules of (i) feature extraction from non-invasively acquired medical images and (ii) feature classification for prediction of malignancy of lesions detected or localized in the medical images. This study investigates their individual performances for diagnosis of low-dose computed tomography (CT) screening-detected lesions of pulmonary nodules and colorectal polyps.</p><p><strong>Approach: </strong>Three feature extraction methods were investigated. One uses the mathematical descriptor of gray-level co-occurrence image texture measure to extract the Haralick image texture features (HFs). One uses the convolutional neural network (CNN) architecture to extract deep learning (DL) image abstractive features (DFs). The third one uses the interactions between lesion tissues and X-ray energy of CT to extract tissue-energy specific characteristic features (TFs). All the above three categories of extracted features were classified by the random forest (RF) classifier with comparison to the DL-CNN method, which reads the images, extracts the DFs, and classifies the DFs in an end-to-end manner. The ML diagnosis of lesions or prediction of lesion malignancy was measured by the area under the receiver operating characteristic curve (AUC). Three lesion image datasets were used. The lesions' tissue pathological reports were used as the learning labels.</p><p><strong>Results: </strong>Experiments on the three datasets produced AUC values of 0.724 to 0.878 for the HFs, 0.652 to 0.965 for the DFs, and 0.985 to 0.996 for the TFs, compared to the DL-CNN of 0.694 to 0.964. These experimental outcomes indicate that the RF classifier performed comparably to the DL-CNN classification module and the extraction of tissue-energy specific characteristic features dramatically improved AUC value.</p><p><strong>Conclusions: </strong>The feature extraction module is more important than the feature classification module. Extraction of tissue-energy specific characteristic features is more important than extraction of image abstractive and characteristic features.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11234229/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141591735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Task-based assessment for neural networks: evaluating undersampled MRI reconstructions based on human observer signal detection.","authors":"Joshua D Herman, Rachel E Roca, Alexandra G O'Neill, Marcus L Wong, Sajan Goud Lingala, Angel R Pineda","doi":"10.1117/1.JMI.11.4.045503","DOIUrl":"10.1117/1.JMI.11.4.045503","url":null,"abstract":"<p><strong>Purpose: </strong>Recent research explores using neural networks to reconstruct undersampled magnetic resonance imaging. Because of the complexity of the artifacts in the reconstructed images, there is a need to develop task-based approaches to image quality. We compared conventional global quantitative metrics to evaluate image quality in undersampled images generated by a neural network with human observer performance in a detection task. The purpose is to study which acceleration (2×, 3×, 4×, 5×) would be chosen with the conventional metrics and compare it to the acceleration chosen by human observer performance.</p><p><strong>Approach: </strong>We used common global metrics for evaluating image quality: the normalized root mean squared error (NRMSE) and structural similarity (SSIM). These metrics are compared with a measure of image quality that incorporates a subtle signal for a specific task to allow for image quality assessment that locally evaluates the effect of undersampling on a signal. We used a U-Net to reconstruct under-sampled images with 2×, 3×, 4×, and 5× one-dimensional undersampling rates. Cross-validation was performed for a 500- and a 4000-image training set with both SSIM and MSE losses. A two-alternative forced choice (2-AFC) observer study was carried out for detecting a subtle signal (small blurred disk) from images with the 4000-image training set.</p><p><strong>Results: </strong>We found that for both loss functions, the human observer performance on the 2-AFC studies led to a choice of a 2× undersampling, but the SSIM and NRMSE led to a choice of a 3× undersampling.</p><p><strong>Conclusions: </strong>For this detection task using a subtle small signal at the edge of detectability, SSIM and NRMSE led to an overestimate of the achievable undersampling using a U-Net before a steep loss of image quality between 2×, 3×, 4×, 5× undersampling rates when compared to the performance of human observers in the detection task.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11321363/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141983636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Left ventricular structural integrity on tetralogy of Fallot patients: approach using longitudinal relaxation time mapping.","authors":"Giorgos Broumpoulis, Efstratios Karavasilis, Niki Lama, Ioannis Papadopoulos, Panagiotis Zachos, Sotiria Apostolopoulou, Nikolaos Kelekis","doi":"10.1117/1.JMI.11.4.044004","DOIUrl":"10.1117/1.JMI.11.4.044004","url":null,"abstract":"<p><strong>Purpose: </strong>Tetralogy of Fallot (TOF) is a congenital heart disease, and patients undergo surgical repair early in their lives. The evaluation of TOF patients is continuous through their adulthood. The use of cardiac magnetic resonance imaging (CMR) is vital for the evaluation of TOF patients. We aim to correlate advanced MRI sequences [parametric longitudinal relaxation time (T1), extracellular volume (ECV) mapping] with cardiac functionality to provide biomarkers for the evaluation of these patients.</p><p><strong>Methods: </strong>A complete CMR examination with the same imaging protocol was conducted in a total of 11 TOF patients and a control group of 25 healthy individuals. A Modified Look-Locker Inversion recovery (MOLLI) sequence was included to acquire the global T1 myocardial relaxation times of the left ventricular (LV) pre and post-contrast administration. Appropriate software (Circle cmr42) was used for the CMR analysis and the calculation of native, post-contrast T1, and ECV maps. A regression analysis was conducted for the correlation between global LV T1 values and right ventricular (RV) functional indices.</p><p><strong>Results: </strong>Statistically significant results were obtained for RV cardiac index [RV_CI= -32.765 + 0.029 × T1 native; <math><mrow><mi>p</mi> <mo>=</mo> <mn>0.003</mn></mrow> </math> ], RV end diastolic volume [RV_EDV/BSA = -1023.872 + 0.902 × T1 native; <math><mrow><mi>p</mi> <mo>=</mo> <mn>0.001</mn></mrow> </math> ], and RV end systolic volume [RV_ESV/BSA = -536.704 + 0.472 × T1 native; <math><mrow><mi>p</mi> <mo>=</mo> <mn>0.011</mn></mrow> </math> ].</p><p><strong>Conclusions: </strong>We further support the diagnostic importance of T1 mapping as a structural imaging tool in CMR. In addition to the well-known affected RV function in TOF patients, the LV structure is also impaired as there is a strong correlation between LV T1 mapping and RV function, evoking that the heart operates as an entity.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11293558/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141890473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cone-beam CT with a noncircular (sine-on-sphere) orbit: imaging performance of a clinical system for image-guided interventions.","authors":"A Kyle Jones, Moiz Ahmad, Shaan M Raza, Stephen R Chen, Jeffrey H Siewerdsen","doi":"10.1117/1.JMI.11.4.043503","DOIUrl":"10.1117/1.JMI.11.4.043503","url":null,"abstract":"<p><strong>Purpose: </strong>We aim to compare the imaging performance of a cone-beam CT (CBCT) imaging system with noncircular scan protocols (sine-on-sphere) to a conventional circular orbit.</p><p><strong>Approach: </strong>A biplane C-arm system (ARTIS Icono; Siemens Healthineers) capable of circular and noncircular CBCT acquisition was used, with the latter orbit (sine-on-sphere, \"Sine Spin\") executing a sinusoidal motion with <math><mrow><mo>±</mo> <mn>10</mn> <mtext>  </mtext> <mi>deg</mi></mrow> </math> tilt amplitude over the half-scan orbit. A test phantom was used for the characterization of image uniformity, noise, noise-power spectrum (NPS), spatial resolution [modulation transfer function (MTF) in axial and oblique directions], and cone-beam artifacts. Findings were interpreted using an anthropomorphic head phantom with respect to pertinent tasks in skull base neurosurgery.</p><p><strong>Results: </strong>The noncircular scan protocol exhibited several advantages associated with improved 3D sampling-evident in the NPS as filling of the null cone about the <math> <mrow><msub><mi>f</mi> <mi>z</mi></msub> </mrow> </math> spatial frequency axis and reduction of cone-beam artifacts. The region of support at the longitudinal extrema was reduced from 16 to <math><mrow><mo>∼</mo> <mn>12</mn> <mtext>  </mtext> <mi>cm</mi></mrow> </math> at a radial distance of 6.5 cm. Circular and noncircular orbits exhibited nearly identical image uniformity and quantum noise, demonstrating cupping of <math><mrow><mo>-</mo> <mn>16.7</mn> <mo>%</mo></mrow> </math> and overall noise of <math><mrow><mo>∼</mo> <mn>27</mn> <mtext>  </mtext> <mi>HU</mi></mrow> </math> . Although both the radially averaged axial MTF ( <math> <mrow><msub><mi>f</mi> <mrow><mi>x</mi> <mo>,</mo> <mi>y</mi></mrow> </msub> </mrow> </math> ) and 45 deg oblique MTF ( <math> <mrow><msub><mi>f</mi> <mrow><mi>x</mi> <mo>,</mo> <mi>y</mi> <mo>,</mo> <mi>z</mi></mrow> </msub> </mrow> </math> ) were <math><mrow><mo>∼</mo> <mn>20</mn> <mo>%</mo></mrow> </math> lower for the noncircular orbit compared with the circular orbit at the default full reconstruction field of view (FOV), there was no difference in spatial resolution for the medium reconstruction FOV (smaller voxel size). Differences in the perceptual image quality for the anthropomorphic phantom reinforced the objective, quantitative findings, including reduced beam-hardening and cone-beam artifacts about structures of interest in the skull base.</p><p><strong>Conclusions: </strong>Image quality differences between circular and noncircular CBCT orbits were quantitatively evaluated on a clinical system in the context of neurosurgery. The primary performance advantage for the noncircular orbit was the improved sampling and elimination of cone-beam artifacts.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11342057/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142056921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of human observer impression of X-ray fluoroscopy and angiography image quality with technical changes to image quality.","authors":"Jelena M Mihailovic, Yoshihisa Kanaji, Daniel Miller, Malcolm R Bell, Kenneth A Fetterly","doi":"10.1117/1.JMI.11.4.045502","DOIUrl":"10.1117/1.JMI.11.4.045502","url":null,"abstract":"<p><strong>Purpose: </strong>Spatio-temporal variability in clinical fluoroscopy and cine angiography images combined with nonlinear image processing prevents the application of traditional image quality measurements in the cardiac catheterization laboratory. We aimed to develop and validate methods to measure human observer impressions of the image quality.</p><p><strong>Approach: </strong>Multi-frame images of the thorax of a euthanized pig were acquired to provide an anatomical background. The detector dose was varied from 6 to 200 nGy (increments 2×), and 0.6 and 1.0 mm focal spots were used. Two coronary stents with/without 0.5 mm separation and a synthetic right coronary artery (RCA) with hemispherical defects were embedded into the background images as test objects. The quantitative observer ( <math><mrow><mi>n</mi> <mo>=</mo> <mn>17</mn></mrow> </math> ) performance was measured using a two-alternating forced-choice test of whether stents were separated and by a count of visible right coronary artery defects. Qualitative impressions of noise, spatial resolution, and overall image quality were measured using a visual analog scale (VAS). A paired <math><mrow><mi>t</mi></mrow> </math> -test and multinomial logistic regression model were used to identify statistically significant factors affecting the observer's impression image quality.</p><p><strong>Results: </strong>The proportion of correct detection of stent separation and the number of reported right coronary artery defects changed significantly with detector dose increment in the 6 to 100 nGy ( <math><mrow><mi>p</mi> <mo><</mo> <mn>0.05</mn></mrow> </math> ). Although a trend favored the 0.6 versus 1.0 mm focal spot for these quantitative assessments, this was insignificant. Visual analog scale measurements changed significantly with detector dose increments in the range of 24 to 100 nGy and focal spot size ( <math><mrow><mi>p</mi> <mo><</mo> <mn>0.05</mn></mrow> </math> ). The application of multinomial logistic regression analysis to observer VAS scores demonstrated sensitivity matching of the paired <math><mrow><mi>t</mi></mrow> </math> -test applied to quantitative observer performance measurements.</p><p><strong>Conclusions: </strong>Both quantitative and qualitative measurements of observer impression of the image quality were sensitive to image quality changes associated with changing the detector dose and focal spot size. These findings encourage future work that uses qualitative image quality measurements to assess clinical fluoroscopy and angiography image quality.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11316400/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141917779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring synthetic datasets for computer-aided detection: a case study using phantom scan data for enhanced lung nodule false positive reduction.","authors":"Mohammad Mehdi Farhangi, Michael Maynord, Cornelia Fermüller, Yiannis Aloimonos, Berkman Sahiner, Nicholas Petrick","doi":"10.1117/1.JMI.11.4.044507","DOIUrl":"10.1117/1.JMI.11.4.044507","url":null,"abstract":"<p><strong>Purpose: </strong>Synthetic datasets hold the potential to offer cost-effective alternatives to clinical data, ensuring privacy protections and potentially addressing biases in clinical data. We present a method leveraging such datasets to train a machine learning algorithm applied as part of a computer-aided detection (CADe) system.</p><p><strong>Approach: </strong>Our proposed approach utilizes clinically acquired computed tomography (CT) scans of a physical anthropomorphic phantom into which manufactured lesions were inserted to train a machine learning algorithm. We treated the training database obtained from the anthropomorphic phantom as a simplified representation of clinical data and increased the variability in this dataset using a set of randomized and parameterized augmentations. Furthermore, to mitigate the inherent differences between phantom and clinical datasets, we investigated adding unlabeled clinical data into the training pipeline.</p><p><strong>Results: </strong>We apply our proposed method to the false positive reduction stage of a lung nodule CADe system in CT scans, in which regions of interest containing potential lesions are classified as nodule or non-nodule regions. Experimental results demonstrate the effectiveness of the proposed method; the system trained on labeled data from physical phantom scans and unlabeled clinical data achieves a sensitivity of 90% at eight false positives per scan. Furthermore, the experimental results demonstrate the benefit of the physical phantom in which the performance in terms of competitive performance metric increased by 6% when a training set consisting of 50 clinical CT scans was enlarged by the scans obtained from the physical phantom.</p><p><strong>Conclusions: </strong>The scalability of synthetic datasets can lead to improved CADe performance, particularly in scenarios in which the size of the labeled clinical data is limited or subject to inherent bias. Our proposed approach demonstrates an effective utilization of synthetic datasets for training machine learning algorithms.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11304989/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141907942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-based automated segmentation for ovarian/adnexal masses and their internal components on ultrasound imaging.","authors":"Heather M Whitney, Roni Yoeli-Bik, Jacques S Abramowicz, Li Lan, Hui Li, Ryan E Longman, Ernst Lengyel, Maryellen L Giger","doi":"10.1117/1.JMI.11.4.044505","DOIUrl":"10.1117/1.JMI.11.4.044505","url":null,"abstract":"<p><strong>Purpose: </strong>Segmentation of ovarian/adnexal masses from surrounding tissue on ultrasound images is a challenging task. The separation of masses into different components may also be important for radiomic feature extraction. Our study aimed to develop an artificial intelligence-based automatic segmentation method for transvaginal ultrasound images that (1) outlines the exterior boundary of adnexal masses and (2) separates internal components.</p><p><strong>Approach: </strong>A retrospective ultrasound imaging database of adnexal masses was reviewed for exclusion criteria at the patient, mass, and image levels, with one image per mass. The resulting 54 adnexal masses (36 benign/18 malignant) from 53 patients were separated by patient into training (26 benign/12 malignant) and independent test (10 benign/6 malignant) sets. U-net segmentation performance on test images compared to expert detailed outlines was measured using the Dice similarity coefficient (DSC) and the ratio of the Hausdorff distance to the effective diameter of the outline ( <math> <mrow> <msub><mrow><mi>R</mi></mrow> <mrow><mi>HD</mi> <mtext>-</mtext> <mi>D</mi></mrow> </msub> </mrow> </math> ) for each mass. Subsequently, in discovery mode, a two-level fuzzy c-means (FCM) unsupervised clustering approach was used to separate the pixels within masses belonging to hypoechoic or hyperechoic components.</p><p><strong>Results: </strong>The DSC (median [95% confidence interval]) was 0.91 [0.78, 0.96], and <math> <mrow> <msub><mrow><mi>R</mi></mrow> <mrow><mi>HD</mi> <mtext>-</mtext> <mi>D</mi></mrow> </msub> </mrow> </math> was 0.04 [0.01, 0.12], indicating strong agreement with expert outlines. Clinical review of the internal separation of masses into echogenic components demonstrated a strong association with mass characteristics.</p><p><strong>Conclusion: </strong>A combined U-net and FCM algorithm for automatic segmentation of adnexal masses and their internal components achieved excellent results compared with expert outlines and review, supporting future radiomic feature-based classification of the masses by components.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11301525/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141903209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Field-of-view extension for brain diffusion MRI via deep generative models.","authors":"Chenyu Gao, Shunxing Bao, Michael E Kim, Nancy R Newlin, Praitayini Kanakaraj, Tianyuan Yao, Gaurav Rudravaram, Yuankai Huo, Daniel Moyer, Kurt Schilling, Walter A Kukull, Arthur W Toga, Derek B Archer, Timothy J Hohman, Bennett A Landman, Zhiyuan Li","doi":"10.1117/1.JMI.11.4.044008","DOIUrl":"10.1117/1.JMI.11.4.044008","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;In brain diffusion magnetic resonance imaging (dMRI), the volumetric and bundle analyses of whole-brain tissue microstructure and connectivity can be severely impeded by an incomplete field of view (FOV). We aim to develop a method for imputing the missing slices directly from existing dMRI scans with an incomplete FOV. We hypothesize that the imputed image with a complete FOV can improve whole-brain tractography for corrupted data with an incomplete FOV. Therefore, our approach provides a desirable alternative to discarding the valuable brain dMRI data, enabling subsequent tractography analyses that would otherwise be challenging or unattainable with corrupted data.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Approach: &lt;/strong&gt;We propose a framework based on a deep generative model that estimates the absent brain regions in dMRI scans with an incomplete FOV. The model is capable of learning both the diffusion characteristics in diffusion-weighted images (DWIs) and the anatomical features evident in the corresponding structural images for efficiently imputing missing slices of DWIs in the incomplete part of the FOV.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;For evaluating the imputed slices, on the Wisconsin Registry for Alzheimer's Prevention (WRAP) dataset, the proposed framework achieved &lt;math&gt; &lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;PSNR&lt;/mi&gt; &lt;mrow&gt;&lt;mi&gt;b&lt;/mi&gt; &lt;mn&gt;0&lt;/mn&gt;&lt;/mrow&gt; &lt;/msub&gt; &lt;mo&gt;=&lt;/mo&gt; &lt;mn&gt;22.397&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; , &lt;math&gt; &lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;SSIM&lt;/mi&gt; &lt;mrow&gt;&lt;mi&gt;b&lt;/mi&gt; &lt;mn&gt;0&lt;/mn&gt;&lt;/mrow&gt; &lt;/msub&gt; &lt;mo&gt;=&lt;/mo&gt; &lt;mn&gt;0.905&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; , &lt;math&gt; &lt;mrow&gt; &lt;msub&gt;&lt;mrow&gt;&lt;mi&gt;PSNR&lt;/mi&gt;&lt;/mrow&gt; &lt;mrow&gt;&lt;mi&gt;b&lt;/mi&gt; &lt;mn&gt;1300&lt;/mn&gt;&lt;/mrow&gt; &lt;/msub&gt; &lt;mo&gt;=&lt;/mo&gt; &lt;mn&gt;22.479&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; , and &lt;math&gt; &lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;SSIM&lt;/mi&gt; &lt;mrow&gt;&lt;mi&gt;b&lt;/mi&gt; &lt;mn&gt;1300&lt;/mn&gt;&lt;/mrow&gt; &lt;/msub&gt; &lt;mo&gt;=&lt;/mo&gt; &lt;mn&gt;0.893&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; ; on the National Alzheimer's Coordinating Center (NACC) dataset, it achieved &lt;math&gt; &lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;PSNR&lt;/mi&gt; &lt;mrow&gt;&lt;mi&gt;b&lt;/mi&gt; &lt;mn&gt;0&lt;/mn&gt;&lt;/mrow&gt; &lt;/msub&gt; &lt;mo&gt;=&lt;/mo&gt; &lt;mn&gt;21.304&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; , &lt;math&gt; &lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;SSIM&lt;/mi&gt; &lt;mrow&gt;&lt;mi&gt;b&lt;/mi&gt; &lt;mn&gt;0&lt;/mn&gt;&lt;/mrow&gt; &lt;/msub&gt; &lt;mo&gt;=&lt;/mo&gt; &lt;mn&gt;0.892&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; , &lt;math&gt; &lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;PSNR&lt;/mi&gt; &lt;mrow&gt;&lt;mi&gt;b&lt;/mi&gt; &lt;mn&gt;1300&lt;/mn&gt;&lt;/mrow&gt; &lt;/msub&gt; &lt;mo&gt;=&lt;/mo&gt; &lt;mn&gt;21.599&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; , and &lt;math&gt; &lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;SSIM&lt;/mi&gt; &lt;mrow&gt;&lt;mi&gt;b&lt;/mi&gt; &lt;mn&gt;1300&lt;/mn&gt;&lt;/mrow&gt; &lt;/msub&gt; &lt;mo&gt;=&lt;/mo&gt; &lt;mn&gt;0.877&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; . The proposed framework improved the tractography accuracy, as demonstrated by an increased average Dice score for 72 tracts ( &lt;math&gt;&lt;mrow&gt;&lt;mi&gt;p&lt;/mi&gt; &lt;mo&gt;&lt;&lt;/mo&gt; &lt;mn&gt;0.001&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; ) on both the WRAP and NACC datasets.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Results suggest that the proposed framework achieved sufficient imputation performance in brain dMRI data with an incomplete FOV for improving whole-brain tractography, thereby repairing the corrupted data. Our approach achieved more accurate whole-brain tractography results with an extended and complete FOV and reduced the uncertainty when analyzing bundles associa","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11344266/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142056922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lung vessel connectivity map as anatomical prior knowledge for deep learning-based lung lobe segmentation.","authors":"Simone Bendazzoli, Emelie Bäcklin, Örjan Smedby, Birgitta Janerot-Sjoberg, Bryan Connolly, Chunliang Wang","doi":"10.1117/1.JMI.11.4.044001","DOIUrl":"10.1117/1.JMI.11.4.044001","url":null,"abstract":"<p><strong>Purpose: </strong>Our study investigates the potential benefits of incorporating prior anatomical knowledge into a deep learning (DL) method designed for the automated segmentation of lung lobes in chest CT scans.</p><p><strong>Approach: </strong>We introduce an automated DL-based approach that leverages anatomical information from the lung's vascular system to guide and enhance the segmentation process. This involves utilizing a lung vessel connectivity (LVC) map, which encodes relevant lung vessel anatomical data. Our study explores the performance of three different neural network architectures within the nnU-Net framework: a standalone U-Net, a multitasking U-Net, and a cascade U-Net.</p><p><strong>Results: </strong>Experimental findings suggest that the inclusion of LVC information in the DL model can lead to improved segmentation accuracy, particularly, in the challenging boundary regions of expiration chest CT volumes. Furthermore, our study demonstrates the potential for LVC to enhance the model's generalization capabilities. Finally, the method's robustness is evaluated through the segmentation of lung lobes in 10 cases of COVID-19, demonstrating its applicability in the presence of pulmonary diseases.</p><p><strong>Conclusions: </strong>Incorporating prior anatomical information, such as LVC, into the DL model shows promise for enhancing segmentation performance, particularly in the boundary regions. However, the extent of this improvement has limitations, prompting further exploration of its practical applicability.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11231955/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141581239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}