Artificial intelligence (AI) may extract prognostic information from MRI for localized prostate cancer. We evaluate whether AI-derived prostate and gross tumor volume (GTV) are associated with toxicity and oncologic outcomes after radiotherapy. We conducted a retrospective study of patients, who underwent radiotherapy between 2010 and 2017. We trained an AI segmentation algorithm to contour the prostate and GTV from patients treated with external-beam RT, and applied the algorithm to those treated with brachytherapy. AI prostate and GTV volumes were calculated from segmentation results. We evaluated whether AI GTV volume was associated with biochemical failure (BF) and metastasis. We evaluated whether AI prostate volume was associated with acute and late grade 2+ genitourinary toxicity, and International Prostate Symptom Score (IPSS) resolution for monotherapy and combination sets, separately. We identified 187 patients who received brachytherapy (monotherapy (N = 154) or combination therapy (N = 33)). AI GTV volume was associated with BF (hazard ratio (HR):1.28[1.14,1.44];p < 0.001) and metastasis (HR:1.34[1.18,1.53;p < 0.001). For the monotherapy subset, AI prostate volume was associated with both acute (adjusted odds ratio:1.16[1.07,1.25];p < 0.001) and late grade 2 + genitourinary toxicity (adjusted HR:1.04[1.01,1.07];p = 0.01), but not IPSS resolution (0.99[0.97,1.00];p = 0.13). For the combination therapy subset, AI prostate volume was not associated with either acute (p = 0.72) or late (p = 0.75) grade 2 + urinary toxicity. However, AI prostate volume was associated with IPSS resolution (0.96[0.93, 0.99];p = 0.01). AI-derived prostate and GTV volumes may be prognostic for toxicity and oncologic outcomes after RT. Such information may aid in treatment decision-making, given differences in outcomes among RT treatment modalities.

Accurate brain tumor segmentation from MRI images is critical in the medical industry, directly impacts the efficacy of diagnostic and treatment plans. Accurate segmentation of tumor region can be challenging, especially when noise and abnormalities are present. This research provides a systematic review of automatic brain tumor segmentation techniques, with a specific focus on the design of network architectures. The review categorizes existing methods into unsupervised and supervised learning techniques, as well as machine learning and deep learning approaches within supervised techniques. Deep learning techniques are thoroughly reviewed, with a particular focus on CNN-based, U-Net-based, transfer learning-based, transformer-based, and hybrid transformer-based methods. This survey encompasses a broad spectrum of automatic segmentation methodologies, from traditional machine learning approaches to advanced deep learning frameworks. It provides an in-depth comparison of performance metrics, model efficiency, and robustness across multiple datasets, particularly the BraTS dataset. The study further examines multi-modal MRI imaging and its influence on segmentation accuracy, addressing domain adaptation, class imbalance, and generalization challenges. The analysis highlights the current challenges in Computer-aided Diagnostic (CAD) systems, examining how different models and imaging sequences impact performance. Recent advancements in deep learning, especially the widespread use of U-Net architectures, have significantly enhanced medical image segmentation. This review critically evaluates these developments, focusing the iterative improvements in U-Net models that have driven progress in brain tumor segmentation. Furthermore, it explores various techniques for improving U-Net performance for medical applications, focussing on its potential for improving diagnostic and treatment planning procedures. The efficiency of these automated segmentation approaches is rigorously evaluated using the BraTS dataset, a benchmark dataset, part of the annual Multimodal Brain Tumor Segmentation Challenge (MICCAI). This evaluation provides insights into the current state-of-the-art and identifies key areas for future research and development.

Atrial fibrillation (AF) is the most common cardiac arrhythmia, affecting up to 2 % of the population. Catheter ablation is a promising treatment for AF, particularly for paroxysmal AF patients, but it often has high recurrence rates. Developing in silico models of patients' atria during the ablation procedure using cardiac MRI data may help reduce these rates. This study aims to develop an effective automated deep learning-based segmentation pipeline by compiling a specialized dataset and employing standardized labeling protocols to improve segmentation accuracy and efficiency. In doing so, we aim to achieve the highest possible accuracy and generalization ability while minimizing the burden on clinicians involved in manual data segmentation. We collected LGE-MRI data from VMRC and the cDEMRIS database. Two specialists manually labeled the data using standardized protocols to reduce subjective errors. Neural network (nnU-Net and smpU-Net++) performance was evaluated using statistical tests, including sensitivity and specificity analysis. A new database of LGE-MRI images, based on manual segmentation, was created (VMRC). Our approach with consistent labeling protocols achieved a Dice coefficient of 92.4 % ± 0.8 % for the cavity and 64.5 % ± 1.9 % for LA walls. Using the pre-trained RIFE model, we attained a Dice score of approximately 89.1 % ± 1.6 % for atrial LGE-MRI imputation, outperforming classical methods. Sensitivity and specificity values demonstrated substantial enhancement in the performance of neural networks trained with the new protocol. Standardized labeling and RIFE applications significantly improved machine learning tool efficiency for constructing 3D LA models. This novel approach supports integrating state-of-the-art machine learning methods into broader in silico pipelines for predicting ablation outcomes in AF patients.

Genome-wide association studies (GWAS) facilitate construction of polygenic risk scores (PRSs) for rheumatoid arthritis (RA) and idiopathic pulmonary fibrosis (IPF). We investigated associations of RA and IPF PRSs with RA and high-resolution chest computed tomography (HRCT) parenchymal lung abnormalities. Participants in COPDGene, a prospective multicenter cohort of current/former smokers, had chest HRCT at study enrollment. Using genome-wide genotyping, RA and IPF PRSs were constructed using GWAS summary statistics. HRCT imaging underwent visual inspection for interstitial lung abnormalities (ILA) and quantitative CT (QCT) analysis using a machine-learning algorithm that quantified percentage of normal lung, interstitial abnormalities, and emphysema. RA was identified through self-report and DMARD use. We investigated associations of RA and IPF PRSs with RA, ILA, and QCT features using multivariable logistic and linear regression. We analyzed 9,230 COPDGene participants (mean age 59.6 years, 46.4 % female, 67.2 % non-Hispanic White, 32.8 % Black/African American). In non-Hispanic White participants, RA PRS was associated with RA diagnosis (OR 1.32 per unit, 95 %CI 1.18-1.49) but not ILA or QCT features. Among non-Hispanic White participants, IPF PRS was associated with ILA (OR 1.88 per unit, 95 %CI 1.52-2.32) and quantitative interstitial abnormalities (adjusted β=+0.50 % per unit, p = 7.3 × 10^-8) but not RA. There were no statistically significant associations among Black/African American participants. RA and IPF PRSs were associated with their intended phenotypes among non-Hispanic White participants but performed poorly among Black/African American participants. PRS may have future application to risk stratify for RA diagnosis among patients with ILD or for ILD among patients with RA.

Scanner-referenced T1 (srT1) is a method for measuring pancreas T1 relaxation time. The purpose of this multi-centre study is 2-fold: (1) to evaluate the repeatability of manual ROI-based analysis of srT1, (2) to validate a semi-automated measurement method with an automatic quality control (QC) module to identify likely discrepancies between automated and manual measurements. Pancreatic MRI scans from a scan-rescan cohort (46 subjects) were used to evaluate the repeatability of manual analysis. Seven hundred and eight scans from a longitudinal multi-centre study of 466 subjects were divided into training, internal validation (IV), and external validation (EV) cohorts. A semi-automated method for measuring srT1 using machine learning is proposed and compared against manual analysis on the validation cohorts with and without automated QC. Inter-operator agreement between manual ROI-based method and semi-automated method had low bias (3.8 ms or 0.5%) and limits of agreement [-36.6, 44.1] ms. There was good agreement between the 2 methods without automated QC (IV: 3.2 [-47.1, 53.5] ms, EV: -0.5 [-35.2, 34.2] ms). After QC, agreement on the IV set improved, was unchanged in the EV set, and the agreement in both was within inter-operator bounds (IV: -0.04 [-33.4, 33.3] ms, EV: -1.9 [-37.6, 33.7] ms). The semi-automated method improved scan-rescan agreement versus manual analysis (manual: 8.2 [-49.7, 66] ms, automated: 6.7 [-46.7, 60.1] ms). The semi-automated method for characterization of standardized pancreatic T1 using MRI has the potential to decrease analysis time while maintaining accuracy and improving scan-rescan agreement. We provide intra-operator, inter-operator, and scan-rescan agreement values for manual measurement of srT1, a standardized biomarker for measuring pancreas fibro-inflammation. Applying a semi-automated measurement method improves scan-rescan agreement and agrees well with manual measurements, while reducing human effort. Adding automated QC can improve agreement between manual and automated measurements. We describe a method for semi-automated, standardized measurement of pancreatic T1 (srT1), which includes automated quality control. Measurements show good agreement with manual ROI-based analysis, with comparable consistency to inter-operator performance.

The skeletal muscles that athletes should train vary depending on their discipline and position. Therefore, individual skeletal muscle cross-sectional area assessment is important in the development of training strategies. To measure the cross-sectional area of skeletal muscle, manual segmentation of each muscle is performed using magnetic resonance (MR) imaging. This task is time-consuming and requires significant effort. Additionally, interobserver variability can sometimes be problematic. The purpose of this study was to develop an automated computerized method for semantic segmentation of individual thigh skeletal muscles from MR images of athletes. Our database consisted of 697 images from the thighs of 697 elite athletes. The images were randomly divided into a training dataset (70%), a validation dataset (10%), and a test dataset (20%). A label image was generated for each image by manually annotating 15 object classes: 12 different skeletal muscles, fat, bones, and vessels and nerves. Using the validation dataset, DeepLab v3+ was chosen from three different semantic segmentation models as a base model for segmenting individual thigh skeletal muscles. The feature extractor in DeepLab v3+ was also optimized to ResNet50. The mean Jaccard index and Dice index for the proposed method were 0.853 and 0.916, respectively, which were significantly higher than those from conventional DeepLab v3+ (Jaccard index: 0.810, p < .001; Dice index: 0.887, p < .001). The proposed method achieved a mean area error for 15 objective classes of 3.12%, useful in the assessment of skeletal muscle cross-sectional area from MR images.

Scoliosis, a 3-D spinal deformity, requires early detection and intervention. Ultrasound curve angle (UCA) measurement using ultrasound images has emerged as a promising diagnostic tool. However, calculating the UCA directly from ultrasound images remains challenging due to low contrast, high noise, and irregular target shapes. Accurate segmentation results are therefore crucial to enhance image clarity and precision prior to UCA calculation. We propose the SSAT-Swin model, a transformer-based multi-class segmentation framework designed for ultrasound image analysis in scoliosis diagnosis. The model integrates a boundary-enhancement module in the decoder and a channel attention module in the skip connections. Additionally, self-supervised proxy tasks are used during pre-training on 1,170 images, followed by fine-tuning on 109 image-label pairs. The SSAT-Swin achieved Dice scores of 85.6% and Jaccard scores of 74.5%, with a 92.8% scoliosis bone feature detection rate, outperforming state-of-the-art models. Self-supervised learning enhances the model's ability to capture global context information, making it well-suited for addressing the unique challenges of ultrasound images, ultimately advancing scoliosis assessment through more accurate segmentation.

Accurately evaluating bone mineral density (BMD) in patients with unilateral hip osteoarthritis (OA) is crucial for diagnosing osteoporosis and selecting implants for hip arthroplasty. Our goal was to measure the BMD differences between sides, examine contributing factors, and identify the optimal side for BMD assessment in these patients. We analyzed 108 women with unilateral hip OA. Bilateral hip BMD was assessed automatically through quantitative CT (QCT) utilizing a validated, deep-learning-based approach. We evaluated BMD variations between the OA and healthy hips across total, neck, and distal regions. To determine their contributions, we analyzed factors, including patient demographics, Crowe classification, Bombelli classification, knee OA status, hip functional score, and gluteal muscle volume and density. Furthermore, we examined how side-to-side BMD differences influenced osteoporosis diagnosis using T-scores based on QCT. The average BMD on the OA side was 6.9 % lower in the total region, 14.5 % higher in the neck region, and 9.4 % lower in the distal region than on the healthy side. Contributing factors to the reduced BMD in the OA hip included younger age, Bombelli classification (atrophic type), and significant gluteal muscle atrophy. Diagnoses from the OA side revealed lower sensitivity (61 %) than those from the healthy side (88 %). Analysis on one side alone yields a more precise osteoporosis diagnosis from the healthy side. Nonetheless, bilateral BMD assessment remains crucial, particularly in younger individuals and those with atrophic OA types. Although based on QCT, our findings support bilateral analysis by dual-energy X-ray absorptiometry for these patients.

We aimed to develop and validate an Artificial Intelligence (AI) model that leverages CCTA and optical coherence tomography (OCT) images for automated analysis of plaque characteristics and coronary function. A total of 100 patients who underwent invasive coronary angiography, OCT, and CCTA before discharge were included in this study. The data were randomly divided into a training set (80 %) and a test set (20 %). The training set, comprising 21,471 tomography images, was used to train a deep-learning convolutional neural network. Subsequently, the AI model was integrated with flow reserve score calculation software developed by Ruixin Medical. The results from the test set demonstrated excellent agreement between the AI model and OCT analysis for calcified plaque (McNemar test, p = 0.683), non-calcified plaque (McNemar test, p = 0.752), mixed plaque (McNemar test, p = 1.000), and low-attenuation plaque (McNemar test, p = 1.000). Additionally, there was excellent agreement for deep learning-derived minimum lumen diameter (intraclass correlation coefficient [ICC] 0.91, p < 0.001), mean vessel diameter (ICC 0.88, p < 0.001), and percent diameter stenosis (ICC 0.82, p < 0.001). In diagnosing >50 % coronary stenosis, the diagnostic accuracy of the AI model surpassed that of conventional CCTA (AUC 0.98 vs. 0.76, p = 0.008). When compared with quantitative flow fraction, there was excellent agreement between QFR and AI-derived CT-FFR (ICC 0.745, p < 0.0001). Our AI model effectively provides automated analysis of plaque characteristics from CCTA images, with the analysis results showing strong agreement with OCT findings. Moreover, the CT-FFR automatically analyzed by the AI model exhibits high consistency with QFR derived from coronary angiography.

Sarcopenia is associated with worse survival in non-small cell lung cancer (NSCLC), but less studied in association with toxicity. Here, we investigated the association between imaging-assessed sarcopenia with toxicity in patients with NSCLC. We analyzed a "chemoradiation" cohort (n = 318) of patients with NSCLC treated with chemoradiation, and an external validation "chemo-surgery" cohort (n = 108) who were treated with chemotherapy and surgery from 2002 to 2013 at a different institution. A deep-learning pipeline utilized pretreatment computed tomography scans to estimate SM area at the third lumbar vertebral level. Sarcopenia was defined by dichotomizing SM index, (SM adjusted for height and sex). Primary endpoint was NCI CTCAE v5.0 grade 3 to 5 (G3-5) toxicity within 21-days of first chemotherapy cycle. Multivariable analyses (MVA) of toxicity endpoints with sarcopenia and baseline characteristics were performed by logistic regression, and overall survival (OS) was analyzed using Cox regression. Sarcopenia was identified in 36% and 36% of patients in the chemoradiation and chemo-surgery cohorts, respectively. On MVA, sarcopenia was associated with worse G3-5 toxicity in chemoradiation (HR 2.00, P < .01) and chemo-surgery cohorts (HR 2.95, P = .02). In the chemoradiation cohort, worse OS was associated with G3-5 toxicity (HR 1.42, P = .02) but not sarcopenia on MVA. In chemo-surgery cohort, worse OS was associated with sarcopenia (HR 2.03, P = .02) but not G3-5 toxicity on MVA. Sarcopenia, assessed by an automated deep-learning system, was associated with worse toxicity and survival outcomes in patients with NSCLC. Sarcopenia can be utilized to tailor treatment decisions to optimize adverse events and survival.