External validation and comparison of MR-based radiomics models for predicting pathological complete response in locally advanced rectal cancer: a two-centre, multi-vendor study.

OBJECTIVES: The aim of this study was two-fold: (1) to develop and externally validate a multiparameter MR-based machine learning model to predict the pathological complete response (pCR) in locally advanced rectal cancer (LARC) patients after neoadjuvant chemoradiotherapy (nCRT), and (2) to compare different classifiers' discriminative performance for pCR prediction. METHODS: This retrospective study includes 151 LARC patients divided into internal (centre A, n = 100) and external validation set (centre B, n = 51). The clinical and MR radiomics features were derived to construct clinical, radiomics, and clinical-radiomics model. Random forest (RF), support vector machine (SVM), logistic regression (LR), K-nearest neighbor (KNN), naive Bayes (NB), and extreme gradient boosting (XGBoost) were used as classifiers. The predictive performance was assessed using the receiver operating characteristic (ROC) curve. RESULTS: Eleven radiomics and four clinical features were chosen as pCR-related signatures. In the radiomics model, the RF algorithm achieved 74.0% accuracy (an AUC of 0.863) and 84.4% (an AUC of 0.829) in the internal and external validation sets. In the clinical-radiomics model, RF algorithm exhibited high and stable predictive performance in the internal and external validation datasets with an AUC of 0.906 (87.3% sensitivity, 73.7% specificity, 76.0% accuracy) and 0.872 (77.3% sensitivity, 88.2% specificity, 86.3% accuracy), respectively. RF showed a better predictive performance than the other classifiers in the external validation datasets of three models. CONCLUSIONS: The multiparametric clinical-radiomics model combined with RF algorithm is optimal for predicting pCR in the internal and external sets, and might help improve clinical stratifying management of LARC patients. KEY POINTS: • A two-centre study showed that radiomics analysis of pre- and post-nCRT multiparameter MR images could predict pCR in patients with LARC. • The combined model was superior to the clinical and radiomics model in predicting pCR in locally advanced rectal cancer. • The RF classifier performed best in the current study.

Solitaire AB stent mechanical embolization combined with catheter contact thrombolysis for acute renal artery embolism: A case report.

Acute renal artery embolization is a rare disease resulting in interruption of blood flow, resulting in renal tissue ischemia or necrosis, and even developing into acute renal failure. It is urgent to diagnose timely, recanalize the occluded renal artery early, and recover renal blood perfusion. Here, the article reports a case of acute renal artery embolization, which was successfully cured by interventional therapy.

Mimicking DNA Periodic Docking Grooves for Adaptive Identification of l-/d-Tryptophan in a Biological Metal-Organic Framework.

Bioinspired metal-organic frameworks (MOFs) serve as suitable crystalline models for recognition and sensing of biomolecules mimicking natural processes, providing new ideas and concepts for cutting-edge biomedical applications. Here, we have successfully prepared a robust biological metal-organic framework with periodic docking grooves resembling the major and minor grooves in the DNA double helix structure, which can be used as unique recognition sites for selectively identifying l-/d-tryptophan (l-/d-Trp). Notably, successful encapsulation of Trp could be observed by single-crystal X-ray diffraction for the first time. Trp has matched size and shape to fit snugly into the major groove. Combined with isothermal titration calorimetry, it was found that ZnBTCHx could spontaneously capture l-/d-Trp through two different thermodynamic pathways: enthalpy-driven for encapsulating l-Trp and entropy-driven for uptaking d-Trp. Furthermore, molecular dynamics and density functional theory verified the role of hydrogen bonding and π-π/C-H···π interactions in the host-guest interface. This work provides unique insight for the construction of bionic models to mimic the natural binding properties, which is of great significance for the fields of pharmaceutical chemistry and biomedical science.

(TS)2WM: Tumor Segmentation and Tract Statistics for Assessing White Matter Integrity with Applications to Glioblastoma Patients.

Glioblastoma (GBM) brain tumor is the most aggressive white matter (WM) invasive cerebral primary neoplasm. Due to its inherently heterogeneous appearance and shape, previous studies pursued either the segmentation precision of the tumors or qualitative analysis of the impact of brain tumors on WM integrity with manual delineation of tumors. This paper aims to develop a comprehensive analytical pipeline, called (TS)2WM, to integrate both the superior performance of brain tumor segmentation and the impact of GBM tumors on the WM integrity via tumor segmentation and tract statistics using the diffusion tensor imaging (DTI) technique. The (TS)2WM consists of three components: (i) A dilated densely connected convolutional network (D2C2N) for automatically segment GBM tumors. (ii) A modified structural connectome processing pipeline to characterize the connectivity pattern of WM bundles. (iii) A multivariate analysis to delineate the local and global associations between different DTI-related measurements and clinical variables on both brain tumors and language-related regions of interest. Among those, the proposed D2C2N model achieves competitive tumor segmentation accuracy compared with many state-of-the-art tumor segmentation methods. Significant differences in various DTI-related measurements at the streamline, weighted network, and binary network levels (e.g., diffusion properties along major fiber bundles) were found in tumor-related, language-related, and hand motor-related brain regions in 62 GBM patients as compared to healthy subjects from the Human Connectome Project.

Machine-learning based MRI radiomics models for early detection of radiation-induced brain injury in nasopharyngeal carcinoma.

BACKGROUND: Early radiation-induced temporal lobe injury (RTLI) diagnosis in nasopharyngeal carcinoma (NPC) is clinically challenging, and prediction models of RTLI are lacking. Hence, we aimed to develop radiomic models for early detection of RTLI. METHODS: We retrospectively included a total of 242 NPC patients who underwent regular follow-up magnetic resonance imaging (MRI) examinations, including contrast-enhanced T1-weighted and T2-weighted imaging. For each MRI sequence, four non-texture and 10,320 texture features were extracted from medial temporal lobe, gray matter, and white matter, respectively. The relief and 0.632 + bootstrap algorithms were applied for initial and subsequent feature selection, respectively. Random forest method was used to construct the prediction model. Three models, 1, 2 and 3, were developed for predicting the results of the last three follow-up MRI scans at different times before RTLI onset, respectively. The area under the curve (AUC) was used to evaluate the performance of models. RESULTS: Of the 242 patients, 171 (70.7%) were men, and the mean age of all the patients was 48.5 ± 10.4 years. The median follow-up and latency from radiotherapy until RTLI were 46 and 41 months, respectively. In the testing cohort, models 1, 2, and 3, with 20 texture features derived from the medial temporal lobe, yielded mean AUCs of 0.830 (95% CI: 0.823-0.837), 0.773 (95% CI: 0.763-0.782), and 0.716 (95% CI: 0.699-0.733), respectively. CONCLUSION: The three developed radiomic models can dynamically predict RTLI in advance, enabling early detection and allowing clinicians to take preventive measures to stop or slow down the deterioration of RTLI.

Limits to anatomical accuracy of diffusion tractography using modern approaches.

Diffusion MRI fiber tractography is widely used to probe the structural connectivity of the brain, with a range of applications in both clinical and basic neuroscience. Despite widespread use, tractography has well-known pitfalls that limits the anatomical accuracy of this technique. Numerous modern methods have been developed to address these shortcomings through advances in acquisition, modeling, and computation. To test whether these advances improve tractography accuracy, we organized the 3-D Validation of Tractography with Experimental MRI (3D-VoTEM) challenge at the ISBI 2018 conference. We made available three unique independent tractography validation datasets - a physical phantom and two ex vivo brain specimens - resulting in 176 distinct submissions from 9 research groups. By comparing results over a wide range of fiber complexities and algorithmic strategies, this challenge provides a more comprehensive assessment of tractography's inherent limitations than has been reported previously. The central results were consistent across all sub-challenges in that, despite advances in tractography methods, the anatomical accuracy of tractography has not dramatically improved in recent years. Taken together, our results independently confirm findings from decades of tractography validation studies, demonstrate inherent limitations in reconstructing white matter pathways using diffusion MRI data alone, and highlight the need for alternative or combinatorial strategies to accurately map the fiber pathways of the brain.

Preoperative simulation results and intraoperative image fusion guidance for transjugular intrahepatic portosystemic shunt placement: a feasibility study of nineteen patients.

PURPOSE: The purpose is to evaluate the feasibility and efficacy of preoperative simulation results and intraoperative image fusion guidance during transjugular intrahepatic portosystemic shunt (TIPS) creation. METHODS: Nineteen patients were enrolled in the present study. The three-dimensional (3D) structures of the bone, liver, portal vein, inferior vena cava, and hepatic vein in the contrast-enhanced computed tomography (CT) scanning area were reconstructed in the Mimics software. The virtual Rosch-Uchida liver access set and the VIATORR stent model were established in the 3D Max software. The puncture path from the hepatic vein to the portal vein and the release position of the stent were simulated in the Mimics and 3D Max software, respectively. The simulation results were exported to Photoshop software, and the 3D reconstructed top of the liver diaphragm was used as the registration point to fuse with the liver diaphragmatic surface of the intraoperative fluoroscopy image. The selected portal vein system fusion image was overlaid on the reference display screen to provide image guidance during the operation. As a control, the last 19 consecutive cases of portal vein puncture under the guidance of conventional fluoroscopy were analyzed retrospectively, including the number of puncture attempts, puncture time, total procedure time, total fluoroscopy time, and total exposure dose (dose area product). RESULTS: The average time of preoperative simulation was about 61.26 ± 6.98 minutes. The average time of intraoperative image fusion was 6.05 ± 1.13 minutes. The median number of puncture attempts was not significantly different between the study group (n = 3) and the control group (n = 3; P = 0.175). The mean puncture time in the study group (17.74 ± 12.78 min) was significantly lower than that in the control group (58.32 ± 47.11 min; P = 0.002). The mean total fluoroscopy time was not significantly different between the study group (26.63 ± 12.84 min) and the control group (40.00 ± 23.44 min; P = 0.083). The mean total procedure time was significantly lower in the study group (79.74 ± 37.39 min) compared with the control group (121.70 ± 62.24 min; P = 0.019). The dose area product of the study group (220.60 ± 128.4 Gy. cm2) was not significantly different from that of the control group (228.5 ± 137.3 Gy. cm2; P = 0.773). There were no image guidance-related complications. CONCLUSION: The use of preoperative simulation results and intraoperative image fusion to guide a portal vein puncture is feasible, safe, and effective when creating a TIPS. The method is cheap and may improve portal vein puncture, which may be valuable for hospitals lacking intravascular ultrasound and digital subtraction angiography (DSA) equipment equipped with a CT-angiography function.

DoseDiff: Distance-aware Diffusion Model for Dose Prediction in Radiotherapy.

Treatment planning, which is a critical component of the radiotherapy workflow, is typically carried out by a medical physicist in a time-consuming trial-and-error manner. Previous studies have proposed knowledge-based or deep-learning-based methods for predicting dose distribution maps to assist medical physicists in improving the efficiency of treatment planning. However, these dose prediction methods usually fail to effectively utilize distance information between surrounding tissues and targets or organs-at-risk (OARs). Moreover, they are poor at maintaining the distribution characteristics of ray paths in the predicted dose distribution maps, resulting in a loss of valuable information. In this paper, we propose a distance-aware diffusion model (DoseDiff) for precise prediction of dose distribution. We define dose prediction as a sequence of denoising steps, wherein the predicted dose distribution map is generated with the conditions of the computed tomography (CT) image and signed distance maps (SDMs). The SDMs are obtained by distance transformation from the masks of targets or OARs, which provide the distance from each pixel in the image to the outline of the targets or OARs. We further propose a multi-encoder and multi-scale fusion network (MMFNet) that incorporates multi-scale and transformer-based fusion modules to enhance information fusion between the CT image and SDMs at the feature level. We evaluate our model on two in-house datasets and a public dataset, respectively. The results demonstrate that our DoseDiff method outperforms state-of-the-art dose prediction methods in terms of both quantitative performance and visual quality.

Efficacy and safety of a panthenol-enriched mask for individuals with distinct impaired skin barrier subtypes.

BACKGROUND: The protection for different skin types with impaired skin barrier in the market is insufficient. AIM: To evaluate the efficacy and safety of a panthenol-enriched mask (La Roche-Posay Mask Pro) in addressing various skin barrier impairment subgroups, including dry sensitive, oily sensitive, and oily acne skin. METHODS: A total of 177 participants were enrolled in the study and divided into three subgroups based on their skin type. Participants used the mask following the specified protocol, with measurements taken for skin hydration, transepidermal water loss (TEWL), sebum content, and skin redness-factors that are directly influenced by skin barrier function. Assessments were conducted at baseline and after 1 day (tested 15 min post-application), 7 days, and 14 days of application using Sebumeter, Tewameter, Corneometer, Mexameter, and VISIA. RESULTS: Results showed significant improvements in skin parameters across all subgroups. In the dry sensitive skin subgroup, the mask increased skin hydration, sebum content, and reduced redness. For the oily sensitive skin subgroup, the mask regulated sebum production and improved skin hydration. In the oily acne skin subgroup, the mask reduced sebum content, redness, TEWL, and post-inflammatory erythema and hyperpigmentation. Tolerance was excellent for all skin types, with no adverse reactions observed. CONCLUSIONS: This study highlights the efficacy and safety of the panthenol-enriched LRP Mask Pro for individuals with distinct skin barrier impairment subgroups. The mask's versatile formulation and proven efficacy make it a valuable skincare product for addressing various skin concerns and achieving healthier, more balanced skin.

Multi-Scale Tokens-Aware Transformer Network for Multi-Region and Multi-Sequence MR-to-CT Synthesis in a Single Model.

The superiority of magnetic resonance (MR)-only radiotherapy treatment planning (RTP) has been well demonstrated, benefiting from the synthesis of computed tomography (CT) images which supplements electron density and eliminates the errors of multi-modal images registration. An increasing number of methods has been proposed for MR-to-CT synthesis. However, synthesizing CT images of different anatomical regions from MR images with different sequences using a single model is challenging due to the large differences between these regions and the limitations of convolutional neural networks in capturing global context information. In this paper, we propose a multi-scale tokens-aware Transformer network (MTT-Net) for multi-region and multi-sequence MR-to-CT synthesis in a single model. Specifically, we develop a multi-scale image tokens Transformer to capture multi-scale global spatial information between different anatomical structures in different regions. Besides, to address the limited attention areas of tokens in Transformer, we introduce a multi-shape window self-attention into Transformer to enlarge the receptive fields for learning the multi-directional spatial representations. Moreover, we adopt a domain classifier in generator to introduce the domain knowledge for distinguishing the MR images of different regions and sequences. The proposed MTT-Net is evaluated on a multi-center dataset and an unseen region, and remarkable performance was achieved with MAE of 69.33 ± 10.39 HU, SSIM of 0.778 ± 0.028, and PSNR of 29.04 ± 1.32 dB in head & neck region, and MAE of 62.80 ± 7.65 HU, SSIM of 0.617 ± 0.058 and PSNR of 25.94 ± 1.02 dB in abdomen region. The proposed MTT-Net outperforms state-of-the-art methods in both accuracy and visual quality.

A novel stratification scheme combined with internal arteries in CT imaging for guiding postoperative adjuvant transarterial chemoembolization in hepatocellular carcinoma: a retrospective cohort study.

BACKGROUND: Although postoperative adjuvant transarterial chemoembolization (PA-TACE) improves survival outcomes in a subset of patients with resected hepatocellular carcinoma (HCC), the lack of reliable biomarkers for patient selection remains a significant challenge. The present study aimed to evaluate whether computed tomography imaging can provide more value for predicting benefits from PA-TACE and to establish a new scheme for guiding PA-TACE benefits. METHODS: In this retrospective study, patients with HCC who had undergone preoperative contrast-enhanced computed tomography and curative hepatectomy were evaluated. Inverse probability of treatment weight was performed to balance the difference of baseline characteristics. Cox models were used to test the interaction among PA-TACE, imaging features, and pathological indicators. An HCC imaging and pathological classification (HIPC) scheme incorporating these imaging and pathological indicators was established. RESULTS: This study included 1488 patients [median age, 52 years (IQR, 45-61 years); 1309 male]. Microvascular invasion (MVI) positive, and diameter >5 cm tumors achieved a higher recurrence-free survival (RFS), and overall survival (OS) benefit, respectively, from PA-TACE than MVI negative, and diameter ≤5 cm tumors. Patients with internal arteries (IA) positive benefited more than those with IA-negative in terms of RFS ( P =0.016) and OS ( P =0.018). PA-TACE achieved significant RFS and OS improvements in HIPC3 (IA present and diameter >5 cm, or two or three tumors) patients but not in HIPC1 (diameter ≤5 cm, MVI negative) and HIPC2 (other single tumor) patients. Our scheme may decrease the number of patients receiving PA-TACE by ~36.5% compared to the previous suggestion. CONCLUSIONS: IA can provide more value for predicting the benefit of PA-TACE treatment. The proposed HIPC scheme can be used to stratify patients with and without survival benefits from PA-TACE.

A radiograph-based deep learning model improves radiologists' performance for classification of histological types of primary bone tumors: A multicenter study.

PURPOSE: To develop a deep learning (DL) model for classifying histological types of primary bone tumors (PBTs) using radiographs and evaluate its clinical utility in assisting radiologists. METHODS: This retrospective study included 878 patients with pathologically confirmed PBTs from two centers (638, 77, 80, and 83 for the training, validation, internal test, and external test sets, respectively). We classified PBTs into five categories by histological types: chondrogenic tumors, osteogenic tumors, osteoclastic giant cell-rich tumors, other mesenchymal tumors of bone, or other histological types of PBTs. A DL model combining radiographs and clinical features based on the EfficientNet-B3 was developed for five-category classification. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate model performance. The clinical utility of the model was evaluated in an observer study with four radiologists. RESULTS: The combined model achieved a macro average AUC of 0.904/0.873, with an accuracy of 67.5 %/68.7 %, a macro average sensitivity of 66.9 %/57.2 %, and a macro average specificity of 92.1 %/91.6 % on the internal/external test set, respectively. Model-assisted analysis improved accuracy, interpretation time, and confidence for junior (50.6 % vs. 72.3 %, 53.07[s] vs. 18.55[s] and 3.10 vs. 3.73 on a 5-point Likert scale [P < 0.05 for each], respectively) and senior radiologists (68.7 % vs. 75.3 %, 32.50[s] vs. 21.42[s] and 4.19 vs. 4.37 [P < 0.05 for each], respectively). CONCLUSION: The combined DL model effectively classified histological types of PBTs and assisted radiologists in achieving better classification results than their independent visual assessment.

[Design and application of a central venous pressure measurement tool].

Central venous pressure (CVP) reflects the comprehensive condition of effective blood volume, cardiac function and vascular tone. Clinical monitoring of CVP can indirectly understand and evaluate the dynamic changes of blood volume in patients, and provide a reference for patients to venous fluid. At present, the traditional manual measurement method is widely used for measurement, which has some shortcomings such as zero shift, cumbersome operation (requires two health care workers to cooperate). In order to overcome the above problems, the author invented a new fixable CVP measurement tool and obtained the national utility model patent (ZL 2021 2 1451705.7). The tool is mainly composed of a base plate, a movable frame and a measuring department, etc. When used, the base plate is placed into the back of the patient and pressed and fixed, the movable frame is adjusted, the zero point is found, and the measurement data is read from the measuring department. It has the advantages of simple and convenient operation, small measurement error, wide applicability (different body types) and so on, which is suitable for clinical promotion.

Clinical effect of standardized nursing for lymphoma patients and the influencing factors of nosocomial infection.

To analyze the clinical effect of standardized nursing for lymphoma patients and the influencing factors of nosocomial infection, a total of 360 diffuse large B-cell lymphoma patients with disease recurrence or progression after first-line treatment were retrospectively selected from our hospital from January 2021 to July 2022. After standardized nursing, the overall infection rate of lymphoma patients was 2.50% (9/360), which was significantly lower than the overall infection rate of our hospital in 2021 (7.44%, 844/11342) (P < .05). The proportion of 3 kinds of pathogenic bacteria detected were G+ bacteria (33.5%), G- bacteria (53.3%), and fungi (13.2%). The pathogenic bacteria genus with the most G+ bacteria is Enterococcus, the pathogenic bacteria genus with the most G+ bacteria is Enterobacteriaceae, and the pathogenic bacteria with the most fungi is Candida albicans. Female infection rate was significantly higher than male (P < .05). There was no significant difference in nosocomial infection among different marital status/fertility status (P > .05). The nosocomial infection of patients with different hospitalization times was statistically significant (P < .05). The duration of hospitalization in the infected group was significantly higher than that in the non-infected group (P < .05). The clinical effect of standardized nursing for lymphoma patients is significant, and the influencing factors of nosocomial infection include patient gender, hospitalization frequency, and hospitalization duration.

Efficacy and safety of PD1/PDL1 inhibitors combined with radiotherapy and anti-angiogenic therapy for solid tumors: A systematic review and meta-analysis.

BACKGROUND: The triple combination of programmed cell death 1 (PD1)/programmed cell death ligand 1 (PDL1) inhibitors, radiotherapy (RT), and anti-angiogenesis agents has been widely used in the treatment of solid tumors and has shown positive efficacy. We conducted a meta-analysis to evaluate the efficacy and safety of PD1/PDL1 inhibitors combined with anti-angiogenic agents and RT for the treatment of solid cancers. METHODS: A systematic search of PubMed, Embase, Cochrane Library, and Web of Science databases was conducted from inception to October 31, 2022. Studies involving patients with solid cancers who received PD1/PDL1 inhibitors combined with RT and anti-angiogenic agents treatment that reported overall response rate, complete remission rate, disease control rate, and adverse events (AEs) were included. A random-effects or fixed-effects model was used for the pooled rates, and 95% confidence intervals (CIs) were determined for all outcomes. The quality of the included literature was assessed using the methodological index for nonrandomized studies critical appraisal checklist. Egger test was used to assess the publication bias in the included studies. RESULTS: Ten studies (4 nonrandomized controlled trials and 6 single-arm trials), including 365 patients, were identified and included in the meta-analysis. The pooled overall response rate after treatment with PD1/PDL1 inhibitors combined with RT and anti-angiogenic agents was 59% (95% CI: 48-70%), whereas the disease control rate and complete remission rate were 92% (95% CI: 81-103%) and 48% (95% CI: 35-61%), respectively. Moreover, the meta-analysis showed that compared with triple-regimen, monotherapy or dual-combination treatment did not improve overall survival (hazard ratio = 0.499, 95% CI: 0.399-0.734) and progression-free survival (hazard ratio = 0.522, 95% CI: 0.352-0.774). The pooled rate of grade 3 to 4 AEs was 26.9% (95% CI: 7.8%-45.9), and the common AEs to triple therapy included leukopenia (25%), thrombocytopenia (23.8%), fatigue (23.2%), gastrointestinal discomfort (22%), increased alanine aminotransferase (22%), and neutropenia (21.4%). CONCLUSION: In the treatment of solid tumors, PD1/PDL1 inhibitors combined with RT and anti-angiogenic drugs achieved a positive response and better survival benefits than monotherapy or dual therapy. In addition, combination therapy is tolerable and safe. REGISTRATION: PROSPERO ID: CRD42022371433.

Whole mandibular canal segmentation using transformed dental CBCT volume in Frenet frame.

Accurate segmentation of the mandibular canal is essential in dental implant and maxillofacial surgery, which can help prevent nerve or vascular damage inside the mandibular canal. Achieving this is challenging because of the low contrast in CBCT scans and the small scales of mandibular canal areas. Several innovative methods have been proposed for mandibular canal segmentation with positive performance. However, most of these methods segment the mandibular canal based on sliding patches, which may adversely affect the morphological integrity of the tubular structure. In this study, we propose whole mandibular canal segmentation using transformed dental CBCT volume in the Frenet frame. Considering the connectivity of the mandibular canal, we propose to transform the CBCT volume to obtain a sub-volume containing the whole mandibular canal based on the Frenet frame to ensure complete 3D structural information. Moreover, to further improve the performance of mandibular canal segmentation, we use clDice to guarantee the integrity of the mandibular canal structure and segment the mandibular canal. Experimental results on our CBCT dataset show that integrating the proposed transformed volume in the Frenet frame into other state-of-the-art methods achieves a 0.5%∼12.1% improvement in Dice performance. Our proposed method can achieve impressive results with a Dice value of 0.865 (±0.035), and a clDice value of 0.971 (±0.020), suggesting that our method can segment the mandibular canal with superior performance.

Breath-Hold CBCT-Guided CBCT-to-CT Synthesis via Multimodal Unsupervised Representation Disentanglement Learning.

Adaptive radiation therapy (ART) aims to deliver radiotherapy accurately and precisely in the presence of anatomical changes, in which the synthesis of computed tomography (CT) from cone-beam CT (CBCT) is an important step. However, because of serious motion artifacts, CBCT-to-CT synthesis remains a challenging task for breast-cancer ART. Existing synthesis methods usually ignore motion artifacts, thereby limiting their performance on chest CBCT images. In this paper, we decompose CBCT-to-CT synthesis into artifact reduction and intensity correction, and we introduce breath-hold CBCT images to guide them. To achieve superior synthesis performance, we propose a multimodal unsupervised representation disentanglement (MURD) learning framework that disentangles the content, style, and artifact representations from CBCT and CT images in the latent space. MURD can synthesize different forms of images using the recombination of disentangled representations. Also, we propose a multipath consistency loss to improve structural consistency in synthesis and a multidomain generator to improve synthesis performance. Experiments on our breast-cancer dataset show that MURD achieves impressive performance with a mean absolute error of 55.23±9.94 HU, a structural similarity index measurement of 0.721±0.042, and a peak signal-to-noise ratio of 28.26±1.93 dB in synthetic CT. The results show that compared to state-of-the-art unsupervised synthesis methods, our method produces better synthetic CT images in terms of both accuracy and visual quality.

United multi-task learning for abdominal contrast-enhanced CT synthesis through joint deformable registration.

Synthesizing abdominal contrast-enhanced computed tomography (CECT) images from non-enhanced CT (NECT) images is of great importance, in the delineation of radiotherapy target volumes, to reduce the risk of iodinated contrast agent and the registration error between NECT and CECT for transferring the delineations. NECT images contain structural information that can reflect the contrast difference between lesions and surrounding tissues. However, existing methods treat synthesis and registration as two separate tasks, which neglects the task collaborative and fails to address misalignment between images after the standard image pre-processing in training a CECT synthesis model. Thus, we propose an united multi-task learning (UMTL) for joint synthesis and deformable registration of abdominal CECT. Specifically, our UMTL is an end-to-end multi-task framework, which integrates a deformation field learning network for reducing the misalignment errors and a 3D generator for synthesizing CECT images. Furthermore, the learning of enhanced component images and the multi-loss function are adopted for enhancing the performance of synthetic CECT images. The proposed method is evaluated on two different resolution datasets and a separate test dataset from another center. The synthetic venous phase CECT images of the separate test dataset yield mean absolute error (MAE) of 32.78±7.27 HU, mean MAE of 24.15±5.12 HU on liver region, mean peak signal-to-noise rate (PSNR) of 27.59±2.45 dB, and mean structural similarity (SSIM) of 0.96±0.01. The Dice similarity coefficients of liver region between the true and synthetic venous phase CECT images are 0.96±0.05 (high-resolution) and 0.95±0.07 (low-resolution), respectively. The proposed method has great potential in aiding the delineation of radiotherapy target volumes.

QACL: Quartet attention aware closed-loop learning for abdominal MR-to-CT synthesis via simultaneous registration.

Synthesis of computed tomography (CT) images from magnetic resonance (MR) images is an important task to overcome the lack of electron density information in MR-only radiotherapy treatment planning (RTP). Some innovative methods have been proposed for abdominal MR-to-CT synthesis. However, it is still challenging due to the large misalignment between preprocessed abdominal MR and CT images and the insufficient feature information learned by models. Although several studies have used the MR-to-CT synthesis to alleviate the difficulty of multi-modal registration, this misalignment remains unsolved when training the MR-to-CT synthesis model. In this paper, we propose an end-to-end quartet attention aware closed-loop learning (QACL) framework for MR-to-CT synthesis via simultaneous registration. Specifically, the proposed quartet attention generator and mono-modal registration network form a closed-loop to improve the performance of MR-to-CT synthesis via simultaneous registration. In particular, a quartet-attention mechanism is developed to enlarge the receptive fields in networks to extract the long-range and cross-dimension spatial dependencies. Experimental results on two independent abdominal datasets demonstrate that our QACL achieves impressive results with MAE of 55.30±10.59 HU, PSNR of 22.85±1.43 dB, and SSIM of 0.83±0.04 for synthesis, and with Dice of 0.799±0.129 for registration. The proposed QACL outperforms the state-of-the-art MR-to-CT synthesis and multi-modal registration methods.

A transformer-based multi-task deep learning model for simultaneous infiltrated brain area identification and segmentation of gliomas.

BACKGROUND: The anatomical infiltrated brain area and the boundaries of gliomas have a significant impact on clinical decision making and available treatment options. Identifying glioma-infiltrated brain areas and delineating the tumor manually is a laborious and time-intensive process. Previous deep learning-based studies have mainly been focused on automatic tumor segmentation or predicting genetic/histological features. However, few studies have specifically addressed the identification of infiltrated brain areas. To bridge this gap, we aim to develop a model that can simultaneously identify infiltrated brain areas and perform accurate segmentation of gliomas. METHODS: We have developed a transformer-based multi-task deep learning model that can perform two tasks simultaneously: identifying infiltrated brain areas segmentation of gliomas. The multi-task model leverages shaped location and boundary information to enhance the performance of both tasks. Our retrospective study involved 354 glioma patients (grades II-IV) with single or multiple brain area infiltrations, which were divided into training (N = 270), validation (N = 30), and independent test (N = 54) sets. We evaluated the predictive performance using the area under the receiver operating characteristic curve (AUC) and Dice scores. RESULTS: Our multi-task model achieved impressive results in the independent test set, with an AUC of 94.95% (95% CI, 91.78-97.58), a sensitivity of 87.67%, a specificity of 87.31%, and accuracy of 87.41%. Specifically, for grade II-IV glioma, the model achieved AUCs of 95.25% (95% CI, 91.09-98.23, 84.38% sensitivity, 89.04% specificity, 87.62% accuracy), 98.26% (95% CI, 95.22-100, 93.75% sensitivity, 98.15% specificity, 97.14% accuracy), and 93.83% (95%CI, 86.57-99.12, 92.00% sensitivity, 85.71% specificity, 87.37% accuracy) respectively for the identification of infiltrated brain areas. Moreover, our model achieved a mean Dice score of 87.60% for the whole tumor segmentation. CONCLUSIONS: Experimental results show that our multi-task model achieved superior performance and outperformed the state-of-the-art methods. The impressive performance demonstrates the potential of our work as an innovative solution for identifying tumor-infiltrated brain areas and suggests that it can be a practical tool for supporting clinical decision making.