LeSAM: Adapt Segment Anything Model for medical lesion segmentation.

The Segment Anything Model (SAM) is a foundational model that has demonstrated impressive results in the field of natural image segmentation. However, its performance remains suboptimal for medical image segmentation, particularly when delineating lesions with irregular shapes and low contrast. This can be attributed to the significant domain gap between medical images and natural images on which SAM was originally trained. In this paper, we propose an adaptation of SAM specifically tailored for lesion segmentation termed LeSAM. LeSAM first learns medical-specific domain knowledge through an efficient adaptation module and integrates it with the general knowledge obtained from the pre-trained SAM. Subsequently, we leverage this merged knowledge to generate lesion masks using a modified mask decoder implemented as a lightweight U-shaped network design. This modification enables better delineation of lesion boundaries while facilitating ease of training. We conduct comprehensive experiments on various lesion segmentation tasks involving different image modalities such as CT scans, MRI scans, ultrasound images, dermoscopic images, and endoscopic images. Our proposed method achieves superior performance compared to previous state-of-the-art methods in 8 out of 12 lesion segmentation tasks while achieving competitive performance in the remaining 4 datasets. Additionally, ablation studies are conducted to validate the effectiveness of our proposed adaptation modules and modified decoder.

Skeletal Rearrangement of Oxazole to Azepine and Pyrrole through Dynamic 8π Electrocyclizations.

We present a novel approach for the skeletal rearrangement of an oxazole into an azepine and pyrrole through a dynamic electrocyclization process, showing an innovative, unconventional reaction sequence. This method enables precise control of regioselectivity in competitive 6π and 8π electrocyclization reactions, rendering the final products rich in functional groups that can be further developed for the synthesis of nitrogen-containing scaffolds. This is an unprecedented example of the selective synthesis of seven- and five-member heterocycles via dynamic electrocyclization ring opening or closure.

A combined nomogram based on radiomics and hematology to predict the pathological complete response of neoadjuvant immunochemotherapy in esophageal squamous cell carcinoma.

BACKGROUND: To predict pathological complete response (pCR) in patients receiving neoadjuvant immunochemotherapy (nICT) for esophageal squamous cell carcinoma (ESCC), we explored the factors that influence pCR after nICT and established a combined nomogram model. METHODS: We retrospectively included 164 ESCC patients treated with nICT. The radiomics signature and hematology model were constructed utilizing least absolute shrinkage and selection operator (LASSO) regression, and the radiomics score (radScore) and hematology score (hemScore) were determined for each patient. Using the radScore, hemScore, and independent influencing factors obtained through univariate and multivariate analyses, a combined nomogram was established. The consistency and prediction ability of the nomogram were assessed utilizing calibration curve and the area under the receiver operating factor curve (AUC), and the clinical benefits were assessed utilizing decision curve analysis (DCA). RESULTS: We constructed three predictive models.The AUC values of the radiomics signature and hematology model reached 0.874 (95% CI: 0.819-0.928) and 0.772 (95% CI: 0.699-0.845), respectively. Tumor length, cN stage, the radScore, and the hemScore were found to be independent factors influencing pCR according to univariate and multivariate analyses (P < 0.05). A combined nomogram was constructed from these factors, and AUC reached 0.934 (95% CI: 0.896-0.972). DCA demonstrated that the clinical benefits brought by the nomogram for patients across an extensive range were greater than those of other individual models. CONCLUSIONS: By combining CT radiomics, hematological factors, and clinicopathological characteristics before treatment, we developed a nomogram model that effectively predicted whether ESCC patients would achieve pCR after nICT, thus identifying patients who are sensitive to nICT and assisting in clinical treatment decision-making.

Accurate location describe and management of lymph node recurrence after esophagectomy for thoracic esophageal squamous cell carcinoma：a retrospective cohort study.

BACKGROUND: Describe the accurate locations of lymph node recurrence LNR of Chinese patients with postoperative thoracic esophageal squamous cell carcinoma (ESCC) is essential for determining the need for further surveillance protocols and treatments. We aimed to evaluate the patterns of postoperative ESCC and its current risk stratification with LNR. METHODS: This population-based cohort study included a retrospective review of the medical records and image material of patients with ESCC who underwent LNR after radical surgery between January 2013 and September 2022, with a median follow-up time of 5.71 years. Clinical features were extracted from these records, and survival analysis was performed. The primary endpoint was the accurate location and range of LNR according to the nomenclature of the Japanese Society for Esophageal Diseases. The second endpoints was to explore the related factors of recurrence range (RR) and overall survival (OS) . RESULTS: A total of 3268 lymph node regions were recurrence from 1129 patients, with a mean of 2.89 regions per patient. No.104, 106 and 107 was the most common recurrence of thoracic ESCC with an LNR rate higher than 15%. In upper thoracic ESCC, No.105 was a common recurrence site and abdominal lymph node recurrence was rare. In lower thoracic ESCC, retroperitoneal lymph node was a unique regions (15.4%). Anastomotic recurrence is an important recurrence pattern in patients with postoperative esophageal cancer, with an incidence of 24.5%. Rates of lymph node recurrence in range of lymph node dissection was low (13.9%). The median time of LRT was 20.0 (1.5-184.0) months. High range of recurrence was associated with significantly poorer OS in patients. Multiple linear regression analysis identified demonstrated N stage, tumor differentiation, adjuvant radiotherapy and total lymph nodes removed were association with recurrence range for patients. CONCLUSIONS: Supraclavicular and upper mediastinums lymph nodes were common recurrence site for ESCC patients , and careful initial staging and surveillance are needed. Thorough lymph node dissection may reduce the range of regional recurrence.

Synthesis of virtual monoenergetic images from kilovoltage peak images using wavelet loss enhanced CycleGAN for improving radiomics features reproducibility.

Background: Dual-energy computed tomography (CT) can provide a range of image information beyond conventional CT through virtual monoenergetic images (VMIs). The purpose of this study was to investigate the impact of material decomposition in detector-based spectral CT on radiomics features and effectiveness of using deep learning-based image synthesis to improve the reproducibility of radiomics features. Methods: In this paper, spectral CT image data from 45 esophageal cancer patients were collected for investigation retrospectively. First, we computed the correlation coefficient of radiomics features between conventional kilovoltage peak (kVp) CT images and VMI. Then, a wavelet loss-enhanced CycleGAN (WLL-CycleGAN) with paired loss terms was developed to synthesize virtual monoenergetic CT images from the corresponding conventional single-energy CT (SECT) images for improving radiomics reproducibility. Finally, the radiomic features in 6 different categories, including gray-level co-occurrence matrix (GLCM), gray-level difference matrix (GLDM), gray-level run-length matrix (GLRLM), gray-level size-zone matrix (GLSZM), neighborhood gray-tone difference matrix (NGTDM), and wavelet, were extracted from the gross tumor volumes from conventional single energy CT, synthetic virtual monoenergetic CT images, and virtual monoenergetic CT images. Comparison between errors in the VMI and synthetic VMI (sVMI) suggested that the performance of our proposed deep learning method improved the radiomic feature accuracy. Results: Material decomposition of dual-layer dual-energy CT (DECT) can substantially influence the reproducibility of the radiomic features, and the degree of impact is feature dependent. The average reduction of radiomics errors for 15 patients in testing sets was 96.9% for first-order, 12.1% for GLCM, 12.9% for GLDM, 15.7% for GLRLM, 50.3% for GLSZM, 53.4% for NGTDM, and 6% for wavelet features. Conclusions: The work revealed that material decomposition has a significant effect on the radiomic feature values. The deep learning-based method reduced the influence of material decomposition in VMIs and might improve the robustness and reproducibility of radiomic features in esophageal cancer. Quantitative results demonstrated that our proposed wavelet loss-enhanced paired CycleGAN outperforms the original CycleGAN.

The Assessment of Volumetric Changes for Alveolar Ridge Preservation or Reconstruction by Three-dimensional Analysis at Posterior Extraction Sites with Severe Bone Defects Using DBBM-C Collagen Membrane and PRF: A Prospective and Randomized Clinical Trial.

STATEMENT OF PROBLEM: Volumetric resorption of the alveolar ridge often occurs following tooth extraction in both horizontal and vertical directions. There is a specific lack of evidence for alveolar ridge reconstruction at molar and premolar sites with severe bone resorption. PURPOSE: This randomized and controlled trial aimed to use three dimensional and linear analyses to evaluate volumetric changes of the alveolar bone following alveolar ridge reconstruction (ARR) at molar and premolar sites with severe bone resorption as compared with non-assisted socket healing be implant placement. MATERIAL AND METHODS: A total of 31 patients (15 males and 16 females) with more than 50% of hard tissue loss in one or more socket walls were recruited and randomized into either a test group (ARR after extraction using deproteinized bovine bone mineral with 10% collagen (DBBM-C) and platelet-rich fibrin (PRF) with a resorbable collagen membrane) or a control group (natural healing after extraction). Then, the clinical, linear, volumetric implant-related and patient-reported outcomes were analyzed after a 4-month healing process. RESULTS: Linear bone assessments revealed significantly greater gains of ridge width in the test group (25% in the mesial, mid-facial and distal aspects) and less reduction of vertical bone ridge than in the control group (P＜0.05). Furthermore, volumetric bone remodeling was significantly higher in the test group (ARR=35.1±34.9%, control=14.2±12.8%, P＜0.05). Patient-reported discomfort and keratinized mucosal changes were comparable between groups. CONCLUSIONS: Alveolar ridge reconstruction with a combination of DBBM-C, PRF, and a resorbable membrane at posterior sites with severe socket wall deficiency (＞ 50% bone loss) is a safe and more capable therapeutic method when compared with natural healing and non-assisted sockets. CLINICAL IMPLICATIONS: Collectively, our analyses demonstrated that alveolar ridge reconstruction represents an efficient method to maintain and augment crestal bone at posterior extraction sites with severe bone defects when assessed after four months of healing.

Assessing the Impact of a 1.5†T Transverse Magnetic Field in Radiotherapy for Esophageal Cancer Patients.

Purpose: Magnetic resonance (MR)-guided radiotherapy enables visualization of static anatomy, capturing tumor motion, and extracting quantitative image features for treatment verification and outcome monitoring. However, magnetic fields in online MR imaging (MRI) require efforts to ensure accurate dose measurements. This study aimed to assess the dosimetric impact of a 1.5 T magnetic field in esophageal cancer radiotherapy using MR-linac, exploring treatment adaptation potential and personalized medicine benefits. Methods: A prospective cohort study enrolled 100 esophageal squamous cell carcinoma patients undergoing 4DCT and 3DCT scans before radiotherapy. The heart was contoured on 3DCT, 4DCT end expiration (EE), and 4DCT end inhalation (EI) images by the same radiation oncologist. Reference RT plans were designed on 3DCT, with adjustments for different phases generating 5 plan types per patient. Variations in dose-volume parameters for organs at risk and the target area among different plans were compared using Monaco 5.40.04. Results: Slight dose distortions at air-tissue interfaces were observed in the magnetic field's presence. Dose at air-tissue interfaces (chest wall and heart wall) was slightly higher in some patients (3.0% tissue increased by 4.3 Gy on average) compared to nonmagnetic conditions. Average clinical target volume coverage V100 dropped from 99% to 95% compared to reference plans (planEI and planEE). Dose-volume histogram variation between the original plan and reference plans was within 2.3%. Superior-inferior (SI) direction displacement was significantly larger than lateral and anterior-posterior directions (P < .05). Conclusion: Significant SI direction shift in lower esophageal cancerous regions during RT indicates the magnetic field's dosimetric impact, including the electron return effect at tissue-air boundaries. Changes in OAR dose could serve as valuable indicators of organ impairment and target dose alterations, especially for cardiac tissue when using the 1.5 T linac method. Reoptimizing the plan with the magnetic field enhances the feasibility of achieving a clinically acceptable treatment plan for esophageal cancer patients.

A Phase 1b Clinical Trial of Neoadjuvant Radio-immunotherapy for Esophageal Squamous Cell Cancer.

PURPOSE: Neoadjuvant chemoradiotherapy is the recommended treatment for patients with resectable esophageal cancer but is associated with a higher incidence of adverse effects. Given the efficacy of immunotherapy, we propose a chemotherapy-free regimen of neoadjuvant radio-immunotherapy (NRIT) to balance therapeutic efficacy and potential side effects or overtreatment. METHODS AND MATERIALS: In this phase 1b clinical trial, we assessed the safety and efficacy of NRIT in esophageal squamous cell cancer. The enrolled patients received 41.4 Gy of radiation and 4 cycles of 240 mg of toripalimab injection before surgery. The primary endpoint was treatment-related adverse events and the secondary endpoints were pathologic complete response and major pathologic response. Immunohistochemistry and multiplex immunofluorescence staining were used to evaluate the tumor microenvironment before and after neoadjuvant treatment. RESULTS: Of the 22 patients enrolled, 19 underwent R0 surgery. One patient discontinued neoadjuvant immune therapy due to experiencing a grade 3 treatment-related adverse event. Three patients did not undergo surgery due to tumor progression or side effects. Among the patients who underwent surgery, 3 patients experienced serious complications shortly after surgery. Upon pathologic evaluation, the pathologic complete response and major pathologic response rates were 47.4% and 68.4%, respectively. CONCLUSIONS: The NRIT regimen is safe and feasible for patients with esophageal squamous cell cancer.

CT synthesis from MR images using frequency attention conditional generative adversarial network.

Magnetic resonance (MR) image-guided radiotherapy is widely used in the treatment planning of malignant tumors, and MR-only radiotherapy, a representative of this technique, requires synthetic computed tomography (sCT) images for effective radiotherapy planning. Convolutional neural networks (CNN) have shown remarkable performance in generating sCT images. However, CNN-based models tend to synthesize more low-frequency components and the pixel-wise loss function usually used to optimize the model can result in blurred images. To address these problems, a frequency attention conditional generative adversarial network (FACGAN) is proposed in this paper. Specifically, a frequency cycle generative model (FCGM) is designed to enhance the inter-mapping between MR and CT and extract more rich tissue structure information. Additionally, a residual frequency channel attention (RFCA) module is proposed and incorporated into the generator to enhance its ability in perceiving the high-frequency image features. Finally, high-frequency loss (HFL) and cycle consistency high-frequency loss (CHFL) are added to the objective function to optimize the model training. The effectiveness of the proposed model is validated on pelvic and brain datasets and compared with state-of-the-art deep learning models. The results show that FACGAN produces higher-quality sCT images while retaining clearer and richer high-frequency texture information.

Surgery versus radiotherapy for limited-stage small cell esophageal carcinoma: a multicenter, retrospective, cohort study in China (ChiSCEC).

BACKGROUND: There is no standard management for small cell esophageal carcinoma (SCEC). The purpose of this multicenter, retrospective study (ChiSCER) was to investigate the treatment, outcomes, and risk factors impacting survival endpoints in patients with limited-stage SCEC (LS-SCEC). MATERIALS AND METHODS: Consecutive patients with LS-SCEC from 14 institutions between 2000 and 2020 in China were enrolled. Survival curves were constructed using the Kaplan-Meier method and compared using a log-rank test. Univariate and multivariate Cox regression models and propensity score matching (PSM) analysis were adopted in the prognostic analysis. Results were reported as hazard ratio (HR), 95% confidence interval (CI), and P value. Statistical significance was set as P value <0.05 in a two-tailed test. RESULTS: Among 458 LS-SCEC patients, the median age was 63 [interquartile range (IQR), 57-68] years, and 318 (69%) were males. Eighty-four (18%), 167 (36%), and 207 (45%) patients received chemotherapy (CT) alone, CT plus definitive radiotherapy (CT+RT), and CT plus radical surgery (CT+S), respectively. With a median follow-up time of 58.7 (95% CI 48.9-68.6) months, the median overall survival (OS) and 3-year OS rate for all patients 24.3 (95% CI 21.6-27) months and 37.3% (95% CI 32.8-42.5%), respectively. Multivariate analysis indicated that treatment modes, Karnofsky performance status (KPS), TNM stage, and CT cycle were independent prognostic factors for OS ( P <0.05). Compared with CT alone, patients treated with CT+RT (HR 0.57, 95% CI 0.41-0.8, P =0.001) or CT+S (HR 0.59, 95% CI 0.42-0.82, P =0.002) had an improved OS, with no significant survival differences between CT+S and CT+RT groups after multivariate and PSM analyses ( P >0.05). Subgroup analysis indicated that compared with CT+RT, patients with tumor location at lower 1/3 (HR 0.59, 95% CI 0.37-0.93, P =0.03) or tumor length >5 cm (HR 0.52, 95% CI 0.3-0.9, P =0.02) could obtain significant OS benefit from CT+S. Patients with tumor location at middle 1/3 (HR 1.55, 95% CI 1.03-2.36, P =0.04) or tumor length ≤5 cm (HR 1.49, 95% CI 1.02-2.17, P =0.04) favored CT+RT. Distant metastasis accounted for 73.7% of all treatment failures after multidisciplinary treatments. CONCLUSION: Surgery and RT were equally effective local therapies for patients with LS-SCEC. The personalized decision of local therapy should be made after comprehensive considerations on tumor location, length, comorbidities, and organ preservation.

Systemic therapy with or without local intervention for oligometastatic oesophageal squamous cell carcinoma (ESO-Shanghai 13): an open-label, randomised, phase 2 trial.

BACKGROUND: The efficacy of local therapy for patients with oligometastatic oesophageal squamous cell carcinoma is unclear. We aimed to assess the efficacy of local plus systemic therapy compared with systemic therapy alone in patients with oligometastatic oesophageal squamous cell carcinoma. METHODS: The ESO-Shanghai 13 trial was a randomised, open-label, multicentre, phase 2 trial. Patients (aged ≥18 years) were recruited from six hospitals in China with histological confirmation of oligometastatic oesophageal squamous cell carcinoma with a controlled primary tumour and one to four metastatic lesions. Eligible patients were randomly assigned via a computer-generated schedule in a 1:1 ratio to receive either systemic therapy alone (ie, systemic therapy only group) or combined systemic and local therapy (ie, systemic and local therapy group). The systemic therapy regimens in both groups were at the discretion of the investigator and included chemotherapy alone, anti-PD-1 antibodies alone, or chemotherapy plus anti-PD-1 antibodies. Local therapy-radiotherapy, surgery, or thermal ablation-was delivered to all metastatic lesions for patients in the systemic and local therapy group. Randomisation was balanced dynamically on three factors: the number of disease sites, the lines of systemic therapy, and the location of the metastases. Patients and investigators were not masked to treatment allocation. The primary endpoint was progression-free survival, defined as the time from randomisation to progression or death from any cause in the intention-to-treat population. The safety population included all patients who had undergone random assignment and at least one of the intended therapies. This trial is registered with ClinicalTrials.gov, NCT03904927. The trial is ongoing but closed to new participants. FINDINGS: 116 patients were screened for enrolment between March 5, 2019, and Sept 16, 2021, and 104 patients who met the eligibility criteria were randomly assigned to the systemic and local therapy group (n=53) or the systemic therapy only group (n=51). 20 (38%) patients in the systemic plus local therapy group and 23 (45%) patients in the systemic therapy only group received anti-PD-1 antibody-based systemic therapy; three patients in the systemic and local therapy group did not receive systemic therapy. At a median follow-up of 30·5 months (IQR 24·7-37·8), median progression-free survival was 15·3 months (95% CI 10·1-20·5) in the systemic and local therapy group versus 6·4 months (5·2-7·6) in the systemic therapy only group (stratified hazard ratio 0·26 [95% CI 0·16-0·42]; stratified log rank p<0·0001). Grade 1-2 acute oesophagitis was more common in the systemic and local therapy group than in the systemic therapy only group (10 [19%] vs one [2%] patients; p=0·036). The number of patients who had grade 3 or worse treatment-related adverse events was similar between groups (25 [47%] vs 21 [41%]; p=0·538), with the most common adverse events being leukocytopenia (17 [32%] vs 18 [35%]) and neutropenia (19 [36%] vs 20 [39%]). Treatment-related deaths occurred in two patients in the systemic and local therapy group and one patient in the systemic therapy only group. INTERPRETATION: The addition of local treatment for metastases could significantly improve progression-free survival among patients with oligometastatic oesophageal squamous cell carcinoma being treated with systemic therapy. Our findings suggest that combining local and systemic therapy could be a treatment option for patients with oligometastatic oesophageal squamous cell carcinoma, but further support from phase 3 trials is required. FUNDING: Science and Technology Commission of Shanghai Municipality, National Nature Science Foundation of China, and Shanghai Municipal Health Commission. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.

YY1 modulates the radiosensitivity of esophageal squamous cell carcinoma through KIF3B-mediated Hippo signaling pathway.

Radiotherapy is an important strategy in the comprehensive treatment of esophageal squamous cell carcinoma (ESCC). However, effectiveness of radiotherapy is still restricted by radioresistance. Herein, we aimed to understand the mechanisms underlying ESCC radioresistance, for which we looked into the potential role of YY1. YY1 was upregulated in radioresistant tissues and correlated with poor prognosis of patients with ESCC. YY1 depletion enhanced the radiosensitivity of ESCC in vitro and in vivo. Multi-group sequencing showed that downregulation of YY1 inhibited the transcriptional activity of Kinesin Family Member 3B (KIF3B), which further activated the Hippo signaling pathway by interacting with Integrin-beta1 (ITGB1). Once the Hippo pathway was activated, its main effector, Yes-associated protein 1 (YAP1), was phosphorylated in the cytoplasm and its expression reduced in the nucleus, thus enhancing the radiosensitivity by regulating its targeted genes. Our study provides new insights into the mechanisms underlying ESCC radioresistance and highlights the potential role of YY1 as a therapeutic target for ESCC.

A glycosylation-related signature predicts survival in pancreatic cancer.

BACKGROUND: Tumor initiation and progression are closely associated with glycosylation. However, glycosylated molecules have not been the subject of extensive studies as prognostic markers for pancreatic cancer. The objectives of this study were to identify glycosylation-related genes in pancreatic cancer and use them to construct reliable prognostic models. MATERIALS AND METHODS: The Cancer Genome Atlas and Gene Expression Omnibus databases were used to assess the differential expression of glycosylation-related genes; four clusters were identified based on consistent clustering analysis. Kaplan-Meier analyses identified three glycosylation-related genes associated with overall survival. LASSO analysis was then performed on The Cancer Genome Atlas and International Cancer Genome Consortium databases to identify glycosylation-related signatures. We identified 12 GRGs differently expressed in pancreatic cancer and selected three genes (SEL1L, TUBA1C, and SDC1) to build a prognostic model. Thereafter, patients were divided into high and low-risk groups. Eventually, we performed Quantitative real-time PCR (qRT-PCR) to validate the signature. RESULTS: Clinical outcomes were significantly poorer in the high-risk group than in the low-risk group. There were also significant correlations between the high-risk group and several risk factors, including no-smoking history, drinking history, radiotherapy history, and lower tumor grade. Furthermore, the high-risk group had a higher proportion of immune cells. Eventually, three glycosylation-related genes were validated in human PC cell lines. CONCLUSION: This study identified the glycosylation-related signature for pancreatic cancer. It is an effective predictor of survival and can guide treatment decisions.

[Research progress on the identification of central lung cancer and atelectasis using multimodal imaging].

Central lung cancer is a common disease in clinic which usually occurs above the segmental bronchus. It is commonly accompanied by bronchial stenosis or obstruction, which can easily lead to atelectasis. Accurately distinguishing lung cancer from atelectasis is important for tumor staging, delineating the radiotherapy target area, and evaluating treatment efficacy. This article reviews domestic and foreign literatures on how to define the boundary between central lung cancer and atelectasis based on multimodal images, aiming to summarize the experiences and propose the prospects.

Dual contrast attention-guided multi-frequency fusion for multi-contrast MRI super-resolution.

Objective. Multi-contrast magnetic resonance (MR) imaging super-resolution (SR) reconstruction is an effective solution for acquiring high-resolution MR images. It utilizes anatomical information from auxiliary contrast images to improve the quality of the target contrast images. However, existing studies have simply explored the relationships between auxiliary contrast and target contrast images but did not fully consider different anatomical information contained in multi-contrast images, resulting in texture details and artifacts unrelated to the target contrast images.Approach. To address these issues, we propose a dual contrast attention-guided multi-frequency fusion (DCAMF) network to reconstruct SR MR images from low-resolution MR images, which adaptively captures relevant anatomical information and processes the texture details and low-frequency information from multi-contrast images in parallel. Specifically, after the feature extraction, a feature selection module based on a dual contrast attention mechanism is proposed to focus on the texture details of the auxiliary contrast images and the low-frequency features of the target contrast images. Then, based on the characteristics of the selected features, a high- and low-frequency fusion decoder is constructed to fuse these features. In addition, a texture-enhancing module is embedded in the high-frequency fusion decoder, to highlight and refine the texture details of the auxiliary contrast and target contrast images. Finally, the high- and low-frequency fusion process is constrained by integrating a deeply-supervised mechanism into the DCAMF network.Main results. The experimental results show that the DCAMF outperforms other state-of-the-art methods. The peak signal-to-noise ratio and structural similarity of DCAMF are 39.02 dB and 0.9771 on the IXI dataset and 37.59 dB and 0.9770 on the BraTS2018 dataset, respectively. The image recovery is further validated in segmentation tasks.Significance. Our proposed SR model can enhance the quality of MR images. The results of the SR study provide a reliable basis for clinical diagnosis and subsequent image-guided treatment.

Middle east warming in spring enhances summer rainfall over Pakistan.

The edge of a monsoon region is usually highly sensitive to climate change. Pakistan, which is located on the northern edge of the Indian monsoon, is highly vulnerable to heavy rainfall and has witnessed several debilitating floods exacerbated by global warming in recent years. However, the mechanisms for the frequent Pakistan floods are yet not fully understood. Here, we show that the Middle East is undergoing an increase in land heating during spring, which is responsible for 46% of the intensified rainfall over Pakistan and northwestern India during 1979-2022. This springtime land warming causes a decline in sea level pressure (SLP), which strengthens the meridional SLP gradient between the Middle East and the southern Arabian Sea and drives the changes of low-level jet (LLJ) subsequently. The impact persists into summer and results in a northward shift of the monsoonal LLJ, accompanied by strong positive vorticity in the atmosphere and enhanced moisture supply to Pakistan. Consequently, the transition region between the summer monsoon in South Asia and the desert climate in West Asia is shifted northwestward, posing significantly enhanced risk of floods over Pakistan and northwestern India.

Online prediction for respiratory movement compensation: a patient-specific gating control for MRI-guided radiotherapy.

BACKGROUND: This study aims to validate the effectiveness of linear regression for motion prediction of internal organs or tumors on 2D cine-MR and to present an online gating signal prediction scheme that can improve the accuracy of MR-guided radiotherapy for liver and lung cancer. MATERIALS AND METHODS: We collected 2D cine-MR sequences of 21 liver cancer patients and 10 lung cancer patients to develop a binary gating signal prediction algorithm that forecasts the crossing-time of tumor motion traces relative to the target threshold. Both 0.4 s and 0.6 s prediction windows were tested using three linear predictors and three recurrent neural networks (RNNs), given the system delay of 0.5 s. Furthermore, an adaptive linear regression model was evaluated using only the first 30 s as the burn-in period, during which the model parameters were adapted during the online prediction process. The accuracy of the predicted traces was measured using amplitude metrics (MAE, RMSE, and R2), and in addition, we proposed three temporal metrics, namely crossing error, gating error, and gating accuracy, which are more relevant to the nature of the gating signals. RESULTS: In both 0.6 s and 0.4 s prediction cases, linear regression outperformed other methods, demonstrating significantly smaller amplitude errors compared to the RNNs (P < 0.05). The proposed algorithm with adaptive linear regression had the best performance with an average gating accuracy of 98.3% and 98.0%, a gating error of 44 ms and 45 ms, for liver cancer and lung cancer patients, respectively. CONCLUSION: A functional online gating control scheme was developed with an adaptive linear regression that is both more cost-efficient and accurate than sophisticated RNN based methods in all studied metrics.

Divergent access to 5,6,7-perifused cycles.

Nitrogen-containing heterocycles are the key components in many pharmaceuticals and functional materials. In this study, we report a transition metal-catalyzed high-order reaction sequence for synthesizing a structurally unique N-center 5,6,7-perifused cycle (NCPC). The key characteristics include the formation of a seven-membered ring by the 8π electrocyclization of various alkenes and aromatic heterocycles as π-components, in which metal carbene species are generated that further induce the cleavage of the α-C-H or -C-C bond. Specifically, the latter can react with various nucleophilic reagents containing -O, -S, -N, and -C. The stereo-controlled late-stage modification of some complicated pharmaceuticals indicates the versatility of this protocol.

Deep learning-based combination of [18F]-FDG PET and CT images for producing pulmonary perfusion image.

BACKGROUND: The main application of [18F] FDG-PET (18 FDG-PET) and CT images in oncology is tumor identification and quantification. Combining PET and CT images to mine pulmonary perfusion information for functional lung avoidance radiation therapy (FLART) is desirable but remains challenging. PURPOSE: To develop a deep-learning-based (DL) method to combine 18 FDG-PET and CT images for producing pulmonary perfusion images (PPI). METHODS: Pulmonary technetium-99 m-labeled macroaggregated albumin SPECT (PPISPECT ), 18 FDG-PET, and CT images obtained from 53 patients were enrolled. CT and PPISPECT images were rigidly registered, and registration displacement was subsequently used to align 18 FDG-PET and PPISPECT images. The left/right lung was separated and rigidly registered again to improve the registration accuracy. A DL model based on 3D Unet architecture was constructed to directly combine multi-modality 18 FDG-PET and CT images for producing PPI (PPIDLM ). 3D Unet architecture was used as the basic architecture, and the input was expanded from a single-channel to a dual-channel to combine multi-modality images. For comparative evaluation, 18 FDG-PET images were also used alone to generate PPIDLPET . Sixty-seven samples were randomly selected for training and cross-validation, and 36 were used for testing. The Spearman correlation coefficient (rs ) and multi-scale structural similarity index measure (MS-SSIM) between PPIDLM /PPIDLPET and PPISPECT were computed to assess the statistical and perceptual image similarities. The Dice similarity coefficient (DSC) was calculated to determine the similarity between high-/low- functional lung (HFL/LFL) volumes. RESULTS: The voxel-wise rs and MS-SSIM of PPIDLM /PPIDLPET were 0.78 ± 0.04/0.57 ± 0.03, 0.93 ± 0.01/0.89 ± 0.01 for cross-validation and 0.78 ± 0.11/0.55 ± 0.18, 0.93 ± 0.03/0.90 ± 0.04 for testing. PPIDLM /PPIDLPET achieved averaged DSC values of 0.78 ± 0.03/0.64 ± 0.02 for HFL and 0.83 ± 0.01/0.72 ± 0.03 for LFL in the training dataset and 0.77 ± 0.11/0.64 ± 0.12, 0.82 ± 0.05/0.72 ± 0.06 in the testing dataset. PPIDLM yielded a stronger correlation and higher MS-SSIM with PPISPECT than PPIDLPET (p < 0.001). CONCLUSIONS: The DL-based method integrates lung metabolic and anatomy information for producing PPI and significantly improved the accuracy over methods based on metabolic information alone. The generated PPIDLM can be applied for pulmonary perfusion volume segmentation, which is potentially beneficial for FLART treatment plan optimization.