Enhanced Multimodal Brain Tumor Classification in MR Images using 2D ResNet as backbone with Explicit Tumor Size Information.

It's a major public health problem of global concern that malignant gliomas tend to grow rapidly and infiltrate surrounding tissues. Accurate grading of the tumor can determine the degree of malignancy to formulate the best treatment plan, which can eliminate the tumor or limit widespread metastasis of the tumor, saving the patient's life and improving their prognosis. To more accurately predict the grading of gliomas, we proposed a novel method of combining the advantages of 2D and 3D Convolutional Neural Networks for tumor grading by multimodality on Magnetic Resonance Imaging. The core of the innovation lies in our combination of tumor 3D information extracted from multimodal data with those obtained from a 2D ResNet50 architecture. It solves both the lack of temporal-spatial information provided by 3D imaging in 2D convolutional neural networks and avoids more noise from too much information in 3D convolutional neural networks, which causes serious overfitting problems. Incorporating explicit tumor 3D information, such as tumor volume and surface area, enhances the grading model's performance and addresses the limitations of both approaches. By fusing information from multiple modalities, the model achieves a more precise and accurate characterization of tumors. The model I s trained and evaluated using two publicly available brain glioma datasets, achieving an AUC of 0.9684 on the validation set. The model's interpretability is enhanced through heatmaps, which highlight the tumor region. The proposed method holds promise for clinical application in tumor grading and contributes to the field of medical diagnostics for prediction.

Ultrasound-Guided External Oblique Intercostal Block as Part of Multimodal Analgesia for Unplanned Open Cholecystectomy.

We present the case of a 56-year-old female with a significant medical history of cholelithiasis and recurrent choledocholithiasis. Following an elective cholecystectomy, an obstructing gallstone in the common bile duct led to a series of interventions, including endoscopic retrograde cholangiopancreatography and stent placement. The patient was scheduled for a robot-assisted laparoscopic common bile duct exploration. Due to severe adhesions, the procedure was converted to open with a large right upper quadrant incision. Intraoperative continuous external oblique block and catheter placement were performed at the end of surgery in the OR. Peripheral nerve blocks have become an integral part of multimodal pain management strategies. This case report describes the successful implementation of an ultrasound-guided right external oblique intercostal block and catheter placement for postoperative pain control and minimization of opioids. This case highlights the efficacy and safety of ultrasound-guided peripheral nerve blocks for postoperative pain management. Successful pain control contributed to the patient's overall postoperative recovery.

The role of multimodality imaging in the selection and management of patients treated with cytoreductive surgery and HIPEC.

Cytoreductive surgery (CRS) with or without hyperthermic intraperitoneal chemotherapy (HIPEC) is the mainstay of potentially curative surgical treatment for malignancies that have spread to peritoneal surfaces. This surgical procedure is however associated with high morbidity and appropriate patient selection and planning is therefore essential. Available multimodality imaging techniques include CT with oral and intravenous contrast, MRI including use of dedicated peritoneal protocol and FDG-PET/CT. These used with the correct technique, read by specialist radiologists and discussed under the auspices of a dedicated multidisciplinary team, can help to improve outcomes. We demonstrate that imaging not only provides information about peritoneal disease burden but more importantly want to shift the reader's focus to disease distribution. Our examples highlight how imaging helps avoid futile surgery by identifying patients with disease in unfavourable sites and show the strength and limitations of the various imaging modalities. We share how MR imaging can help identify multifocal and often occult sites including widespread miliary disease. Our examples provide a comprehensive overview demonstrating how imaging can help plan surgery by identifying patients who may need splenic vaccinations, counselling for stoma, egg harvesting and input from surgeons with other specialist expertise greatly increasing likelihood of achieving complete cytoreduction.

18F-FDG PET/CT Radiomics-Based Multimodality Fusion Model for Preoperative Individualized Noninvasive Prediction of Peritoneal Metastasis in Advanced Gastric Cancer.

PURPOSE: This study was designed to develop and validate a machine learning-based, multimodality fusion (MMF) model using 18F-fluorodeoxyglucose (FDG) PET/CT radiomics and kernelled support tensor machine (KSTM), integrated with clinical factors and nuclear medicine experts' diagnoses to individually predict peritoneal metastasis (PM) in advanced gastric cancer (AGC). METHODS: A total of 167 patients receiving preoperative PET/CT and subsequent surgery were included between November 2006 and September 2020 and were divided into a training and testing cohort. The PM status was confirmed via laparoscopic exploration and postoperative pathology. The PET/CT signatures were constructed by classic radiomic, handcrafted-feature-based model and KSTM self-learning-based model. The clinical nomogram was constructed by independent risk factors for PM. Lastly, the PET/CT signatures, clinical nomogram, and experts' diagnoses were fused using evidential reasoning to establish the MMF model. RESULTS: The MMF model showed excellent performance in both cohorts (area under the curve [AUC] 94.16% and 90.84% in training and testing), and demonstrated better prediction accuracy than clinical nomogram or experts' diagnoses (net reclassification improvement p < 0.05). The MMF model also had satisfactory generalization ability, even in mucinous adenocarcinoma and signet ring cell carcinoma which have poor uptake of 18F-FDG (AUC 97.98% and 89.71% in training and testing). CONCLUSIONS: The 18F-FDG PET/CT radiomics-based MMF model may have significant clinical implications in predicting PM in AGC, revealing that it is necessary to combine the information from different modalities for comprehensive prediction of PM.

Adapting a group-based, multimodal aphasia treatment for telehealth - co-design of M-MAT Tele.

Multi-Modality Aphasia Treatment (M-MAT) is an effective group intervention for post-stroke aphasia. M-MAT employs interactive card games and the modalities of gesture, drawing, reading, and writing to improve spoken language. However, there are challenges to implementation of group interventions such as M-MAT, particularly for those who cannot travel or live in rural areas. To maximise access to this effective treatment, we aimed to adapt M-MAT to telehealth format (M-MAT Tele). The Human-Centred Design Framework was utilized to guide the adaptation approach. We identified the intended context of use (outpatient/community rehabilitation) and the stakeholders (clinicians, people with aphasia, health service funders). People with aphasia and practising speech pathologists were invited to co-design M-MAT Tele in a series of iterative workshops, to ensure the end product was user-friendly and clinically feasible. The use of co-design allowed us to understand the hardware, software and other constraints and preferences of end users. In particular, clinicians (n = 3) required software compatible with a range of telehealth platforms and people with aphasia (n = 3) valued solutions with minimal technical demands and costs for participants. Co-design within the Human-Centred Design Framework led to a telehealth solution compatible with all major telehealth platforms, with minimal hardware or software requirements. Pilot testing is underway to confirm acceptability of M-MAT Tele to clinicians and people with aphasia, aiming to provide an effective, accessible tool for aphasia therapy in telehealth settings.

Accurate segmentation of liver tumor from multi-modality non-contrast images using a dual-stream multi-level fusion framework.

The use of multi-modality non-contrast images (i.e., T1FS, T2FS and DWI) for segmenting liver tumors provides a solution by eliminating the use of contrast agents and is crucial for clinical diagnosis. However, this remains a challenging task to discover the most useful information to fuse multi-modality images for accurate segmentation due to inter-modal interference. In this paper, we propose a dual-stream multi-level fusion framework (DM-FF) to, for the first time, accurately segment liver tumors from non-contrast multi-modality images directly. Our DM-FF first designs an attention-based encoder-decoder to effectively extract multi-level feature maps corresponding to a specified representation of each modality. Then, DM-FF creates two types of fusion modules, in which a module fuses learned features to obtain a shared representation across multi-modality images to exploit commonalities and improve the performance, and a module fuses the decision evidence of segment to discover differences between modalities to prevent interference caused by modality's conflict. By integrating these three components, DM-FF enables multi-modality non-contrast images to cooperate with each other and enables an accurate segmentation. Evaluation on 250 patients including different types of tumors from two MRI scanners, DM-FF achieves a Dice of 81.20%, and improves performance (Dice by at least 11%) when comparing the eight state-of-the-art segmentation architectures. The results indicate that our DM-FF significantly promotes the development and deployment of non-contrast liver tumor technology.

Neuroimage Analysis Methods and Artificial Intelligence Techniques for Reliable Biomarkers and Accurate Diagnosis of Schizophrenia: Achievements Made by Chinese Scholars Around the Past Decade.

BACKGROUND AND HYPOTHESIS: Schizophrenia (SZ) is characterized by significant cognitive and behavioral disruptions. Neuroimaging techniques, particularly magnetic resonance imaging (MRI), have been widely utilized to investigate biomarkers of SZ, distinguish SZ from healthy conditions or other mental disorders, and explore biotypes within SZ or across SZ and other mental disorders, which aim to promote the accurate diagnosis of SZ. In China, research on SZ using MRI has grown considerably in recent years. STUDY DESIGN: The article reviews advanced neuroimaging and artificial intelligence (AI) methods using single-modal or multimodal MRI to reveal the mechanism of SZ and promote accurate diagnosis of SZ, with a particular emphasis on the achievements made by Chinese scholars around the past decade. STUDY RESULTS: Our article focuses on the methods for capturing subtle brain functional and structural properties from the high-dimensional MRI data, the multimodal fusion and feature selection methods for obtaining important and sparse neuroimaging features, the supervised statistical analysis and classification for distinguishing disorders, and the unsupervised clustering and semi-supervised learning methods for identifying neuroimage-based biotypes. Crucially, our article highlights the characteristics of each method and underscores the interconnections among various approaches regarding biomarker extraction and neuroimage-based diagnosis, which is beneficial not only for comprehending SZ but also for exploring other mental disorders. CONCLUSIONS: We offer a valuable review of advanced neuroimage analysis and AI methods primarily focused on SZ research by Chinese scholars, aiming to promote the diagnosis, treatment, and prevention of SZ, as well as other mental disorders, both within China and internationally.

Combining Nuclear Medicine With Other Modalities: Future Prospect for Multimodality Imaging.

This meeting report summarizes a consultants meeting that was held at International Atomic Energy Agency Headquarters, Vienna, in July 2022 to provide an update on the development of multimodality imaging by combining nuclear medicine imaging agents with other nonradioactive molecular probes and/or biomedical imaging techniques.

A Novel Multi-Effect Photosensitizer for Tumor Destruction via Multimodal Imaging Guided Synergistic Cancer Phototherapy.

Background: How to ingeniously design multi-effect photosensitizers (PSs), including multimodal imaging and multi-channel therapy, is of great significance for highly spatiotemporal controllable precise phototherapy of malignant tumors. Methods: Herein, a novel multifunctional zinc(II) phthalocyanine-based planar micromolecule amphiphile (ZnPc 1) was successfully designed and synthesized, in which N atom with photoinduced electron transfer effect was introduced to enhance the near-infrared absorbance and nonradiative heat generation. After simple self-assembling into nanoparticles (NPs), ZnPc 1 NPs would exhibit enhanced multimodal imaging properties including fluorescence (FL) imaging (FLI) /photoacoustic (PA) imaging (PAI) /infrared (IR) thermal imaging, which was further used to guide the combined photodynamic therapy (PDT) and photothermal therapy (PTT). Results: It was that under the self-guidance of the multimodal imaging, ZnPc 1 NPs could precisely pinpoint the tumor from the vertical and horizontal boundaries achieving highly efficient and accurate treatment of cancer. Conclusion: Accordingly, the integration of FL/PA/IR multimodal imaging and PDT/PTT synergistic therapy pathway into one ZnPc 1 could provide a blueprint for the next generation of phototherapy, which offered a new paradigm for the integration of diagnosis and treatment in tumor and a promising prospect for precise cancer therapy.

Why educators endorse a neuromyth: relationships among educational priorities, beliefs about learning styles, and instructional decisions.

Despite evidence to the contrary, many people believe in learning styles (LS)-the idea that students learn best in their preferred modality, such as visual, auditory, or kinesthetic. However, the impact of this belief on instructional decisions remains unclear. Therefore, this study investigated how belief in the neuromyth impacts instructional choices and why educators choose an LS lesson plan or an alternative. We found that educators' beliefs about LS indeed predicted their instructional choice, but that other factors influenced their decisions as well. Three themes encapsulate educators' justifications for their lesson plan choices: beliefs about LS, practical considerations, and student learning and motivation. These findings suggest that for many educators, implementing an LS lesson provides an opportunity to integrate diverse teaching strategies that address multiple educational priorities. Although many prior studies have replicated the prevalence of the myth, this is one of the first to explore the reasons that LS is attractive to educators. Attempts to dispel the LS neuromyth could leverage the reasons educators find LS appealing to provide alternative research-backed approaches to meet their goals. Future research should examine the extent to which beliefs in the LS neuromyth are translated into instructional practices within classroom lessons and explore potential differences across grade levels.

Infective endocarditis associated with left atrial appendage occlusion device: a contemporary systematic review.

BACKGROUND: Data are limited regarding infective endocarditis (IE) complicating left atrial appendage occlusion (LAAO) device procedures. This systematic review examines the etiology, diagnosis, and management of infective endocarditis (IE) following LAAO. METHODS: A comprehensive search of six databases was performed between 2007 and 2022. In selecting studies, articles were included if they provided information about IE complicating LAAO, with relevant clinical and imaging details. Articles were excluded if they were editorials, study protocols, letters, or abstracts. RESULTS: We identified seven cases of IE complicating LAAO published between 2007 and 2022, from the United States and Europe, highlighting the exceedingly rare reported incidence of the condition. Staphylococcus aureus is the predominant organism implicated in LAAO infections. Echocardiography is a key imaging modality for diagnosing LAAO IE. Both antibiotic therapy and surgical intervention in appropriate patients are important for managing LAAO device-related IE. CONCLUSIONS: The limited data in the current literature regarding LAAO IE underscores the need for prospective clinical trials to establish evidence-based guidelines for infection prophylaxis, diagnosis, and management. Our findings emphasize the importance of vigilance for device-related infections, especially as the use of LAAO devices continues to grow worldwide.

Deep learning-driven dyslexia detection model using multi-modality data.

Background: Dyslexia is a neurological disorder that affects an individual's language processing abilities. Early care and intervention can help dyslexic individuals succeed academically and socially. Recent developments in deep learning (DL) approaches motivate researchers to build dyslexia detection models (DDMs). DL approaches facilitate the integration of multi-modality data. However, there are few multi-modality-based DDMs. Methods: In this study, the authors built a DL-based DDM using multi-modality data. A squeeze and excitation (SE) integrated MobileNet V3 model, self-attention mechanisms (SA) based EfficientNet B7 model, and early stopping and SA-based Bi-directional long short-term memory (Bi-LSTM) models were developed to extract features from magnetic resonance imaging (MRI), functional MRI, and electroencephalography (EEG) data. In addition, the authors fine-tuned the LightGBM model using the Hyperband optimization technique to detect dyslexia using the extracted features. Three datasets containing FMRI, MRI, and EEG data were used to evaluate the performance of the proposed DDM. Results: The findings supported the significance of the proposed DDM in detecting dyslexia with limited computational resources. The proposed model outperformed the existing DDMs by producing an optimal accuracy of 98.9%, 98.6%, and 98.8% for the FMRI, MRI, and EEG datasets, respectively. Healthcare centers and educational institutions can benefit from the proposed model to identify dyslexia in the initial stages. The interpretability of the proposed model can be improved by integrating vision transformers-based feature extraction.

Hydrodynamic Assessment of Explanted Degenerated Transcatheter Aortic Valves: Novel Insights Into Noncalcific and Calcific Mechanisms.

BACKGROUND: The etiology of transcatheter aortic valve (TAV) degeneration is poorly understood, particularly noncalcific mechanisms. OBJECTIVES: The authors sought to investigate noncalcific and calcific mechanisms of TAV degeneration and evaluate their impact on leaflet function by bench testing, imaging, and histology. METHODS: TAV explants were obtained from the EXPLANT THV registry and clinical institutions. Hydrodynamic assessment was performed using a heart valve pulse duplicator system under physiological conditions. Micro-computed tomography, high-resolution photography, high speed video, and hematoxylin and eosin staining were used to evaluate the morphological appearance, leaflet kinematics, and calcium burden of TAVs. RESULTS: A total of 14 explants were evaluated: 10 self-expanding CoreValve/Evolut TAVs (Medtronic), 3 balloon-expandable SAPIEN 3 TAVs (Edwards Lifesciences), and 1 mechanically expandable Lotus TAV (Boston Scientific). The median patient age at explantation was 73.0 years (Q1-Q3: 64.5-80.0 years), with a time to explantation of 4 years 1 month (1 year 5 months to 4 years 11 months). Six TAV explants were found to have leaflet calcification (162.4 mm3; 58.8-603.0 mm3), and 8 had no calcification detectable by micro-computed tomography and histology. All samples had impaired leaflet kinematics. There was no significant difference in the hydrodynamic mean gradient between calcified (47.2 mm Hg; 26.6-74.1 mm Hg) and noncalcified (27.6 mm Hg; 15.2-36.7 mm Hg; P = 0.28) TAVs. Leaflet calcification had a weak but nonsignificant association with the hydrodynamic mean gradient (r = 0.42; P = 0.14). CONCLUSIONS: TAV function can be severely impacted by noncalcific and calcific mechanisms of tissue degeneration. Importantly, functional stenosis can occur in TAVs in the absence of obvious and significant calcification.

Diagnostic Challenges in Aortic Stenosis.

Aortic stenosis (AS) is the most prevalent degenerative valvular disease in western countries. Transthoracic echocardiography (TTE) is considered, nowadays, to be the main imaging technique for the work-up of AS due to high availability, safety, low cost, and excellent capacity to evaluate aortic valve (AV) morphology and function. Despite the diagnosis of AS being considered straightforward for a very long time, based on high gradients and reduced aortic valve area (AVA), many patients with AS represent a real dilemma for cardiologist. On the one hand, the acoustic window may be inadequate and the TTE limited in some cases. On the other hand, a growing body of evidence shows that patients with low gradients (due to systolic dysfunction, concentric hypertrophy or coexistence of another valve disease such as mitral stenosis or regurgitation) may develop severe AS (low-flow low-gradient severe AS) with a similar or even worse prognosis. The use of complementary imaging techniques such as transesophageal echocardiography (TEE), multidetector computed tomography (MDTC), or cardiac magnetic resonance (CMR) plays a key role in such scenarios. The aim of this review is to summarize the diagnostic challenges associated with patients with AS and the advantages of a comprehensive multimodality cardiac imaging (MCI) approach to reach a precise grading of the disease, a crucial factor to warrant an adequate management of patients.

Recent Trends and Potential of Radiotherapy in the Treatment of Anaplastic Thyroid Cancer.

Anaplastic thyroid cancer (ATC) is a rare but highly aggressive malignancy characterized by advanced disease at diagnosis and a poor prognosis. Despite multimodal therapeutic approaches that include surgery, radiotherapy, and chemotherapy, an optimal treatment strategy remains elusive. Current developments in targeted therapies and immunotherapy offer promising avenues for improved outcomes, particularly for BRAF-mutant patients. However, challenges remain regarding overcoming drug resistance and developing effective treatments for BRAF-wild-type tumors. This comprehensive review examines the clinical and biological features of ATC, outlines the current standards of care, and discusses recent developments with a focus on the evolving role of radiotherapy. Moreover, it emphasizes the necessity of a multidisciplinary approach and highlights the urgent need for further research to better understand ATC pathogenesis and identify new therapeutic targets. Collaborative efforts, including large-scale clinical trials, are essential for translating these findings into improved patient outcomes.

A Rare Case of Immunoglobulin G4-Related Constrictive Pericarditis Diagnosed Via Multimodality Imaging.

Constrictive pericarditis (CP) presents as a pathophysiological state where the pericardium becomes inelastic due to fibrotic changes, most commonly secondary to a protracted inflammatory process. The disease is characterized by compromised diastolic cardiac function due to loss of pericardial compliance. Immunoglobulin G4 (IgG4)-related disease, an entity marked by the insidious proliferation of IgG4-positive plasma cells and subsequent fibrosis within various organs, is an infrequent but recognized cause of CP. A case of a 55-year-old male patient with clinical manifestations of dyspnea and edema in the lower extremities elucidates the diagnostic complexity inherent to CP. Echocardiography revealed a constellation of signs, including annulus reversus, septal bounce, and a congested inferior vena cava; cardiac magnetic resonance imaging (MRI) demonstrated diffuse pericardial thickening with delayed gadolinium enhancement, suggestive of a long-term inflammatory state; and right heart catheterization confirmed the hemodynamic hallmark of CP-equalization of diastolic pressures across the cardiac chambers. The serological analysis elicited elevated serum levels of IgG4 and IgE, pointing to the differential diagnosis of IgG4-related disease. Given the nonspecific clinical presentation of IgG4-related CP, a heightened index of suspicion combined with a systematic approach to imaging and serological evaluation is paramount.

STEMI or not STEMI? A multimodality imaging approach to a challenging intracardiac mass with a tricky presentation.

Cardiac tumors, due to the various clinical scenarios and their histological subtypes, are still challenging for clinicians. They are differentiated into primary and secondary. The latest are more common and are usually lung and breast cancers, melanomas, and lymphoma metastasis. We present a case of a 73-year-old woman, with a history of breast cancer 10 years earlier, admitted to Cath lab for an elevation of the ST-segment of the electrocardiogram, myocardial infarction. Echocardiogram showed a curious abnormality in the myocardial wall. Thanks to a multimodality imaging strategy, including contrast-enhanced echocardiography and cardiac magnetic resonance, characterization of the underlying pathology was clear and, thus, the appropriate management and therapy.

This is the case of a cardiac metastatic tumor, whose certain diagnosis can only be made by myocardial biopsy ­ an invasive sample of heart tissue ­ unfortunately not available in our case. Alternatively, we puzzled data from two second-level imaging techniques: contrast-enhanced cardiac ultrasound and cardiac magnetic resonance, which allowed us to better evaluate the nature of this cardiac mass. The former gave information about its blood supply, the latter gave information about tissue characterization. In this paper, we show how a complete integration of data from clinical and a stepwise multimodality imaging-based approach may allow a diagnosis in a complex clinical case.

The dynamic duo: A narrative review on the synergy between stereotactic body radiotherapy and immunotherapy in lung cancer treatment (Review).

Immunotherapy, particularly immune checkpoint inhibitors (ICIs), is undoubtedly one of the major breakthroughs in lung cancer research. Patient survival and prognosis have all been improved as a result, although numerous patients do not respond to immunotherapy due to various immune escape mechanisms of the tumor cells. Recent preclinical and clinical evidence has shown that stereotactic body radiotherapy (SBRT), also known as stereotactic ablative radiotherapy, has a prominent immune priming effect that could elicit antitumor immunity against specific tumor antigens and destroy distant tumor cells, thereby achieving the elusive abscopal effect, with the resulting immuno­active tumor environment also being more conducive to ICIs. Some landmark trials have already demonstrated the survival benefit of the dynamic duo of SBRT plus immunotherapy in metastatic non­small­cell lung cancer, while others such as PEMBRO­RT further suggest that the addition of SBRT to immunotherapy could expand the current indication to those who have historically responded poorly to ICIs. In the present review, the biological mechanisms that drive the synergistic effect of SBRT and immunotherapy were first briefly outlined; then, the current understanding from clinical trials was summarized and new insight into the evolving role of immunotherapy and SBRT synergy in lung cancer treatment was provided. Finally, novel avenues for discovery were highlighted. The innovation of the present review lies in the inclusion of non­ICI immunotherapy in the discussion, which provides a more comprehensive view on the current development and future trend of SBRT + immunotherapy synergy.

Multi-modal segmentation with missing image data for automatic delineation of gross tumor volumes in head and neck cancers.

BACKGROUND: Head and neck (HN) gross tumor volume (GTV) auto-segmentation is challenging due to the morphological complexity and low image contrast of targets. Multi-modality images, including computed tomography (CT) and positron emission tomography (PET), are used in the routine clinic to assist radiation oncologists for accurate GTV delineation. However, the availability of PET imaging may not always be guaranteed. PURPOSE: To develop a deep learning segmentation framework for automated GTV delineation of HN cancers using a combination of PET/CT images, while addressing the challenge of missing PET data. METHODS: Two datasets were included for this study: Dataset I: 524 (training) and 359 (testing) oropharyngeal cancer patients from different institutions with their PET/CT pairs provided by the HECKTOR Challenge; Dataset II: 90 HN patients(testing) from a local institution with their planning CT, PET/CT pairs. To handle potentially missing PET images, a model training strategy named the "Blank Channel" method was implemented. To simulate the absence of a PET image, a blank array with the same dimensions as the CT image was generated to meet the dual-channel input requirement of the deep learning model. During the model training process, the model was randomly presented with either a real PET/CT pair or a blank/CT pair. This allowed the model to learn the relationship between the CT image and the corresponding GTV delineation based on available modalities. As a result, our model had the ability to handle flexible inputs during prediction, making it suitable for cases where PET images are missing. To evaluate the performance of our proposed model, we trained it using training patients from Dataset I and tested it with Dataset II. We compared our model (Model 1) with two other models which were trained for specific modality segmentations: Model 2 trained with only CT images, and Model 3 trained with real PET/CT pairs. The performance of the models was evaluated using quantitative metrics, including Dice similarity coefficient (DSC), mean surface distance (MSD), and 95% Hausdorff Distance (HD95). In addition, we evaluated our Model 1 and Model 3 using the 359 test cases in Dataset I. RESULTS: Our proposed model(Model 1) achieved promising results for GTV auto-segmentation using PET/CT images, with the flexibility of missing PET images. Specifically, when assessed with only CT images in Dataset II, Model 1 achieved DSC of 0.56 ± 0.16, MSD of 3.4 ± 2.1 mm, and HD95 of 13.9 ± 7.6 mm. When the PET images were included, the performance of our model was improved to DSC of 0.62 ± 0.14, MSD of 2.8 ± 1.7 mm, and HD95 of 10.5 ± 6.5 mm. These results are comparable to those achieved by Model 2 and Model 3, illustrating Model 1's effectiveness in utilizing flexible input modalities. Further analysis using the test dataset from Dataset I showed that Model 1 achieved an average DSC of 0.77, surpassing the overall average DSC of 0.72 among all participants in the HECKTOR Challenge. CONCLUSIONS: We successfully refined a multi-modal segmentation tool for accurate GTV delineation for HN cancer. Our method addressed the issue of missing PET images by allowing flexible data input, thereby providing a practical solution for clinical settings where access to PET imaging may be limited.