Deep-learning-based 3D super-resolution MRI radiomics model: superior predictive performance in preoperative T-staging of rectal cancer

Research on the developments of artificial intelligence in radiomics for oncology over the past decade: a bibliometric and visualized analysis

OBJECTIVE

To assess the publications' bibliographic features and look into how the advancement of artificial intelligence (AI) and its subfields in radiomics has affected the growth of oncology.

METHODS

The researchers conducted a search in the Web of Science (WoS) for scientific publications in cancer pertaining to AI and radiomics, published in English from 1 January 2015 to 31 December 2024.The research included a scientometric methodology and comprehensive data analysis utilising scientific visualization tools, including the Bibliometrix R software package, VOSviewer, and CiteSpace. Bibliometric techniques utilised were co-authorship, co-citation, co-occurrence, citation burst, and performance Analysis.

RESULTS

The final study encompassed 4,127 publications authored by 5,026 individuals and published across 597 journals. China (2087;50.57%) and USA (850;20.6%) were the two most productive countries. The authors with the highest publication counts were Tian Jie (60) and Cuocolo Renato (30). Fudan University (169;4.09%) and Sun Yat-sen University (162;3.93%) were the most active institutions. The foremost journals were Frontiers in Oncology and Cancer. The predominant author keywords were radiomics, artificial intelligence, and oncology research.

CONCLUSION

Investigations into the integration of AI with radiomics in oncology remain nascent, with numerous studies concentrating on biology, diagnosis, treatment, and cancer risk evaluation.

Artificial Intelligence in Gastrointestinal Imaging: Advances and Applications

While artificial intelligence (AI) has shown considerable progress in many areas of medical imaging, applications in abdominal imaging, particularly for the gastrointestinal (GI) system, have notably lagged behind advancements in other body regions. This article reviews foundational concepts in AI and highlights examples of AI applications in GI tract imaging. The discussion on AI applications includes acute & emergent GI imaging, inflammatory bowel disease, oncology, and other miscellaneous applications. It concludes with a discussion of important considerations for implementing AI tools in clinical practice, and steps we can take to accelerate future developments in the field.

Computer-aided diagnosis tool utilizing a deep learning model for preoperative T-staging of rectal cancer based on three-dimensional endorectal ultrasound

BACKGROUND

The prognosis and treatment outcomes for patients with rectal cancer are critically dependent on an accurate and comprehensive preoperative evaluation.Three-dimensional endorectal ultrasound (3D-ERUS) has demonstrated high accuracy in the T staging of rectal cancer. Thus, we aimed to develop a computer-aided diagnosis (CAD) tool using a deep learning model for the preoperative T-staging of rectal cancer with 3D-ERUS.

METHODS

We retrospectively analyzed the data of 216 rectal cancer patients who underwent 3D-ERUS. The patients were randomly assigned to a training cohort (n = 156) or a testing cohort (n = 60). Radiologists interpreted the 3D-ERUS images of the testing cohort with and without the CAD tool. The diagnostic performance of the CAD tool and its impact on the radiologists' interpretations were evaluated.

RESULTS

The CAD tool demonstrated high diagnostic efficacy for rectal cancer tumors of all T stages, with the best diagnostic performance achieved for T1-stage tumors (AUC, 0.85; 95% CI, 0.73-0.93). With assistance from the CAD tool, the AUC for T1 tumors improved from 0.76 (95% CI, 0.63-0.86) to 0.80 (95% CI, 0.68-0.94) (P = 0.020) for junior radiologist 2. For junior radiologist 1, the AUC improved from 0.61 (95% CI, 0.48-0.73) to 0.79 (95% CI, 0.66-0.88) (P = 0.013) for T2 tumors and from 0.73 (95% CI, 0.60-0.84) to 0.84 (95% CI, 0.72-0.92) (P = 0.038) for T3 tumors. The diagnostic consistency (κ value) also improved from 0.31 to 0.64 (P = 0.005) for the junior radiologists and from 0.52 to 0.66 (P = 0.005) for the senior radiologists.

CONCLUSION

A CAD tool utilizing a deep learning model based on 3D-ERUS images showed strong performance in T staging rectal cancer. This tool could improve the performance of and consistency between radiologists in preoperatively assessing rectal cancer patients.

Can Habitat-Based MRI Radiomics Distinguish Between T2 and T3 Stages in Rectal Cancer?

RATIONALE AND OBJECTIVES

This study aims to investigate the use of multiparametric MRI (mp-MRI) habitat imaging techniques and radiomics to accurately predict the T2-T3 stages of rectal cancer.

MATERIALS AND METHODS

A retrospective analysis was conducted on data from 507 rectal cancer patients across three medical centers. Data from Center 1 were randomly assigned in a 7:3 ratio to the training (n=264) and internal validation cohort (n=113). Data from Centers 2 and 3 served as external validation (n=130). Preoperative clinical data were analyzed, and independent predictors were identified using multivariable regression to develop a clinical model. MRI habitat imaging and radiomics were employed to derive radiomics feature scores, which were then used to construct habitat models.

RESULTS

Among 10 clinical factors, invasion depth and MR-report T stage were identified as independent predictive factors for the clinical model. Tumors were divided into three subregions using k-means clustering, and radiomics features were extracted from each subregion. After feature selection, 40, 37, and 39 highly correlated features were retained for habitat models 1, 2, and 3, respectively. The habitat combined (habitat C) model, which integrated all three individual habitat models, was developed. The AUC values for the clinical model in predicting T2-T3 stages ranged from 0.745 to 0.834, while the AUC values for the habitat models ranged from 0.817 to 0.981, with the habitat C model demonstrating the best predictive performance.

CONCLUSION

The mp-MRI habitat model developed in this study offers precise prediction of T2-T3 staging in rectal cancer.

Habitat Radiomics and Deep Learning Features Based on CT for Predicting Lymphovascular Invasion in T1-stage Lung Adenocarcinoma: A Multicenter Study

RATIONALE AND OBJECTIVES

The research aims to examine how CT-derived habitat radiomics can be used to predict lymphovascular invasion (LVI) in patients with T1-stage lung adenocarcinoma (LUAD), and compare its effectiveness to traditional radiomics and deep learning (DL) models.

MATERIALS AND METHODS

We retrospectively analyzed 349 T1-stage LUAD patients from three centers from January 2021 to March 2024. The K-means algorithm was utilized to cluster CT images and apparent diffusion coefficient maps. Following features selection, we constructed three types of models, namely radiomics, habitat, and DL to identify patients with LVI. The evaluation of all models was conducted by employing the area under the receiver operating characteristic curve (AUC), calibration curves and decision curve analysis.

RESULTS

349 eligible patients were divided into an internal training set of 210 and an external test set of 139. We identified four distinct habitats, with the AUC for the overall habitat area outperforming that of the four sub-areas. Within the test set, the habitat model reached a higher AUC of 0.941 in contrast to the radiomics model at 0.918 and the deep learning model at 0.896.

CONCLUSION

CT-based habitat radiomics shows promise in predicting LVI in T1-stage LUAD patients, with the habitat signature demonstrating superior performance and significant advantages in identifying patients who are LVI-positive.

A High-resolution T2WI-based Deep Learning Model for Preoperative Discrimination Between T2 and T3 Rectal Cancer: A Multicenter Study

RATIONALE AND OBJECTIVES

To construct a deep learning model (DL) based on high-resolution T2-weighted images for preoperative differentiation between T2 and T3 stage rectal cancer (RC), and to compare its performance with experienced radiologists.

METHODS

This retrospective study included 281 patients with pathologically confirmed RC from four centers (January 2017-December 2022). A DenseNet model was developed using 255 patients from three centers (training:validation ratio=8:2) and externally tested on 26 patients from a fourth center. Two experienced radiologists independently assessed T staging. Diagnostic performance was evaluated using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).

RESULTS

The DL model outperformed radiologists in differentiating T2 and T3 stages across all datasets. In the training set, the DL model achieved an AUC of 0.810, compared to 0.578 and 0.625 for radiologists A and B, respectively. In the external test set, the DL model maintained superior diagnostic performance (AUC=0.715) compared to radiologist A (AUC=0.549) and radiologist B (AUC=0.493). The DL model demonstrated higher accuracy for T2 staging (0.625-0.787) and T3 staging (0.611-0.814) compared to radiologists (0.373-0.526 for T2; 0.611-0.783 for T3), who showed a tendency to over-stage T2 tumors. Inter-observer agreement between radiologists was moderate (kappa=0.451).

CONCLUSION

The DenseNet-based DL model demonstrated superior accuracy and diagnostic efficiency than radiologists in preoperative differentiation between T2 and T3 stages RC. This automated approach could potentially improve staging accuracy and support clinical decision-making in RC treatment planning.

Novel deep learning algorithm based MRI radiomics for predicting lymph node metastases in rectal cancer

To explore the value of applying the MRI-based radiomic nomogram for predicting lymph node metastasis (LNM) in rectal cancer (RC). This retrospective analysis used data from 430 patients with RC from two medical centers. The patients were categorized into the LNM negative (LNM-) and LNM positive (LNM+) according to their surgical pathology results. We developed a physician model by selecting clinical independent predictors through physician assessments. Additionally, we developed deep learning radscore (DLRS) models by extracting deep features from multiparametric MRI (mpMRI) images. A nomogram model was constructed by combining the physician model and DLRS models. Among the patients, 192 (44.65%, 192/430) experienced LNM+. Six prediction models were developed, namely the physician model, three sequence models, the DLRS, and the nomogram. The physician model achieved AUC of the receiver operating characteristic (ROC) values of 0.78, 0.79, and 0.7, whereas the sequence models, DLRS model, and nomogram model achieved AUC values ranging from 0.83 to 0.99. The predictive performance of the DLRS and nomogram models was superior to that of the physician model. DLRS and nomogram models based on mpMRI provided higher accuracy in predicting LNM status in patients with RC than the other models.

Habitat Radiomics Based on MRI for Predicting Metachronous Liver Metastasis in Locally Advanced Rectal Cancer: a Two‑center Study

RATIONALE AND OBJECTIVES

This study aimed to explore the feasibility of using habitat radiomics based on magnetic resonance imaging (MRI) to predict metachronous liver metastasis (MLM) in locally advanced rectal cancer (LARC) patients. A nomogram was developed by integrating multiple factors to enhance predictive accuracy.

METHODS

Retrospective data from 385 LARC patients across two centers were gathered. The data from Center 1 were split into a training set of 203 patients and an internal validation set of 87 patients, while Center 2 provided an external test set of 95 patients. K - means clustering was used on T2 - weighted images, and the region of interest was extended at different thicknesses. After feature extraction and selection, four machine - learning algorithms were utilized to build radiomics models. A nomogram was created by combining habitat radiomics, conventional radiomics, and clinical independent predictors. Model performance was evaluated by the AUC, and clinical utility was assessed through calibration curve and DCA.

RESULTS

Habitat radiomics outperformed other single models in predicting MLM, with AUCs of 0.926, 0.864, and 0.851 in respective sets. The integrated nomogram achieved even higher AUCs of 0.959, 0.925, and 0.889. DCA and calibration curve analysis showed its high net benefit and good calibration.

CONCLUSION

MRI - based habitat radiomics can effectively predict MLM in LARC patients. The integrated nomogram has optimal predictive performance and improves model accuracy significantly.

Enhancing the role of MRI in rectal cancer: advances from staging to prognosis prediction

Rectal cancer (RC) is one of the major health challenges worldwide. Accurate staging, restaging, invasiveness assessment, and treatment efficacy evaluation are crucial for its clinical management. Magnetic resonance imaging (MRI) plays a significant role in these processes. However, standard MRI techniques, including T2-weighted and diffusion-weighted imaging, have uncertainties in identifying early-stage tumors, high-risk nodules, extramural vascular invasion, and treatment efficacy, potentially leading to inappropriate treatment. Recent advances suggest that the integration of traditional MRI methods, including diffusion-weighted imaging, opposed-phase or contrast-enhanced T1-weighted imaging, as well as emerging synthetic MRI, could address these challenges. Additionally, improvements in imaging technology have spurred research into advanced functional MRI techniques such as diffusion kurtosis imaging and amide proton transfer weighted MRI, yielding promising results in RC assessment. Total neoadjuvant therapy has emerged as a new treatment paradigm for locally advanced RC, with neoadjuvant immunotherapy and chemotherapy offering viable alternatives to neoadjuvant chemoradiotherapy. However, the lack of standards for the early prediction of patient survival and tumor response to neoadjuvant therapy highlights a critical unmet need in matching therapies to suitable patients. Furthermore, organ preservation strategies after neoadjuvant therapy provide personalized options based on tumor response and patient preferences, yet traditional MRI assessments show significant variability. Radiomics and artificial intelligence hold promise for revealing complex patterns in MRI images associated with patient prognosis and treatment response. This review provides an overview of current MRI advancements in RC assessment and emphasizes how future research can refine tailored treatment strategies to improve patient outcomes. KEY POINTS: Question The accurate diagnosis of early-stage rectal tumors, high-risk nodules, treatment responses, and the early prediction of patient survival and therapeutic outcomes remain an unmet need. Findings Visual MRI has improved staging, restaging, and invasiveness evaluation. Advanced MRI, radiomics and artificial intelligence provide significant potential for tumor characterization and outcome prediction. Clinical relevance Advances in visual MRI are improving routine imaging protocols and radiomics and artificial intelligence show promise in enhancing treatment decisions through precise tumor characterization and outcome prediction.

AI-assisted compressed sensing MRI improves imaging quality in rectal cancer: a comparative study with conventional acceleration techniques

Background

Artificial intelligence (AI)-assisted compressed sensing (ACS) is widely used in various parts of the body, but the application of this technology in the rectum is still rare. This study aimed to evaluate the feasibility of super-resolution (SR) T2-weighted imaging (T2WI) based on ACS in rectal cancer (RC) by comparing with compressed sensing (CS) and parallel imaging (PI).

Methods

In this prospective study, 29 patients with rectal adenocarcinoma were enrolled, and three groups of SR rectal T2WI images based on ACS, CS, and PI (ACS-T2WI, CS-T2WI, and PI-T2WI) were obtained, using the same scanning time for each group. Two radiologists independently assessed the visibility of structures, tissue edge sharpness, image artifacts, overall image quality, and confidence in N staging for the three sequences using a five-point Likert scale; the scores of the three sequences were compared and the agreement between two readers was assessed. In addition, the quantitative parameters of the three groups, sharpness, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were compared. T staging based on magnetic resonance imaging (MRI) was performed by two readers separately using the three sequences combined with other conventional scanning sequences. The consistency between T staging based on MRI (mrT staging) and pathological T staging (PT staging) of the two readers and the diagnostic accuracy of every sequence was compared.

Results

The scores of ACS-T2WI were higher in visibility of structures, tissue edge sharpness, overall image quality, and confidence in N staging than CS-T2WI and PI-T2WI (P<0.001). There was no statistical difference in the scores of image artifacts among the three sequences (P=0.18). The sharpness of ACS-T2WI was higher than that of CS-T2WI and PI-T2WI (P<0.001). The SNR of CS-T2WI was slightly higher than that of ACS-T2WI and PI-T2WI (P=0.004). There was no statistically significant difference in CNR among the three sequences (P=0.425). The consistency between mrT staging of ACS-T2WI and PT staging was higher than that of CS-T2WI and PI-T2WI. The two readers had a higher diagnostic accuracy for ACS-T2WI (89.66%) than for CS-T2WI (79.31%) and PI-T2WI (75.86%), but the difference was not statistically significant.

Conclusions

By using ACS to increase the resolution through a larger matrix size, higher quality images can be obtained within the same scanning time as traditional acceleration techniques. The SR T2WI based on ACS can be well applied in the clinical scanning of RC.

Assessing the Feasibility and Diagnostic Value of Percutaneous Transhepatic Cholangioscopy Biopsy for Biliary Strictures

OBJECTIVE

To evaluate the feasibility and diagnostic value of percutaneous transhepatic cholangioscopy biopsy (PTCB) for identifying the causes of biliary strictures.

METHODS

This retrospective study included 34 patients (18 females and 16 males), with a mean age of 59.4 ± 13 years. The study population consisted of patients with suspected malignant biliary strictures on imaging or biliary lesions suspected of malignancy during percutaneous transhepatic endoscopic biliary lithotripsy (PTEBL). The final diagnosis for each patient was confirmed based on surgical pathology results, additional histopathological data, or through close clinical and imaging follow-up for at least one year.

RESULTS

Among the patients, 20 (58.9%) underwent PTCB alone, while 14 (41.1%) underwent PTCB combined with PTEBL. Biopsy locations included: 12 patients (35.3%) with intrahepatic bile duct, 12 patients (35.3%) with hilar bile duct, and 10 patients (29.4%) with common bile duct. Technical success of PTCB was defined as successful access to the biliary lesion, with the collection of an adequate histopathological tissue sample achieved in 100% of patients. The sensitivity, specificity, and accuracy of PTCB were 90%, 100%, and 97.1%, respectively. Minor complications were observed in 3 patients (8.8%).

CONCLUSION

PTCB is a feasible and effective method for diagnosing the causes of biliary strictures, offering high sensitivity, specificity, and accuracy.

Predicting Surgical Difficulty in Rectal Cancer Surgery: A Systematic Review of Artificial Intelligence Models Applied to Pre-Operative MRI

Introduction: Following the rapid advances in minimally invasive surgery, there are a multitude of surgical modalities available for resecting rectal cancers. Robotic resections represent the current pinnacle of surgical approaches. Currently, decisions on the surgical modality depend on local resources and the expertise of the surgical team. Given limited access to robotic surgery, developing tools based on pre-operative data that can predict the difficulty of surgery would streamline the efficient utilisation of resources. This systematic review aims to appraise the existing literature on artificial intelligence (AI)-driven preoperative MRI analysis for surgical difficulty prediction to identify knowledge gaps and promising models warranting further clinical evaluation. Methods: A systematic review and narrative synthesis were undertaken in accordance with PRISMA and SWiM guidelines. Systematic searches were performed on Medline, Embase, and the CENTRAL Trials register. Studies published between 2012 and 2024 were included where AI was applied to preoperative MRI imaging of adult rectal cancer patients undergoing surgeries, of any approach, for the purpose of stratifying surgical difficulty. Data were extracted according to a pre-specified protocol to capture study characteristics and AI design; the objectives and performance outcome metrics were summarised. Results: Systematic database searches returned 568 articles, 40 ultimately included in this review. AI to support preoperative difficulty assessments were identified across eight domains (direct surgical difficulty grading, extramural vascular invasion (EMVI), lymph node metastasis (LNM), lymphovascular invasion (LVI), perineural invasion (PNI), T staging, and the requirement for multiple linear stapler firings. For each, at least one model was identified with very good performance (AUC scores of >0.80), with several showing excellent performance considerably above this threshold. Conclusions: AI tools applied to preoperative rectal MRI to support preoperative difficulty assessment for rectal cancer surgeries are emerging, with the progressing development and strong performance of many promising models. These warrant further clinical evaluation, which can aid personalised surgical approaches and ensure the adequate utilisation of limited resources.

A comprehensive dataset of germinoma on MRI/CT with clinical and radiomic data

Intracranial germ cell tumors (GCTs) are rare neoplasms with a peak incidence in adolescents. Germinoma is the most common histological subtype of intracranial GCTs. Its symptoms include intracranial hypertension, visual field defects, and hormonal disorders, affecting the physical health of adolescents. Germinoma is sensitive to chemo-radiotherapy, and most patients do not require neurosurgical resection. Therefore, improving the accuracy of germinoma diagnosis helps to avoid unnecessary surgery. At present, the application of artificial intelligence (AI) in medical imaging has improved the accuracy of disease diagnosis. However, few studies focused on the AI model to diagnosis germinoma and there are no publicly available imaging datasets for germinoma. This study aimed to create a comprehensive dataset for germinoma using magnetic resonance imaging/computed tomography findings with clinical and radiomic data to train and validate AI models. Featuring 65 pathologically confirmed germinomas, the dataset included axial T2-weighted imaging, T2-weighted fluid-attenuated inversion recovery, T1-weighted imaging, T1-weighted imaging with contrast enhancement, diffusion-weighted MR imaging, CT images, clinical data, and morphological and radiomic-based features obtained by segmentation.

MRI-Based Radiomics Features for Prediction of Pathological Deterioration Upgrading in Rectal Tumor

PURPOSE

Our aim is to develop and validate an MRI-based diagnostic model for predicting pathological deterioration upgrading in rectal tumor.

METHODS

This retrospective study included 158 eligible patients from January 2017 to November 2023. The patients were divided into a training group (n = 110) and a validation group (n = 48). Radiomics features were extracted from T2-weighted images to create a radiomics score model. Significant factors identified through multifactor analysis were used to develop the final clinical feature model. By combining these two models, an combined radiomics-clinical model was established. The model's performance was evaluated using Receiver Operating Characteristic (ROC) analysis and the Area Under the ROC Curve (AUC).

RESULTS

A total of 1197 features were extracted, with 11 features selected for calculating the radiomics score to establish the radiomics model. This model demonstrated good predictive performance for pathological upgrading in both the training and validation groups (AUC of 0.863 and 0.861, respectively). Clinical factors such as chief complaint and differential carcinoembryonic antigen levels showed statistical significance (P < 0.05). The clinical model, incorporating these factors, yielded AUC values of 0.669 and 0.651 for the training and validation groups, respectively. Furthermore, the radiomics-clinical combined model outperformed the individual models in predicting preoperative pathological upgrading in both the training and validation groups (AUC of 0.932 and 0.907, respectively).

CONCLUSIONS

A radiomics-clinical model, which combines clinical features with radiomics features based on MRI, can predict pathological deterioration upgrading in patients with rectal tumor and provide valuable insights for personalized treatment strategies.

Role of Artificial Intelligence in MRI-Based Rectal Cancer Staging: A Systematic Review

Several studies explored the application of artificial intelligence (AI) in magnetic resonance imaging (MRI)-based rectal cancer (RC) staging, but a comprehensive evaluation remains lacking. This systematic review aims to review the performance of AI models in MRI-based RC staging. PubMed and Embase were searched from the inception of the database till October 2024 without any language and year restrictions. The prospective or retrospective studies evaluating AI models (including machine learning (ML) and deep learning (DL)) for diagnostic performance in MRI-based RC staging compared with any comparator were included in this review. The performance metrics were considered as outcomes. Two independent reviewers were involved in the study selection and data extraction to limit bias; any disagreements were resolved through mutual consensus or discussion with a third reviewer. A total of 716 records were identified from the databases. Out of these, 14 studies (1.95%) were finally included in this review. These studies were published between 2019 and 2024. Various MRI technologies were adapted by the studies and multiple AI models were developed. DL was the most common. The MRI images including T1-weighted images (14.28%), T2-weighted images (85.71%), diffusion-weighted images (42.85%), or the combination of these from different landscapes and systems were used to develop the AI models. The models were built using various techniques, mainly DL such as conventional neural network (28.57%), DL reconstruction (14.28%), Weakly supervISed model DevelOpment fraMework (7.12%), deep neural network (7.12%), Faster region-based CNN (7.12%), ResNet, DL-based clinical-radiomics nomogram (7.12%), LASSO (7.12%), and random forest classifier (7.12%). All the models that used single-type images or combined imaging modalities showed a better performance than manual assessment in terms of higher accuracy, sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and area under the curve with a score of >0.75. This is considered to be a good performance. The current study indicates that MRI-based AI models for RC staging show great promise with a high performance.

Nomogram for predicting cervical lymph node metastasis of papillary thyroid carcinoma using deep learning-based super-resolution ultrasound image

OBJECTIVES

To investigate the feasibility and effectiveness of a deep learning (DL) super-resolution (SR) ultrasound image reconstruction model for predicting cervical lymph node status in patients with papillary thyroid carcinoma(PTC).

METHODS

In this retrospective study, researchers recruited 544 patients with PTC and randomly assigned them to training and test sets. SR ultrasound images were acquired using SR technology to improve image resolution, and artificial features and DL features were extracted from the original (OR) and SR images, respectively, to construct a ML, DL model. The best model was selected and aggregated with clinical parameters to construct the nomogram. The performance of the model is evaluated by ROC curves, calibration curves and decision curves.

RESULTS

In distinguishing the presence or absence of metastatic lymph nodes, the predictive performance of the SR_ResNet 101 and SR_SVM models based on SR outperformed those based on OR. In the test set, SR_SVM AUC was 0.878 (95% CI 0.8203-0.9358), accuracy 0.854, while OR_SVM AUC was 0.822 (95% CI 0.7500-0.8937), accuracy 0.665. SR_ResNet 101 AUC was 0.799 (95% CI 0.7175-0.8806), accuracy 0.793, and OR_ResNet101 AUC was 0.751 (95% CI 0.6620-0.8401), accuracy 0.713. Subsequently, Nomogram_A and Nomogram_B were constructed by integrating the SR_SVM model and SR_ResNet 101 model, respectively, with clinical parameters, while Nomogram_C was constructed solely based on clinical indicators. In the test set, Nomogram_A demonstrated the best performance with an AUC of 0.930 (95% CI 0.8913-0.9682) and accuracy was 0.829. Nomogram_B AUC 0.868 (95% CI 0.8102-0.9261) and accuracy was 0.829, while Nomogram_C AUC 0.880 (95% CI 0.8257-0.9349) and accuracy was 0.787. The DeLong test revealed that the diagnostic performance of Nomogram_A based on SR_SVM was significantly higher than that of Nomogram_B, Nomogram_C, and the level of Radiologist (P < 0.05). The calibration curves and Hosmer-Lemeshow tests confirmed a high degree of fit, and the decision curve analysis demonstrated clinical value and potential patient benefit.

CONCLUSIONS

The predictive model constructed using SR reconstructed ultrasound images demonstrated superior performance in predicting preoperative cervical lymph node metastasis in PTC compared to OR images. The nomogram prediction model based on SR images has the potential to enhance the accuracy of predictive models and aid in clinical decision-making.

Visualization analysis of research hotspots and trends in MRI-based artificial intelligence in rectal cancer

Background

Rectal cancer (RC) is one of the most common types of cancer worldwide. With the development of artificial intelligence (AI), the application of AI in preoperative evaluation and follow-up treatment of RC based on magnetic resonance imaging (MRI) has been the focus of research in this field. This review was conducted to develop comprehensive insight into the current research progress, hotspots, and future trends in AI based on MRI in RC, which remains to be studied.

Methods

Literature related to AI based on MRI and RC, as of November 2023, was obtained from the Web of Science Core Collection database. Visualization and bibliometric analyses of publication quantity and content were conducted to explore temporal trends, spatial distribution, collaborative networks, influential articles, keyword co-occurrence, and research directions.

Results

A total of 177 papers (152 original articles and 25 reviews) were identified from 24 countries/regions, 351 institutions, and 81 journals. Since 2019, the number of studies on this topic has rapidly increased. China and the United States have contributed the highest number of publications and institutions, cultivating the most intimate collaborative relationship. The highest number of articles derive from Sun Yat-sen University, while Frontiers in Oncology has published the highest number of relevant articles. Research on MRI-based AI in this field has mainly focused on preoperative diagnosis and prediction of treatment efficacy and prognosis.

Conclusions

This study provides an objective and comprehensive overview of the publications on MRI-based AI in RC and identifies the present research landscape, hotspots, and prospective trends in this field, which can provide valuable guidance for scholars worldwide.

Prospective and multi-reader evaluation of deep learning reconstruction-based accelerated rectal MRI: image quality, diagnostic performance, and reading time

OBJECTIVES

To evaluate deep learning reconstruction (DLR)-based accelerated rectal magnetic resonance imaging (MRI) compared with standard MRI.

MATERIALS AND METHODS

Patients with biopsy-confirmed rectal adenocarcinoma between November/2022 and May/2023 in a single centre were prospectively enrolled for an intra-individual comparison between standard fast spin-echo (FSEstandard) and DLR-based FSE (FSEDL) sequences. Quantitative and qualitative image quality metrics of the pre-therapeutic MRIs were evaluated in all patients; diagnostic performance and evaluating time for T-staging, N-staging, extramural vascular invasion (EMVI), and mesorectal fascia (MRF) status was further analysed in patients undergoing curative surgery, with histopathologic results as the diagnostic gold standard.

RESULTS

A total of 117 patients were enrolled, with 60 patients undergoing curative surgery. FSEDL reduced the acquisition time by 65% than FSEstandard. FSEDL exhibited higher signal-to-noise ratios, contrast-to-noise ratio, and subjective scores (noise, tumour margin clarity, visualisation of bowel wall layering and MRF, overall image quality, and diagnostic confidence) than FSEstandard (p < 0.001). Reduced artefacts were observed in FSEDL for patients without spasmolytics (p < 0.05). FSEDL provided higher T-staging accuracy by junior readers than FSEstandard (reader 1, 58.33% vs 70.00%, p = 0.016; reader 3, 60.00% vs 76.67%, p = 0.021), with similar N-staging, EMVI, and MRF performance. No significant difference was observed for senior readers. FSEDL exhibited shorter diagnostic time in all readers' T-staging and overall evaluation, and junior readers' EMVI and MRF (p < 0.05).

CONCLUSION

FSEDL provided improved image quality, reading time, and junior radiologists' T-staging accuracy than FSEstandard, while reducing the acquisition time by 65%.

CLINICAL RELEVANCE STATEMENT

DLR is clinically applicable for rectal MRI, providing improved image quality with shorter scanning time, which may ease the examination burden. It is beneficial for diagnostic optimisation in improving junior radiologists' T-staging accuracy and reading time.

KEY POINTS

The rising incidence of rectal cancer has demanded enhanced efficiency and quality in imaging examinations. FSEDL demonstrated superior image quality and had a 65% reduced acquisition time. FSEDL can improve the diagnostic accuracy of T-staging and reduce the reading time for assessing rectal cancer.

Evaluation of super resolution technology for digestive endoscopic images

Object

This study aims to evaluate the value of super resolution (SR) technology in augmenting the quality of digestive endoscopic images.

Methods

In the retrospective study, we employed two advanced SR models, i.e., SwimIR and ESRGAN. Two discrete datasets were utilized, with training conducted using the dataset of the First Affiliated Hospital of Soochow University (12,212 high-resolution images) and evaluation conducted using the HyperKvasir dataset (2,566 low-resolution images). Furthermore, an assessment of the impact of enhanced low-resolution images was conducted using a 5-point Likert scale from the perspectives of endoscopists. Finally, two endoscopic image classification tasks were employed to evaluate the effect of SR technology on computer vision (CV).

Results

SwinIR demonstrated superior performance, which achieved a PSNR of 32.60, an SSIM of 0.90, and a VIF of 0.47 in test set. 90 % of endoscopists supported that SR preprocessing moderately ameliorated the readability of endoscopic images. For CV, enhanced images bolstered the performance of convolutional neural networks, whether in the classification task of Barrett's esophagus (improved F1-score: 0.04) or Mayo Endoscopy Score (improved F1-score: 0.04).

Conclusions

SR technology demonstrates the capacity to produce high-resolution endoscopic images. The approach enhanced clinical readability and CV models' performance of low-resolution endoscopic images.

Super-resolution reconstruction improves multishell diffusion: using radiomics to predict adult-type diffuse glioma IDH and grade

Objectives

Multishell diffusion scanning is limited by low spatial resolution. We sought to improve the resolution of multishell diffusion images through deep learning-based super-resolution reconstruction (SR) and subsequently develop and validate a prediction model for adult-type diffuse glioma, isocitrate dehydrogenase status and grade 2/3 tumors.

Materials and methods

A simple diffusion model (DTI) and three advanced diffusion models (DKI, MAP, and NODDI) were constructed based on multishell diffusion scanning. Migration was performed with a generative adversarial network based on deep residual channel attention networks, after which images with 2x and 4x resolution improvements were generated. Radiomic features were used as inputs, and diagnostic models were subsequently constructed via multiple pipelines.

Results

This prospective study included 90 instances (median age, 54.5 years; 39 men) diagnosed with adult-type diffuse glioma. Images with both 2x- and 4x-improved resolution were visually superior to the original images, and the 2x-improved images allowed better predictions than did the 4x-improved images (P<.001). A comparison of the areas under the curve among the multiple pipeline-constructed models revealed that the advanced diffusion models did not have greater diagnostic performance than the simple diffusion model (P>.05). The NODDI model constructed with 2x-improved images had the best performance in predicting isocitrate dehydrogenase status (AUC_validation=0.877; Brier score=0.132). The MAP model constructed with the original images performed best in classifying grade 2 and grade 3 tumors (AUC_validation=0.806; Brier score=0.168).

Conclusion

SR improves the resolution of multishell diffusion images and has different advantages in achieving different goals and creating different target diffusion models.

Different radiomics annotation methods comparison in rectal cancer characterisation and prognosis prediction: a two-centre study

OBJECTIVES

To explore the performance differences of multiple annotations in radiomics analysis and provide a reference for tumour annotation in large-scale medical image analysis.

METHODS

A total of 342 patients from two centres who underwent radical resection for rectal cancer were retrospectively studied and divided into training, internal validation, and external validation cohorts. Three predictive tasks of tumour T-stage (pT), lymph node metastasis (pLNM), and disease-free survival (pDFS) were performed. Twelve radiomics models were constructed using Lasso-Logistic or Lasso-Cox to evaluate and four annotation methods, 2D detailed annotation along tumour boundaries (2D), 3D detailed annotation along tumour boundaries (3D), 2D bounding box (2DBB), and 3D bounding box (3DBB) on T2-weighted images, were compared. Radiomics models were used to establish combined models incorporating clinical risk factors. The DeLong test was performed to compare the performance of models using the receiver operating characteristic curves.

RESULTS

For radiomics models, the area under the curve values ranged from 0.627 (0.518-0.728) to 0.811 (0.705-0.917) in the internal validation cohort and from 0.619 (0.469-0.754) to 0.824 (0.689-0.918) in the external validation cohort. Most radiomics models based on four annotations did not differ significantly, except between the 3D and 3DBB models for pLNM (p = 0.0188) in the internal validation cohort. For combined models, only the 2D model significantly differed from the 2DBB (p = 0.0372) and 3D models (p = 0.0380) for pDFS.

CONCLUSION

Radiomics and combined models constructed with 2D and bounding box annotations showed comparable performances to those with 3D and detailed annotations along tumour boundaries in rectal cancer characterisation and prognosis prediction.

CRITICAL RELEVANCE STATEMENT

For quantitative analysis of radiological images, the selection of 2D maximum tumour area or bounding box annotation is as representative and easy to operate as 3D whole tumour or detailed annotations along tumour boundaries.

KEY POINTS

There is currently a lack of discussion on whether different annotation efforts in radiomics are predictively representative. No significant differences were observed in radiomics and combined models regardless of the annotations (2D, 3D, detailed, or bounding box). Prioritise selecting the more time and effort-saving 2D maximum area bounding box annotation.

Deep-learning-based 3D super-resolution CT radiomics model: Predict the possibility of the micropapillary/solid component of lung adenocarcinoma

Objective

Invasive lung adenocarcinoma（ILA） with micropapillary (MPP)/solid (SOL) components has a poor prognosis. Preoperative identification is essential for decision-making for subsequent treatment. This study aims to construct and evaluate a super-resolution（SR） enhanced radiomics model designed to predict the presence of MPP/SOL components preoperatively to provide more accurate and individualized treatment planning.

Methods

Between March 2018 and November 2023, patients who underwent curative intent ILA resection were included in the study. We implemented a deep transfer learning network on CT images to improve their resolution, resulting in the acquisition of preoperative super-resolution CT (SR-CT) images. Models were developed using radiomic features extracted from CT and SR-CT images. These models employed a range of classifiers, including Logistic Regression (LR), Support Vector Machines (SVM), k-Nearest Neighbors (KNN), Random Forest, Extra Trees, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Multilayer Perceptron (MLP). The diagnostic performance of the models was assessed by measuring the area under the curve (AUC).

Result

A total of 245 patients were recruited, of which 109 (44.5 %) were diagnosed with ILA with MPP/SOL components. In the analysis of CT images, the SVM model exhibited outstanding effectiveness, recording AUC scores of 0.864 in the training group and 0.761 in the testing group. When this SVM approach was used to develop a radiomics model with SR-CT images, it recorded AUCs of 0.904 in the training and 0.819 in the test cohorts. The calibration curves indicated a high goodness of fit, while decision curve analysis (DCA) highlighted the model's clinical utility.

Conclusion

The study successfully constructed and evaluated a deep learning（DL）-enhanced SR-CT radiomics model. This model outperformed conventional CT radiomics models in predicting MPP/SOL patterns in ILA. Continued research and broader validation are necessary to fully harness and refine the clinical potential of radiomics when combined with SR reconstruction technology.

Compressed sensing 3D T2WI radiomics model: improving diagnostic performance in muscle invasion of bladder cancer

BACKGROUND

Preoperative discrimination between non-muscle-invasive bladder cancer (NMIBC) and the muscle invasive bladder cancer (MIBC) is a determinant of management. The purpose of this research is to employ radiomics to evaluate the diagnostic value in determining muscle invasiveness of compressed sensing (CS) accelerated 3D T2-weighted-SPACE sequence with high resolution and short acquisition time.

METHODS

This prospective study involved 108 participants who underwent preoperative 3D-CS-T2-weighted-SPACE, 3D-T2-weighted-SPACE and T2-weighted sequences. The cohort was divided into training and validation cohorts in a 7:3 ratio. In the training cohort, a Rad-score was constructed based on radiomic features selected by intraclass correlation coefficients, pearson correlation coefficient and least absolute shrinkage and selection operator . Multivariate logistic regression was used to develop a nomogram combined radiomics and clinical indices. In the validation cohort, the performances of the models were evaluated by ROC, calibration, and decision curves.

RESULTS

In the validation cohort, the area under ROC curve of 3D-CS-T2-weighted-SPACE, 3D-T2-weighted-SPACE and T2-weighted models were 0.87(95% confidence interval (CI):0.73-1.00), 0.79(95%CI:0.63-0.96) and 0.77(95%CI:0.60-0.93), respectively. The differences in signal-to-noise ratio and contrast-to-noise ratio between 3D-CS-T2-weighted-SPACE and 3D-T2-weighted-SPACE sequences were not statistically significant(p > 0.05). While the clinical model composed of three clinical indices was 0.74(95%CI:0.55-0.94) and the radiomics-clinical nomogram model was 0.88(95%CI:0.75-1.00). The calibration curves confirmed high goodness of fit, and the decision curve also showed that the radiomics model and combined nomogram model yielded higher net benefits than the clinical model.

CONCLUSION

The radiomics model based on compressed sensing 3D T2WI sequence, which was acquired within a shorter acquisition time, showed superior diagnostic efficacy in muscle invasion of bladder cancer. Additionally, the nomogram model could enhance the diagnostic performance.

CT-Based Super-Resolution Deep Learning Models with Attention Mechanisms for Predicting Spread Through Air Spaces of Solid or Part-Solid Lung Adenocarcinoma

RATIONALE AND OBJECTIVES

Spread through air space (STAS) is a novel invasive pattern of lung adenocarcinoma (LUAD), and preoperative knowledge of STAS status is helpful in choosing an appropriate surgical approach.

MATERIALS AND METHODS

This retrospective study collected and analyzed 602 patients diagnosed with LUAD from two medical centers: center 1 was randomly partitioned into training (n = 358) and validation cohorts (n = 154) at a 7:3 ratio; and center 2 was the external test cohort (n = 90). Super resolution was performed on all images to acquire high-resolution images, which were used to train the SE-ResNet50 model, before creating an equivalent parameter ResNet50 model. Disparities were compared between the two models using receiver operating characteristic curves, area under the curve, accuracy, precision, sensitivity, and specificity.

RESULTS

In this study, 512 and 90 patients with LUAD were enrolled from centers 1 and 2, respectively. The curve values of the SE-ResNet50 and ResNet50 models were compared for training, validation, and test cohorts, resulting in values of 0.933 vs 0.909, 0.783 vs 0.728, and 0.806 vs 0.695, respectively. In the external test cohort, the accuracy of the SE-ResNet50 model demonstrated a 10% improvement over the ResNet50 model (82.2% vs 72.2%).

CONCLUSION

The SE-ResNet50 model based on computed tomography super-resolution has great potential for predicting STAS status in patients with solid or partially solid LUAD, with superior predictive performance compared to traditional deep learning models.

A nomogram based on MRI radiomics features of mesorectal fat for diagnosing T2- and T3-stage rectal cancer

PURPOSE

To develop and validate a nomogram for the preoperative diagnosis of T2 and T3 stage rectal cancer using MRI radiomics features of mesorectal fat.

METHODS

The data of 288 patients with T2 and T3 stage rectal cancer were retrospectively collected. Radiomics features were extracted from the lesion region of interest (ROI) in the MRI high-resolution T2WI, apparent diffusion coefficient (ADC), and diffusion-weighted imaging (DWI) sequences. After using ICC inter-group consistency analysis and Pearson correlation analysis to reduce dimensions, LASSO regression analysis was performed to select features and calculate Rad-score for each sequence. Then, Combined_Radscore and nomogram were constructed based on the LASSO-selected features and clinical data for each sequence. Receiver operating characteristic curve (ROC) area under the curve (AUC) was used to evaluate the performance of the Rad-score model and nomogram. Decision curve analysis (DCA) was performed to evaluate the clinical usability of the radiomics nomogram, which were combined with calibration curves to evaluate the prediction accuracy.

RESULTS

The nomogram based on MRI-report T status and Combined_Radscore achieved AUCs of 0.921 and 0.889 in the training and validation cohorts, respectively.

CONCLUSION

The nomogram can be stated that the radiomics nomogram based on multi-sequence MRI imaging of the mesorectal fat has excellent diagnosing performance for preoperative differentiation of T2 and T3 stage rectal cancer.

Speeding Up and Improving Image Quality in Glioblastoma MRI Protocol by Deep Learning Image Reconstruction

A fully diagnostic MRI glioma protocol is key to monitoring therapy assessment but is time-consuming and especially challenging in critically ill and uncooperative patients. Artificial intelligence demonstrated promise in reducing scan time and improving image quality simultaneously. The purpose of this study was to investigate the diagnostic performance, the impact on acquisition acceleration, and the image quality of a deep learning optimized glioma protocol of the brain. Thirty-three patients with histologically confirmed glioblastoma underwent standardized brain tumor imaging according to the glioma consensus recommendations on a 3-Tesla MRI scanner. Conventional and deep learning-reconstructed (DLR) fluid-attenuated inversion recovery, and T2- and T1-weighted contrast-enhanced Turbo spin echo images with an improved in-plane resolution, i.e., super-resolution, were acquired. Two experienced neuroradiologists independently evaluated the image datasets for subjective image quality, diagnostic confidence, tumor conspicuity, noise levels, artifacts, and sharpness. In addition, the tumor volume was measured in the image datasets according to Response Assessment in Neuro-Oncology (RANO) 2.0, as well as compared between both imaging techniques, and various clinical-pathological parameters were determined. The average time saving of DLR sequences was 30% per MRI sequence. Simultaneously, DLR sequences showed superior overall image quality (all p < 0.001), improved tumor conspicuity and image sharpness (all p < 0.001, respectively), and less image noise (all p < 0.001), while maintaining diagnostic confidence (all p > 0.05), compared to conventional images. Regarding RANO 2.0, the volume of non-enhancing non-target lesions (p = 0.963), enhancing target lesions (p = 0.993), and enhancing non-target lesions (p = 0.951) did not differ between reconstruction types. The feasibility of the deep learning-optimized glioma protocol was demonstrated with a 30% reduction in acquisition time on average and an increased in-plane resolution. The evaluated DLR sequences improved subjective image quality and maintained diagnostic accuracy in tumor detection and tumor classification according to RANO 2.0.

Progress of MRI in predicting the circumferential resection margin of rectal cancer: A narrative review

Rectal cancer (RC) is the third most frequently diagnosed cancer worldwide, and the status of its circumferential resection margin (CRM) is of paramount significance for treatment strategies and prognosis. CRM involvement is defined as tumor touching or within 1 mm from the outermost part of tumor or outer border of the mesorectal or lymph node deposits to the resection margin. The incidence of involved CRM varied from 5.4 % to 36 %, which may associate with an in consistent definition of CRM, the quality of surgeries, and the different examination modalities. Although T and N status are essential factors in determining whether a patient should receive neoadjuvant therapy before surgery, CRM status is a powerful predictor of local and distant recurrence as well as survival rate. This review explores the significance of CRM, the various assessment methods, and the role of magnetic resonance imaging (MRI) and artificial intelligence-based MRI in predicting CRM status. MRI showed potential advantage in predicting CRM status with a high sensitivity and specificity compared to computed tomography (CT). We also discuss MRI advancements in RC imaging, including conventional MRI with body coil, high-resolution MRI with phased-array coil, and endorectal MRI. Along with a discussion of artificial intelligence-based MRI techniques to predict the CRM status of RCs before and after treatments.

Improving radiomic modeling for the identification of symptomatic carotid atherosclerotic plaques using deep learning-based 3D super-resolution CT angiography

Rationale and objectives

Radiomic models based on normal-resolution (NR) computed tomography angiography (CTA) images can fail to distinguish between symptomatic and asymptomatic carotid atherosclerotic plaques. This study aimed to explore the effectiveness of a deep learning-based three-dimensional super-resolution (SR) CTA radiomic model for improved identification of symptomatic carotid atherosclerotic plaques.

Materials and methods

A total of 193 patients with carotid atherosclerotic plaques were retrospectively enrolled and allocated into either a symptomatic (n = 123) or an asymptomatic (n = 70) groups. SR CTA images were derived from NR CTA images using deep learning-based three-dimensional SR technology. Handcrafted radiomic features were extracted from both the SR and NR CTA images and three risk models were developed based on manually measured quantitative CTA characteristics and NR and SR radiomic features. Model performances were assessed via receiver operating characteristic, calibration, and decision curve analyses.

Results

The SR model exhibited the optimal performance (area under the curve [AUC] 0.820, accuracy 0.802, sensitivity 0.854, F1 score 0.847) in the testing cohort, outperforming the other two models. The calibration curve analyses and Hosmer-Lemeshow test demonstrated that the SR model exhibited the best goodness of fit, and decision curve analysis revealed that SR model had the highest clinical value and potential patient benefits.

Conclusions

Deep learning-based three-dimensional SR technology could improve the CTA-based radiomic models in identifying symptomatic carotid plaques, potentially providing more accurate and valuable information to guide clinical decision-making to reduce the risk of ischemic stroke.

Deep Learning Reconstruction for DWIs by EPI and FASE Sequences for Head and Neck Tumors

BACKGROUND

Diffusion-weighted images (DWI) obtained by echo-planar imaging (EPI) are frequently degraded by susceptibility artifacts. It has been suggested that DWI obtained by fast advanced spin-echo (FASE) or reconstructed with deep learning reconstruction (DLR) could be useful for image quality improvements. The purpose of this investigation using in vitro and in vivo studies was to determine the influence of sequence difference and of DLR for DWI on image quality, apparent diffusion coefficient (ADC) evaluation, and differentiation of malignant from benign head and neck tumors.

METHODS

For the in vitro study, a DWI phantom was scanned by FASE and EPI sequences and reconstructed with and without DLR. Each ADC within the phantom for each DWI was then assessed and correlated for each measured ADC and standard value by Spearman's rank correlation analysis. For the in vivo study, DWIs obtained by EPI and FASE sequences were also obtained for head and neck tumor patients. Signal-to-noise ratio (SNR) and ADC were then determined based on ROI measurements, while SNR of tumors and ADC were compared between all DWI data sets by means of Tukey's Honest Significant Difference test.

RESULTS

For the in vitro study, all correlations between measured ADC and standard reference were significant and excellent (0.92 ≤ ρ ≤ 0.99, p < 0.0001). For the in vivo study, the SNR of FASE with DLR was significantly higher than that of FASE without DLR (p = 0.02), while ADC values for benign and malignant tumors showed significant differences between each sequence with and without DLR (p < 0.05).

CONCLUSION

In comparison with EPI sequence, FASE sequence and DLR can improve image quality and distortion of DWIs without significantly influencing ADC measurements or differentiation capability of malignant from benign head and neck tumors.

A nomogram model of spectral CT quantitative parameters and clinical characteristics predicting lymphovascular invasion of gastric cancer

Objective

The study established a nomogram based on quantitative parameters of spectral computed tomography (CT) and clinical characteristics, aiming to evaluate its predictive value for preoperative lymphovascular invasion (LVI) in gastric cancer (GC).

Methods

From December 2019 to December 2021, 171 patients with pathologically confirmed GC were retrospectively collected with corresponding clinical data and spectral CT quantitative data. Patients were divided into LVI-positive and LVI-negative groups based on their pathological results. The univariate and multivariate logistic regression analyses were used to identify the risk factors and construct a nomogram. The calibration curve and receiver operating characteristic (ROC) curve were adopted to evaluate the predictive accuracy of nomogram.

Results

Four clinical characteristics or spectral CT quantitative parameters, including Borrmann classification (P = 0.039), CA724 (P = 0.007), tumor thickness (P = 0.031), and iodine concentration in the venous phase (VIC) (P = 0.004) were identified as independent factors for LVI in GC patients. The nomogram was established based on the four factors, which had a potent predictive accuracy in the training, internal validation and external validation cohorts, with the area under the ROC curve (AUC) of 0.864 (95% CI, 0.798-0.930), 0.964 (95% CI, 0.903-1.000) and 0.877 (95% CI, 0.759-0.996), respectively.

Conclusion

This study constructed a comprehensive nomogram consisting spectral CT quantitative parameters and clinical characteristics of GC, which exhibited a robust efficiency in predicting LVI in GC patients.

Should the Baseline MRI Staging Criteria Differentiate Between Mucinous and Classical Rectal Adenocarcinoma?

RATIONALE AND OBJECTIVES

To compare baseline MR imaging features for pre-treatment staging between rectal mucinous adenocarcinoma (RMAC) and rectal classical adenocarcinoma (RCAC), and to investigate whether the subtype of mucinous carcinoma influences MRI evaluation criteria and high-risk tumors identifying.

METHODS

A total of 306 patients who underwent surgical rectal cancer resection were retrospectively reviewed in the study. MR imaging parameters of the primary tumor and lymph nodes (LNs) were compared between two subtypes. Logistic regression and receiver operating characteristic analyses were performed to test significant associations between LN imaging parameters and malignant LN status in RMAC and RCAC, respectively.

RESULTS

The length of mucinous tumors was larger than RCAC tumors in pT3 and pT4 stage. For pN0 patients, the long and short diameters of the largest LN on MRI were more likely to be larger in RCAC than RMAC. For pN+ patients, the proportion of LNs exhibiting internal heterogeneity in RMAC was obviously greater than that in RCAC. The best cut-off value of the largest short diameter of malignant LNs was 6.05 mm for RMAC and 8.05 mm for RCAC. And the highest AUC for predicting LNs metastases based on the largest short diameter was 0.794 for RMAC using 6 mm size cut-off, and 0.667 for RCAC using 8 mm cut-off.

CONCLUSION

The imaging features that were associated with LN metastases were different between RMAC and RCAC, and different size criteria of LNs was suggested to distinguish high-risk tumors. Clinicians should stay vigilant of LN status and take histologic subtypes into consideration before assigning clinical strategies.

Arbitrary scale super-resolution diffusion model for brain MRI images

Given the constraints posed by hardware capacity, scan duration, and patient cooperation, the reconstruction of magnetic resonance imaging (MRI) images emerges as a pivotal aspect of medical imaging research. Currently, deep learning-based super-resolution (SR) methods have been widely discussed in medical image processing due to their ability to reconstruct high-quality, high resolution (HR) images from low resolution (LR) inputs. However, most existing MRI SR methods are designed for specific magnifications and cannot generate MRI images at arbitrary scales, which hinders the radiologists from fully visualizing the lesions. Moreover, current arbitrary scale SR methods often suffer from issues like excessive smoothing and artifacts. In this paper, we propose an Arbitrary Scale Super-Resolution Diffusion Model (ASSRDM), which combines implicit neural representation with the denoising diffusion probabilistic model to achieve arbitrary-scale, high-fidelity medical images SR. Moreover, we formulate a continuous resolution regulation mechanism, comprising a multi-scale LR guidance network and a scaling factor. The scaling factor finely adjusts the resolution and dynamically influences the weighting of LR details and synthesized features in the final output. This capability allows the model to seamlessly adapt to the requirements of continuous resolution adjustments. Additionally, the multi-scale LR guidance network provides the denoising block with multi-resolution LR features to enrich texture information and restore high-frequency details. Extensive experiments conducted on the IXI and fastMRI datasets demonstrate that our ASSRDM exhibits superior performance compared to existing techniques and has tremendous potential in clinical practice.

Deep Learning-Based Multiparametric MRI Model for Preoperative T-Stage in Rectal Cancer

BACKGROUND

Conventional MRI staging can be challenging in the preoperative assessment of rectal cancer. Deep learning methods based on MRI have shown promise in cancer diagnosis and prognostication. However, the value of deep learning in rectal cancer T-staging is unclear.

PURPOSE

To develop a deep learning model based on preoperative multiparametric MRI for evaluation of rectal cancer and to investigate its potential to improve T-staging accuracy.

STUDY TYPE

Retrospective.

POPULATION

After cross-validation, 260 patients (123 with T-stage T1-2 and 134 with T-stage T3-4) with histopathologically confirmed rectal cancer were randomly divided to the training (N = 208) and test sets (N = 52).

FIELD STRENGTH/SEQUENCE

3.0 T/Dynamic contrast enhanced (DCE), T2-weighted imaging (T2W), and diffusion-weighted imaging (DWI).

ASSESSMENT

The deep learning (DL) model of multiparametric (DCE, T2W, and DWI) convolutional neural network were constructed for evaluating preoperative diagnosis. The pathological findings served as the reference standard for T-stage. For comparison, the single parameter DL-model, a logistic regression model composed of clinical features and subjective assessment of radiologists were used.

STATISTICAL TESTS

The receiver operating characteristic curve (ROC) was used to evaluate the models, the Fleiss' kappa for the intercorrelation coefficients, and DeLong test for compare the diagnostic performance of ROCs. P-values less than 0.05 were considered statistically significant.

RESULTS

The Area Under Curve (AUC) of the multiparametric DL-model was 0.854, which was significantly higher than the radiologist's assessment (AUC = 0.678), clinical model (AUC = 0.747), and the single parameter DL-models including T2W-model (AUC = 0.735), DWI-model (AUC = 0.759), and DCE-model (AUC = 0.789).

DATA CONCLUSION

In the evaluation of rectal cancer patients, the proposed multiparametric DL-model outperformed the radiologist's assessment, the clinical model as well as the single parameter models. The multiparametric DL-model has the potential to assist clinicians by providing more reliable and precise preoperative T staging diagnosis.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Automatic Quantification of Enlarged Perivascular Space in Patients With Traumatic Brain Injury Using Super-Resolution of T2-Weighted Images

The perivascular space (PVS) is important to brain waste clearance and brain metabolic homeostasis. Enlarged PVS (ePVS) becomes visible on magnetic resonance imaging (MRI) and is best appreciated on T2-weighted (T2w) images. However, quantification of ePVS is challenging because standard-of-care T1-weighted (T1w) and T2w images are often obtained via two-dimensional (2D) acquisition, whereas accurate quantification of ePVS normally requires high-resolution volumetric three-dimensional (3D) T1w and T2w images. The purpose of this study was to investigate the use of a deep-learning-based super-resolution (SR) technique to improve ePVS quantification from 2D T2w images for application in patients with traumatic brain injury (TBI). We prospectively recruited 26 volunteers (age: 31 ± 12 years, 12 male/14 female) where both 2D T2w and 3D T2w images were acquired along with 3D T1w images to validate the ePVS quantification using SR T2w images. We then applied the SR method to retrospectively acquired 2D T2w images in 41 patients with chronic TBI (age: 41 ± 16 years, 32 male/9 female). ePVS volumes were automatically quantified within the whole-brain white matter and major brain lobes (temporal, parietal, frontal, occipital) in all subjects. Pittsburgh Sleep Quality Index (PSQI) scores were obtained on all patients with TBI. Compared with the silver standard (3D T2w), in the validation study, the SR T2w provided similar whole-brain white matter ePVS volume (r = 0.98, p < 0.0001), and similar age-related ePVS burden increase (r = 0.80, p < 0.0001). In the patient study, patients with TBI with poor sleep showed a higher age-related ePVS burden increase than those with good sleep. Sleep status is a significant interaction factor in the whole brain (p = 0.047) and the frontal lobe (p = 0.027). We demonstrate that images produced by SR of 2D T2w images can be automatically analyzed to produce results comparable to those obtained by 3D T2 volumes. Reliable age-related ePVS burden across the whole-brain white matter was observed in all subjects. Poor sleep, affecting the glymphatic function, may contribute to the accelerated increase of ePVS burden following TBI.

Assessment of LI-RADS efficacy in classification of hepatocellular carcinoma and benign liver nodules using DCE-MRI features and machine learning

Purpose

The current study aimed to evaluate the efficiency of dynamic contrast-enhanced (DCE) MRI visual features in classifying benign liver nodules and hepatocellular carcinoma (HCC) using a machine learning model.

Methods

115 LI-RADS3, 137 LI-RADS4, and 140 LI-RADS5 nodules were included (392 nodules from 245 patients), which were evaluated by follow-up imaging for LR-3 and pathology results for LR-4 and LR-5 nodules. Data was collected retrospectively from 3 T and 1.5 T MRI scanners. All the lesions were categorized into 124 benign and 268 HCC lesions. Visual features included tumor size, arterial-phase hyper-enhancement (APHE), washout, lesion segment, mass/mass-like, and capsule presence. Gini-importance method extracted the most important features to prevent over-fitting. Final dataset was split into training(70%), validation(10%), and test dataset(20%). The SVM model was used to train the classifying algorithm. For model validation, 5-fold cross-validation was utilized, and the test data set was used to assess the final accuracy. The area under the curve and receiver operating characteristic curves were used to assess the performance of the classifier model.

Results

For test dataset, the accuracy, sensitivity, and specificity values for classifying benign and HCC lesions were 82%,84%, and 81%, respectively. APHE, washout, tumor size, and mass/mass-like features significantly differentiated benign and HCC lesions with p-value < .001.

Conclusions

The developed classification model employing DCE-MRI features showed significant performance of visual features in classifying benign and HCC lesions. Our study also highlighted the significance of mass and mass-like features in addition to LI-RADS categorization. For future work, this study suggests developing a deep-learning algorithm for automatic lesion segmentation and feature assessment to reduce lesion categorization errors.

Deep learning models for preoperative T-stage assessment in rectal cancer using MRI: exploring the impact of rectal filling

Background

The objective of this study was twofold: firstly, to develop a convolutional neural network (CNN) for automatic segmentation of rectal cancer (RC) lesions, and secondly, to construct classification models to differentiate between different T-stages of RC. Additionally, it was attempted to investigate the potential benefits of rectal filling in improving the performance of deep learning (DL) models.

Methods

A retrospective study was conducted, including 317 consecutive patients with RC who underwent MRI scans. The datasets were randomly divided into a training set (n = 265) and a test set (n = 52). Initially, an automatic segmentation model based on T2-weighted imaging (T2WI) was constructed using nn-UNet. The performance of the model was evaluated using the dice similarity coefficient (DSC), the 95th percentile Hausdorff distance (HD95), and the average surface distance (ASD). Subsequently, three types of DL-models were constructed: Model 1 trained on the total training dataset, Model 2 trained on the rectal-filling dataset, and Model 3 trained on the non-filling dataset. The diagnostic values were evaluated and compared using receiver operating characteristic (ROC) curve analysis, confusion matrix, net reclassification index (NRI), and decision curve analysis (DCA).

Results

The automatic segmentation showed excellent performance. The rectal-filling dataset exhibited superior results in terms of DSC and ASD (p = 0.006 and 0.017). The DL-models demonstrated significantly superior classification performance to the subjective evaluation in predicting T-stages for all test datasets (all p < 0.05). Among the models, Model 1 showcased the highest overall performance, with an area under the curve (AUC) of 0.958 and an accuracy of 0.962 in the filling test dataset.

Conclusion

This study highlighted the utility of DL-based automatic segmentation and classification models for preoperative T-stage assessment of RC on T2WI, particularly in the rectal-filling dataset. Compared with subjective evaluation, the models exhibited superior performance, suggesting their noticeable potential for enhancing clinical diagnosis and treatment practices.

AI-Powered Mental Health Virtual Assistants' Acceptance: An Empirical Study on Influencing Factors Among Generations X, Y, and Z

STUDY PURPOSE

This study aims to analyze various influencing factors among generations X (Gen X), Y (Gen Y), and Z (Gen Z) of artificial intelligence (AI)-powered mental health virtual assistants.

METHODS

A cross-sectional survey design was adopted in this study. The study sample consisted of outpatients diagnosed with various mental health illnesses, such as anxiety, depression, schizophrenia, and behavioral disorders. A survey questionnaire was designed based on the factors (performance expectancy, effort expectancy, social influence, facilitating conditions, and behavioural intention) identified from the unified theory of acceptance and use of the technology model. Ethical approval was received from the Ethics Committee at Imam Abdulrahman Bin Faisal University, Saudi Arabia.

RESULTS

A total of 506 patients participated in the study, with over 80% having moderate to high experience in using mental health AI assistants. The ANOVA results for performance expectancy (PE), effort expectancy (EE), social influence (SI), facilitating conditions (FC), and behavioral intentions (BI) indicate that there are statistically significant differences (p < 0.05) between the Gen X, Gen Y, and Gen Z participants.

CONCLUSION

The findings underscore the significance of considering generational differences in attitudes and perceptions, with Gen Y and Gen Z demonstrating more positive attitudes and stronger intentions to use AI mental health virtual assistants, while Gen X appears to be more cautious.

Multiphase and multiparameter MRI-based radiomics for prediction of tumor response to neoadjuvant therapy in locally advanced rectal cancer

BACKGROUND

To develop and validate radiomics models for prediction of tumor response to neoadjuvant therapy (NAT) in patients with locally advanced rectal cancer (LARC) using both pre-NAT and post-NAT multiparameter magnetic resonance imaging (mpMRI).

METHODS

In this multicenter study, a total of 563 patients were included from two independent centers. 453 patients from center 1 were split into training and testing cohorts, the remaining 110 from center 2 served as an external validation cohort. Pre-NAT and post-NAT mpMRI was collected for feature extraction. The radiomics models were constructed using machine learning from a training cohort. The accuracy of the models was verified in a testing cohort and an independent external validation cohort. Model performance was evaluated using area under the curve (AUC), sensitivity, specificity, positive predictive value, and negative predictive value.

RESULTS

The model constructed with pre-NAT mpMRI had favorable accuracy for prediction of non-response to NAT in the training cohort (AUC = 0.84), testing cohort (AUC = 0.81), and external validation cohort (AUC = 0.79). The model constructed with both pre-NAT and post-NAT mpMRI had powerful diagnostic value for pathologic complete response in the training cohort (AUC = 0.86), testing cohort (AUC = 0.87), and external validation cohort (AUC = 0.87).

CONCLUSIONS

Models constructed with multiphase and multiparameter MRI were able to predict tumor response to NAT with high accuracy and robustness, which may assist in individualized management of LARC.

A Contrast-Enhanced CT-Based Deep Learning System for Preoperative Prediction of Colorectal Cancer Staging and RAS Mutation

PURPOSE

This study aimed to build a deep learning system using enhanced computed tomography (CT) portal-phase images for predicting colorectal cancer patients' preoperative staging and RAS gene mutation status.

METHODS

The contrast-enhanced CT image dataset comprises the CT portal-phase images from a retrospective cohort of 231 colorectal cancer patients. The deep learning system was developed via migration learning for colorectal cancer detection, staging, and RAS gene mutation status prediction. This study used pre-trained Yolov7, vision transformer (VIT), swin transformer (SWT), EfficientNetV2, and ConvNeXt. 4620, and contrast-enhanced CT images and annotated tumor bounding boxes were included in the tumor identification and staging dataset. A total of 19,700 contrast-enhanced CT images comprise the RAS gene mutation status prediction dataset.

RESULTS

In the validation cohort, the Yolov7-based detection model detected and staged tumors with a mean accuracy precision (IoU = 0.5) (mAP_0.5) of 0.98. The area under the receiver operating characteristic curve (AUC) in the test set and validation set for the VIT-based prediction model in predicting the mutation status of the RAS genes was 0.9591 and 0.9554, respectively. The detection network and prediction network of the deep learning system demonstrated great performance in explaining contrast-enhanced CT images.

CONCLUSION

In this study, a deep learning system was created based on the foundation of contrast-enhanced CT portal-phase imaging to preoperatively predict the stage and RAS mutation status of colorectal cancer patients. This system will help clinicians choose the best treatment option to increase colorectal cancer patients' chances of survival and quality of life.

Radiomics based on preoperative rectal cancer MRI to predict the metachronous liver metastasis

PURPOSE

At present, there are few effective method to predict metachronous liver metastasis (MLM) from rectal cancer. We aim to investigate the efficacy of radiomics based on multiparametric MRI of first diagnosed rectal cancer in predicting MLM from rectal cancer.

METHODS

From 301 consecutive histopathologically confirmed rectal cancer patients, 130 patients who have no distant metastasis detected at the time of diagnosis were enrolled and divided into MLM group (n = 49) and non-MLM group (n = 81) according to whether liver metastasis be detected later than 6 month after the first diagnosis of rectal cancer within 3 years' follow-up. The 130 patients were divided into a training set (n = 91) and a testing set (n = 39) at a ratio of 7:3 by stratified sampling using SPSS 24.0 software. The DWI model, HD T₂WI model, and DWI + HD T₂WI model were constructed respectively. The best performing model was selected and combined with the screened clinical features (including non-radiomics MRI features) to construct a fusion model. The testing set was used to evaluate the performance of the models, and the area under the curve (AUC) of receiver operating characteristics (ROC) was calculated for both the training set and the testing set.

RESULTS

The AUC of the DWI + HD T₂WI model in the testing set was higher than that of the DWI or the HD T₂ model alone with statistically significance (P < 0.05). The screened clinical features were extramural vascular invasion (EMVI), T and N stages in MRI (_mrT, _mrN), and the distance from the lower edge of the tumor to the anal verge. The AUC of the fusion model in the testing set was 0.911. Decision curves and nomogram also showed that the fusion model had excellent clinical performance.

CONCLUSION

The fusion model of primary rectal cancer MRI based radiomics combing clinical features can effectively predict MLM from rectal cancer, which may assist clinicians in formulating individualized monitoring and treatment plans.

A bibliometric and visual analysis of publications on artificial intelligence in colorectal cancer (2002-2022)

Background

Colorectal cancer (CRC) has the third-highest incidence and second-highest mortality rate of all cancers worldwide. Early diagnosis and screening of CRC have been the focus of research in this field. With the continuous development of artificial intelligence (AI) technology, AI has advantages in many aspects of CRC, such as adenoma screening, genetic testing, and prediction of tumor metastasis.

Objective

This study uses bibliometrics to analyze research in AI in CRC, summarize the field's history and current status of research, and predict future research directions.

Method

We searched the SCIE database for all literature on CRC and AI. The documents span the period 2002-2022. we used bibliometrics to analyze the data of these papers, such as authors, countries, institutions, and references. Co-authorship, co-citation, and co-occurrence analysis were the main methods of analysis. Citespace, VOSviewer, and SCImago Graphica were used to visualize the results.

Result

This study selected 1,531 articles on AI in CRC. China has published a maximum number of 580 such articles in this field. The U.S. had the most quality publications, boasting an average citation per article of 46.13. Mori Y and Ding K were the two authors with the highest number of articles. Scientific Reports, Cancers, and Frontiers in Oncology are this field's most widely published journals. Institutions from China occupy the top 9 positions among the most published institutions. We found that research on AI in this field mainly focuses on colonoscopy-assisted diagnosis, imaging histology, and pathology examination.

Conclusion

AI in CRC is currently in the development stage with good prospects. AI is currently widely used in colonoscopy, imageomics, and pathology. However, the scope of AI applications is still limited, and there is a lack of inter-institutional collaboration. The pervasiveness of AI technology is the main direction of future housing development in this field.

Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer

Neoadjuvant systemic treatment before surgery is a prevalent regimen in the patients with advanced-stage or high-risk tumor, which has shaped the treatment strategies and cancer survival in the past decades. However, some patients present with poor response to the neoadjuvant treatment. Therefore, it is of great significance to develop tools to help distinguish the patients that could achieve pathological complete response before surgery to avoid inappropriate treatment. Here, this study demonstrated a multi-task deep learning tool called DeepInteg. In the DeepInteg framework, the segmentation module was constructed based on the CE-Net with a context extractor to achieve end-to-end delineation of region of interest (ROI) from radiological images, then the features of segmented Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) images of each case were fused and input to the classification module based on a convolution neural network for treatment outcome prediction. The dataset with 1700 MRI and CT slices collected from the prospectively randomized clinical trial (NCT01211210) on systemic treatment for rectal cancer was used to develop and systematically optimize DeepInteg. As a result, DeepInteg achieved automatic segmentation of tumoral ROI with Dices of 0.766 and 0.719 and mIoUs of 0.788 and 0.756 in CT and MRI images, respectively. In addition, DeepInteg achieved AUC of 0.833, accuracy of 0.826 and specificity of 0.856 in the prediction for pathological complete response after treatment, which showed better performance compared with the model based on CT or MRI alone. This study provide a robust framework to develop disease-specific tools for automatic delineation of ROI and clinical outcome prediction. The well-trained DeepInteg could be readily applied in clinic to predict pathological complete response after neoadjuvant therapy in rectal cancer patients.