Abdominal CT Images Research Articles

A National Study on the Association of Abdominal Ultrasound with CT Utilization and Disposition in the Emergency Department

Background Ultrasound and CT imaging have distinct and overlapping roles in the assessment of undifferentiated abdominal pain in the emergency department (ED). CT imaging is the gold standard for many pathologies, ranging from bowel obstruction to aortic pathology whereas ultrasound benefits from less radiation exposure and the ability to employ at bedside. In this pilot study, we utilize nationally representative data to identify associations between ultrasound use in ED patients with a primary complaint of abdominal pain with abdominal CT imaging use and disposition. Methods We analyzed retrospective, cross-sectional data on ED patient visits obtained from the National Hospital Ambulatory Medical Care Survey from 2016-2020. This dataset utilizes a weighed multistage, probability sample of ED patient visits involving a four-stage sampling design, including data at county-level geographic regions, hospitals within these regions, emergency service areas in these hospitals, and patient visit records. The study population includes adult patient ED visits with an age of 18 and up presenting with a primary complaint of atraumatic abdominal pain. Descriptive statistics was utilized to describe the sample population. Survey-weighted multivariate logistic regression analysis with calculated odds ratios evaluated for differences between the binary dependent variable of abdominal pain visits with versus without ultrasound use with independent variables of disposition and abdominal CT imaging use while controlling for visit acuity and adjusting for demographic information. Results A total of 7563 patient visits met inclusion criteria, representing approximately 60 million patient visits from 2016-2020. In this study population, 18.5% of visits involved ultrasound, whereas 39.8% of visits involved CT imaging use. 14.6% of visits resulted in hospital admission. On weight-adjusted regression analysis, visits involving ultrasound were less likely to require CT imaging and more likely to be admitted, with ORs of 0.49 (95% CI: 0.37, 0.64) and 1.97 (95% CI: 1.44, 2.68), respectively. Visits involving ultrasound were more likely to be associated with an emergency medicine residency program and an emergent acuity level, with ORs of 1.40 (95% CI: 1.01, 1.94) and 1.53 (95% CI: 1.01, 2.31), respectively. Conclusion In this national pilot study, abdominal pain visits involving ultrasound were associated with a lower likelihood of CT imaging use and a highly likelihood admission and an emergent acuity level.

RMCNet: A Liver Cancer Segmentation Network Based on 3D Multi-Scale Convolution, Attention, and Residual Path

Abdominal CT images are important clues for diagnosing liver cancer lesions. However, liver cancer presents challenges such as significant differences in tumor size, shape, and location, which can affect segmentation accuracy. To address these challenges, we propose an end-to-end 3D segmentation algorithm, RMCNet. In the shallow encoding part of RMCNet, we incorporated a 3D multiscale convolution (3D-Multiscale Convolution) module to more effectively extract tumors of varying sizes. Moreover, the convolutional block attention module (CBAM) is used in the encoding part to help the model focus on both the shape and location of tumors. Additionally, a residual path is introduced in each encoding layer to further enrich the extracted feature maps. Our method achieved DSC scores of 76.56% and 72.96%, JCC scores of 75.82% and 71.25%, HD values of 11.07 mm and 17.06 mm, and ASD values of 2.54 mm and 10.51 mm on the MICCAI 2017 Liver Tumor Segmentation public dataset and the 3Dircadb-01 public dataset, respectively. Compared to other methods, RMCNet demonstrates superior segmentation performance and stronger generalization capability.

WAW-TACE: A Hepatocellular Carcinoma Multiphase CT Dataset with Segmentations, Radiomics Features, and Clinical Data.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. The WAW-TACE dataset contains baseline multiphase abdominal CT images from 233 treatment-naive patients with hepatocellular carcinoma treated with transarterial chemoembolization and includes with 377 hand-crafted liver tumor masks, automated segmentations of multiple internal organs, extracted radiomics features, and corresponding extensive clinical data. The dataset can be accessed at: https://zenodo.org/records/12741586 (DOI:10.5281/zenodo.11063784).

Prognostic Value of Myosteatosis and Albumin-Bilirubin Grade for Survival in Hepatocellular Carcinoma Post Chemoembolization.

This study aimed to investigate the prognostic value of preoperative myosteatosis and the albumin-bilirubin (ALBI) grade in patients with hepatocellular carcinoma (HCC) undergoing transarterial chemoembolization (TACE) and develop a robust prognostic score based on these factors. Patients with HCC who underwent TACE between January 2009 and December 2020 were included. Multivariate Cox regression analysis identified prognostic factors. CT-based body composition parameters were acquired from baseline abdominal CT images at the level of the third lumbar vertebra. A prognostic score (Myo-ALBI) was developed based on the presence of preoperative myosteatosis and the ALBI grade, and its prognostic value was evaluated. Of 446 patients, 63% were male, and the mean age was 62.4 years. Preoperative myosteatosis was present in 41.5% of patients. The BCLC stages were mostly B (67.9%). Multivariate analysis shows that preoperative myosteatosis, ALBI grade 2, and ALBI grade 3 were independent prognostic factors. The Myo-ALBI grade was incorporated into a prognostic model, including alpha-fetoprotein and up-to-seven criteria, to generate a nomogram. The C-index of the nomogram based on the Myo-ALBI grade (0.743) was significantly higher than the non-Myo-ALBI nomogram (0.677), the up-to-seven criteria (0.653), the ALBI grade (0.616), and the Child-Pugh class (0.573) (all p < 0.05). The t-ROC curve for the nomogram was consistently superior to the other models throughout the observation period in all patients and the BCLC-B subgroup. The combination of preoperative CT-derived myosteatosis and ALBI grade enhances prognostication for patients with unresectable HCC undergoing TACE. The Myo-ALBI nomogram constructed in this study could support individualized prognosis prediction, assisting in treatment decision-making for HCC patients.

Body composition as a potential imaging biomarker for predicting the progression risk of chronic kidney disease

PurposeTo investigate whether the body composition parameters can be employed as potential biomarkers for predicting the progression risk of chronic kidney disease (CKD).Materials and methodsFour hundred sixteen patients diagnosed with CKD were included in this retrospective study. Patients with a greater than 50% decline in estimated glomerular filtration rate or progression to end-stage kidney disease were in the high-risk group, otherwise, they were in a low-risk group. Body composition area, the index, and radiodensities in the Hounsfield unit (HU), which reflect the degree of X-ray absorption, were measured on abdominal CT images. Risk factors in body composition and clinical parameters of CKD were identified by Cox regression and utilized to construct the nomogram. The performance of the nomogram was assessed using time receiver operating characteristics curves, calibration curves, and decision curve analysis.ResultsThere were 254 patients in low-risk group and 162 in high-risk group (268 males, 148 females, mean age: 55.89 years). Urea, diabetes, 24 h-urinary protein, mean arterial pressure, and subcutaneous adipose tissue radiodensity (SATd) were valuable indicators for predicting the high-risk group. The area under curve values for the nomogram of training/validation set at 1 year, 2 years, and 3 years were 0.805/0.753, 0.784/0.783, and 0.846/0.754, respectively. For diabetic CKD patients, extra attention needs to be paid to visceral to subcutaneous fat ratio and renal sinus fat radiodensity.ConclusionSATd was the most valuable noninvasive indicator of all body composition parameters for predicting high-risk populations with CKD. The nomogram we constructed has generalization with easily obtainable indicators, good performance, differentiation, and clinical practicability.Critical relevance statementRadiodensity rather than an area of adipose tissue can be used as a new biomarker of prognosis for CKD patients, providing new insights into risk assessment, stratified management, and treatment for CKD patients.Key PointsObesity is an independent risk factor for the development and prognosis of CKD.Adipose tissue radiodensity is more valuable than fat area in prognosticating for kidney disease.Parameters that prognosticate in diabetic CKD patients are different from those in other CKD patients.Graphical

12529 Pre And Post-operative Evaluation And Outcomes After Adrenalectomy At A Tertiary Referral Center

Abstract Disclosure: C. Hung: None. L.M. Fishbein: None. M.R. Clay: None. M.B. Albuja-Cruz: None. C. Raeburn: None. K. Kiseljak-Vassiliades: None. M.E. Wierman: None. Introduction: The prevalence of adrenal nodules has increased over time due to increased abdominal CT imaging. Laboratory evaluation to screen for hypercortisolism, primary aldosteronism, or pheochromocytoma is recommended depending on nodule appearance and clinical risk factors. Our aim was to retrospectively determine the preoperative hormonal workup prior to adrenalectomy and to identify the postoperative comorbidities as they relate to preoperative hypercortisolism. Methods: From May 2017-March 2023, 205 adrenalectomies were performed for adrenal nodules. Preoperative and postoperative comorbidities, medications, laboratory results, imaging and pathology were assessed up to 1 year post surgery. Patients were stratified by degree of hypercortisolism, based on 1 mg dexamethasone suppression test, into cortisol 1.8-5 μg/dL (DST 1.8-5) or cortisol &amp;gt;5 μg/dL (DST &amp;gt;5). Statistical analysis included Fischer’s exact test and two-sample proportion test. Results: Of 205 adrenalectomies, 51 patients had primary aldosteronism (24.9%), 51 had pheochromocytoma (24.9%), 23 had ACC (11.2%), 15 had non-functional adrenal adenomas (7.3%), and 65 had adenomas associated with hypercortisolism (31.7%)—42 with DST 1.8-5 (20.5%), 23 with DST &amp;gt;5 (11.2%). Preoperatively 9 (17.6%) patients with PA underwent 1 mg DST, while 54 (83.1%) patients with hypercortisolism (DST &amp;gt;1.8) had aldosterone measured. Overall, 183/205 patients (89.3%) had hypertension preoperatively. Of the patients with hypercortisolism (DST&amp;gt;1.8), 58 (89.2%) had hypertension, without a difference in prevalence between DST 1.8-5 and DST &amp;gt;5 groups. For those with abnormal DST, no significant reduction in hypertension was observed within 2 months following adrenalectomy, but at 1 year postop, prevalence was reduced (89.2% preop vs 71.9% postop, p=0.03). There was no significant reduction in the prevalence of type 2 diabetes (p=0.78), prediabetes (p=0.48), hyperlipidemia (p=0.33), osteoporosis (p=0.53), or osteopenia (p=0.67) at 1 year postop in those with hypercortisolism. After adrenalectomy, 42.9% patients in the DST1.8-5 and 73.9% in the DST &amp;gt;5 group were discharged on glucocorticoids. Many patients were lost to long-term follow up. In those remaining, at 1 year postop, 14.3% patients in the DST1.8-5 and 50% in the DST &amp;gt;5 group still required steroids for adrenal insufficiency. Conclusions Not all patients with adrenal nodules are being screened for excess hormone production. Hypercortisolism is prevalent in patients undergoing adrenalectomy. Preoperative workup is essential to identify these patients before surgery as adrenal insufficiency can persist postoperatively. Adrenalectomy for hypercortisolism is associated with a reduction in hypertension at 1 year postoperatively. Presentation: 6/3/2024

Automated Segmentation of Individual Kidney Cysts in Routine Abdominal CT Images

Automated Segmentation of Individual Kidney Cysts in Routine Abdominal CT Images

DELR-Net: a network for 3D multimodal medical image registration in more lightweight application scenarios.

3D multimodal medical image deformable registration plays a significant role in medical image analysis and diagnosis. However, due to the substantial differences between images of different modalities, registration is challenging and requires high computational costs. Deep learning-based registration methods face these challenges. The primary aim of this paper is to design a 3D multimodal registration network that ensures high-quality registration results while reducing the number of parameters. This study designed a Dual-Encoder More Lightweight Registration Network (DELR-Net). DELR-Net is a low-complexity network that integrates Mamba and ConvNet. The State Space Sequence Module and the Dynamic Large Kernel block are used as the main components of the dual encoders, while the Dynamic Feature Fusion block is used as the main component of the decoder. This study conducted experiments on 3D brain MR images and abdominal MR and CT images. Compared to existing registration methods, DELR-Net achieved better registration results while maintaining a lower number of parameters. Additionally, generalization experiments on other modalities showed that DELR-Net has superior generalization capabilities. DELR-Net significantly improves the limitations of 3D multimodal medical image deformable registration, achieving better registration performance with fewer parameters.

Dual knowledge‐guided two‐stage model for precise small organ segmentation in abdominal CT images

Dual knowledge‐guided two‐stage model for precise small organ segmentation in abdominal CT images

Outcome of the novel description of arterial position changes after major liver resections: retrospective study.

After major liver resections, anatomical shifts due to liver parenchymal hypertrophy and organ displacement can happen. The aim of this study was to evaluate the impact of these anatomical changes on the main abdominal arteries (coeliac trunk and superior mesenteric artery) and on patient outcomes. All patients who underwent major liver resections (between January 2010 and July 2021) and who underwent preoperative and postoperative arterial-phase contrast-enhanced abdominal CT imaging were studied. Observed arterial position changes were classified into three groups: no position changes; class I position changes (vessel displacement with or without kinking with a vessel angle greater than 105°); and class II position changes (kinking less than or equal to 105°). The Mann-Whitney test and the Kruskal-Wallis test were used to compare continuous variables and the chi-squared test and Fisher's exact test were used to compare categorical variables. Univariable and multivariable logistic regression analyses were used to identify the risk factors for morbidity and mortality. A total of 265 patients (149 men and median age of 59 years) were enrolled. Arterial position changes were detected in a total of 145 patients (54.7%) (99 patients (37%) with class I position changes and 46 patients (18%) with class II position changes) and were observed more often after extended resection and right-sided resection (P < 0.001). Major complications were seen in 94 patients (35%) and the rate of mortality was 15% (40 patients died). Post-hepatectomy liver failure (P = 0.030), major complications (P < 0.001), and mortality (P = 0.004) occurred more frequently in patients with class II position changes. In multivariable analysis, arterial position change was an independent risk factor for post-hepatectomy liver failure (OR 2.86 (95% c.i. 1.06 to 7.72); P = 0.038), major complications (OR 2.10 (95% c.i. 1.12 to 3.93); P = 0.020), and mortality (OR 2.39 (95% c.i. 1.03 to 5.56); P = 0.042). Arterial position changes post-hepatectomy are observed in the majority of patients and are significantly related to postoperative morbidities and mortality.

Findings of Abdominal Computed Tomography In COVID-19 Patients with Abnormal Abdominal Symptoms In Siriraj Hospital

Background: The coronavirus (COVID-19) is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Chest imaging findings of COVID-19 disease have been widely published. Only a few studies of abdominal imaging findings have been documented. The majority of these studies demonstrate thrombotic events associated with COVID-19. Previous studies were mainly conducted in the USA, Europe and China which limited the applicability in Southeast Asia (SEA) including Thailand. Objective: To provide a summary of various abdominal imaging findings of COVID-19 patients admitted to xxx Hospital with findings associated with clinical outcomes. Materials and Methods: All CT abdominal imaging of adult patients who tested positive for COVID-19 performed from January 1st, 2020 to August 31st, 2022 were retrospectively reviewed. We collected clinical data, abdominal signs and symptoms, laboratory data and various CT findings, for example; bowel-wall thickening, bowel ischemia, fluid-filled colon and bleeding manifestations. The clinical outcomes were gathered as death confirmation, invasive mechanical ventilation, days of invasive mechanical ventilation and days of hospitalization. Results: A large number of patients who had stage 3-5 chronic kidney disease (CKD), abdominal distension, abnormal bowel findings and longer days of hospitalization were significantly observed in a group with worse clinical outcomes. Abnormal intestinal imaging findings were related to a higher risk of worse outcomes, invasive mechanical ventilation, death and days of hospitalization without statistical significance. Conclusion: Abdominal CT scans performed on COVID-19 patients frequently revealed abnormal bowel findings, which were strongly associated with poor clinical outcomes. Radiologists need to be concerned about abnormal bowel findings and point them out to clinicians and surgeons.

A 3D U-NET BASED ON EARLY FUSION MODEL: IMPROVEMENT, COMPARATIVE ANALYSIS WITH STATE-OF-THE-ART MODELS AND FINE-TUNING

Multi-organ segmentation is the process of identifying and separating multiple organs in medical images. This segmentation allows for the detection of structural abnormalities by examining the morphological structure of organs. Carrying out the process quickly and precisely has become an important issue in today's conditions. In recent years, researchers have used various technologies for the automatic segmentation of multiple organs. In this study, improvements were made to increase the multi-organ segmentation performance of the 3D U-Net based fusion model combining HSV and grayscale color spaces and compared with state-of-the-art models. Training and testing were performed on the MICCAI 2015 dataset published at Vanderbilt University, which contains 3D abdominal CT images in NIfTI format. The model's performance was evaluated using the Dice similarity coefficient. In the tests, the liver organ showed the highest Dice score. Considering the average Dice score of all organs, and comparing it with other models, it has been observed that the fusion approach model yields promising results.

Feasibility of a single-phase portal venous CT protocol using bolus tracking technique and lean body weight-based contrast media dose.

To evaluate the impact of the use of lean body weight (LBW)-based contrast material (CM) dose and bolus tracking technique on portal venous phase abdominal CT image quality. IRB-approved prospective study; informed consent was acquired. In the period July-November 2023, we randomly selected 105 oncologic patients scheduled for a portal venous phase abdominal CT to undergo our experimental protocol (i.e., 0.7 gI/Kg of LBW CM administration and bolus tracking on the liver). Included patients had performed a "standard" portal venous phase abdominal CT (i.e., 0.6 gI/Kg of total body weight (TBW) contrast material administration and 70 s fixed delay) on the same scanner within the previous 12 months. One reader evaluated CT images measuring liver, portal vein, kidney cortex, and spleen attenuation; values were normalized to paraspinal muscles. Median administered contrast dose (350 mgI/mL CM) was 99 mL (IQR: 81-115 mL) using the experimental protocol and 110 mL (IQR: 100-120 mL) using the standard one (p < 0.0001). Median acquisition delay using the experimental protocol was 65" (IQR 59-73"). Median normalized hepatic enhancement was significantly higher using the experimental protocol (1.97, IQR: 1.83-2.47 vs. 1.86, IQR: 1.58-2.11; p < 0.0001). Median normalized portal vein enhancement was significantly higher using the experimental protocol (3.43, IQR: 2.73-4.04 vs. 2.91, IQR: 2.58-3.41; p < 0.0001). No statistically significant differences were found in the kidneys' cortex and aorta normalized enhancement (p > 0.05). The combination of LBW-based CM dose administration and bolus tracking allows a significant CM dose reduction and a significant liver and portal vein enhancement increase. Lean body weight-based contrast material (CM) dose administration and bolus tracking technique in portal venous phase CT scans overcome differences in body composition and hemodynamics, improving reproducibility. It allows a significant CM dose reduction with increased liver and portal vein enhancement. Lean body weight (LBW)-based contrast material (CM) dosing could be superior to total body weight dosing. Portal venous phase CT with a liver bolus tracking technique improved liver and spleen enhancement with a reduced contrast dose. The combination of LBW-based CM dosing and liver bolus tracking technique enables more "customized" CT examinations.

A study predicting long-term survival capacity in postoperative advanced gastric cancer patients based on MAOA and subcutaneous muscle fat characteristics

BackgroundThe prognosis of advanced gastric cancer (AGC) is relatively poor, and long-term survival depends on timely intervention. Currently, predicting survival rates remains a hot topic. The application of radiomics and immunohistochemistry-related techniques in cancer research is increasingly widespread. However, their integration for predicting long-term survival in AGC patients has not been fully explored.MethodsWe Collected 150 patients diagnosed with AGC at the Affiliated Zhongshan Hospital of Dalian University who underwent radical surgery between 2015 and 2019. Following strict inclusion and exclusion criteria, 90 patients were included in the analysis. We Collected postoperative pathological specimens from enrolled patients, analyzed the expression levels of MAOA using immunohistochemical techniques, and quantified these levels as the MAOAHScore. Obtained plain abdominal CT images from patients, delineated the region of interest at the L3 vertebral body level, and extracted radiomics features. Lasso Cox regression was used to select significant features to establish a radionics risk score, convert it into a categorical variable named risk, and use Cox regression to identify independent predictive factors for constructing a clinical prediction model. ROC, DCA, and calibration curves validated the model’s performance.ResultsThe enrolled patients had an average age of 65.71 years, including 70 males and 20 females. Multivariate Cox regression analysis revealed that risk (P = 0.001, HR = 3.303), MAOAHScore (P = 0.043, HR = 2.055), and TNM stage (P = 0.047, HR = 2.273) emerged as independent prognostic risk factors for 3-year overall survival (OS) and The Similar results were found in the analysis of 3-year disease-specific survival (DSS). The nomogram developed could predict 3-year OS and DSS rates, with areas under the ROC curve (AUCs) of 0.81 and 0.797, respectively. Joint calibration and decision curve analyses (DCA) confirmed the nomogram’s good predictive performance and clinical utility.ConclusionIntegrating immunohistochemistry and muscle fat features provides a more accurate prediction of long-term survival in gastric cancer patients. This study offers new perspectives and methods for a deeper understanding of survival prediction in AGC.

Computed tomographic anatomic variations of the phrenicoabdominal veins in cats.

There are no published reports describing the anatomic variations of the phrenicoabdominal (PhAbd) veins in cats. The aim of this study was to evaluate the anatomic variations of the PhAbd veins in cats without adrenal disease. This is an anatomic study. Abdominal CT images of cats acquired from January 2021 to February 2023 were retrospectively reviewed. Inclusion criteria were the presence of pre- and postcontrast CT images of the abdomen and the absence of any abdominal diseases that compromise the left and right PhAbd veins visualization. A total of 128 cats were included. Three different vascular anatomic variations were found in the distal pericaval segment of the left phrenicoabdominal (LPhAbd) vein. In the first type, found in 65 cases (50.8%), the LPhAbd vein drained directly into the caudal vena cava. In the second type defined IIa, found in 25 cases (19.5%), the LPhAbd vein drained into the distal third of the left renal vein, less than 5mm from its opening into the caudal vena cava. In the third type defined IIb, found in 38 cases (29.7%), the LPhAbd vein drained into the distal third of the left renal vein, more than 5mm from its opening into the caudal vena cava. The right phrenicoabdominal vein had a consistent path and drained into the caudal vena cava in all cases. The knowledge of these vascular variations is expected to help the surgeon during adrenalectomy due to masses with vascular invasion in cats.

Pretreatment Sarcopenia and MRI-Based Radiomics to Predict the Response of Neoadjuvant Chemotherapy in Triple-Negative Breast Cancer.

The association between sarcopenia and the effectiveness of neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC) remains uncertain. This study aims to examine the potential of sarcopenia as a predictive factor for the response to NAC in TNBC, and to assess whether its combination with MRI radiomic signatures can improve the predictive accuracy. We collected clinical and pathological information, as well as pretreatment breast MRI and abdominal CT images, of 121 patients with TNBC who underwent NAC at our hospital between January 2012 and September 2021. The presence of pretreatment sarcopenia was assessed using the L3 skeletal muscle index. Clinical models were constructed based on independent risk factors identified by univariate regression analysis. Radiomics data were extracted on breast MRI images and the radiomics prediction models were constructed. We integrated independent risk factors and radiomic features to build the combined models. The results of this study demonstrated that sarcopenia is an independent predictive factor for NAC efficacy in TNBC. The combination of sarcopenia and MRI radiomic signatures can further improve predictive performance.

Preoperative prediction of renal fibrous capsule invasion in clear cell renal cell carcinoma using CT-based radiomics model.

To develop radiomics-based classifiers for preoperative prediction of fibrous capsule invasion in renal cell carcinoma (RCC) patients by CT images. In this study, clear cell RCC (ccRCC) patients who underwent both preoperative abdominal contrast-enhanced CT and nephrectomy surgery at our hospital were analyzed. By transfer learning, we used base model obtained from Kidney Tumor Segmentation challenge dataset to semi-automatically segment kidney and tumors from corticomedullary phase (CMP) CT images. Dice similarity coefficient (DSC) was measured to evaluate the performance of segmentation models. Ten machine learning classifiers were compared in our study. Performance of the models was assessed by their accuracy, precision, recall and area under the receiver operating characteristic curve (AUC). The reporting and methodological quality of our study was assessed by the CLEAR checklist and METRICS Score. This retrospective study enrolled 163 ccRCC patients. The semiautomatic segmentation model using CMP CT images obtained DSCs of 0.98 on training cohort and 0.96 on test cohort for kidney segmentation, and DSCs of 0.94 and 0.86 for tumor segmentation on training and test set, respectively. For preoperative prediction of renal capsule invasion, the AdaBoost had best performance in batch1, with accuracy, precision, recall and F1-score equal to 0.8571, 0.8333, 0.9091 and 0.8696, respectively; and the same classifier was also the most suitable for this classification in batch 2. The AUCs of AdaBoost for batch 1 and batch 2 were 0.83 (95% CI: 0.68-0.98) and 0.74 (95% CI: 0.51-0.97), respectively. Nine common significant features for classification were found from two independent batch datasets, including morphological and texture features. The CT-based radiomics classifiers performed well for preoperative prediction of fibrous capsule invasion in ccRCC. Noninvasive prediction of renal fibrous capsule invasion in RCC is rather difficult by abdominal CT images before surgery.A machine learning classifier integrated with radiomics features shows a promising potential to assist surgical treatment options for RCC patients.

DistilIQA: Distilling Vision Transformers for no-reference perceptual CT image quality assessment

No-reference image quality assessment (IQA) is a critical step in medical image analysis, with the objective of predicting perceptual image quality without the need for a pristine reference image. The application of no-reference IQA to CT scans is valuable in providing an automated and objective approach to assessing scan quality, optimizing radiation dose, and improving overall healthcare efficiency. In this paper, we introduce DistilIQA, a novel distilled Vision Transformer network designed for no-reference CT image quality assessment. DistilIQA integrates convolutional operations and multi-head self-attention mechanisms by incorporating a powerful convolutional stem at the beginning of the traditional ViT network. Additionally, we present a two-step distillation methodology aimed at improving network performance and efficiency. In the initial step, a ”teacher ensemble network” is constructed by training five vision Transformer networks using a five-fold division schema. In the second step, a ”student network”, comprising of a single Vision Transformer, is trained using the original labeled dataset and the predictions generated by the teacher network as new labels. DistilIQA is evaluated in the task of quality score prediction from low-dose chest CT scans obtained from the LDCT and Projection data of the Cancer Imaging Archive, along with low-dose abdominal CT images from the LDCTIQAC2023 Grand Challenge. Our results demonstrate DistilIQA‘s remarkable performance in both benchmarks, surpassing the capabilities of various CNNs and Transformer architectures. Moreover, our comprehensive experimental analysis demonstrates the effectiveness of incorporating convolutional operations within the ViT architecture and highlights the advantages of our distillation methodology.

AATCT-IDS: A benchmark Abdominal Adipose Tissue CT Image Dataset for image denoising, semantic segmentation, and radiomics evaluation

Background and objective:The metabolic syndrome induced by obesity is closely associated with cardiovascular disease, and the prevalence is increasing globally, year by year. Obesity is a risk marker for detecting this disease. However, current research on computer-aided detection of adipose distribution is hampered by the lack of open-source large abdominal adipose datasets. Methods:In this study, a benchmark Abdominal Adipose Tissue CT Image Dataset (AATCT-IDS) containing 300 subjects is prepared and published. AATCT-IDS publics 13,732 raw CT slices, and the researchers individually annotate the subcutaneous and visceral adipose tissue regions of 3213 of those slices that have the same slice distance to validate denoising methods, train semantic segmentation models, and study radiomics. For different tasks, this paper compares and analyzes the performance of various methods on AATCT-IDS by combining the visualization results and evaluation data. Thus, verify the research potential of this data set in the above three types of tasks. Results:In the comparative study of image denoising, algorithms using a smoothing strategy suppress mixed noise at the expense of image details and obtain better evaluation data. Methods such as BM3D preserve the original image structure better, although the evaluation data are slightly lower. The results show significant differences among them. In the comparative study of semantic segmentation of abdominal adipose tissue, the segmentation results of adipose tissue by each model show different structural characteristics. Among them, BiSeNet obtains segmentation results only slightly inferior to U-Net with the shortest training time and effectively separates small and isolated adipose tissue. In addition, the radiomics study based on AATCT-IDS reveals three adipose distributions in the subject population. Conclusion:AATCT-IDS contains the ground truth of adipose tissue regions in abdominal CT slices. This open-source dataset can attract researchers to explore the multi-dimensional characteristics of abdominal adipose tissue and thus help physicians and patients in clinical practice. AATCT-IDS is freely published for non-commercial purpose at: https://figshare.com/articles/dataset/AATTCT-IDS/23807256.

The impact of skeletal muscle index at the third lumbar spine on nosocomial deterioration and short-term prognosis in acute pancreatitis: a retrospective observational study.

To investigate the impact of the third lumbar skeletal muscle index (L3-SMI) assessed by CT on the in-hospital severity and short-term prognosis of acute pancreatitis. A total of 224 patients with severe acute pancreatitis admitted to Yantaishan Hospital from January 2021 to June 2022 were selected as the subjects. Based on the in-hospital treatment outcomes, they were divided into a mortality group of 59 cases as well as a survival group of 165 cases. Upon admission, general information such as the Acute Physiology and Chronic Health Evaluation II (APACHE II) score, along with the abdominal CT images of each patient, were analyzed. The L3-SMI was calculated, and the Modified CT Severity Index (MCTSI) and Balthazar CT grade were used to assess the severity of in-hospital complications of acute pancreatitis. The evaluation value of L3-SMI for the prognosis of severe acute pancreatitis was analyzed, as well as the factors influencing the prognosis of severe acute pancreatitis. No statistically significant differences in gender, age, BMI, etiology, duration of anti-inflammatory drug use, and proportion of surgical patients between the survival and mortality groups were observed. But the mortality group showed higher proportions of patients with an elevated APACHE II score upon admission, mechanical ventilation, and renal replacement therapy, compared to the survival group, with statistically significant differences (P < 0.001). Furthermore, the mortality group had higher MCTSI scores (6.42 ± 0.69) and Balthazar CT grades (3.78 ± 0.45) than the survival group, with statistically significant differences (P < 0.001). The mortality group also had a lower L3-SMI (39.68 ± 3.25) compared to the survival group (42.71 ± 4.28), with statistically significant differences (P < 0.001). L3-SMI exhibited a negative correlation with MCTSI scores and Balthazar CT grades (r = -0.889, -0.790, P < 0.001). Logistic regression analysis, with mortality of acute pancreatitis patients as the dependent variable and MCTSI scores, Balthazar CT grades, L3-SMI, APACHE II score upon admission, mechanical ventilation, and renal replacement therapy as independent variables, revealed that MCTSI scores and L3-SMI were risk factors for mortality in acute pancreatitis patients (P < 0.001). Logistic regression analysis using the same variables confirmed that all these factors were risk factors for mortality in acute pancreatitis patients. This study confirmed that diagnosing muscle depletion using L3-SMI is a valuable radiological parameter for predicting in-hospital severity and short-term prognosis in patients with acute pancreatitis.