A Novel Approach to Breast Tumor Detection: Enhanced Speckle Reduction and Hybrid Classification in Ultrasound Imaging

Breast cancer detection heavily relies on medical imaging, particularly ultrasound, for early diagnosis and effectivetreatment. This research addresses the challenges associated with computer-aided diagnosis (CAD) of breastcancer fromultrasound images. The primary challenge is accurately distinguishing between malignant and benigntumors, complicated by factors such as speckle noise, variable image quality, and the need for precise segmentationand classification. The main objective of the research paper is to develop an advanced methodology for breastultrasound image classification, focusing on speckle noise reduction, precise segmentation, feature extraction, andmachine learning-based classification. A unique approach is introduced that combines Enhanced Speckle ReducedAnisotropic Diffusion (SRAD) filters for speckle noise reduction, U-NET-based segmentation, Genetic Algorithm(GA)-based feature selection, and Random Forest and Bagging Tree classifiers, resulting in a novel and efficientmodel. To test and validate the hybrid model, rigorous experimentations were performed and results state thatthe proposed hybrid model achieved accuracy rate of 99.9%, outperforming other existing techniques, and alsosignificantly reducing computational time. This enhanced accuracy, along with improved sensitivity and specificity,makes the proposed hybrid model a valuable addition to CAD systems in breast cancer diagnosis, ultimatelyenhancing diagnostic accuracy in clinical applications.

Structured magnetic resonance imaging and endoanal ultrasound anal fistulas reporting template(SMART):An interdisciplinary Delphi consensus

BACKGROUND There is still considerable heterogeneity regarding which features of cryptoglandular anal fistula on magnetic resonance imaging(MRI)and endoanal ultrasound(EAUS)are relevant to surgical decision-making.As a con-sequence,the quality and completeness of the report are highly dependent on the training and experience of the examiners.AIM To develop a structured MRI and EAUS template(SMART)reporting the minimum dataset of information for the treatment of anal fistulas.METHODS This modified Delphi survey based on the RAND-UCLA appropriateness for consensus-building was conducted between May and August 2023.One hundred and fifty-one articles selected from a systematic review of the lite-rature formed the database to generate the evidence-based statements for the Delphi study.Fourteen questions were anonymously voted by an interdisciplinary multidisciplinary group for a maximum of three iterative rounds.The degree of agreement was scored on a numeric 0–10 scale.Group consensus was defined as a score≥8 for≥80%of the panelists.RESULTS Eleven scientific societies(3 radiological and 8 surgical)endorsed the study.After three rounds of voting,the experts(69 colorectal surgeons,23 radiologists,2 anatomists,and 1 gastroenterologist)achieved consensus for 12 of 14 statements(85.7%).Based on the results of the Delphi process,the six following features of anal fistulas were included in the SMART:Primary tract,secondary extension,internal opening,presence of collection,coexisting le-sions,and sphincters morphology.CONCLUSION A structured template,SMART,was developed to standardize imaging reporting of fistula-in-ano in a simple,systematic,time-efficient way,providing the minimum dataset of information and visual diagram useful to refer-ring physicians.

The Application Value of Ultrasound Imaging in the Differential Diagnosis of Benign and Malignant Breast Nodules of BI-RADS 3 and Above

Objective:To explore the diagnostic value of ultrasound imaging for breast nodules of breast imaging-reporting and data system(BI-RADS)category 3 and above.Methods:From June 2021 to July 2022,163 patients with breast nodules of BI-RADS 3 or above were selected as the research subjects.After pathological diagnosis,24 cases were malignant breast nodules of BI-RADS 3 or above,while 139 cases were benign breast nodules of BI-RADS 3 or above.The diagnosis rate of malignant and benign breast nodules of BI-RADS 3 or above,including 95%CI,was observed and analyzed.Results:The malignant and benign detection rates of conventional ultrasound were 88.63%and 75.00%,respectively,and the malignant and benign detection rates of ultrasound imaging were 93.18%and 87.50%,respectively,with 95%CIs greater than 0.7.Conclusion:Ultrasound imaging can help improve the diagnostic accuracy of benign and malignant breast nodules of BI-RADS 3 and above and reduce the misdiagnosis rate.

Data augmentation of ultrasound imaging for non-invasive white blood cell in vitro peritoneal dialysis

The limited amount of data in the healthcare domain and the necessity of training samples for increased performance of deep learning models is a recurrent challenge,especially in medical imaging.Newborn Solutions aims to enhance its non-invasive white blood cell counting device,Neosonics,by creating synthetic in vitro ultrasound images to facilitate a more efficient image generation process.This study addresses the data scarcity issue by designing and evaluating a continuous scalar conditional Generative Adversarial Network(GAN)to augment in vitro peritoneal dialysis ultrasound images,increasing both the volume and variability of training samples.The developed GAN architecture incorporates novel design features:varying kernel sizes in the generator’s transposed convolutional layers and a latent intermediate space,projecting noise and condition values for enhanced image resolution and specificity.The experimental results show that the GAN successfully generated diverse images of high visual quality,closely resembling real ultrasound samples.While visual results were promising,the use of GAN-based data augmentation did not consistently improve the performance of an image regressor in distinguishing features specific to varied white blood cell concentrations.Ultimately,while this continuous scalar conditional GAN model made strides in generating realistic images,further work is needed to achieve consistent gains in regression tasks,aiming for robust model generalization.

Imaging and endoscopic tools in pediatric inflammatory bowel disease: What’s new?

Pediatric inflammatory bowel disease(IBD)is a chronic inflammatory disorder,with increasing incidence and prevalence worldwide.There have been recent advances in imaging and endoscopic technology for disease diagnosis,treatment,and monitoring.Intestinal ultrasound,including transabdominal,transperineal,and endoscopic,has been emerging for the assessment of transmural bowel inflammation and disease complications(e.g.,fistula,abscess).Aside from surgery,IBD-related intestinal strictures now have endoscopic treatment options including through-the-scope balloon dilatation,injection,and needle knife stricturotomy and new evaluation tools such as endoscopic functional lumen imaging probe.Unsedated transnasal endoscopy may have a role in patients with upper gastrointestinal Crohn’s disease or those with IBD with new upper gastrointestinal symptoms.Improvements to dysplasia screening in pediatric patients with longstanding colonic disease or primary sclerosing cholangitis hold promise with the addition of virtual chromoendoscopy and ongoing research in the field of artificial intelligence-assisted endoscopic detection.Artificial intelligence and machine learning is a rapidly evolving field,with goals of further personalizing IBD diagnosis and treatment selection as well as prognostication.This review summarized these advancements,focusing on pediatric patients with IBD.

A Modified CycleGAN for Multi-Organ Ultrasound Image Enhancement via Unpaired Pre-Training

Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image quality of handheld ultrasound devices is not always satisfactory due to the limited equipment size,which hinders accurate diagnoses by doctors.At the same time,paired ultrasound images are difficult to obtain from the clinic because imaging process is complicated.Therefore,we propose a modified cycle generative adversarial network(cycleGAN) for ultrasound image enhancement from multiple organs via unpaired pre-training.We introduce an ultrasound image pre-training method that does not require paired images,alleviating the requirement for large-scale paired datasets.We also propose an enhanced block with different structures in the pre-training and fine-tuning phases,which can help achieve the goals of different training phases.To improve the robustness of the model,we add Gaussian noise to the training images as data augmentation.Our approach is effective in obtaining the best quantitative evaluation results using a small number of parameters and less training costs to improve the quality of handheld ultrasound devices.

Automatic Fetal Segmentation Designed on Computer-Aided Detection with Ultrasound Images

In the present research,we describe a computer-aided detection(CAD)method aimed at automatic fetal head circumference(HC)measurement in 2D ultrasonography pictures during all trimesters of pregnancy.The HC might be utilized toward determining gestational age and tracking fetal development.This automated approach is particularly valuable in low-resource settings where access to trained sonographers is limited.The CAD system is divided into two steps:to begin,Haar-like characteristics were extracted from ultrasound pictures in order to train a classifier using random forests to find the fetal skull.We identified the HC using dynamic programming,an elliptical fit,and a Hough transform.The computer-aided detection(CAD)program was well-trained on 999 pictures(HC18 challenge data source),and then verified on 335 photos from all trimesters in an independent test set.A skilled sonographer and an expert in medicine personally marked the test set.We used the crown-rump length(CRL)measurement to calculate the reference gestational age(GA).In the first,second,and third trimesters,the median difference between the standard GA and the GA calculated by the skilled sonographer stayed at 0.7±2.7,0.0±4.5,and 2.0±12.0 days,respectively.The regular duration variance between the baseline GA and the health investigator’s GA remained 1.5±3.0,1.9±5.0,and 4.0±14 a couple of days.The mean variance between the standard GA and the CAD system’s GA remained between 0.5 and 5.0,with an additional variation of 2.9 to 12.5 days.The outcomes reveal that the computer-aided detection(CAD)program outperforms an expert sonographer.When paired with the classifications reported in the literature,the provided system achieves results that are comparable or even better.We have assessed and scheduled this computerized approach for HC evaluation,which includes information from all trimesters of gestation.

The Application Progress of Skin Imaging Technology in Psoriasis

Skin imaging technologies such as dermoscopy, high-frequency ultrasound, reflective confocal microscopy and optical coherence tomography are developing rapidly in clinical application. Skin imaging technology can improve clinical diagnosis rate, and its non-invasiveness and repeatability make it occupy an irreplaceable position in clinical diagnosis. With the “booming development” of medical technology, skin imaging technology can improve clinical diagnosis rate. Researchers have made significant advances in assisting clinical diagnosis, prediction, and treatment of disease. This article reviews the application and progress of skin imaging in the diagnosis of psoriasis.

Recent Research Advances in Imaging of Prostate Cancer

Imaging study plays a crucial role in the diagnosis of prostate cancer. As early screening and management of prostate cancer has evolved over the past decade, research is now focusing on how to detect clinically significant prostate cancer and avoid overdiagnosis accurately. This article provides an overview of recent advances in imaging in prostate cancer diagnosis, including new ultrasound imaging techniques, positron emission computed tomography, multiparametric magnetic resonance imaging, and emerging areas such as imaging histology, by systematically reviewing and summarizing the existing literature.

Quantitative ultrasound brain imaging with multiscale deconvolutional waveform inversion

High-resolution images of human brain are critical for monitoring the neurological conditions in a portable and safe manner.Sound speed mapping of brain tissues provides unique information for such a purpose.In addition,it is particularly important for building digital human acoustic models,which form a reference for future ultrasound research.Conventional ultrasound modalities can hardly image the human brain at high spatial resolution inside the skull due to the strong impedance contrast between hard tissue and soft tissue.We carry out numerical experiments to demonstrate that the time-domain waveform inversion technique,originating from the geophysics community,is promising to deliver quantitative images of human brains within the skull at a sub-millimeter level by using ultra-sound signals.The successful implementation of such an approach to brain imaging requires the following items:signals of sub-megahertz frequencies transmitting across the inside of skull,an accurate numerical wave equation solver simulating the wave propagation,and well-designed inversion schemes to reconstruct the physical parameters of targeted model based on the optimization theory.Here we propose an innovative modality of multiscale deconvolutional waveform inversion that improves ultrasound imaging resolution,by evaluating the similarity between synthetic data and observed data through using limited length Wiener filter.We implement the proposed approach to iteratively update the parametric models of the human brain.The quantitative imaging method paves the way for building the accurate acoustic brain model to diagnose associated diseases,in a potentially more portable,more dynamic and safer way than magnetic resonance imaging and x-ray computed tomography.

Value of ultrasound and magnetic resonance imaging combined with tumor markers in the diagnosis of ovarian tumors

BACKGROUND Compare the diagnostic performance of ultrasound(US),magnetic resonance imaging(MRI),and serum tumor markers alone or in combination for detecting ovarian tumors.AIM To investigate the diagnostic value of US,MRI combined with tumor markers in ovarian tumors.METHODS The data of 110 patients with ovarian tumors,confirmed by surgery and pathology,were collected in our hospital from February 2018 to May 2023.The dataset included 60 cases of benign tumors and 50 cases of malignant tumors.Prior to surgery,all patients underwent preoperative US and MRI examinations,as well as serum tumor marker tests[carbohydrate antigen 125(CA125),human epididymis protein 4(HE4)].The aim of the study was to compare the diagnostic performance of these three methods individually and in combination for ovarian tumors.RESULTS This study found statistically significant differences in the ultrasonic imaging characteristics between benign and malignant tumors.These differences include echo characteristics,presence or absence of a capsule,blood flow resistance index,clear tumor shape,and blood flow signal display rate(P<0.05).The apparent diffusion coefficient values of the solid and cystic parts in benign tumors were found to be higher compared to malignant tumors(P<0.05).Additionally,the time-intensity curve image features of benign and malignant tumors showed significant statistical differences(P<0.05).The levels of serum CA125 and HE4 in benign tumors were lower than those in malignant tumors(P<0.05).The combined use of US,MRI,and tumor markers in the diagnosis of ovarian tumors demonstrates higher accuracy,sensitivity,and specificity compared to using each method individually(P<0.05).CONCLUSION US,MRI,and tumor markers each have their own advantages and disadvantages when it comes to diagnosing ovarian tumors.However,by combining these three methods,we can significantly enhance the accuracy of ovarian tumor diagnosis,enabling early detection and identification of the tumor’s nature,and providing valuable guidance for clinical treatment.

Non-invasive evaluation of liver steatosis with imaging modalities:New techniques and applications

In the world,nonalcoholic fatty liver disease(NAFLD)accounts for majority of diffuse hepatic diseases.Notably,substantial liver fat accumulation can trigger and accelerate hepatic fibrosis,thus contributing to disease progression.Moreover,the presence of NAFLD not only puts adverse influences for liver but is also associated with an increased risk of type 2 diabetes and cardiovascular diseases.Therefore,early detection and quantified measurement of hepatic fat content are of great importance.Liver biopsy is currently the most accurate method for the evaluation of hepatic steatosis.However,liver biopsy has several limitations,namely,its invasiveness,sampling error,high cost and moderate intraobserver and interobserver reproducibility.Recently,various quantitative imaging techniques have been developed for the diagnosis and quantified measurement of hepatic fat content,including ultrasound-or magnetic resonancebased methods.These quantitative imaging techniques can provide objective continuous metrics associated with liver fat content and be recorded for comparison when patients receive check-ups to evaluate changes in liver fat content,which is useful for longitudinal follow-up.In this review,we introduce several imaging techniques and describe their diagnostic performance for the diagnosis and quantified measurement of hepatic fat content.

Basic physical, acoustic properties, and in vitro ultrasound imaging enhancement of the lipid-coated microbubbles

Aim To research on a stable microbubble with good acoustic properties and excellent imaging enhancing effect, and to make it to be a promising agent for the enhancement of ultrasound imaging in the ultrasound diagnosis of cardiovascular system diseases. Methods The morphology, size and zeta potential of lipid-coated microbubbles （LCM）, the acoustic properties of backscatter, and the second harmonic scatter of LCM were determined. Furthermore, the relationship between the concentrations and the amplitude values of the second harmonic was investigated by testing the intensities of the second harmonic at different concentrations. The imaging effect of LCM was also studied in vitro. Results The mean diameter of LCM was 3.38 μm with 95% of the bubbles under 5 μm. The scatter signal generated by microbubbles was observed under different concentrations in the bistatic modes while the position of transmitting transducer and receiving transducer was orthogonal. The intensity of the second harmonic scatter fell with the decrease of microbubble concentration. The increase rate of the second harmonic amplitude values generated by the microbubbles versus that by physiological saline was linear with the natural logarithm of bubble concentrations. The LCM could enhance the ultrasound image of thrombus. Conclusion The LCM exhibited good physical state and acoustic properties, which could increase the imaging quality.

Vault predicting after implantable collamer lens implantation using random forest network based on different features in ultrasound biomicroscopy images

AIM:To analyze ultrasound biomicroscopy(UBM)images using random forest network to find new features to make predictions about vault after implantable collamer lens(ICL)implantation.METHODS:A total of 450 UBM images were collected from the Lixiang Eye Hospital to provide the patient’s preoperative parameters as well as the vault of the ICL after implantation.The vault was set as the prediction target,and the input elements were mainly ciliary sulcus shape parameters,which included 6 angular parameters,2 area parameters,and 2 parameters,distance between ciliary sulci,and anterior chamber height.A random forest regression model was applied to predict the vault,with the number of base estimators(n_estimators)of 2000,the maximum tree depth(max_depth)of 17,the number of tree features(max_features)of Auto,and the random state(random_state)of 40.0.RESULTS:Among the parameters selected in this study,the distance between ciliary sulci had a greater importance proportion,reaching 52%before parameter optimization is performed,and other features had less influence,with an importance proportion of about 5%.The importance of the distance between the ciliary sulci increased to 53% after parameter optimization,and the importance of angle 3 and area 1 increased to 5% and 8%respectively,while the importance of the other parameters remained unchanged,and the distance between the ciliary sulci was considered the most important feature.Other features,although they accounted for a relatively small proportion,also had an impact on the vault prediction.After parameter optimization,the best prediction results were obtained,with a predicted mean value of 763.688μm and an actual mean value of 776.9304μm.The R²was 0.4456 and the root mean square error was 201.5166.CONCLUSION:A study based on UBM images using random forest network can be performed for prediction of the vault after ICL implantation and can provide some reference for ICL size selection.

Contrast-enhanced ultrasound improved performance of breast imaging reporting and data system evaluation of critical breast lesions

AIM: To determine whether contrast-enhanced ultrasound(CEUS) can improve the precision of breast imaging reporting and data system(BI-RADS) categorization. METHODS: A total of 230 patients with 235 solid breast lesions classified as BI-RADS 4 on conventional ultrasound were evaluated. CEUS was performed within one week before core needle biopsy or surgical resection and a revised BI-RADS classification was assigned based on 10 CEUS imaging characteristics. Receiver operating characteristic curve analysis was then conducted to evaluate the diagnostic performance of CEUS-based BI-RADS assignment with pathological examination as reference criteria. RESULTS: The CEUS-based BI-RADS evaluation classified 116/235(49.36%) lesions into category 3, 20(8.51%), 13(5.53%) and 12(5.11%) lesions into categories 4A, 4B and 4C, respectively, and 74(31.49%) into category 5. Selecting CEUS-based BI-RADS category 4A as an appropriate cut-off gave sensitivity and specificity values of 85.4% and 87.8%, respectively, for the diagnosisof malignant disease. The cancer-to-biopsy yield was 73.11% with CEUS-based BI-RADS 4A selected as the biopsy threshold compared with 40.85% otherwise, while the biopsy rate was only 42.13% compared with 100% otherwise. Overall, only 4.68% of invasive cancers were misdiagnosed.CONCLUSION: This pilot study suggests that evaluation of BI-RADS 4 breast lesions with CEUS results in reduced biopsy rates and increased cancer-to-biopsy yields.

Endorectal ultrasonography versus phased-array magnetic resonance imaging for preoperative staging of rectal cancer

AIM: To compare the diagnostic accuracy of pelvic phased-array magnetic resonance imaging (MRI) and endorectal ultrasonography (ERUS) in the preoperative staging of rectal carcinoma. METHODS: Thirty-four patients (15 males, 19 females) with ages ranging between 29 and 75 who have biopsy proven rectal tumor underwent both MRI and ERUS examinations before surgery. All patients were evaluated to determine the diagnostic accuracy of depth of transmural tumor invasion and lymph node metastases. Imaging results were correlated with histopathological findings regarded as the gold standard and both modalities were compared in terms of predicting preoperative local staging of rectal carcinoma. RESULTS: The pathological T stage of the tumors was: pT1 in 1 patient, pT2 in 9 patients, pT3 in 21 patients and pT4 in 3 patients. The pathological N stage of the tumors was: pN0 in 19 patients, pN1 in 9 patients and pN2 in 6 patients. The accuracy of T staging for MRI was 89.70% (27 out of 34). The sensitivity was 79.41% and the specificity was 93.14%. The accuracy of T staging for ERUS was 85.29% (24 out of 34). The sensitivity was 70.59% and the specificity was 90.20%. Detection of lymph node metastases usingphased-array MRI gave an accuracy of 74.50% (21 out of 34). The sensitivity and specificity was found to be 61.76% and 80.88%, respectively. By using ERUS in the detection of lymph node metastases, an accuracy of 76.47% (18 out of 34) was obtained. The sensitivity and specificity were found to be 52.94% and 84.31%, respectively. CONCLUSION: ERUS and phased-array MRI are complementary methods in the accurate preoperative staging of rectal cancer. In conclusion, we can state that phased-array MRI was observed to be slightly superior in determining the depth of transmural invasion (T stage) and has same value in detecting lymph node metastases (N stage) as compared to ERUS.

Ultrasound Imaging of Pipeline Crack Based on Composite Transducer Array

Cracks, especially small cracks are di cult to be detected in oil and gas transportation pipelines buried underground or covered with layers of material by using the traditional ultrasonic inspection techniques. Therefore, a new com?posite ultrasonic transducer array with three acoustic beam incidence modes is developed. The space model of the array is also established to obtain the defect reflection point location. And the crack ultrasound image is thus formed through a series of small cubical elements expanded around the point locations by using the projection of binariza?tion values extracted from the received ultrasonic echo signals. Laboratory experiments are performed on a pipeline sample with di erent types of cracks to verify the e ectiveness and performance of the proposed technique. From the image, the presence of small cracks can be clearly observed, in addition to the sizes and orientations of the cracks. The proposed technique can not only inspect common flaws, but also detect cracks with various orientations, which is helpful for defect evaluation in pipeline testing.

Predictive model for contrast-enhanced ultrasound of the breast: Is it feasible in malignant risk assessment of breast imaging reporting and data system 4 lesions?

AIM: To build and evaluate predictive models for contrast-enhanced ultrasound(CEUS) of the breast to distinguish between benign and malignant lesions. METHODS: A total of 235 breast imaging reporting and data system(BI-RADS) 4 solid breast lesions were imaged via CEUS before core needle biopsy or surgical resection. CEUS results were analyzed on 10 enhancing patterns to evaluate diagnostic performance of three benign and three malignant CEUS models, with pathological results used as the gold standard. A logistic regression model was developed basing on the CEUS results, and then evaluated with receiver operating curve(ROC). RESULTS: Except in cases of enhanced homogeneity, the rest of the 9 enhancement appearances were statistically significant(P < 0.05). These 9 enhancement patterns were selected in the final step of the logistic regression analysis, with diagnostic sensitivity and specificity of 84.4% and 82.7%, respectively, and the area under the ROC curve of 0.911. Diagnostic sensitivity, specificity, and accuracy of the malignant vs benign CEUS models were 84.38%, 87.77%, 86.38% and 86.46%, 81.29% and 83.40%, respectively. CONCLUSION: The breast CEUS models can predict risk of malignant breast lesions more accurately, decrease false-positive biopsy, and provide accurate BIRADS classification.

The performance of transrectal ultrasound in the diagnosis of seminal vesicle defects： a comparison with magnetic resonance imaging

Obstructive azoospermia （OA） is one of the most common causes of male infertility. Transrectal ultrasound （TRUS） has been used to diagnose OA for many years. From 2009 to 2013, we evaluated a prospective cohort of 1249 patients with suspected OA using TRUS. It was found that dilation of the ejaculatory duct （ED） （29.9%, 374/1249） was the most common cause of OA, followed by seminal vesicle （SV） abnormalities （28.5%, 356/1249）. A total of 237 patients were diagnosed with congenital defects （agenesis and/or hypoplasia） of the SV, constituting more than half of the cases of SV disease in OA （19.0%, 237/1249）. In contrast to ED, congenital defects of the SV could not be corrected with surgical treatment. Therefore, it is meaningful to compare TRUS and magnetic resonance imaging （MRI） for accurate diagnosis of SV defects. Among our patients, 30 with agenesis or/and hypoplasia of the SV on TRUS were further evaluated using pelvic MRI within 2 years, with the objective of verifying the TRUS results. The concordance rate for diagnosing congenital defects of the SV was 73.3% （22/30）. We concluded that TRUS is a reliable and convenient method for diagnosing agenesis or hypoplasia of the SV in OA patients with a high concordance with MRI while MRI is useful in patients with inconclusive TRUS findings.

Transrectal ultrasound and magnetic resonance imaging measurement of extramural tumor spread in rectal cancer

AIM： To evaluate the agreement between transrectal ultrasound （TRUS） and magnetic resonance imaging （MRI） in classification of ≥ T3 rectal tumors. METHODS： From January 2010 to January 2012, 86 consecutive patients with ≥ T3 tumors were included in this study. The mean age of the patients was 66.4 years （range： 26-91 years）. The tumors were all ≥ T3 on TRUS. The sub-classification was defined by the penetration of the rectal wall： a： 0 to 1 mm; b： 1-5 mm, c： 6-15; d： 〉 15 mm. Early tumors as ab （≤ 5 ram） and advanced tumors as cd （〉 5 mm）. All patients underwent TRUS using a 6.5 MHz transrectal transducer. The MRI was performed with a 1.5 T Phil- ips unit. The TRUS findings were blinded to the radiol- ogist performing the interpretation of the MRI images and measuring the depth of extramural tumor spread RESULTS： TRUS found 51 patients to have an early ≥ T3 tumors and 35 to have an advanced tumor, where- as MRI categorized 48 as early ≥ T3 tumors and 38 as advanced tumors. No patients with tumors classified as advanced by TRUS were found to be early on MRI. The kappa value in classifying early versus advanced T3 rectal tumors was 0.93 （95% CI： 0.85-1.00）. We found a kappa value of 0.74 （95% CI： 0.63-0.86） for the total sub-classification between the two methods. The mean maximal tumor outgrowth measured by TRUS, 5.5 mm ± 5.63 mm and on MRI, 6.3 mm ±6.18 mm, P = 0.004. In 19 of the 86 patients the following CT scan or surgery revealed distant metastases; of the 51 patients in the ultrasound ab group three （5.9%） had metastases, whereas 16 （45.7%） of 35 in the cd group harbored distant metastases, P = 0.00002. The odds ratio of having distant metastases in the ultra- sound cd group compared to the ab group was 13.5 （95% CI： 3.5-51.6）, P = 0.00002. The mean maximal ultrasound measured outgrowth was 4.3 mm （95% CI： 3.2-5.5 mm） in patients without distant metastases, while the mean maximal outgrowth was 9.5 mm （95% CI： 6.2-12.8 ram） in the patients with metastases, P = 0.00004. Using the MRI classification three （6.3%） of 48 in the MRI ab group had distant metastases, while 16 （42.1%） of the 38 in the MRI cd group, P = 0.00004. The MRI odds ratio was 10.9 （95% CI： 2.9-41.4）, P = 0.00008. The mean maximal MRI measured out- growth was 4.9 mm （95% CI： 3.7-6.1 turn） in patients without distant metastases, while the mean maximal outgrowth was 11.5 mm （95% CI： 7.8-15.2 mm） in the patients with metastases, P = 0.000006. CONCLUSION： There is good agreement between TRUS and MRI in the pretreatment sub-classification of ≥ T3 tumors. Distant metastases are more frequent in the advanced group.