Accuracy Of Lesion Classification Research Articles

Oral mucosal lesions triage via YOLOv7 models

Background/purposeThe global incidence of lip and oral cavity cancer continues to rise, necessitating improved early detection methods. This study leverages the capabilities of computer vision and deep learning to enhance the early detection and classification of oral mucosal lesions. MethodsA dataset initially consisting of 6903 white-light macroscopic images collected from 2006 to 2013 was expanded to over 50,000 images to train the YOLOv7 deep learning model. Lesions were categorized into three referral grades: benign (green), potentially malignant (yellow), and malignant (red), facilitating efficient triage. ResultsThe YOLOv7 models, particularly the YOLOv7-E6, demonstrated high precision and recall across all lesion categories. The YOLOv7-D6 model excelled at identifying malignant lesions with notable precision, recall, and F1 scores. Enhancements, including the integration of coordinate attention in the YOLOv7-D6-CA model, significantly improved the accuracy of lesion classification. ConclusionThe study underscores the robust comparison of various YOLOv7 model configurations in the classification to triage oral lesions. The overall results highlight the potential of deep learning models to contribute to the early detection of oral cancers, offering valuable tools for both clinical settings and remote screening applications.

Enhancing skin lesion classification with advanced deep learning ensemble models: a path towards accurate medical diagnostics

Skin cancer, including the highly lethal malignant melanoma, poses a significant global health challenge with a rising incidence rate. Early detection plays a pivotal role in improving survival rates. This study aims to develop an advanced deep learning-based approach for accurate skin lesion classification, addressing challenges such as limited data availability, class imbalance, and noise. Modern deep neural network designs, such as ResNeXt101, SeResNeXt101, ResNet152V2, DenseNet201, GoogLeNet, and Xception, which are used in the study and ze optimised using the SGD technique. The dataset comprises diverse skin lesion images from the HAM10000 and ISIC datasets. Noise and artifacts are tackled using image inpainting, and data augmentation techniques enhance training sample diversity. The ensemble technique is utilized, creating both average and weighted average ensemble models. Grid search optimizes model weight distribution. The individual models exhibit varying performance, with metrics including recall, precision, F1 score, and MCC. The "Average ensemble model" achieves harmonious balance, emphasizing precision, F1 score, and recall, yielding high performance. The "Weighted ensemble model" capitalizes on individual models' strengths, showcasing heightened precision and MCC, yielding outstanding performance. The ensemble models consistently outperform individual models, with the average ensemble model attaining a macro-average ROC-AUC score of 96 % and the weighted ensemble model achieving a macro-average ROC-AUC score of 97 %. This research demonstrates the efficacy of ensemble techniques in significantly improving skin lesion classification accuracy. By harnessing the strengths of individual models and addressing their limitations, the ensemble models exhibit robust and reliable performance across various metrics. The findings underscore the potential of ensemble techniques in enhancing medical diagnostics and contributing to improved patient outcomes in skin lesion diagnosis.

Computer-aided diagnosis in real-time endoscopy for all stages of gastric carcinogenesis: Development and validation study.

Using endoscopic images, we have previously developed computer-aided diagnosis models to predict the histopathology of gastric neoplasms. However, no model that categorizes every stage of gastric carcinogenesis has been published. In this study, a deep-learning-based diagnosis model was developed and validated to automatically classify all stages of gastric carcinogenesis, including atrophy and intestinal metaplasia, in endoscopy images. A total of 18,701 endoscopic images were collected retrospectively and randomly divided into train, validation, and internal-test datasets in an 8:1:1 ratio. The primary outcome was lesion-classification accuracy in six categories: normal/atrophy/intestinal metaplasia/dysplasia/early /advanced gastric cancer. External-validation of performance in the established model used 1427 novel images from other institutions that were not used in training, validation, or internal-tests. The internal-test lesion-classification accuracy was 91.2% (95% confidence interval: 89.9%-92.5%). For performance validation, the established model achieved an accuracy of 82.3% (80.3%-84.3%). The external-test per-class receiver operating characteristic in the diagnosis of atrophy and intestinal metaplasia was 93.4±0% and 91.3±0%, respectively. The established model demonstrated high performance in the diagnosis of preneoplastic lesions (atrophy and intestinal metaplasia) as well as gastric neoplasms.

Explainable AI for Medical Image Analysis in Medical Cyber-Physical Systems: Enhancing Transparency and Trustworthiness of IoMT.

Medical image analysis plays a crucial role in healthcare systems of Internet of Medical Things (IoMT), aiding in the diagnosis, treatment planning, and monitoring of various diseases. With the increasing adoption of artificial intelligence (AI) techniques in medical image analysis, there is a growing need for transparency and trustworthiness in decision-making. This study explores the application of explainable AI (XAI) in the context of medical image analysis within medical cyber-physical systems (MCPS) to enhance transparency and trustworthiness. To this end, this study proposes an explainable framework that integrates machine learning and knowledge reasoning. The explainability of the model is realized when the framework evolution target feature results and reasoning results are the same and are relatively reliable. However, using these technologies also presents new challenges, including the need to ensure the security and privacy of patient data from IoMT. Therefore, attack detection is an essential aspect of MCPS security. For the MCPS model with only sensor attacks, the necessary and sufficient conditions for detecting attacks are given based on the definition of sparse observability. The corresponding attack detector and state estimator are designed by assuming that some IoMT sensors are under protection. It is expounded that the IoMT sensors under protection play an important role in improving the efficiency of attack detection and state estimation. The experimental results show that the XAI in the context of medical image analysis within MCPS improves the accuracy of lesion classification, effectively removes low-quality medical images, and realizes the explainability of recognition results. This helps doctors understand the logic of the system's decision-making and can choose whether to trust the results based on the explanation given by the framework.

Clinical Decision Support System for All Stages of Gastric Carcinogenesis in Real-Time Endoscopy: Model Establishment and Validation Study.

Our research group previously established a deep-learning-based clinical decision support system (CDSS) for real-time endoscopy-based detection and classification of gastric neoplasms. However, preneoplastic conditions, such as atrophy and intestinal metaplasia (IM) were not taken into account, and there is no established model that classifies all stages of gastric carcinogenesis. This study aims to build and validate a CDSS for real-time endoscopy for all stages of gastric carcinogenesis, including atrophy and IM. A total of 11,868 endoscopic images were used for training and internal testing. The primary outcomes were lesion classification accuracy (6 classes: advanced gastric cancer, early gastric cancer, dysplasia, atrophy, IM, and normal) and atrophy and IM lesion segmentation rates for the segmentation model. The following tests were carried out to validate the performance of lesion classification accuracy: (1) external testing using 1282 images from another institution and (2) evaluation of the classification accuracy of atrophy and IM in real-world procedures in a prospective manner. To estimate the clinical utility, 2 experienced endoscopists were invited to perform a blind test with the same data set. A CDSS was constructed by combining the established 6-class lesion classification model and the preneoplastic lesion segmentation model with the previously established lesion detection model. The overall lesion classification accuracy (95% CI) was 90.3% (89%-91.6%) in the internal test. For the performance validation, the CDSS achieved 85.3% (83.4%-97.2%) overall accuracy. The per-class external test accuracies for atrophy and IM were 95.3% (92.6%-98%) and 89.3% (85.4%-93.2%), respectively. CDSS-assisted endoscopy showed an accuracy of 92.1% (88.8%-95.4%) for atrophy and 95.5% (92%-99%) for IM in the real-world application of 522 consecutive screening endoscopies. There was no significant difference in the overall accuracy between the invited endoscopists and established CDSS in the prospective real-clinic evaluation (P=.23). The CDSS demonstrated a segmentation rate of 93.4% (95% CI 92.4%-94.4%) for atrophy or IM lesion segmentation in the internal testing. The CDSS achieved high performance in terms of computer-aided diagnosis of all stages of gastric carcinogenesis and demonstrated real-world application potential.

Reevaluating diagnostic categories and associated malignancy risks in thyroid core needle biopsy.

As the application of core needle biopsy (CNB) in evaluating thyroid nodules rises in clinical practice, the 2023 Korean Thyroid Association Management Guidelines for Patients with Thyroid Nodules have officially recognized its value for the first time. CNB procures tissue samples preserving both histologic structure and cytologic detail, thereby supplying substantial material for an accurate diagnosis and reducing the necessity for repeated biopsies or subsequent surgical interventions. The current review introduces the risk of malignancy within distinct diagnostic categories, emphasizing the implications of noninvasive follicular thyroid neoplasm with papillary-like nuclear features on these malignancy risks. Prior research has indicated diagnostic challenges associated with follicular-patterned lesions, resulting in notable variation within indeterminate diagnostic categories. The utilization of mutation-specific immunostaining in CNB enhances the accuracy of lesion classification. This review underlines the essential role of a multidisciplinary approach in diagnosing follicular-patterned lesions and the potential of mutation-specific immunostaining to strengthen diagnostic consensus and inform patient management decisions.

Tactile, Orientation, and Optical Sensor Fusion for Tactile Breast Image Mosaicking

Breast cancer screening using tactile imaging (TI) is an advancing field of low-cost noninvasive medical imaging. Utilizing arrays of capacitive pressure transducers to perform a differential stress measurement of suspicious tissue, TI has been shown to be effective in measuring lesion size and stiffness, and subsequent differentiation of malignant and benign conditions, in repeated clinical studies. In order to further improve the lesion classification accuracy of clinical TI, this article presents a novel method of mosaicking tactile images to form a large composite tactile map using the vein structure within the breast to spatially register tactile data. This article demonstrates practical nonrigid tactile image mosaicking, using probe contact force and relative orientation sensor fusion to correct for the tissue deformation during tactile scanning, miniaturized and applied to a pre-clinical TI prototype. Testing of the proposed TI prototype on representative, tissue-mimicking, and silicone breast phantoms, with varying baseline elasticity and internal vein structure, yields typical image registration accuracies of 0.33% ± 0.15%. In similar testing, the proposed system measures the background elasticity of the samples with worst case error < 4.5% over the range of 9–60 kPa, required for accurate lesion characterization. This work will lead into further clinical validation of TI for measurement and classification of in situ phantom and breast lesions, utilizing the delivered metrics from this work to improve differentiation accuracy.

An Automatic Breast Tumor Detection and Classification including Automatic Tumor Volume Estimation Using Deep Learning Technique.

This study aims to develop automatic breast tumor detection and classification including automatic tumor volume estimation using deep learning techniques based on computerized analysis of breast ultrasound images. When the skill levels of the radiologists and image quality are important to detect and diagnose the tumor using handheld ultrasound, the ability of this approach tends to assist the radiologist's decision for breast cancer diagnosis. Breast ultrasound images were provided by the Department of Radiology of Thammasat University and Queen Sirikit Center of Breast Cancer of Thailand. The dataset consists of 655 images including 445 benign and 210 malignant. Several data augmentation methods including blur, flip vertical, flip horizontal, and noise have been applied to increase the training and testing dataset. The tumor detection, localization, and classification were performed by drawing the appropriate bounding box around it using YOLO7 architecture based on deep learning techniques. Then, the automatic tumor volume estimation was performed using a simple pixel per metric technique. The model demonstrated excellent tumor detection performance with a confidence score of 0.95. In addition, the model yielded satisfactory predictions on the test sets, with a lesion classification accuracy of 95.07%, a sensitivity of 94.97%, a specificity of 95.24%, a PPV of 97.42%, and an NPV of 90.91%. An automatic breast tumor detection and classification including automatic tumor volume estimation using deep learning technique yielded satisfactory predictions in distinguishing benign from malignant breast lesions. In addition, automatic tumor volume estimation was performed. Our approach could be integrated into the conventional breast ultrasound machine to assist the radiologist's decision for breast cancer diagnosis.

Improving the Segmentation Accuracy of Ovarian-Tumor Ultrasound Images Using Image Inpainting.

Diagnostic results can be radically influenced by the quality of 2D ovarian-tumor ultrasound images. However, clinically processed 2D ovarian-tumor ultrasound images contain many artificially recognized symbols, such as fingers, crosses, dashed lines, and letters which assist artificial intelligence (AI) in image recognition. These symbols are widely distributed within the lesion's boundary, which can also affect the useful feature-extraction-utilizing networks and thus decrease the accuracy of lesion classification and segmentation. Image inpainting techniques are used for noise and object elimination from images. To solve this problem, we observed the MMOTU dataset and built a 2D ovarian-tumor ultrasound image inpainting dataset by finely annotating the various symbols in the images. A novel framework called mask-guided generative adversarial network (MGGAN) is presented in this paper for 2D ovarian-tumor ultrasound images to remove various symbols from the images. The MGGAN performs to a high standard in corrupted regions by using an attention mechanism in the generator to pay more attention to valid information and ignore symbol information, making lesion boundaries more realistic. Moreover, fast Fourier convolutions (FFCs) and residual networks are used to increase the global field of perception; thus, our model can be applied to high-resolution ultrasound images. The greatest benefit of this algorithm is that it achieves pixel-level inpainting of distorted regions without clean images. Compared with other models, our model achieveed better results with only one stage in terms of objective and subjective evaluations. Our model obtained the best results for 256 × 256 and 512 × 512 resolutions. At a resolution of 256 × 256, our model achieved 0.9246 for SSIM, 22.66 for FID, and 0.07806 for LPIPS. At a resolution of 512 × 512, our model achieved 0.9208 for SSIM, 25.52 for FID, and 0.08300 for LPIPS. Our method can considerably improve the accuracy of computerized ovarian tumor diagnosis. The segmentation accuracy was improved from 71.51% to 76.06% for the Unet model and from 61.13% to 66.65% for the PSPnet model in clean images.

1041 Impact of Spectral Contamination and Anatomical Location on Diagnostic Accuracy of Single-Voxel Spectroscopy in Pre-Operative Glioma Characterisation

Abstract Aim Single-voxel spectroscopy (SVS) discriminates amongst brain tumours by measuring metabolite variations reflective of malignant transformation. However, spectral contamination may affect diagnostic accuracy, impacting radiological opinion of regions of interest (ROI) required to determine extent of surgical resection. Method A single-centre, retrospective, observational study, including 93 SVS meaningfully interpretable examinations between 2012 and 2018. Accuracy of lesion classification was assessed by comparison of histological diagnosis as reference standards against discrimination between entities and tumour grades by SVS, with consideration for voxel location, volume, and proximity to the calvaria or ventricular system. Quantification of metabolites was recorded as ratios, and visual inspection, qualitative and descriptive analysis were undertaken. Results SVS demonstrated high entity accuracy (100%) but lower grade accuracy (87%), ranging from periventricular (73%) vs non-periventricular (90%), and subcalvarial (86%) vs subcortical (88%) voxels. CSF contamination caused metabolite dilution and/or enhanced lactate signals from sub-arachnoid or ventricular CSF, especially in areas of increased brain-skull distance; lipid contamination from peri-calvarial fat and subcutaneous tissue resulted in enhanced lipid signals neighbouring areas of increased brain-scalp distance. Misclassified lesions were located regions of increased cranial concavity, reduced cerebral cortical thickness and inappropriate outer volume suppression (OVS). Voxel volume variation had no impact across cerebral coordinates (p=0.605), calvaria proximity (p=0.127) or ventricular proximity (p=0.367). Conclusion Spectral contamination significantly impacted grade accuracy, with metabolite dilution and enhance lactate and lipids signals leading to radiological under- and overestimation of glioma grade, respectively, thus indicating that avoidance of contaminating tissues and OVS are pivotal to adequate spectral quality for diagnostic accuracy.

Improving Skin Color Diversity in Cancer Detection: Deep Learning Approach

Background The lack of dark skin images in pathologic skin lesions in dermatology resources hinders the accurate diagnosis of skin lesions in people of color. Artificial intelligence applications have further disadvantaged people of color because those applications are mainly trained with light skin color images. Objective The aim of this study is to develop a deep learning approach that generates realistic images of darker skin colors to improve dermatology data diversity for various malignant and benign lesions. Methods We collected skin clinical images for common malignant and benign skin conditions from DermNet NZ, the International Skin Imaging Collaboration, and Dermatology Atlas. Two deep learning methods, style transfer (ST) and deep blending (DB), were utilized to generate images with darker skin colors using the lighter skin images. The generated images were evaluated quantitively and qualitatively. Furthermore, a convolutional neural network (CNN) was trained using the generated images to assess the latter’s effect on skin lesion classification accuracy. Results Image quality assessment showed that the ST method outperformed DB, as the former achieved a lower loss of realism score of 0.23 (95% CI 0.19-0.27) compared to 0.63 (95% CI 0.59-0.67) for the DB method. In addition, ST achieved a higher disease presentation with a similarity score of 0.44 (95% CI 0.40-0.49) compared to 0.17 (95% CI 0.14-0.21) for the DB method. The qualitative assessment completed on masked participants indicated that ST-generated images exhibited high realism, whereby 62.2% (1511/2430) of the votes for the generated images were classified as real. Eight dermatologists correctly diagnosed the lesions in the generated images with an average rate of 0.75 (360 correct diagnoses out of 480) for several malignant and benign lesions. Finally, the classification accuracy and the area under the curve (AUC) of the model when considering the generated images were 0.76 (95% CI 0.72-0.79) and 0.72 (95% CI 0.67-0.77), respectively, compared to the accuracy of 0.56 (95% CI 0.52-0.60) and AUC of 0.63 (95% CI 0.58-0.68) for the model without considering the generated images. Conclusions Deep learning approaches can generate realistic skin lesion images that improve the skin color diversity of dermatology atlases. The diversified image bank, utilized herein to train a CNN, demonstrates the potential of developing generalizable artificial intelligence skin cancer diagnosis applications. International Registered Report Identifier (IRRID) RR2-10.2196/34896

A Deep Learning Approach Based on Explainable Artificial Intelligence for Skin Lesion Classification

The skin lesion types result in delayed diagnosis due to high similarity in early stages of the skin cancer. In this regard, deep learning algorithms are well-recognized solutions; however, these black box approaches result in lack of trust as dermatologists are unable to interpret and validate the decisions made by the models. In this paper, an explainable artificial intelligence (XAI) based skin lesion classification system is proposed to improve the skin lesion classification accuracy. This will help the dermatologists to make rational diagnosis in the early stages of skin cancer. The proposed XAI model is validated using International Skin Imaging Collaboration (ISIC) 2019 dataset. The developed model correctly identifies the eight types of skin lesions (dermatofibroma, squamous cell carcinoma, benign keratosis, melanocytic nevus, vascular lesion, actinic keratosis, basal cell carcinoma and melanoma) with classification accuracy, precision, recall and F1 score as 94.47%, 93.57%, 94.01%, and 94.45% respectively. These predictions are further analyzed using the local interpretable model-agnostic explanations (LIME) framework to generate visual explanations that match a prior belief and general explanation best practices. The explainability integrated within our model will enhance its applicability in real clinical practice.

Blind source separation with mixture models – A hybrid approach to MR brain classification

The development of automated segmentation approaches, which do not suffer from excessive computational burden and intra- and inter-observer variability, is the holy grail of multispectral MR image classification. A new segmentation approach to the data set of MR brain images using a combination of Independent Component Analysis (ICA) with a generalized version of the popular Gaussian Mixture Model (GMM) for unsupervised classification is proposed to be superior to conventional methods in this paper. We propose to optimize the parameters of the mixture model using a meta-heuristic approach like the Particle Swarm Optimization (PSO) to escape the problem of local traps (maxima or minima). Experiments were carried out initially on a synthetic MR Brainweb image set as proof of concept and subsequently on 152 sets of clinical MR images with T1w, T2w and FLAIR sequences. The major advantage of the proposed algorithm is the increased accuracy of lesion classification – average of 94.79% (±1.7) against 85.85% (±3.1) without ICA. As a result of the incorporation of ICA, the inherent computational overhead was also lowered as evidenced by faster convergence. Comparative studies using quantitative and qualitative analysis against conventional algorithms establish the superiority of the proposed approach.

Total variation based DCE-MRI decomposition by separating lesion from background for time-intensity curve estimation.

This study aims to obtain the accurate time intensity curve (TIC) of a dynamic contrast-enhanced magnetic resonance image (DCE-MRI) by eliminating the normal tissue enhancement and obtaining pure lesion information. The TIC of DCE-MRI is sometimes distorted because of the influence of normal tissue. In this paper, a new tracer-kinetic modeling based on total variation (DC-TV) is proposed to address this problem by decomposing the DCE-MRI into the normal tissue image and the lesion image. As TIC generation is not standardized and a credible program is expected, an accurate TIC generation is presented in this paper. We propose a new tracer-kinetic model DC-TV to decompose the lesion region in breast DCE-MRIs. The original image is decomposed into a normal tissue image and a lesion image to obtain the pure lesion enhancement information. The acquired lesion images are smooth and correspond to the diffusion of the contrast agent in the lesion. The normal tissue image sequences are stable and correspond to the enhanced normal tissue. To speed up the computational process of our convergent algorithm, the split Bregman iteration algorithm is applied. To compare the algorithm results, images generated by decomposed methods without normal tissue constraint based on total variation are compared with those generated by our method. The performance of the proposed method is evaluated by the correlation of normal tissue images with the lesion classification accuracy of lesion images. Ninety-eight lesions, including 40 benign and 58 malignant, are evaluated. The dataset includes various typical pathologies of the breast such as invasive ductal carcinoma, ductal carcinoma in situ, tubular carcinoma, phyllodes tumor, hyperplasia, and fibroadenoma, among others. The area under the ROC for the pure lesion enhancement images acquired by DC-TV is greater than that acquired by the original DCE-MRIs. The pure enhancement information from the original breast DCE-MRI lesions can be successfully obtained using our DC-TV. The TICs based on the acquired pure enhancement information closely conform to three-time-point model, which is a classic diagnosis rule. The experiment shows that DC-TV provide a credible TIC generation program.

Computer Based Melanocytic and Nevus Image Enhancement and Segmentation.

Digital dermoscopy aids dermatologists in monitoring potentially cancerous skin lesions. Melanoma is the 5th common form of skin cancer that is rare but the most dangerous. Melanoma is curable if it is detected at an early stage. Automated segmentation of cancerous lesion from normal skin is the most critical yet tricky part in computerized lesion detection and classification. The effectiveness and accuracy of lesion classification are critically dependent on the quality of lesion segmentation. In this paper, we have proposed a novel approach that can automatically preprocess the image and then segment the lesion. The system filters unwanted artifacts including hairs, gel, bubbles, and specular reflection. A novel approach is presented using the concept of wavelets for detection and inpainting the hairs present in the cancer images. The contrast of lesion with the skin is enhanced using adaptive sigmoidal function that takes care of the localized intensity distribution within a given lesion's images. We then present a segmentation approach to precisely segment the lesion from the background. The proposed approach is tested on the European database of dermoscopic images. Results are compared with the competitors to demonstrate the superiority of the suggested approach.

Weighted locality-constrained linear coding for lesion classification in CT images.

Computed tomography is a popular imaging modality for detecting abnormalities associated with abdominal organs such as the liver, kidney and uterus. In this paper, we propose a novel weighted locality-constrained linear coding (LLC) method followed by a weighted max-pooling method to classify liver lesions into three classes: cysts, metastases, hemangiomas. We first divide the lesions into same-size patches. Then, we extract the raw features in all patches followed by Principal Components Analysis (PCA) and apply K means to obtain a single LLC dictionary. Since the interior lesion patches and the boundary patches contribute different information in the image, we assign different weights on these two types of patches to obtain the LLC codes. Moreover, a weighted max pooling approach is also proposed to further evaluate the importance of these two types of patches in feature pooling. Experiments on 109 images of liver lesions were carried out to validate the proposed method. The proposed method achieves a best lesion classification accuracy of 96.33%, which appears to be superior compared with traditional image coding methods: LLC method and Bag-of-words method (BoW) and traditional features: Local Binary Pattern (LBP) features, uniform LBP and complete LBP, demonstrating that the proposed method provides better classification.

A new automated method for the segmentation and characterization of breast masses on ultrasound images

Segmentation is one of the first steps in most computer-aided diagnosis systems for characterization of masses as malignant or benign. In this study, the authors designed an automated method for segmentation of breast masses on ultrasound (US) images. The method automatically estimated an initial contour based on a manually identified point approximately at the mass center. A two-stage active contour method iteratively refined the initial contour and performed self-examination and correction on the segmentation result. To evaluate the method, the authors compared it with manual segmentation by two experienced radiologists (R1 and R2) on a data set of 488 US images from 250 biopsy-proven masses (100 malignant and 150 benign). Two area overlap ratios (AOR1 and AOR2) and an area error measure were used as performance measures to evaluate the segmentation accuracy. Values for AOR1, defined as the ratio of the intersection of the computer and the reference segmented areas to the reference segmented area, were 0.82 +/- 0.16 and 0.84 +/- 0.18, respectively, when manually segmented mass regions by R1 and R2 were used as the reference. Although this indicated a high agreement between the computer and manual segmentations, the two radiologists' manual segmentation results were significantly (p < 0.03) more consistent, with AOR1 = 0.84 +/- 0.16 and 0.91 +/- 0.12, respectively, when the segmented regions by R1 and R2 were used as the reference. To evaluate the segmentation method in terms of lesion classification accuracy, feature spaces were formed by extracting texture, width-to-height, and posterior shadowing features based on either automated computer segmentation or the radiologists' manual segmentation. A linear discriminant analysis classifier was designed using stepwise feature selection and two-fold cross validation to characterize the mass as malignant or benign. For features extracted from computer segmentation, the case-based test A(z) values ranged from 0.88 +/- 0.03 to 0.92 +/- 0.02, indicating a comparable performance to those extracted from manual segmentation by radiologists (A(z) value range: 0.87 +/- 0.03 to 0.90 +/- 0.03).

Liver Tumor Characterization

In our multi center trial we compared the potentials of biphasic contrast-enhanced computed tomography (CT) and a novel tissue-specific magnetic resonance imaging (MRI) contrast agent gadoxetic acid disodium in liver lesion characterization. A total of 176 patients with 252 liver lesions were analyzed. There were 104 malignant and 148 benign lesions. High-field strength (1.0 T or 1.5 T) MR systems with T1-and T2-weighted sequences were used with and without fat suppression. After gadoxetic acid disodium injection, dynamic imaging and hepatocyte phase MR imaging were performed. Biphasic with 150 mg I/kg of body weight (100-200 mL) spiral CT was also performed. Image reading consisted of on-site (by study investigators) and fully blinded off-site (by E.S.P; C.R; and A.S) evaluations. The classification (benign or malignant) and characterization (lesion type) outcomes of both techniques were assessed. All imaging results were verified against a standard of reference. Both on-site and off-site evaluations demonstrated increases in the lesion classification accuracy with gadoxetic acid disodium-enhanced MRI when compared with spiral CT. This improvement was also shown for characterization. Gadoxetic acid disodium was well tolerated. Gadoxetic acid disodium offers a safe and diagnostically powerful tool for the evaluation of patients with focal liver lesions with a reliable assessment of lesion classification and characterization.