A Cost-Affordable Methodology of 3D Printing of Bone Fractures Using DICOM Files in Traumatology.

Three-dimensional (3D) printing has gained popularity across various domains but remains less integrated into medical surgery due to its complexity. Existing literature primarily discusses specific applications, with limited detailed guidance on the entire process. The methodological details of converting Computed Tomography (CT) images into 3D models are often found in amateur 3D printing forums rather than scientific literature. To address this gap, we present a comprehensive methodology for converting CT images of bone fractures into 3D-printed models. This involves transferring files in Digital Imaging and Communications in Medicine (DICOM) format to stereolithography format, processing the 3D model, and preparing it for printing. Our methodology outlines step-by-step guidelines, time estimates, and software recommendations, prioritizing free open-source tools. We also share our practical experience and outcomes, including the successful creation of 72 models for surgical planning, patient education, and teaching. Although there are challenges associated with utilizing 3D printing in surgery, such as the requirement for specialized expertise and equipment, the advantages in surgical planning, patient education, and improved outcomes are evident. Further studies are warranted to refine and standardize these methodologies for broader adoption in medical practice.

Reshaping free-text radiology notes into structured reports with generative question answering transformers.

BACKGROUND: Radiology reports are typically written in a free-text format, making clinical information difficult to extract and use. Recently, the adoption of structured reporting (SR) has been recommended by various medical societies thanks to the advantages it offers, e.g. standardization, completeness, and information retrieval. We propose a pipeline to extract information from Italian free-text radiology reports that fits with the items of the reference SR registry proposed by a national society of interventional and medical radiology, focusing on CT staging of patients with lymphoma. METHODS: Our work aims to leverage the potential of Natural Language Processing and Transformer-based models to deal with automatic SR registry filling. With the availability of 174 Italian radiology reports, we investigate a rule-free generative Question Answering approach based on the Italian-specific version of T5: IT5. To address information content discrepancies, we focus on the six most frequently filled items in the annotations made on the reports: three categorical (multichoice), one free-text (free-text), and two continuous numerical (factual). In the preprocessing phase, we encode also information that is not supposed to be entered. Two strategies (batch-truncation and ex-post combination) are implemented to comply with the IT5 context length limitations. Performance is evaluated in terms of strict accuracy, f1, and format accuracy, and compared with the widely used GPT-3.5 Large Language Model. Unlike multichoice and factual, free-text answers do not have 1-to-1 correspondence with their reference annotations. For this reason, we collect human-expert feedback on the similarity between medical annotations and generated free-text answers, using a 5-point Likert scale questionnaire (evaluating the criteria of correctness and completeness). RESULTS: The combination of fine-tuning and batch splitting allows IT5 ex-post combination to achieve notable results in terms of information extraction of different types of structured data, performing on par with GPT-3.5. Human-based assessment scores of free-text answers show a high correlation with the AI performance metrics f1 (Spearman's correlation coefficients>0.5, p-values<0.001) for both IT5 ex-post combination and GPT-3.5. The latter is better at generating plausible human-like statements, even if it systematically provides answers even when they are not supposed to be given. CONCLUSIONS: In our experimental setting, a fine-tuned Transformer-based model with a modest number of parameters (i.e., IT5, 220 M) performs well as a clinical information extraction system for automatic SR registry filling task. It can extract information from more than one place in the report, elaborating it in a manner that complies with the response specifications provided by the SR registry (for multichoice and factual items), or that closely approximates the work of a human-expert (free-text items); with the ability to discern when an answer is supposed to be given or not to a user query.

Streamlining Radiology Workflows Through the Development and Deployment of Automated Microservices.

Microservices are a software development approach where an application is structured as a collection of loosely coupled, independently deployable services, each focusing on executing a specific purpose. The development of microservices could have a significant impact on radiology workflows, allowing routine tasks to be automated and improving the efficiency and accuracy of radiologic tasks. This technical report describes the development of several microservices that have been successfully deployed in a tertiary cancer center, resulting in substantial time savings for radiologists and other staff involved in radiology workflows. These microservices include the automatic generation of shift emails, notifying administrative staff and faculty about fellows on rotation, notifying referring physicians about outside examinations, and populating report templates with information from PACS and RIS. The report outlines the common thought process behind developing these microservices, including identifying a problem, connecting various APIs, collecting data in a database, writing a prototype and deploying it, gathering feedback and refining the service, putting it in production, and identifying staff who are in charge of maintaining the service. The report concludes by discussing the benefits and challenges of microservices in radiology workflows, highlighting the importance of multidisciplinary collaboration, interoperability, security, and privacy.

Pediatric Hepatoblastoma, Hepatocellular Carcinoma, and Other Hepatic Neoplasms: Consensus Imaging Recommendations from American College of Radiology Pediatric Liver Reporting and Data System (LI-RADS) Working Group.

Appropriate imaging is imperative in evaluating children with a primary hepatic malignancy such as hepatoblastoma or hepatocellular carcinoma. For use in the adult patient population, the American College of Radiology created the Liver Imaging Reporting and Data System (LI-RADS) to provide consistent terminology and to improve imaging interpretation. At present, no similar consensus exists to guide imaging and interpretation of pediatric patients at risk for developing a liver neoplasm or how best to evaluate a pediatric patient with a known liver neoplasm. Therefore, a new Pediatric Working Group within American College of Radiology LI-RADS was created to provide consensus for imaging recommendations and interpretation of pediatric liver neoplasms. The article was drafted based on the most up-to-date existing information as interpreted by imaging experts comprising the Pediatric LI-RADS Working Group. Guidance is provided regarding appropriate imaging modalities and protocols, as well as imaging interpretation and reporting, with the goals to improve imaging quality, to decrease image interpretation errors, to enhance communication with referrers, and to advance patient care. An expanded version of this document that includes broader background information on pediatric hepatocellular carcinoma and rationale for recommendations can be found in Appendix E1 (online).

Open access image repositories: high-quality data to enable machine learning research.

Originally motivated by the need for research reproducibility and data reuse, large-scale, open access information repositories have become key resources for training and testing of advanced machine learning applications in biomedical and clinical research. To be of value, such repositories must provide large, high-quality data sets, where quality is defined as minimising variance due to data collection protocols and data misrepresentations. Curation is the key to quality. We have constructed a large public access image repository, The Cancer Imaging Archive, dedicated to the promotion of open science to advance the global effort to diagnose and treat cancer. Drawing on this experience and our experience in applying machine learning techniques to the analysis of radiology and pathology image data, we will review the requirements placed on such information repositories by state-of-the-art machine learning applications and how these requirements can be met.

ePAD: An Image Annotation and Analysis Platform for Quantitative Imaging.

Medical imaging is critical for assessing the response of patients to new cancer therapies. Quantitative lesion assessment on images is time-consuming, and adopting new promising quantitative imaging biomarkers of response in clinical trials is challenging. The electronic Physician Annotation Device (ePAD) is a freely available web-based zero-footprint software application for viewing, annotation, and quantitative analysis of radiology images designed to meet the challenges of quantitative evaluation of cancer lesions. For imaging researchers, ePAD calculates a variety of quantitative imaging biomarkers that they can analyze and compare in ePAD to identify potential candidates as surrogate endpoints in clinical trials. For clinicians, ePAD provides clinical decision support tools for evaluating cancer response through reports summarizing changes in tumor burden based on different imaging biomarkers. As a workflow management and study oversight tool, ePAD lets clinical trial project administrators create worklists for users and oversee the progress of annotations created by research groups. To support interoperability of image annotations, ePAD writes all image annotations and results of quantitative imaging analyses in standardized file formats, and it supports migration of annotations from various propriety formats. ePAD also provides a plugin architecture supporting MATLAB server-side modules in addition to client-side plugins, permitting the community to extend the ePAD platform in various ways for new cancer use cases. We present an overview of ePAD as a platform for medical image annotation and quantitative analysis. We also discuss use cases and collaborations with different groups in the Quantitative Imaging Network and future directions.

A Web-Based Response-Assessment System for Development and Validation of Imaging Biomarkers in Oncology.

Quantitative imaging biomarkers are increasingly used in oncology clinical trials to assist the evaluation of tumor responses to novel therapies. To identify these biomarkers and ensure smooth clinical translation once they have been validated, it is critical to develop a reliable workflow-efficient imaging platform for integration in clinical settings. Here we will present a web-based volumetric response-assessment system that we developed based on an open-source image viewing platform (WEASIS) and a DICOM image archive (DCM4CHEE). Our web-based response-assessment system offers a DICOM imaging archiving function, standard imaging viewing and manipulation functions, efficient tumor segmentation and quantification algorithms, and a reliable database containing tumor segmentation and measurement results. The prototype system is currently used in our research lab to foster the development and validation of new quantitative imaging biomarkers, including the volumetric computed tomography technique, as a more accurate and early assessment method of solid tumor responses to targeted and immunotherapies.

Institutional Implementation of a Structured Reporting System: Our Experience with the Brain Tumor Reporting and Data System.

RATIONALE AND OBJECTIVES: Analyze the impact of implementing a structured reporting system for primary brain tumors, the Brain Tumor Reporting and Data System, on attitudes toward radiology reports at a single institution. MATERIALS AND METHODS: Following Institutional Review Board approval, an initial 22 question, 5 point (1-worst to 5-best), survey was sent to faculty members, house staff members, and nonphysician providers at our institution who participate in the direct care of brain tumor patients. Results were used to develop a structured reporting strategy for brain tumors which was implemented across an entire neuroradiology section in a staged approach. Nine months following structured reporting implementation, a follow-up 27 question survey was sent to the same group of providers. Keyword search of radiology reports was used to assess usage of Brain Tumor Reporting and Data System over time. RESULTS: Fifty-three brain tumor care providers responded to the initial survey and 38 to the follow-up survey. After implementing BT-RADS, respondents reported improved attitudes across multiple areas including: report consistency (4.3 vs. 3.4; p < 0.001), report ambiguity (4.2 vs. 3.2, p < 0.001), radiologist/physician communication (4.5 vs. 3.8; p < 0.001), facilitation of patient management (4.2 vs. 3.6; p = 0.003), and confidence in reports (4.3 vs. 3.5; p < 0.001). Providers were more satisfied with the BT-RADS structured reporting system (4.3 vs. 3.7; p = 0.04). Use of the reporting template progressively increased with 81% of brain tumor reports dictated using the new template by 9 months. CONCLUSION: Implementing a structured template for brain tumor imaging improves perception of radiology reports among radiologists and referring providers involved in the care of brain tumor patients.

Introduction to the Liver Imaging Reporting and Data System for Hepatocellular Carcinoma.

The Liver Imaging Reporting And Data System (LI-RADS) was created with the support of the American College of Radiology (ACR) to standardize the acquisition, interpretation, reporting, and data collection for imaging examinations in patients at risk for hepatocellular carcinoma (HCC). A comprehensive and rigorous system developed by radiologists, hepatologists, pathologists, and surgeons, LI-RADS addresses a wide range of imaging contexts. Currently, 4 algorithms are available publicly on the ACR website: ultrasound for HCC surveillance, computed tomography and magnetic resonance imaging for HCC diagnosis and tumor staging, contrast-enhanced ultrasound for HCC diagnosis, and computed tomography/magnetic resonance imaging for treatment response assessment. Each algorithm is supported by a decision tree, categorization table, lexicon, atlas, technical requirements, and reporting and management guidance. Category codes reflecting the relative probability of HCC and malignancy are assigned to imaging-detected liver observations, with emerging evidence suggesting that LI-RADS accurately stratifies HCC and malignancy probabilities. LI-RADS is an evolving system and has been updated and refined iteratively since 2011 based on scientific evidence, expert opinion, and user feedback, with input from the American Association for the Study of Liver Diseases and the Organ Procurement Transplantation Network/United Network for Organ Sharing. Concurrent with its most recent update, LI-RADS was integrated into the American Association for the Study of Liver Diseases HCC guidance released in 2018. We anticipate continued refinement of LI-RADS and progressive adoption by radiologists worldwide, with the eventual goal of culminating in a single unified system for international use.

Impact of a Structured Reporting Template on Adherence to Prostate Imaging Reporting and Data System Version 2 and on the Diagnostic Performance of Prostate MRI for Clinically Significant Prostate Cancer.

PURPOSE: The aim of this study was to assess the impact of a structured reporting template on adherence to the Prostate Imaging Reporting and Data System (PI-RADS) version 2 lexicon and on the diagnostic performance of prostate MRI to detect clinically significant prostate cancer (CS-PCa). METHODS: An imaging database was searched for consecutive patients who underwent prostate MRI followed by MRI-ultrasound fusion biopsy from October 2015 through October 2017. The initial MRI reporting template used included only subheadings. In July 2016, the template was changed to a standardized PI-RADS-compliant structured template incorporating dropdown menus. Lesion, patient characteristics, pathology, and adherence to the PI-RADS lexicon were extracted from MRI reports and patient charts. Diagnostic performance of prostate MRI to detect CS-PCa using combined ultrasound-MRI fusion and systematic biopsy as a reference standard was assessed. RESULTS: Three hundred twenty-four lesions in 202 patients (average age, 67 years; average prostate-specific antigen level, 5.9 ng/mL) were analyzed, including 217 MRI peripheral zone (PZ) lesions, 84 MRI non-PZ lesions, and 23 additional PZ lesions found on systematic biopsy but missed on MRI. Thirty-three percent (106 of 324) were CS-PCa. Adherence to the PI-RADS lexicon improved from 32.9% (50 of 152) to 88.4% (152 of 172) (P < .0001) after introduction of the structured template. The sensitivity of prostate MRI for CS-PCa in the PZ increased from 53% to 70% (P = .011). There was no significant change in specificity (60% versus 55%, P = .458). CONCLUSIONS: A structured template with dropdown menus incorporating the PI-RADS lexicon and classification rules improves adherence to PI-RADS and may increase the diagnostic performance of prostate MRI for CS-PCa.

Large-Scale Implementation of Structured Reporting of Adnexal Masses on Ultrasound.

PURPOSE: The aim of this article is to describe the development and implementation of structured reporting of adnexal mass findings on pelvic ultrasound in a large integrated health care delivery system. METHODS: A structured reporting system that includes standardized terminology for describing adnexal masses on ultrasound was developed by a multidisciplinary team of radiologists, gynecologists, and gynecologic oncologists on the basis of literature review and internal data. The system uses a reporting template that requires radiologists to assign abnormal adnexal masses to one of five possible categories on the basis of standardized criteria: category 0, 1, 2, or 3 for masses <10 cm, to reflect increasing concern for malignancy, and category X for masses >10 cm. Unique predefined hashtags were linked to each category to enable electronic data extraction, and a hard stop feature was installed that prevents reports from being finalized without a category designation. In 2014, after a 3-month pilot study, large-scale implementation was supported by an educational campaign consisting of web-based conferences, e-mail announcements, and local presentations. Clinical management recommendations on the basis of category and other clinical factors were provided in a separate practice resource for clinicians. RESULTS: Analysis of adherence revealed that 93% of the approximately 12,000 reports describing abnormal adnexal masses in 2016 included category designations. Feedback from referring providers via an anonymous survey indicated high levels of satisfaction with reports. CONCLUSIONS: Multidisciplinary collaboration and leveraging of technology enabled large-scale implementation of structured reporting with high levels of adherence among radiologists and improved satisfaction among referring providers.

Automated customized retrieval of radiotherapy data for clinical trials, audit and research.

OBJECTIVE: To enable fast and customizable automated collection of radiotherapy (RT) data from tomotherapy storage. METHODS: Human-readable data maps (TagMaps) were created to generate DICOM-RT (Digital Imaging and Communications in Medicine standard for Radiation Therapy) data from tomotherapy archives, and provided access to "hidden" information comprising delivery sinograms, positional corrections and adaptive-RT doses. RESULTS: 797 data sets totalling 25,000 scans were batch-exported in 31.5 h. All archived information was restored, including the data not available via commercial software. The exported data were DICOM-compliant and compatible with major commercial tools including RayStation, Pinnacle and ProSoma. The export ran without operator interventions. CONCLUSION: The TagMap method for DICOM-RT data modelling produced software that was many times faster than the vendor's solution, required minimal operator input and delivered high volumes of vendor-identical DICOM data. The approach is applicable to many clinical and research data processing scenarios and can be adapted to recover DICOM-RT data from other proprietary storage types such as Elekta, Pinnacle or ProSoma. Advances in knowledge: A novel method to translate data from proprietary storage to DICOM-RT is presented. It provides access to the data hidden in electronic archives, offers a working solution to the issues of data migration and vendor lock-in and paves the way for large-scale imaging and radiomics studies.

Utilidad del score PI-RADS 2 en la práctica clínica ¿Se justifica el estudio histológico? / PI-RADS 2 Score utility in clinical practice ¿Is histologic asses justified?

Resumen: Objetivo: Evaluar los resultados de estudios histológicos y si estos se justifican en pacientes categorizados como PI-RADS 2. Materiales y métodos: Se realizó una búsqueda en el PACS de nuestra institución de todos los informes de RM de próstata que incluyeran categoría "PI-RADS 2" entre enero del 2015 y junio del 2017, identificando 1287 informes. Resultados: De los 1287 informes PI-RADS 2, 646 pacientes fueron controlados posterior a la RM en nuestra institución. De ellos, 91 (14,08%) tuvieron un estudio histológico. Se encontraron 10 casos (10,98%) de cáncer prostático (6 con score de Gleason 6, y 4 score de Gleason 7). Conclusión: En nuestro estudio la RM score PI-RADS 2 descartó correctamente neoplasia clínicamente significativa en el 95,6% de los casos. Dar a conocer esta información podría tener un impacto en la conducta del tratante, disminuyendo el número de biopsias prostáticas.

Abstract: Objective: To evaluate the results of histological studies and if these are justified in patients categorized as PI-RADS 2. Materials and methods: A search was made in the PACS of our institution of all prostate MRI reports that included category "PI-RADS 2" between January 2015 and June 2017, identifying 1287 reports. Results: Of the 1287 PI-RADS 2 reports, 646 patients were monitored after the MRI in our institution. Of these, 91 (14.08%) had an histological study. We found 10 cases (10.98%) of prostate cancer (6 with Gleason score 6, and 4 Gleason score 7). Conclusion: In our study, the MR PI-RADS 2 score correctly ruled out clinically significant neoplasia in 95.6% of cases. Making this information known could have an impact on the doctor's course of action, decreasing the number of prostate biopsies.

Unified Database for Rejected Image Analysis Across Multiple Vendors in Radiography.

Reject rate analysis has been part of radiography departments' quality control since the days of screen-film radiography. In the era of digital radiography, one might expect that reject rate analysis is easily facilitated because of readily available information produced by the modality during the examination procedure. Unfortunately, this is not always the case. The lack of an industry standard and the wide variety of system log entries and formats have made it difficult to implement a robust multivendor reject analysis program, and logs do not always include all relevant information. The increased use of digital detectors exacerbates this problem because of higher reject rates associated with digital radiography compared with computed radiography. In this article, the authors report on the development of a unified database for vendor-neutral reject analysis across multiple sites within an academic institution and share their experience from a team-based approach to reduce reject rates.

Rapid Retrieval of Lung Nodule CT Images Based on Hashing and Pruning Methods.

The similarity-based retrieval of lung nodule computed tomography (CT) images is an important task in the computer-aided diagnosis of lung lesions. It can provide similar clinical cases for physicians and help them make reliable clinical diagnostic decisions. However, when handling large-scale lung images with a general-purpose computer, traditional image retrieval methods may not be efficient. In this paper, a new retrieval framework based on a hashing method for lung nodule CT images is proposed. This method can translate high-dimensional image features into a compact hash code, so the retrieval time and required memory space can be reduced greatly. Moreover, a pruning algorithm is presented to further improve the retrieval speed, and a pruning-based decision rule is presented to improve the retrieval precision. Finally, the proposed retrieval method is validated on 2,450 lung nodule CT images selected from the public Lung Image Database Consortium (LIDC) database. The experimental results show that the proposed pruning algorithm effectively reduces the retrieval time of lung nodule CT images and improves the retrieval precision. In addition, the retrieval framework is evaluated by differentiating benign and malignant nodules, and the classification accuracy can reach 86.62%, outperforming other commonly used classification methods.

Enhancement of Structured Reporting - an Integration Reporting Module with Radiation Dose Collection Supporting.

Collection of radiation dose derived from radiological examination is necessary not only for radiation protection, but also for fulfillment of structured reports. However, the material regarding of radiation dose cannot be directly utilized by the Radiological Information System (RIS) since it is generated and only stored in the Picture Archiving and Communication System (PACS). In this paper, an integration reporting module is proposed to facilitate handling of dose information and structured reporting by providing two functionalities. First, a gateway is established to automatically collect the related information from PACS for further analyzing and monitoring the accumulated radiation. Second, the designated structured reporting patterns with corresponding radiation dose measurements can be acquired by radiologists as necessary. In the design, the radiation dose collection gateway and the well-established pattern are collocated to achieve that there is no need to do manual entry for structured reporting, thus increasing productivity and medical quality.

Integrating the Radiology Information System with Computerised Provider Order Entry: The Impact on Repeat Medical Imaging Investigations.

Repeat and redundant procedures in medical imaging are associated with increases in resource utilisation and labour costs. Unnecessary medical imaging in some modalities, such as X-Ray (XR) and Computed Tomography (CT) is an important safety issue because it exposes patients to ionising radiation which can be carcinogenic and is associated with higher rates of cancer. The aim of this study was to assess the impact of implementing an integrated Computerised Provider Order Entry (CPOE)/Radiology Information System (RIS)/Picture Archiving and Communications System (PACS) system on the number of XR and CT imaging procedures (including repeat imaging requests) for inpatients at a large metropolitan hospital. The study found that patients had an average 0.47 fewer XR procedures and 0.07 fewer CT procedures after the implementation of the integrated system. Part of this reduction was driven by a lower rate of repeat procedures: the average inpatient had 0.13 fewer repeat XR procedures within 24-hours of the previous identical XR procedure. A similar decrease was not evident for repeat CT procedures. Reduced utilisation of imaging procedures (especially those within very short intervals from the previous identical procedure, which are more likely to be redundant) has implications for the safety of patients and the cost of medical imaging services.

Diagnostic accuracy of liver imaging reporting and data system (LI-RADS) v2014 for intrahepatic mass-forming cholangiocarcinomas in patients with chronic liver disease on gadoxetic acid-enhanced MRI.

PURPOSE: To investigate the utility of Liver Imaging Reporting and Data System (LI-RADS) v2014 for intrahepatic mass-forming cholangiocarcinomas (IMCC) on gadoxetic acid-enhanced magnetic resonance imaging (MRI). MATERIALS AND METHODS: This retrospective study was approved by our Institutional Review Board with waiver of informed consent. Pathologically confirmed IMCCs (n = 35) and hepatocellular carcinomas (HCCs) (n = 71) in patients with chronic hepatitis B or cirrhosis who had undergone gadoxetic acid-enhanced 3.0T or 1.5T MRI were included. Three radiologists independently assigned LI-RADS categories for each IMCC or HCC. Diagnostic performances of LR-M (probable malignancy, not specific for HCC) and LR-5/5v (definitely HCC) were investigated, and imaging features were compared between IMCCs of LR-M and non-LR-M. RESULTS: In all, 88.6% (31/35), 80.0% (28/35), and 74.3% (26/35) of IMCCs and 12.7% (9/71), 22.5% (16/71), and 16.9% (12/71) of HCCs were assigned as LR-M by the three reviewers with substantial interobserver agreements (kappa = 0.664-0.741). Among IMCCs, 2.9% (1/35), 5.7% (2/35), and 11.4% (4/35) were categorized as LR-5/5v. IMCCs of non-LR-M (n = 8, using the consensus method) were significantly smaller (24.1 ± 17.4 vs. 62.8 ± 30.6 mm, P = 0.002) and showed higher frequencies of arterial hyperenhancement (75.0% (6/8) vs. 7.4% (2/27), P < 0.001) and lower frequencies of non-HCC malignancy-favoring features such as peripheral enhancement (12.5% (1/8) vs. 77.8% (21/27), P = 0.002) or the target appearance on the hepatobiliary phase (0% (0/8) vs. 81.5% (22/27), P < 0.001) than IMCCs of LR-M (n = 27). CONCLUSION: Using LI-RADS, the majority of IMCCs can be accurately categorized as LR-M on gadoxetic acid-enhanced MRI; however, caution is warranted, as some atypical IMCCs may be assigned as LR-5/5v resulting in a false-positive diagnosis of HCC. J. Magn. Reson. Imaging 2016;44:1330-1338.

Risk Analysis for Pathological Changes in Pulmonary Parenchyma Based on Lung Computed Tomography Images.

OBJECTIVE: The purpose of this study is to design a content-based medical image retrieval system, which helps excavate and assess pathological change of pulmonary parenchyma for risks analysis. METHODS: A data set including lung computed tomography images obtained from 115 patients who experienced pathological changes in pulmonary parenchyma is used. Using morphological theory, images are preprocessed and decomposed into groups of pixel blocks (words), which construct vocabulary. A latent Dirichlet allocation (LDA) model is constructed to assess each image for risk analysis with the method of leave-one-out cross-validation. The precision and recall rate are used as the performance assessment criteria. RESULTS: The LDA model generates a relevance rank of retrieval results from high to low. From the top 50 images, precision of identical tissue is 0.76 ± 0.031 and precision of each attribute of pulmonary parenchyma range from 0.776 ± 0.043 to 0.984 ± 0.008. CONCLUSIONS: The study results demonstrate that the proposed LDA model is conductive to lung computed tomography image retrieval and has reliable efficacy on risk analysis about pathological changes of pulmonary parenchyma.

Clinical Evaluation of a 3-D Automatic Annotation Method for Breast Ultrasound Imaging.

The routine clinical breast ultrasound annotation method is limited by the time it consumes, inconsistency, inaccuracy and incomplete notation. A novel 3-D automatic annotation method for breast ultrasound imaging has been developed that uses a spatial sensor to track and record conventional B-mode scanning so as to provide more objective annotation. The aim of the study described here was to test the feasibility of the automatic annotation method in clinical breast ultrasound scanning. An ultrasound scanning procedure using the new method was established. The new method and the conventional manual annotation method were compared in 46 breast cancer patients (49 ± 12 y). The time used for scanning a patient was recorded and compared for the two methods. Intra-observer and inter-observer experiments were performed, and intra-class correlation coefficients (ICCs) were calculated to analyze system reproducibility. The results revealed that the new annotation method had an average scanning time 36 s (42.9%) less than that of the conventional method. There were high correlations between the results of the two annotation methods (r = 0.933, p < 0.0001 for distance; r = 0.995, p < 0.0001 for radial angle). Intra-observer and inter-observer reproducibility was excellent, with all ICCs > 0.92. The results indicated that the 3-D automatic annotation method is reliable for clinical breast ultrasound scanning and can greatly reduce scanning time. Although large-scale clinical studies are still needed, this work verified that the new annotation method has potential to be a valuable tool in breast ultrasound examination.