Report Generation Process Research Articles

AI-Powered Synthesis of Structured Multimodal Breast Ultrasound Reports Integrating Radiologist Annotations and Deep Learning Analysis.

Breast cancer is the most prevalent cancer among women worldwide. B-mode ultrasound (US) is essential for early detection, offering high sensitivity and specificity without radiation exposure. This study introduces a semi-automatic method to streamline breast US report generation, aiming to reduce the burden on radiologists. Our method synthesizes comprehensive breast US reports by combining the extracted information from radiologists' annotations during routine screenings with the analysis results from deep learning algorithms on multimodal US images. Key modules in our method include image classification using visual features (ICVF), type classification via deep learning (TCDL), and automatic report structuring and compilation (ARSC). Experiments showed that the proposed method reduced the average report generation time to 3.8 min compared to manual processes, even when using relatively low-spec hardware. Generated reports perfectly matched ground truth reports for suspicious masses without a single failure on our evaluation datasets. Additionally, the deep-learning-based algorithm, utilizing DenseNet-121 as its core model, achieved an overall accuracy of 0.865, precision of 0.868, recall of 0.847, F1-score of 0.856, and area under the receiver operating characteristics of 0.92 in classifying tissue stiffness in breast US shear-wave elastography (SWE-mode) images. These improvements not only streamline the report generation process but also allow radiologists to dedicate more time and focus on patient care, ultimately enhancing clinical outcomes and patient satisfaction.

Multi-modal transformer architecture for medical image analysis and automated report generation

Medical practitioners examine medical images, such as X-rays, write reports based on the findings, and provide conclusive statements. Manual interpretation of the results and report generation by examiners are time-consuming processes that lead to potential delays in diagnosis. We propose an automated report generation model for medical images leveraging an encoder–decoder architecture. Our model utilizes transformer architectures, including Vision Transformer (ViT) and its variants like Data Efficient Image Transformer (DEiT) and BERT pre-training image transformer (BEiT), as an encoder. These transformers are adapted for processing to extract and gain visual information from medical images. Reports are transformed into text embeddings, and the Generative Pre-trained Transformer (GPT2) model is used as a decoder to generate medical reports. Our model utilizes a cross-attention mechanism between the vision transformer and GPT2, which enables it to create detailed and coherent medical reports based on the visual information extracted by the encoder. In our model, we have extended the report generation with general knowledge, which is independent of the inputs and provides a comprehensive report in a broad sense. We conduct our experiments on the Indiana University X-ray dataset to demonstrate the effectiveness of our models. Generated medical reports from the model are evaluated using word overlap metrics such as Bleu scores, Rouge-L, retrieval augmentation answer correctness, and similarity metrics such as skip thought cs, greedy matching, vector extrema, and RAG answer similarity. Results show that our model is performing better than the recurrent models in terms of report generation, answer similarity, and word overlap metrics. By automating the report generation process and incorporating advanced transformer architectures and general knowledge, our approach has the potential to significantly improve the efficiency and accuracy of medical image analysis and report generation.

Development of an Application for The Management of ZISWAF at LazNas PHR

The advancement of information technology has revolutionized the way institions and agencies operate. To keep up this progress, LazNas PHR needed to develop an application for ZISWaf Management. The conventional reception process was inefficient and did not use the internet, resulting in delayed reports and distributions. A website based ZISWaf management application was created to streamline the acceptance, data collection, distribution, and report generation process. The development process included needs analysis, design, development, testing and conclusion drawing. The application was developed using the single-page application system development method and was tested through user acceptance tests. Results of the tests showed positive evolution, indicating that the application successfully assisted officers in managing the ZISWaf. Application has successfully integrated the use of information technology into the management of ZISWaf at LazNas PHR, contributing to the advancement and modernization of the institution

Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance.

Automatic report generation has arisen as a significant research area in computer-aided diagnosis, aiming to alleviate the burden on clinicians by generating reports automatically based on medical images. In this work, we propose a novel framework for automatic ultrasound report generation, leveraging a combination of unsupervised and supervised learning methods to aid the report generation process. Our framework incorporates unsupervised learning methods to extract potential knowledge from ultrasound text reports, serving as the prior information to guide the model in aligning visual and textual features, thereby addressing the challenge of feature discrepancy. Additionally, we design a global semantic comparison mechanism to enhance the performance of generating more comprehensive and accurate medical reports. To enable the implementation of ultrasound report generation, we constructed three large-scale ultrasound image-text datasets from different organs for training and validation purposes. Extensive evaluations with other state-of-the-art approaches exhibit its superior performance across all three datasets. Code and dataset are valuable at this link.

AERMNet: Attention-enhanced relational memory network for medical image report generation

Background and objectivesThe automatic generation of medical image diagnostic reports can assist doctors in reducing their workload and improving the efficiency and accuracy of diagnosis. However, among the most existing report generation models, there are problems that the weak correlation between generated words and the lack of contextual information in the report generation process. MethodsTo address the above problems, we propose an Attention-Enhanced Relational Memory Network (AERMNet) model, where the relational memory module is continuously updated by the words generated in the previous time step to strengthen the correlation between words in generated medical image report. And the double LSTM with interaction module reduces the loss of context information and makes full use of feature information. Thus, more accurate disease information can be generated by AERMNet for medical image reports. ResultsExperimental results on four medical datasets Fetal heart (FH), Ultrasound, IU X-Ray and MIMIC-CXR, show that our proposed method outperforms some of the previous models with respect to language generation metrics (Cider improving by 2.4% on FH, Bleu1 improving by 2.4% on Ultrasound, Cider improving by 16.4% on IU X-Ray, Bleu2 improving by 9.7% on MIMIC-CXR). ConclusionsThis work promotes the development of medical image report generation and expands the prospects of computer-aided diagnosis applications. Our code is released at https://github.com/llttxx/AERMNET.

Deep understanding of radiology reports: leveraging dynamic convolution in chest X-ray images

PurposeThe purpose of this study is to investigate and demonstrate the advancements achieved in the field of chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Typical convolutional neural networks (CNNs) are unable to capture both local and global contextual information effectively and apply a uniform operation to all pixels in an image. To address this, we propose an innovative approach that integrates a dynamic convolution operation at the encoder stage, improving image encoding quality and disease detection. In addition, a decoder based on the gated recurrent unit (GRU) is used for language modeling, and an attention network is incorporated to enhance consistency. This novel combination allows for improved feature extraction, mimicking the expertise of radiologists by selectively focusing on important areas and producing coherent captions with valuable clinical information.Design/methodology/approachIn this study, we have presented a new report generation approach that utilizes dynamic convolution applied Resnet-101 (DyCNN) as an encoder (Verelst and Tuytelaars, 2019) and GRU as a decoder (Dey and Salemt, 2017; Pan et al., 2020), along with an attention network (see Figure 1). This integration innovatively extends the capabilities of image encoding and sequential caption generation, representing a shift from conventional CNN architectures. With its ability to dynamically adapt receptive fields, the DyCNN excels at capturing features of varying scales within the CXR images. This dynamic adaptability significantly enhances the granularity of feature extraction, enabling precise representation of localized abnormalities and structural intricacies. By incorporating this flexibility into the encoding process, our model can distil meaningful and contextually rich features from the radiographic data. While the attention mechanism enables the model to selectively focus on different regions of the image during caption generation. The attention mechanism enhances the report generation process by allowing the model to assign different importance weights to different regions of the image, mimicking human perception. In parallel, the GRU-based decoder adds a critical dimension to the process by ensuring a smooth, sequential generation of captions.FindingsThe findings of this study highlight the significant advancements achieved in chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Experiments conducted using the IU-Chest X-ray datasets showed that the proposed model outperformed other state-of-the-art approaches. The model achieved notable scores, including a BLEU_1 score of 0.591, a BLEU_2 score of 0.347, a BLEU_3 score of 0.277 and a BLEU_4 score of 0.155. These results highlight the efficiency and efficacy of the model in producing precise radiology reports, enhancing image interpretation and clinical decision-making.Originality/valueThis work is the first of its kind, which employs DyCNN as an encoder to extract features from CXR images. In addition, GRU as the decoder for language modeling was utilized and the attention mechanisms into the model architecture were incorporated.

TATA KELOLA REKAM MEDIS BERBASIS ELEKTRONIK DALAM PEMBUATAN LAPORAN POLIKLINIK PASIEN RAWAT JALAN MENGGUNAKAN METODE AGILE

This study aims to determine the governance of electronic-based medical records in making outpatient polyclinic reports using the agile method. The research method used is qualitative research with a descriptive approach. After analyzing the needs of the polyclinic reporting system, this study presents the steps of implementing the agile method of extreme programming. By using this method, a system that is adaptable, responsive, and focused on user needs can be developed. The results show that the use of the agile extreme programming method in the development of an electronic-based medical record system provides significant benefits. The process of planning, designing, coding, testing, and releasing is done iteratively and collaboratively. With this approach, the system can be continuously improved and adjusted to meet changing user needs and priorities. By describing the system design flowmap, context diagram, DFD and ERD to visualize the relationship between the components in the system that provides a systematic description of the stages of the report generation process. In conclusion, electronic-based medical record governance in making outpatient polyclinic reports using the agile extreme programming method is an effective and efficient approach. By combining the advantages of agile and extreme programming methods, an adaptive and responsive system can be developed.

Machine-Supported Bridge Inspection Image Documentation Using Artificial Intelligence

The purpose of a routine bridge inspection is to assess the physical and functional condition of a bridge according to a regularly scheduled interval. The Federal Highway Administration (FHWA) requires these inspections to be conducted at least every 2 years. Inspectors use simple tools and visual inspection techniques to determine the conditions of both the elements of the bridge structure and the bridge overall. While in the field, the data is collected in the form of images and notes; after the field work is complete, inspectors need to generate a report based on these data to document their findings. The report generation process includes several tasks: (1) evaluating the condition rating of each bridge element according to FHWA Recording and Coding Guide for Structure Inventory and Appraisal of the Nation’s Bridges; and (2) updating and organizing the bridge inspection images for the report. Both of tasks are time-consuming. This study focuses on assisting with the latter task by developing an artificial intelligence (AI)-based method to rapidly organize bridge inspection images and generate a report. In this paper, an image organization schema based on the FHWA Recording and Coding Guide for the Structure Inventory and Appraisal of the Nation’s Bridges and the Manual for Bridge Element Inspection is described, and several convolutional neural network-based classifiers are trained with real inspection images collected in the field. Additionally, exchangeable image file (EXIF) information is automatically extracted to organize inspection images according to their time stamp. Finally, the Automated Bridge Image Reporting Tool (ABIRT) is described as a browser-based system built on the trained classifiers. Inspectors can directly upload images to this tool and rapidly obtain organized images and associated inspection report with the support of a computer which has an internet connection. The authors provide recommendations to inspectors for gathering future images to make the best use of this tool.

Information System Design Of Online Survey On Employee Performance Web-Based Online Survey

This paper aims to describe a web-based online survey information system that has been designed reliably, so as to produce faster, more accurate and relevant information and reports as needed. The sources and types of data used were obtained through field studies and literature studies. Among them by conducting direct observations and interviews on the object of research and supported by appropriate literature. While the data analysis method used is descriptive qualitative method.
 From the results of the research that the researchers have done, it is found that the constraints of the system that are currently running, include: a lot of paper is wasted due to making survey questionnaires, the survey filling process must be awaited and must be face to face, the report generation process is too long because the calculations are still ongoing. manuals, and so on.
 Circumstances like this have prompted the author to create an online survey information system and it is hoped that this information system will be able to overcome the above problems and anticipate them.

Village Fund Allocation Information System Design

Village development has a very important and strategic role in the context of National Development and Regional Development. In village development, the village government is located as a subsystem of the government administration system in Indonesia, so that the village has the authority, duties and obligations to regulate and manage the interests of its own community. In carrying out the authority, duties, and obligations of the village in the administration of government and development, a source of village income is needed. In the process of managing the Village (Gampong) Fund Allocation, Peukan Bada District, Aceh Besar District, the village government is faced with the condition of the community's education level being still weak. Based on previous research, this research has a purpose, namely to describe and analyze the Management of Village Fund Allocation in empowering rural communities; the driving and inhibiting factors for the management of Village Fund Allocation in empowering rural communities in Peukan Bada District, Aceh Besar District. The objectives to be achieved from this research are; create an online budget data processing information system design, and improve all aspects of data forms or expand the relationship or relationship of each data. The design method used is the waterfall model taking basic activities such as specification, development, validation, and evolution and representing them as phases such as requirements specification, software design, implementation, testing and so on. Based on the results of the analysis and design of the village fund allocation information system, it can be seen that until now it is still done manually. The author can conclude including; the design of the village fund allocation application can provide convenience in carrying out the implementation process of gampong development, and the use of a system that is still manual has limitations in the data storage process, data search and report generation process.

Perancangan E-Distribution Sebagai Media Promosi Dan Penjualan (Studi Kasus : A3 Cell)

AbstractOne way that is currently being widely used in an effort to support and increase company income is the use of internet facilities in the trade sector. By utilizing the internet as a medium to market products in large quantities and distribute them to online buyers, it is called E-Distribution. E-Distribution A3 Cell as a store engaged in selling internet quota and cellphone accessories currently does not own and use information media and technology in terms of information dissemination. So far, the system used is in the form of disseminating information from one consumer to another and is limited to the area around A3 Cell. A3 Cell relies on manual information, transactions in A3 Cell are still recorded in the Ledger, the search and report generation process takes a long time. Based on this, an E-distribution-based system is needed that can assist A3 Cell in providing updated product information and improving services to consumers without time and place restrictions. The results of the research that have been designed and tested show that the information system that has been created provides convenience in the sales process, data management of the distribution of goods as well as based on the results of the black box.

SISTEM INFORMASI PENJUALAN DAN PEMBELIAN OBAT PADA APOTEK DIKA FARMA PONTIANAK BERBASIS WEB

ABSTRACT Pharmacies play a very important role in health services. Pharmacy as a form of business that has a high complexity also requires an information system in its business activities. All forms of recording, starting from recording incoming drug data, purchasing transactions, selling, searching for drug data and checking stocks to making reports are still done manually. This designed system aims to produce a drug sales and purchase information system at a web-based pharmacy in which it is integrated with an expired drug notification system, computerized recording of sales and purchase transactions, purchase and sales reports, assisting drug data management, and providing information to the public. regarding the availability of stock and the price of the drug sought at the Dika Farma Pontianak Pharmacy only through the web. This application is made using the stages of the Waterfall model which can produce data that is easily accessible, accurate, and fast in the report generation process.

WEB 3.0 IN LEARNING ENVIRONMENTS: A SYSTEMATIC REVIEW

Web 3.0 technologies have inevitably affected educational research. Many studies have been conducted on the use of Web 3.0 tools in learning environments. The synthesis and summarization of the results of these studies with a systematic review is considered important in terms of being the source of future research and helping to spread the use of these technologies in education. Hence the purpose of this systematic review is to obtain a better understanding of how Web 3.0 technologies can be used to enhance quality of educational settings. The systematic analysis was conducted by 81 papers from 2005 to 2020. The PRISMA Statement was used in the research and report generation process. Papers related to semantic, augmented reality, intelligent tutoring system, 3d visual environments, 3d games and ontologies is included in the study. The results show that in 2008 and 2013 there was an increase in the number of studies. In addition, most experimental studies have been conducted in this literature and the studies in the discipline of science education are more than other disciplines. When the data collection tools used in the studies were examined, it was found that the majority of the studies were quantitative and most benefited from surveys, questionnaires and observational information in the data collection process. In addition, the majority of studies focus on the learning usefulness and learning outcomes of the software used in the research. Furthermore, suggestions for future researches were made in line with the limitations and results of the study.

Improving Report Generation and Delivery System of Microbiological Investigations at MRI – Sri Lanka with Concern to Turn-Around-Time, An Intervention Study

<p>Background: Clinical Bacteriology Laboratory (CBL) of the Medical Research Institute (MRI) is a National Reference Laboratory in Sri Lanka. The service improvement research project aimed at improving the report generation and delivery system. <br />Methods: The mixed-method applied to study the process. Gap identification and designing of the intervention used a qualitative approach. Quantitative methods measured the effectiveness of the improvements. A package of interventions based on total quality management (TQM) principles designed with all stakeholder participation. <br />Results: Delay in sample transport resulted from poor communication, lack of established mechanism and weak coordination between the transport unit and wards. The paper-based report generation process was disorganized, unreliable and error-prone. Additionally, the report delivery to Hospitals revolved on the incoming ambulance or government postal service a tied-up, poorly coordinated system. The interventions promoted coordinated communication. WHONET, a free windows based Laboratory Information System and database software, developed by the World Health Organization for microbiology laboratories installed to generate reliable and accurate automated reports. Reports in PDF format delivered to end-users by secured email. Timeliness, accuracy, quality and uniformity of reports improved. Improvement in post-intervention turn-around-time was statistically significant (p<0.05). <br />Conclusion: The interventions based on TQM principles improved the process of report generation and delivery. Laboratory automation is a feasible and effective solution in the local setting. The end-user satisfaction perceived to be high on the improvements.</p>

On the importance of standardising the process of generating digital forensic reports

The ISO/IEC 27043:2015 international standard provides new standardised guidelines for common investigation processes across various investigation scenarios that mostly involve digital evidence. The reporting process is one of the many investigative processes described in the ISO/IEC 27043:2015 standard, but the manner in which the reporting process is presented does not constitute or cover the specificity of the presentation of the entire processes covered in the standard. In this paper, we posit the importance of having the report generation process covering details obtained from all other classes of the digital investigation processes in a standardised format, as well as the need to standardise the process of generating digital forensic reports. Such a standardised process can facilitate future automation and text analytics, sharing of reports and knowledge across jurisdictions, etc. We also identify a number of key factors, such as the use of Blockchain, which should be added to the ISO/IEC 27043 international standard in order to support a standardised digital forensic report generation process.

Application of LabVIEW-Based Word Report Toolkit in Testing Engineering

Word Report Toolkit is a LabVIEW-based Word format test report generation toolkit developed by the author. This paper briefly describes several methods to generate test reports under LabVIEW environment, introduces the structural composition and technical principle of Word Report Toolkit, provides the implementation program of test report generation system and the test report generation process, and demonstrates the application of this toolkit in test engineering through some examples. It is shown in practices that Word Report Toolkit is simple in structure, easy in installation, flexible in use, convenient in programming and operation, strong in versatility, and can also automatically generate Word format test reports including charts by the custom design of users under LabVIEW environment.

A Report Generator for Database and Web Applications

Report generation is one of the most important tasks for database and e-commerce applications. Current report tools typically provide a set of predefined components that are used to specify report layout and format. However, available layout options are limited, and WYSIWYG formatting is not allowed. This paper proposes a four-phase report generation process to overcome these problems. The first phase retrieves source tables from the database. The second phase reorganizes the layout of the source tables by transferring the source tables into a set of new flat tables (in the first normal form). The third phase restructures the flat tables into a nested table (report) by specifying the report structure. The last phase formats the report with a WYSIWYG format editor supporting a number of formatting rules designed specifically for nested reports. Each phase of the proposed process supports visual programming, giving an easy-to-use user interface and allowing very flexible report layouts and formats. A visual end-user-programming tool, called TPS, is developed to demonstrate the proposed process and show that reports with sophisticated layouts can be created without writing low-level report generation programs.

Comprehensive Audit Process Guides Facilities in Focusing Priorities

How do you consistently and effectively manage biomed programs spread across 27 hospitals under three different supervisors? The team at the University of Vermont Technical Services Program (TSP) has spent the last few years developing and refining a system to do exactly that. Their solution—a comprehensive audit program—ensures that managers regularly review key organizational metrics at every site, systematically assessing the quality of the program and identifying opportunities for improvement. The results: better-trained employees and an improved program.

Monitoring Clinical Trial Data Using an Unblinded Industry Statistician

The three-statistician model of monitoring data from an ongoing trial generated strong reactions from the statistical community. At controversy is the recommendation that an independent statistician serves as unblinded liaison to the data monitoring committee (DMC). We share our experience with using an industry statistician as the unblinded liaison in a study on the early treatment of patent ductus arteriosus in premature infants. The DMC membership included an academic consulting statistician. A DMC charter was drawn up laying down the expectations for committee members. The study statisticians were not involved in dealings with the DMC. Only the liaison statistician responsible for generating reports and analyses was aware of the grouped results A versus B. A report generation process was established ensuring a firewall for maintaining confidentiality of results. In certain situations, employing an industry statistician as the unblinded liaison to the DMC is a viable option for monitoring data.Learning...

Economics of Radiology Report Editing Using Voice Recognition Technology

As voice recognition technology takes hold in radiology practices, independent and hospital-based practices are faced with a decision of who should be responsible for the report-editing process, radiologists or transcriptionists. Although a radiologist's time is expensive compared with a transcriptionist's, if certain other conditions prevail, it may be possible to eliminate transcriptionists from the report generation process. Among these conditions are political, budgeting, psychosocial, and economic constraints. The author presents an econometric model that examines the economic issues involved in such a decision. Practices, both academic and private, can use this model to help determine which course of action makes the most economic sense. This is not always obvious.