No abstract

In this paper, we walk you through our challenges, successes, and experience while participating in a Global Health Outreach Project at the University College Hospital (UCH) Ibadan, Nigeria. The scope of the project was to install a Picture Archive and Communication System (PACS) to establish a centralized viewing network at UCH's Radiology Department, for each of their digital modalities. Installing a PACS requires robust servers, the ability to retrieve and archive studies, ensuring workstations can view studies, and the configuration of imaging modalities to send studies. We anticipated that we might experience hurdles for each of these requirements, due to limited resources and without the availability to make a site visit prior to the start of the project. While we ultimately experienced delays and troubleshooting was required at each turn of the install, with the help of dedicated volunteers both on and off-site and the UCH staff, our shared goal was accomplished.

Voice recognition represents a technology that is finally ready for prime time use. As radiology services continue to acquire a larger percentage of the shrinking health-care dollar, decreasing operating costs and improved services wili become a necessity. The benefits of voice recognition implementation are significant, as are the challenges. This report will discuss the technology, experiences of a major health-care institution with implementation, and potential benefits for the radiology practice. In late 1994, the effort to develop large-vocabulary, continuous speech recognition systems in American English had progressed to the point where accuracy had become a less of an issue and vendors could focus on specific markets. In a recent survey, the Healthcare Information Management and Systems Society found in a worldwide membership survey that 31% of respondents were eager to install VR systems in their practicesl; no specialty was more suited than radiology. Until now, radiologists have either handled the process of dictation manually or on tape to medical transcriptionists; the process has been time-consuming and expensive. The choice of transcribing radiology reports with VR systems is an obvious focus due to the consistent and predictable vocabulary within dictation practices. Multiple solutions have been generated and we will discuss our experiences at the Massachusetts General Hospital (MGH) with IBM Medspeak/Radiology (White Plains, NY). We review the VR technology, challenges encountered through deployment, implementation strategies, and experienced benefits. Speech RecognitionSpeech recognition, also referred to as speech-totext, is the technology that makes it possible for the computer to translate spoken word into type. The first type of speech recognition is spoken command recognition, also known as command and control, and the second is pure dictation. Command and control dictation handles the recognition of single words or short phrases spoken with continuous speech, such as "Begin Dictation" or "Accept and Sign." Dictation comes in two divisions: discrete (or isolated) and continuous. The discrete dictation technology has lower processing power requirements, but requires the end-user to place a short pause between each spoken word. Condnuous dictation, as the name implies, does not carry this limitation and is used in the radiology implementation. Speech SynthesisSpeech synthesis, also referred to as text-tospeech, is the technology that makes it possible for the computer to produce the phonemes we would make when we read text aloud. Within radiology, speech synthesis allows the radiologist to review the report, as well as in playback during dictation of reports. Speaker Identification and VerificationSpeaker identification and verification are two related technologies. These technologies, unlike speech recognition and speech synthesis, deal with the identity of the human speaker and not with what was spoken or with synthesizing the particular human voice. With speaker verification, technology ...

No abstract