Voice-Assisted Image Labeling for Endoscopic Ultrasound Classification Using Neural Networks

Ultrasound imaging is a commonly used technology for visualising patient anatomy in real-time during diagnostic and therapeutic procedures. High operator dependency and low reproducibility make ultrasound imaging and interpretation challenging with a steep learning curve. Automatic image classification using deep learning has the potential to overcome some of these challenges by supporting ultrasound training in novices, as well as aiding ultrasound image interpretation in patient with complex pathology for more experienced practitioners. However, the use of deep learning methods requires a large amount of data in order to provide accurate results. Labelling large ultrasound datasets is a challenging task because labels are retrospectively assigned to 2D images without the 3D spatial context available in vivo or that would be inferred while visually tracking structures between frames during the procedure. In this work, we propose a multi-modal convolutional neural network (CNN) architecture that labels endoscopic ultrasound (EUS) images from raw verbal comments provided by a clinician during the procedure. We use a CNN composed of two branches, one for voice data and another for image data, which are joined to predict image labels from the spoken names of anatomical landmarks. The network was trained using recorded verbal comments from expert operators. Our results show a prediction accuracy of 76% at image level on a dataset with 5 different labels. We conclude that the addition of spoken commentaries can increase the performance of ultrasound image classification, and eliminate the burden of manually labelling large EUS datasets necessary for deep learning applications.

Factors affecting accuracy and precision in ultrasound guided radiotherapy

BACKGROUND AND PURPOSE

Transperineal ultrasound (TPUS) is used clinically for directly assessing prostate motion. Factors affecting accuracy and precision in TPUS motion estimation must be assessed to realise its full potential.

METHODS AND MATERIALS

Patients were imaged using volumetric TPUS during the Clarity-Pro trial (NCT02388308). Prostate motion was measured online at patient set-up and offline by experienced observers. Cone beam CT with markers was used as a comparator and observer performance was also quantified. The influence of different clinical factors was examined to establish specific recommendations towards efficacious ultrasound guided radiotherapy.

RESULTS

From 330 fractions in 22 patients, offline observer random errors were 1.5 mm, 1.3 mm, 1.9 mm (left-right, superior-inferior, anteroposterior respectively). Errors increased in fractions exhibiting poor image quality to 3.3 mm, 3.3 mm and 6.8 mm. Poor image quality was associated with inconsistent probe placement, large anatomical changes and unfavourable imaging conditions within the patient. Online matching exhibited increased observer errors of: 3.2 mm, 2.9 mm and 4.7 mm. Four patients exhibited large systematic residual errors, of which three had poor quality images. Patient habitus showed no correlation with observer error, residual error, or image quality.

CONCLUSIONS

TPUS offers the unique potential to directly assess inter- and intra-fraction motion on conventional linacs. Inconsistent image quality, inexperienced operators and the pressures of the clinical environment may degrade precision and accuracy. Experienced operators are essential and cross-centre standards for training and QA should be established that build upon current guidance. Greater use of automation technologies may further minimise uncertainties.

Improving 3D ultrasound prostate localisation in radiotherapy through increased automation of interfraction matching

BACKGROUND AND PURPOSE

Daily image guidance is standard care for prostate radiotherapy. Innovations which improve the accuracy and efficiency of ultrasound guidance are needed, particularly with respect to reducing interobserver variation. This study explores automation tools for this purpose, demonstrated on the Elekta Clarity Autoscan®. The study was conducted as part of the Clarity-Pro trial (NCT02388308).

MATERIALS AND METHODS

Ultrasound scan volumes were collected from 32 patients. Prostate matches were performed using two proposed workflows and the results compared with Clarity's proprietary software. Gold standard matches derived from manually localised landmarks provided a reference. The two workflows incorporated a custom 3D image registration algorithm, which was benchmarked against a third-party application (Elastix).

RESULTS

Significant reductions in match errors were reported from both workflows compared to standard protocol. Median (IQR) absolute errors in the left-right, anteroposterior and craniocaudal axes were lowest for the Manually Initiated workflow: 0.7(1.0) mm, 0.7(0.9) mm, 0.6(0.9) mm compared to 1.0(1.7) mm, 0.9(1.4) mm, 0.9(1.2) mm for Clarity. Median interobserver variation was ≪0.01 mm in all axes for both workflows compared to 2.2 mm, 1.7 mm, 1.5 mm for Clarity in left-right, anteroposterior and craniocaudal axes. Mean matching times was also reduced to 43 s from 152 s for Clarity. Inexperienced users of the proposed workflows attained better match precision than experienced users on Clarity.

CONCLUSION

Automated image registration with effective input and verification steps should increase the efficacy of interfraction ultrasound guidance compared to the current commercially available tools.

Real-time intrafraction motion monitoring in external beam radiotherapy

Radiotherapy (RT) aims to deliver a spatially conformal dose of radiation to tumours while maximizing the dose sparing to healthy tissues. However, the internal patient anatomy is constantly moving due to respiratory, cardiac, gastrointestinal and urinary activity. The long term goal of the RT community to 'see what we treat, as we treat' and to act on this information instantaneously has resulted in rapid technological innovation. Specialized treatment machines, such as robotic or gimbal-steered linear accelerators (linac) with in-room imaging suites, have been developed specifically for real-time treatment adaptation. Additional equipment, such as stereoscopic kilovoltage (kV) imaging, ultrasound transducers and electromagnetic transponders, has been developed for intrafraction motion monitoring on conventional linacs. Magnetic resonance imaging (MRI) has been integrated with cobalt treatment units and more recently with linacs. In addition to hardware innovation, software development has played a substantial role in the development of motion monitoring methods based on respiratory motion surrogates and planar kV or Megavoltage (MV) imaging that is available on standard equipped linacs. In this paper, we review and compare the different intrafraction motion monitoring methods proposed in the literature and demonstrated in real-time on clinical data as well as their possible future developments. We then discuss general considerations on validation and quality assurance for clinical implementation. Besides photon RT, particle therapy is increasingly used to treat moving targets. However, transferring motion monitoring technologies from linacs to particle beam lines presents substantial challenges. Lessons learned from the implementation of real-time intrafraction monitoring for photon RT will be used as a basis to discuss the implementation of these methods for particle RT.

In Vivo Validation of Elekta's Clarity Autoscan for Ultrasound-based Intrafraction Motion Estimation of the Prostate During Radiation Therapy

PURPOSE

Our purpose was to perform an in vivo validation of ultrasound imaging for intrafraction motion estimation using the Elekta Clarity Autoscan system during prostate radiation therapy. The study was conducted as part of the Clarity-Pro trial (NCT02388308).

METHODS AND MATERIALS

Initial locations of intraprostatic fiducial markers were identified from cone beam computed tomography scans. Marker positions were translated according to Clarity intrafraction 3-dimensional prostate motion estimates. The updated locations were projected onto the 2-dimensional electronic portal imager plane. These Clarity-based estimates were compared with the actual portal-imaged 2-dimensional marker positions. Images from 16 patients encompassing 80 fractions were analyzed. To investigate the influence of intraprostatic markers and image quality on ultrasound motion estimation, 3 observers rated image quality, and the marker visibility on ultrasound images was assessed.

RESULTS

The median difference between Clarity-defined intrafraction marker locations and portal-imaged marker locations was 0.6 mm (with 95% limit of agreement at 2.5 mm). Markers were identified on ultrasound in only 3 of a possible 240 instances. No linear relationship between image quality and Clarity motion estimation confidence was identified. The difference between Clarity-based motion estimates and electronic portal-imaged marker location was also independent of image quality. Clarity estimation confidence was degraded in a single fraction owing to poor probe placement.

CONCLUSIONS

The accuracy of Clarity intrafraction prostate motion estimation is comparable with that of other motion-monitoring systems in radiation therapy. The effect of fiducial markers in the study was deemed negligible as they were rarely visible on ultrasound images compared with intrinsic anatomic features. Clarity motion estimation confidence was robust to variations in image quality and the number of ultrasound-imaged anatomic features; however, it was degraded as a result of poor probe placement.

An evaluation of the impact of a community-based adherence support programme on ART outcomes in selected government HIV treatment sites in South Africa

This study assessed the impact of a community-based adherence support service on the outcomes of patients on antiretroviral therapy (ART). The evaluation was a retrospective study based on patient clinical records. This study noted that a significantly higher proportion of patients with a community-based adherence supporter (also known as a patient advocate, PA) had viral load (VL) of less than 400 copies/ml at six months of treatment (70%, p=0.001); a significantly higher proportion of patients with PAs (89%) attained a treatment pickup rate of over 95% (67%; p=0.021). Patients at health facilities with PA services maintained a suppressed VL for a longer period as opposed to patients at health facilities without PA services (p=0.001), also patients at health facilities with PA services remained in care for longer periods (p=0.001). Therefore, the study concludes that integrated community-based adherence support is crucial in ensuring that patients remain in care, regularly pickup their treatment from ART clinics and are virologically suppressed. The study also underscores the importance of access to health services and the presence of an enabling environment in the treatment of AIDS.

Novel mutations identified using a comprehensive CCR5-denaturing gradient gel electrophoresis assay

BACKGROUND

Most mutations detected for the gene for CC chemokine receptor 5 (CCR5) are either relatively specific to different population groups or rarely observed in Africans.

OBJECTIVES

To develop a comprehensive mutation detection assay for the entire coding region of CCR5 and to identify novel mutations that may play a role in genetic susceptibility to HIV-1 infection, within the diverse South African population.

DESIGN

The study cohort consisted of 103 HIV-seropositive patients and 146 HIV-seronegative controls of predominantly African descent.

METHODS

A mutation detection assay for the entire coding region of CCR5 was designed; this included amplification of part of the coding region of CCR2. The assay was based on denaturing gradient gel electrophoresis (DGGE) and allowed the complete analysis of samples from 10 individuals per denaturing gel.

RESULTS

The use of the CCR5-DGGE assay led to the identification of seven novel and six previously reported mutations. All novel mutations, including a common polymorphism at codon 35, occurred exclusively in non-Caucasians, indicating possible African origin.

CONCLUSION

A comprehensive DGGE mutation detection assay has been developed for the entire coding region of CCR5. Application of this assay resulted in the identification of novel CCR5 mutations, which may have a significant effect on the normal functioning of CCR5 and thus contribute to host variability and susceptibility to HIV-1 infection and/or progression to AIDS within this population.

Service level agreements

Service level agreements provide clearer descriptions of the services to be provided and the objectives to be met. In many instances it is the first time that services have been defined allowing their performance to be suitably measured. They should be output based and not too prescriptive on how the services are to be delivered. The emphasis should be on establishing outputs and the arrangements for monitoring achievement. Customer expectations can exceed available resources and arbitration may become necessary if agreement cannot be reached on internal service level agreements. The main requirements of customers for change through service level agreements is usually improved communications on job status that includes notification of any delays and that agreed response times will be met.

The incidence of malignant mesothelioma in Australia 1982-1988

From 1980 to 1985, the Australian Mesothelioma Surveillance Program, and since 1986, the Australian Mesothelioma Register, have been collecting data on all cases of malignant mesothelioma that could be ascertained in Australia. Incidence rates were calculated on 854 Program and 696 Register cases (total 1271) diagnosed in Australia between January 1, 1982 and December 31, 1988. Australia has one of the highest national rates of mesothelioma in the world (15.8 cases per million of population aged 20 years and older), and the rate is rising. The rate is far higher in males (28.3) than females (3.3). The Western Australian rate (28.9) is the highest among the states, as may be expected because of the crocidolite mine at Wittenoom; however, the largest numbers of cases occur in the more populous and industrial New South Wales. The high incidence rate, its expected continuing increase, and absence of a history of exposure to asbestos in approximately 28% of cases, demand consideration of potential environmental factors other than asbestos in the causation of this tumor, as well as continued surveillance.

Operation Nightingale: the role of BMH Dharan following the 1988. Nepal earthquake, and some observations on Third World earthquake disaster relief missions

Following a large earthquake in Nepal, the experience of a small hospital in dealing with the resulting mass casualties is described. The value of pre-planning and effective triage of the injured is stressed, and aspects of surgical and medical care specific to earthquake victims discussed. Clinical and administrative challenges encountered in mounting a major relief exercise in a Third World setting are also described. frequent exercising of military hospitals and personnel in handling mass casualties is an applicable to civilian natural catastrophies as to battlefield medical support.

The Australian Mesothelioma Surveillance Program 1979-1985

The Australian Mesothelioma Surveillance Program was planned in 1977 in order to improve diagnostic criteria, to monitor the incidence of the disease, to develop methods of counting lung fibres, and to explore occupational and other associations of mesothelioma. This paper presents a preliminary analysis of data that were collected between January 1, 1980 and December 31, 1985 on the pathological findings and the work and environmental history of 858 cases of mesothelioma. The annual incidence rate of mesothelioma in Australia was 15 per million population who were aged 20 years and over. This is more than the incidence rate of mesothelioma in any other country for which data are available. However, uncertainty over diagnostic criteria and the degree of ascertainment of cases places doubt on the validity of such comparisons. In 69% of cases, a history of work with or other exposure to asbestos was obtained. Due to the long interval between the first exposure to asbestos and the provisional diagnosis of a mesothelioma (up to 60 years), more than three-quarters of the 456 exposed cases first contacted asbestos in the years of its heavy use between 1930 and 1959. This article analyses cases by the industry and the occupation in which exposure to asbestos first occurred.