Evaluation of current algorithms for segmentation of scar tissue from late gadolinium enhancement cardiovascular magnetic resonance of the left atrium: an open-access grand challenge.

BACKGROUND: Late Gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging can be used to visualise regions of fibrosis and scarring in the left atrium (LA) myocardium. This can be important for treatment stratification of patients with atrial fibrillation (AF) and for assessment of treatment after radio frequency catheter ablation (RFCA). In this paper we present a standardised evaluation benchmarking framework for algorithms segmenting fibrosis and scar from LGE CMR images. The algorithms reported are the response to an open challenge that was put to the medical imaging community through an ISBI (IEEE International Symposium on Biomedical Imaging) workshop. METHODS: The image database consisted of 60 multicenter, multivendor LGE CMR image datasets from patients with AF, with 30 images taken before and 30 after RFCA for the treatment of AF. A reference standard for scar and fibrosis was established by merging manual segmentations from three observers. Furthermore, scar was also quantified using 2, 3 and 4 standard deviations (SD) and full-width-at-half-maximum (FWHM) methods. Seven institutions responded to the challenge: Imperial College (IC), Mevis Fraunhofer (MV), Sunnybrook Health Sciences (SY), Harvard/Boston University (HB), Yale School of Medicine (YL), King's College London (KCL) and Utah CARMA (UTA, UTB). There were 8 different algorithms evaluated in this study. RESULTS: Some algorithms were able to perform significantly better than SD and FWHM methods in both pre- and post-ablation imaging. Segmentation in pre-ablation images was challenging and good correlation with the reference standard was found in post-ablation images. Overlap scores (out of 100) with the reference standard were as follows: Pre: IC = 37, MV = 22, SY = 17, YL = 48, KCL = 30, UTA = 42, UTB = 45; Post: IC = 76, MV = 85, SY = 73, HB = 76, YL = 84, KCL = 78, UTA = 78, UTB = 72. CONCLUSIONS: The study concludes that currently no algorithm is deemed clearly better than others. There is scope for further algorithmic developments in LA fibrosis and scar quantification from LGE CMR images. Benchmarking of future scar segmentation algorithms is thus important. The proposed benchmarking framework is made available as open-source and new participants can evaluate their algorithms via a web-based interface.

Histological correlates of optical coherence tomography in non-melanoma skin cancer.

BACKGROUND: Non-melanoma skin cancer (NMSC) is rarely fatal but is now the most common malignancy occurring in white populations, accounting for 70% of the cost of managing skin cancer. Optical coherence tomography (OCT) has the potential to improve diagnostic accuracy and help delineate pre-surgical margins in NMSC. Its widespread clinical acceptance awaits the accumulation of evidence from studies of direct histological comparisons. METHOD: In this study, seventy-eight subjects presenting with skin lesions, including 28 NMSCs, were imaged using the VivoSight OCT scanner and a biopsy taken. Haemotoxylin and eosin stained histology sections were compared with the OCT images. RESULTS: The depth of superficial basal cell carcinoma (BCC) lesions (<1 mm) can be measured accurately using OCT. A low-strength OCT signal at the periphery of the cell nests seen in superficial and nodular BCC is identified as corresponding to cellular palisading. A weak inverse linear correlation (r(2) = 0.3) is found between the optical attenuation coefficient measured on OCT and the nuclear-cytoplasmic ratio (N/C) of cells determined from histology. CONCLUSIONS: OCT has clinical value in providing accurate dimensional measurement of superficial BCC and in identifying the presence of peripheral palisading in nodular BCC.

Effectiveness and impact of networked communication interventions in young people with mental health conditions: A rapid review.

OBJECTIVE: To describe the latest evidence of effectiveness and impact of networked communication interventions for young people with mental health conditions. METHODS: Searching five databases from 2009 onwards, we included studies of any design investigating two-way communication interventions for the treatment of young people (mean age 12-25) with a chronic mental health disorder. The data were synthesised using narrative summary. RESULTS: Six studies met the inclusion criteria, covering a range of mental health conditions (depression, psychosis, OCD). Interventions included an online chat room (n = 2), videoconferencing (n = 3) and telephone (n = 1). Where studies compared two groups, equivalence or a statistically significant improvement in symptoms was observed compared to control. Views of patients and clinicians included impact on the patient-clinician interaction. Clinicians did not feel it hindered their diagnostic ability. CONCLUSION: Networked communication technologies show promise in the treatment of young people with mental health problems but the current available evidence remains limited and the evidence base has not advanced much since the previous inception of this review in 2011. PRACTICE IMPLICATIONS: Although the available research is generally positive, robust evidence relating to the provision of care for young persons via these technologies is lacking and healthcare providers should be mindful of this.