Regional registration of whole slide image stacks containing major histological artifacts.

BACKGROUND: High resolution 2D whole slide imaging provides rich information about the tissue structure. This information can be a lot richer if these 2D images can be stacked into a 3D tissue volume. A 3D analysis, however, requires accurate reconstruction of the tissue volume from the 2D image stack. This task is not trivial due to the distortions such as tissue tearing, folding and missing at each slide. Performing registration for the whole tissue slices may be adversely affected by distorted tissue regions. Consequently, regional registration is found to be more effective. In this paper, we propose a new approach to an accurate and robust registration of regions of interest for whole slide images. We introduce the idea of multi-scale attention for registration. RESULTS: Using mean similarity index as the metric, the proposed algorithm (mean ± SD [Formula: see text]) followed by a fine registration algorithm ([Formula: see text]) outperformed the state-of-the-art linear whole tissue registration algorithm ([Formula: see text]) and the regional version of this algorithm ([Formula: see text]). The proposed algorithm also outperforms the state-of-the-art nonlinear registration algorithm (original: [Formula: see text], regional: [Formula: see text]) for whole slide images and a recently proposed patch-based registration algorithm (patch size 256: [Formula: see text] , patch size 512: [Formula: see text]) for medical images. CONCLUSION: Using multi-scale attention mechanism leads to a more robust and accurate solution to the problem of regional registration of whole slide images corrupted in some parts by major histological artifacts in the imaged tissue.

Characteristics and behaviour of screen-detected ductal carcinoma in situ of the breast: comparison with symptomatic patients.

Breast cancer is the most common malignancy in Singapore women. Ductal carcinoma in situ (DCIS) is the putative, non-obligate precursor of the majority of invasive breast cancers. The efficacy of the Singapore breast-screening pilot project in detecting early stage breast cancer led to the launch of a national breast-screening programme, BreastScreen Singapore (BSS), in January 2002. In this study, we compared clinicopathological and immunohistochemical characteristics, as well as clinical outcomes, between screen-detected and symptomatic DCIS. The study cohort comprised 1202 cases of DCIS diagnosed at Singapore General Hospital from 1994 to 2010. Comparison of clinicopathological parameters, immunohistochemical results of ER, PR, HER2, CK14, EGFR, and 34ßE12, and clinical outcomes was carried out between the 2 groups. Amongst 1202 cases, 610 (50.7%) were screen-detected and 592 (49.3%) were symptomatic DCIS. Screen-detected cases were smaller in size (P < 0.001), of lower nuclear grade (P = 0.004), and more frequently expressed ER (P < 0.001). Luminal A phenotype was more frequently observed in screen-detected DCIS, while triple-negative and HER2 phenotypes were more common in symptomatic DCIS (P < 0.001). The basal-like phenotype was also more frequent in symptomatic DCIS (P = 0.041). Mean and median follow-up was 99.7 and 97.8 months, respectively, with a maximum follow-up of 246.0 months. More symptomatic patients developed invasive recurrences compared to screen-detected patients (P = 0.001). A trend for better disease-free survival was observed in screen-detected patients (P = 0.076). Patients who were screen-detected experienced better overall survival than those with symptomatic DCIS (P = 0.007). Our data indicate a more favourable outcome of screen-detected DCIS patients confirming the role of BSS in early identification of this curable disease.

Myeloid Sarcoma Masquerading as Granulation Tissue: A Diagnostic Pitfall.

Myeloid sarcoma is an uncommon neoplasm, comprising an extramedullary tumorous proliferation of immature myeloid cells. Its rarity and tendency for diverse clinical presentation contribute to difficulty in timely diagnosis. This report describes a case of a painful back lump in an elderly Chinese male, which was initially diagnosed as a carbuncle. Histology on the saucerization specimen was reported as inflamed granulation tissue. Failure of expected wound healing prompted surgical debridement; microscopic examination on the subsequent specimen revealed an immature myeloid population with an increased MIB-1 proliferative index, highlighted by myeloperoxidase, lysozyme, CD117, and CD43 immunoreactivity, in keeping with myeloid sarcoma. Despite aggressive management, the patient eventually died. This report draws attention to potential pitfalls in the pathological diagnosis of this uncommon tumor and briefly summarizes its salient features.