Search

High computational cost associated with digital pathology image analysis approaches is a challenge towards their translation in routine pathology clinic. Here, we propose a computationally efficient framework (SuperHistopath), designed to map global context features reflecting the rich tumor morphological heterogeneity. SuperHistopath efficiently combines i) a segmentation approach using the linear iterative clustering (SLIC) superpixels algorithm applied directly on the whole-slide images at low resolution (5x magnification) to adhere to region boundaries and form homogeneous spatial units at tissue-level, followed by ii) classification of superpixels using a convolution neural network (CNN). To demonstrate how versatile SuperHistopath was in accomplishing histopathology tasks, we classified tumor tissue, stroma, necrosis, lymphocytes clusters, differentiating regions, fat, hemorrhage and normal tissue, in 127 melanomas, 23 triple-negative breast cancers, and 73 samples from transgenic mouse models of high-risk childhood neuroblastoma with high accuracy (98.8%, 93.1% and 98.3% respectively). Furthermore, SuperHistopath enabled discovery of significant differences in tumor phenotype of neuroblastoma mouse models emulating genomic variants of high-risk disease, and stratification of melanoma patients (high ratio of lymphocyte-to-tumor superpixels (p = 0.015) and low stroma-to-tumor ratio (p = 0.028) were associated with a favorable prognosis). Finally, SuperHistopath is efficient for annotation of ground-truth datasets (as there is no need of boundary delineation), training and application (~5 min for classifying a whole-slide image and as low as ~30 min for network training). These attributes make SuperHistopath particularly attractive for research in rich datasets and could also facilitate its adoption in the clinic to accelerate pathologist workflow with the quantification of phenotypes, predictive/prognosis markers.

High computational cost associated with digital pathology image analysis approaches is a challenge towards their translation in routine pathology clinic. Here, we propose a computationally efficient framework (SuperHistopath), designed to map global context features reflecting the rich tumor morphological heterogeneity. SuperHistopath efficiently combines i) a segmentation approach using the linear iterative clustering (SLIC) superpixels algorithm applied directly on the whole-slide images at low resolution (5x magnification) to adhere to region boundaries and form homogeneous spatial units at tissue-level, followed by ii) classification of superpixels using a convolution neural network (CNN). To demonstrate how versatile SuperHistopath was in accomplishing histopathology tasks, we classified tumor tissue, stroma, necrosis, lymphocytes clusters, differentiating regions, fat, hemorrhage and normal tissue, in 127 melanomas, 23 triple-negative breast cancers, and 73 samples from transgenic mouse models of high-risk childhood neuroblastoma with high accuracy (98.8%, 93.1% and 98.3% respectively). Furthermore, SuperHistopath enabled discovery of significant differences in tumor phenotype of neuroblastoma mouse models emulating genomic variants of high-risk disease, and stratification of melanoma patients (high ratio of lymphocyte-to-tumor superpixels (p = 0.015) and low stroma-to-tumor ratio (p = 0.028) were associated with a favorable prognosis). Finally, SuperHistopath is efficient for annotation of ground-truth datasets (as there is no need of boundary delineation), training and application (~5 min for classifying a whole-slide image and as low as ~30 min for network training). These attributes make SuperHistopath particularly attractive for research in rich datasets and could also facilitate its adoption in the clinic to accelerate pathologist workflow with the quantification of phenotypes, predictive/prognosis markers. [ABSTRACT FROM AUTHOR]

Gender disparities in scientific publications have been identified in oncological research. Oral research presentations at major conferences enhance visibility of presenters. The share of women presenting at such podia is unknown. We aim to identify gender‐based differences in contributions to presentations at two major oncological conferences. Abstracts presented at plenary sessions of the American Society of Clinical Oncology (ASCO) Annual Meetings and European Society for Medical Oncology (ESMO) Congresses were collected. Trend analyses were used to analyze female contribution over time. The association between presenter's sex, study outcome (positive/negative) and journals' impact factors (IFs) of subsequently published papers was assessed using Chi‐square and Mann–Whitney U tests. Of 166 consecutive abstracts presented at ASCO in 2011–2018 (n = 34) and ESMO in 2008–2018 (n = 132), 21% had female presenters, all originating from Northern America (n = 17) or Europe (n = 18). The distribution of presenter's sex was similar over time (p = 0.70). Of 2,425 contributing authors to these presented abstracts, 28% were women. The proportion of female abstract authors increased over time (p < 0.05) and was higher in abstracts with female (34%) compared to male presenters (26%; p < 0.01). Presenter's sex was not associated with study outcome (p = 0.82). Median journals' IFs were lower in papers with a female first author (p < 0.05). In conclusion, there is a clear gender disparity in research presentations at two major oncological conferences, with 28% of authors and 21% of presenters of these studies being female. Lack of visibility of female presenters could impair acknowledgement for their research, opportunities in their academic career and even hamper heterogeneity in research. What's new? Presenting one's research at a conference is a great way to get your name and ideas heard within the professional community. In this study, the authors investigated how often women served as presenters at plenary sessions of ASCO Annual Meetings and ESMO Congresses. Looking through 166 abstracts over a period of 8 years, they found that 21% had female presenters, while 28% of study authors were female. Lack of visibility for female researchers at conferences can slow their career progress, and greater representation should be encouraged. [ABSTRACT FROM AUTHOR]