Automatic recognition of different tissue types in histological images is an essential part in the digital pathology toolbox. Texture analysis is commonly used to address this problem; mainly in the context of estimating the tumour/stroma ratio on histological samples. However, although histological images typically contain more than two tissue types, only few studies have addressed the multi-class problem. For colorectal cancer, one of the most prevalent tumour types, there are in fact no published results on multiclass texture separation. In this paper we present a new dataset of 5,000 histological images of human colorectal cancer including eight different types of tissue. We used this set to assess the classification performance of a wide range of texture descriptors and classifiers. As a result, we found an optimal classification strategy that markedly outperformed traditional methods, improving the state of the art for tumour-stroma separation from 96.9% to 98.6% accuracy and setting a new standard for multiclass tissue separation (87.4% accuracy for eight classes). We make our dataset of histological images publicly available under a Creative Commons license and encourage other researchers to use it as a benchmark for their studies.

To develop a generic support vector machine (SVM) model by using magnetic resonance (MR) imaging-based blood volume distribution data for preoperative glioma survival associations and to prospectively evaluate the diagnostic effectiveness of this model in autonomous patient data. Institutional and regional medical ethics committees approved the study, and all patients signed a consent form. Two hundred thirty-five preoperative adult patients from two institutions with a subsequent histologically confirmed diagnosis of glioma after surgery were included retrospectively. An SVM learning technique was applied to MR imaging-based whole-tumor relative cerebral blood volume (rCBV) histograms. SVM models with the highest diagnostic accuracy for 6-month and 1-, 2-, and 3-year survival associations were trained on 101 patients from the first institution. With Cox survival analysis, the diagnostic effectiveness of the SVM models was tested on independent data from 134 patients at the second institution. were adjusted for known survival predictors, including patient age, tumor size, neurologic status, and postsurgery treatment, and were compared with survival associations from an expert reader. Compared with total qualitative assessment by an expert reader, the whole-tumor rCBV-based SVM model was the strongest parameter associated with 6-month and 1-, 2-, and 3-year survival in the independent patient data (area under the receiver operating characteristic curve, 0.794-0.851; hazard ratio, 5.4-21.2). Machine learning by means of SVM in combination with whole-tumor rCBV histogram analysis can be used to identify early patient survival in aggressive gliomas. The SVM model returned higher diagnostic accuracy values than an expert reader, and the model appears to be insensitive to patient, observer, and institutional variations.

Myocardial T1-mapping recently emerged as a promising quantitative method for non-invasive tissue characterization in numerous cardiomyopathies. Commonly performed with an inversion-recovery (IR) magnetization preparation at 1.5T, the application at 3T has gained due to increased quantification precision. Alternatively, saturation-recovery (SR) T1-mapping has recently been introduced at 1.5T for improved accuracy. Thus, the purpose of this study is to investigate the robustness and precision of SR T1-mapping at 3T and to establish accurate reference values for native T1-times and extracellular volume fraction (ECV) of healthy myocardium. Balanced Steady-State Free-Precession (bSSFP) Saturation-Pulse Prepared Heart-rate independent Inversion-REcovery (SAPPHIRE) and Saturation-recovery Single-SHot Acquisition (SASHA) T1-mapping were compared with the Modified Look-Locker inversion recovery (MOLLI) sequence at 3T. Accuracy and precision were studied in phantom. Native and post-contrast T1-times and regional ECV were determined in 20 healthy subjects (10 men, 27 ± 5 years). Subjective image quality, susceptibility artifact rating, in-vivo precision and reproducibility were analyzed. SR T1-mapping showed 0.19; intra: p > 0.09) or consistency (inter: p > 0.07; intra: p > 0.17) between the three methods. Saturation-recovery T1-mapping at 3T yields higher accuracy, comparable inter-subject, inter- and intra-observer variability and less than 30 % precision-loss compared to MOLLI.

Blood vessels in solid tumors are not randomly distributed, but are clustered in angiogenic hotspots. Tumor microvessel density (MVD) within these hotspots correlates with patient survival and is widely used both in diagnostic routine and in clinical trials. Still, these hotspots are usually subjectively defined. There is no unbiased, continuous and explicit representation of tumor vessel distribution in histological whole slide images. This shortcoming distorts angiogenesis measurements and may account for ambiguous results in the literature.