Translational AI and Deep Learning in Diagnostic Pathology.

There has been an exponential growth in the application of AI in health and in pathology. This is resulting in the innovation of deep learning technologies that are specifically aimed at cellular imaging and practical applications that could transform diagnostic pathology. This paper reviews the different approaches to deep learning in pathology, the public grand challenges that have driven this innovation and a range of emerging applications in pathology. The translation of AI into clinical practice will require applications to be embedded seamlessly within digital pathology workflows, driving an integrated approach to diagnostics and providing pathologists with new tools that accelerate workflow and improve diagnostic consistency and reduce errors. The clearance of digital pathology for primary diagnosis in the US by some manufacturers provides the platform on which to deliver practical AI. AI and computational pathology will continue to mature as researchers, clinicians, industry, regulatory organizations and patient advocacy groups work together to innovate and deliver new technologies to health care providers: technologies which are better, faster, cheaper, more precise, and safe.

Novel in vitro assays for the characterization of EMT in tumourigenesis.

BACKGROUND: Two novel assays quantifying Epithelial to Mesenchymal Transition (EMT) were compared to traditional motility and migration assays. TGF-beta1 treatment of AY-27 rat bladder cancer cells acted as a model of EMT in tumourigenesis. METHODS: AY-27 rat bladder cancer cells incubated with 3 ng/ml TGF-beta1 or control media for 24 or 48 h were assessed using novel and traditional assays. The Spindle Index, a novel measure of spindle phenotype, was derived from the ratio of maximum length to maximum width of cells. The area covered by cells which migrated from a fixed coverslip towards supplemented agarose was measured in a novel chemoattractant assay. Motility, migration and immunoreactivity for E-cadherin, Vimentin and cytokeratin were assessed. RESULTS: TGF-beta1 treated cells had increased "spindle" phenotype together with decreased E-cadherin, decreased Cytokeratin-18 and increased Vimentin immunoreactivity. After 48 h, the mean Spindle Index of TGF-beta1 treated cells was significantly higher than Mock (p=0.02, Bonferroni test) and there were significant differences in migration across treatment groups measured using the novel chemoattractant assay (p=0.02, Chi-square). TGF-beta1 significantly increased matrigel invasion. CONCLUSION: The Spindle Index and the novel chemoattractant assay are valuable adjunctive assays for objective characterization of EMT changes during tumourigenesis.

Segmentation of squamous epithelium from ultra-large cervical histological virtual slides.

Cervical virtual slides are ultra-large, can have size up to 120K x 80K pixels. This paper introduces an image segmentation method for the automated identification of Squamous epithelium from such virtual slides. In order to produce the best segmentation results, in addition to saving processing time and memory, a multiresolution segmentation strategy was developed. The Squamous epithelium layer is first segmented at a low resolution (2X magnification). The boundaries of segmented Squamous epithelium are further fine tuned at the highest resolution of 40X magnification, using an iterative boundary expanding-shrinking method. The block-based segmentation method uses robust texture feature vectors in combination with a Support Vector Machine (SVM) to perform classification. Medical histology rules are finally applied to remove misclassifications. Results demonstrate that, with typical virtual slides, classification accuracies of between 94.9% and 96.3% are achieved.

Prediction of radiosensitivity in human bladder cell lines using nuclear chromatin phenotype.

BACKGROUND: Nuclear texture analysis measures phenotypic changes in chromatin distribution within a cell nucleus, while the alkaline Comet assay is a sensitive method for measuring the extent of DNA breakage in individual cells. The authors aim to use both methods to provide information about the sensitivity of cells to ionizing radiation. METHODS: The alkaline Comet assay was performed on six human bladder carcinoma cell lines and one human urothelial cell line exposed to gamma-radiation doses from 0 to 10 Gy. Nuclear chromatin texture analysis of 40 features was then performed in the same cell lines exposed to 0, 2, and 6 Gy to explore if nuclear phenotype was related to radiation sensitivity. RESULTS: Comet assay results demonstrated that the cell lines exhibited different levels of radiosensitivity and could be divided into a radiosensitive and a radioresistant group at >6 Gy. Using stepwise discriminant analysis, a subset of important nuclear texture features that best discriminated between sensitive and resistant cell lines were identified A classification function, defined using these features, correctly classified 81.75% of all cells into their radiosensitive or radioresistant groups based on their pretreatment chromatin phenotype. Posttreatment chromatin changes also varied between cell lines, with sensitive cell lines showing a relaxed chromatin conformation following radiation, whereas resistant cell lines exhibited chromatin condensation. CONCLUSIONS: The authors conclude that the alkaline Comet assay and nuclear texture methodologies may prove to be valuable aids in predicting the response of tumor cells to radiotherapy.