A promising deep learning-assistive algorithm for histopathological screening of colorectal cancer.

Colorectal cancer is one of the most common cancers worldwide, accounting for an annual estimated 1.8 million incident cases. With the increasing number of colonoscopies being performed, colorectal biopsies make up a large proportion of any histopathology laboratory workload. We trained and validated a unique artificial intelligence (AI) deep learning model as an assistive tool to screen for colonic malignancies in colorectal specimens, in order to improve cancer detection and classification; enabling busy pathologists to focus on higher order decision-making tasks. The study cohort consists of Whole Slide Images (WSI) obtained from 294 colorectal specimens. Qritive's unique composite algorithm comprises both a deep learning model based on a Faster Region Based Convolutional Neural Network (Faster-RCNN) architecture for instance segmentation with a ResNet-101 feature extraction backbone that provides glandular segmentation, and a classical machine learning classifier. The initial training used pathologists' annotations on a cohort of 66,191 image tiles extracted from 39 WSIs. A subsequent application of a classical machine learning-based slide classifier sorted the WSIs into 'low risk' (benign, inflammation) and 'high risk' (dysplasia, malignancy) categories. We further trained the composite AI-model's performance on a larger cohort of 105 resections WSIs and then validated our findings on a cohort of 150 biopsies WSIs against the classifications of two independently blinded pathologists. We evaluated the area under the receiver-operator characteristic curve (AUC) and other performance metrics. The AI model achieved an AUC of 0.917 in the validation cohort, with excellent sensitivity (97.4%) in detection of high risk features of dysplasia and malignancy. We demonstrate an unique composite AI-model incorporating both a glandular segmentation deep learning model and a classical machine learning classifier, with excellent sensitivity in picking up high risk colorectal features. As such, AI plays a role as a potential screening tool in assisting busy pathologists by outlining the dysplastic and malignant glands.

Image Analysis Using Machine Learning for Automated Detection of Hemoglobin H Inclusions in Blood Smears - A Method for Morphologic Detection of Rare Cells.

BACKGROUND: Morphologic rare cell detection is a laborious, operator-dependent process which has the potential to be improved by the use of image analysis using artificial intelligence. Detection of rare hemoglobin H (HbH) inclusions in red cells in the peripheral blood is a common screening method for alpha-thalassemia. This study aims to develop a convolutional neural network-based algorithm for the detection of HbH inclusions. METHODS: Digital images of HbH-positive and HbH-negative blood smears were used to train and test the software. The software performance was tested on images obtained at various magnifications and on different scanning platforms. Another model was developed for total red cell counting and was used to confirm HbH cell frequency in alpha-thalassemia trait. The threshold minimum red cells to image for analysis was determined by Poisson modeling and validated on image sets. RESULTS: The sensitivity and specificity of the software for HbH+ cells on images obtained at ×100, ×60, and ×40 objectives were close to 91% and 99%, respectively. When an AI-aided diagnostic model was tested on a pilot of 40 whole slide images (WSIs), good inter-rater reliability and high sensitivity and specificity of slide-level classification were obtained. Using the lowest frequency of HbH+ cells (1 in 100,000) observed in our study, we estimated that a minimum of 2.4 × 106 red cells would need to be analyzed to reduce misclassification at the slide level. The minimum required smear size was validated on 78 image sets which confirmed its validity. CONCLUSIONS: WSI image analysis can be utilized effectively for morphologic rare cell detection. The software can be further developed on WISs and evaluated in future clinical validation studies comparing AI-aided diagnosis with the routine diagnostic method.

Author Correction: Single-cell analysis of EphA clustering phenotypes to probe cancer cell heterogeneity.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Author Correction: Single-cell analysis of EphA clustering phenotypes to probe cancer cell heterogeneity.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Single-cell analysis of EphA clustering phenotypes to probe cancer cell heterogeneity.

The Eph family of receptor tyrosine kinases is crucial for assembly and maintenance of healthy tissues. Dysfunction in Eph signaling is causally associated with cancer progression. In breast cancer cells, dysregulated Eph signaling has been linked to alterations in receptor clustering abilities. Here, we implemented a single-cell assay and a scoring scheme to systematically probe the spatial organization of activated EphA receptors in multiple carcinoma cells. We show that cancer cells retain EphA clustering phenotype over several generations, and the degree of clustering reported for migration potential both at population and single-cell levels. Finally, using patient-derived cancer lines, we probed the evolution of EphA signalling in cell populations that underwent metastatic transformation and acquisition of drug resistance. Taken together, our scalable approach provides a reliable scoring scheme for EphA clustering that is consistent over multiple carcinomas and can assay heterogeneity of cancer cell populations in a cost- and time-effective manner.

Matrix mechanics controls FHL2 movement to the nucleus to activate p21 expression.

Substrate rigidity affects many physiological processes through mechanochemical signals from focal adhesion (FA) complexes that subsequently modulate gene expression. We find that shuttling of the LIM domain (domain discovered in the proteins, Lin11, Isl-1, and Mec-3) protein four-and-a-half LIM domains 2 (FHL2) between FAs and the nucleus depends on matrix mechanics. In particular, on soft surfaces or after the loss of force, FHL2 moves from FAs into the nucleus and concentrates at RNA polymerase (Pol) II sites, where it acts as a transcriptional cofactor, causing an increase in p21 gene expression that will inhibit growth on soft surfaces. At the molecular level, shuttling requires a specific tyrosine in FHL2, as well as phosphorylation by active FA kinase (FAK). Thus, we suggest that FHL2 phosphorylation by FAK is a critical, mechanically dependent step in signaling from soft matrices to the nucleus to inhibit cell proliferation by increasing p21 expression.

Nuclear transport of paxillin depends on focal adhesion dynamics and FAT domains.

The nuclear transport of paxillin appears to be crucial for paxillin function but the mechanism of transport remains unclear. Here, we show that the nuclear transport of paxillin is regulated by focal adhesion turnover and the presence of FAT domains. Focal adhesion turnover was controlled using triangular or circular fibronectin islands. Circular islands caused higher focal adhesion turnover and increased the nuclear transport of paxillin relative to triangular islands. Mutating several residues of paxillin had no effect on its nuclear transport, suggesting that the process is controlled by multiple domains. Knocking out FAK (also known as PTK2) and vinculin caused an increase in nuclear paxillin. This could be reversed by rescue with wild-type FAK but not by FAK with a mutated FAT domain, which inhibits paxillin binding. Expressing just the FAT domain of FAK not only brought down nuclear levels of paxillin but also caused a large immobile fraction of paxillin to be present at focal adhesions, as demonstrated by fluorescence recovery after photobleaching (FRAP) studies. Taken together, focal adhesion turnover and FAT domains regulate the nuclear localization of paxillin, suggesting a possible role for transcriptional control, through paxillin, by focal adhesions.