False-positive pathology: improving reproducibility with the next generation of pathologists

Short Training Significantly Improves Ganglion Cell Detection Using an Algorithm-Assisted Approach

CONTEXT.—

Medical education in pathology relies on the accumulation of experience gained through inspection of numerous samples from each entity. Acquiring sufficient teaching material for rare diseases, such as Hirschsprung disease (HSCR), may be difficult, especially in smaller institutes. The current study makes use of a previously developed decision support system using a decision support algorithm meant to aid pathologists in the diagnosis of HSCR.

OBJECTIVE.—

To assess the effect of a short training session on algorithm-assisted HSCR diagnosis.

DESIGN.—

Five pathologists reviewed a data set of 568 image sets (1704 images in total) selected from 50 cases by the decision support algorithm and were tasked with scoring the images for the presence or absence of ganglion cells. The task was repeated a total of 3 times. Each pathologist had to complete a short educational presentation between the second and third iterations.

RESULTS.—

The training resulted in a significantly increased rate of correct diagnoses (true positive/negative) and a decreased need for referrals for expert consultation. No statistically significant changes in the rate of false positives/negatives were detected.

CONCLUSIONS.—

A very short (<10 minutes) training session can greatly improve the pathologist's performance in the algorithm-assisted diagnosis of HSCR. The same approach may be feasible in training for the diagnosis of other rare diseases.

Multiplexed 3D atlas of state transitions and immune interaction in colorectal cancer

Advanced solid cancers are complex assemblies of tumor, immune, and stromal cells characterized by high intratumoral variation. We use highly multiplexed tissue imaging, 3D reconstruction, spatial statistics, and machine learning to identify cell types and states underlying morphological features of known diagnostic and prognostic significance in colorectal cancer. Quantitation of these features in high-plex marker space reveals recurrent transitions from one tumor morphology to the next, some of which are coincident with long-range gradients in the expression of oncogenes and epigenetic regulators. At the tumor invasive margin, where tumor, normal, and immune cells compete, T cell suppression involves multiple cell types and 3D imaging shows that seemingly localized 2D features such as tertiary lymphoid structures are commonly interconnected and have graded molecular properties. Thus, while cancer genetics emphasizes the importance of discrete changes in tumor state, whole-specimen imaging reveals large-scale morphological and molecular gradients analogous to those in developing tissues.

Classification of Mouse Lung Metastatic Tumor with Deep Learning

Traditionally, pathologists microscopically examine tissue sections to detect pathological lesions; the many slides that must be evaluated impose severe work burdens. Also, diagnostic accuracy varies by pathologist training and experience; better diagnostic tools are required. Given the rapid development of computer vision, automated deep learning is now used to classify microscopic images, including medical images. Here, we used a Inception-v3 deep learning model to detect mouse lung metastatic tumors via whole slide imaging (WSI); we cropped the images to 151 by 151 pixels. The images were divided into training (53.8%) and test (46.2%) sets (21,017 and 18,016 images, respectively). When images from lung tissue containing tumor tissues were evaluated, the model accuracy was 98.76%. When images from normal lung tissue were evaluated, the model accuracy (“no tumor”) was 99.87%. Thus, the deep learning model distinguished metastatic lesions from normal lung tissue. Our approach will allow the rapid and accurate analysis of various tissues.

Cell detachment ratio on pH-responsive chitosan: A useful biometric for prognostic judgment and drug efficacy assessment in oncology

The inherently unpredictable complexity of tumors impedes the widespread practice of the molecular biomarkers in outcome prediction. Alternatively, from the biophysical perspective, this study sought to investigate the applicability of the cell detachment ratio (CDR) derived from pH-responsive chitosan as a biometrical identifier for the disease state in cancer prognostic judgment and drug efficacy assessment. In the targeted therapy model, the repression of tumor dissemination in cells harboring aberrant ErbB signals (human non-small cell lung cancer cell line PC9 and breast cancer cell line BT474) were first demonstrated both in vitro and in vivo. Consequently, the corresponding CDR profile goes synchronously with the extent of cancer regression in response to the medication. Definitive integrins that drive the cell detachment were also verified through CDR examination following the integrin functional blockade. Conclusively, CDR is a promising clinical index for evaluation of the metastatic cell behaviors in terms of the cell detachment.

Genetically Engineered Mouse Models of Liver Tumorigenesis Reveal a Wide Histological Spectrum of Neoplastic and Non-Neoplastic Liver Lesions

Genetically engineered mouse models (GEMM) are an elegant tool to study liver carcinogenesis in vivo. Newly designed mouse models need detailed (histopathological) phenotyping when described for the first time to avoid misinterpretation and misconclusions. Many chemically induced models for hepatocarcinogenesis comprise a huge variety of histologically benign and malignant neoplastic, as well as non-neoplastic, lesions. Such comprehensive categorization data for GEMM are still missing. In this study, 874 microscopically categorized liver lesions from 369 macroscopically detected liver "tumors" from five different GEMM for liver tumorigenesis were included. The histologic spectrum of diagnosis included a wide range of both benign and malignant neoplastic (approx. 82%) and non-neoplastic (approx. 18%) lesions including hyperplasia, reactive bile duct changes or oval cell proliferations with huge variations among the various models and genetic backgrounds. Our study therefore critically demonstrates that models of liver tumorigenesis can harbor a huge variety of histopathologically distinct diagnosis and, depending on the genotype, notable variations are expectable. These findings are extremely important to warrant the correct application of GEMM in liver cancer research and clearly emphasize the role of basic histopathology as still being a crucial tool in modern biomedical research.