Evaluating Cellularity Estimation Methods: Comparing AI Counting with Pathologists' Visual Estimates.

The development of next-generation sequencing (NGS) has enabled the discovery of cancer-specific driver gene alternations, making precision medicine possible. However, accurate genetic testing requires a sufficient amount of tumor cells in the specimen. The evaluation of tumor content ratio (TCR) from hematoxylin and eosin (H&E)-stained images has been found to vary between pathologists, making it an important challenge to obtain an accurate TCR. In this study, three pathologists exhaustively labeled all cells in 41 regions from 41 lung cancer cases as either tumor, non-tumor or indistinguishable, thus establishing a "gold standard" TCR. We then compared the accuracy of the TCR estimated by 13 pathologists based on visual assessment and the TCR calculated by an AI model that we have developed. It is a compact and fast model that follows a fully convolutional neural network architecture and produces cell detection maps which can be efficiently post-processed to obtain tumor and non-tumor cell counts from which TCR is calculated. Its raw cell detection accuracy is 92% while its classification accuracy is 84%. The results show that the error between the gold standard TCR and the AI calculation was significantly smaller than that between the gold standard TCR and the pathologist's visual assessment (p<0.05). Additionally, the robustness of AI models across institutions is a key issue and we demonstrate that the variation in AI was smaller than that in the average of pathologists when evaluated by institution. These findings suggest that the accuracy of tumor cellularity assessments in clinical workflows is significantly improved by the introduction of robust AI models, leading to more efficient genetic testing and ultimately to better patient outcomes.

Requirements for implementation of artificial intelligence in the practice of gastrointestinal pathology.

Tremendous advances in artificial intelligence (AI) in medical image analysis have been achieved in recent years. The integration of AI is expected to cause a revolution in various areas of medicine, including gastrointestinal (GI) pathology. Currently, deep learning algorithms have shown promising benefits in areas of diagnostic histopathology, such as tumor identification, classification, prognosis prediction, and biomarker/genetic alteration prediction. While AI cannot substitute pathologists, carefully constructed AI applications may increase workforce productivity and diagnostic accuracy in pathology practice. Regardless of these promising advances, unlike the areas of radiology or cardiology imaging, no histopathology-based AI application has been approved by a regulatory authority or for public reimbursement. Thus, implying that there are still some obstacles to be overcome before AI applications can be safely and effectively implemented in real-life pathology practice. The challenges have been identified at different stages of the development process, such as needs identification, data curation, model development, validation, regulation, modification of daily workflow, and cost-effectiveness balance. The aim of this review is to present challenges in the process of AI development, validation, and regulation that should be overcome for its implementation in real-life GI pathology practice.

Digital/Computational Technology for Molecular Cytology Testing: A Short Technical Note with Literature Review.

This short article describes the method of digital cytopathology using Z-stack scanning with or without extended focusing. This technology is suitable to observe such thick clusters as adenocarcinoma on cytologic specimens. Artificial intelligence (AI) has been applied to histological images, but its application on cytologic images is still limited. This article describes our attempt to apply AI technology to cytologic digital images. For molecular analysis, cytologic materials, such as smear, LBC, and cell blocks, have been successfully used for targeted single gene detection and multiplex gene analysis with next-generation sequencing. As a future perspective, the system can be connected to full automation by combining digital cytopathology with AI application to detect target cancer cells and to perform molecular analysis. The literature review is updated according to the subjects.

Automated histological classification of whole-slide images of gastric biopsy specimens.

BACKGROUND: Automated image analysis has been developed currently in the field of surgical pathology. The aim of the present study was to evaluate the classification accuracy of the e-Pathologist image analysis software. METHODS: A total of 3062 gastric biopsy specimens were consecutively obtained and stained. The specimen slides were anonymized and digitized. At least two experienced gastrointestinal pathologists evaluated each slide for pathological diagnosis. We compared the three-tier (positive for carcinoma or suspicion of carcinoma; caution for adenoma or suspicion of a neoplastic lesion; or negative for a neoplastic lesion) or two-tier (negative or non-negative) classification results of human pathologists and of the e-Pathologist. RESULTS: Of 3062 cases, 33.4% showed an abnormal finding. For the three-tier classification, the overall concordance rate was 55.6% (1702/3062). The kappa coefficient was 0.28 (95% CI, 0.26-0.30; fair agreement). For the negative biopsy specimens, the concordance rate was 90.6% (1033/1140), but for the positive biopsy specimens, the concordance rate was less than 50%. For the two-tier classification, the sensitivity, specificity, positive predictive value, and negative predictive value were 89.5% (95% CI, 87.5-91.4%), 50.7% (95% CI, 48.5-52.9%), 47.7% (95% CI, 45.4-49.9%), and 90.6% (95% CI, 88.8-92.2%), respectively. CONCLUSIONS: Although there are limitations and requirements for applying automated histopathological classification of gastric biopsy specimens in the clinical setting, the results of the present study are promising.

Automated histological classification of whole slide images of colorectal biopsy specimens.

BACKGROUND: An automated image analysis system, e-Pathologist, was developed to improve the quality of colorectal biopsy diagnostics in routine pathology practice. OBJECTIVE: The aim of the study was to evaluate the classification accuracy of the e-Pathologist image analysis software in the setting of routine pathology practice in two institutions. MATERIALS AND METHODS: In total, 1328 colorectal tissue specimens were consecutively obtained from two hospitals (1077 tissues from Tokyo hospital, and 251 tissues from East hospital) and the stained specimen slides were anonymized and digitized. At least two experienced gastrointestinal pathologists evaluated each slide for pathological diagnosis. We compared the 3-tier classification results (carcinoma or suspicion of carcinoma, adenoma, and lastly negative for a neoplastic lesion) between the human pathologists and that of e-Pathologist. RESULTS: For the Tokyo hospital specimens, all carcinoma tissues were correctly classified (n=112), and 9.9% (80/810) of the adenoma tissues were incorrectly classified as negative. For the East hospital specimens, 0 out of the 51 adenoma tissues were incorrectly classified as negative while 9.3% (11/118) of the carcinoma tissues were incorrectly classified as either adenoma, or negative. For the Tokyo and East hospital datasets, the undetected rate of carcinoma, undetected rate of adenoma, and over-detected proportion were 0% and 9.3%, 9.9% and 0%, and 36.1% and 27.1%, respectively. CONCLUSIONS: This image analysis system requires some improvements; however, it has the potential to assist pathologists in quality improvement of routine pathological practice in the not too distant future.

Pathological Diagnosis of Gastric Cancers with a Novel Computerized Analysis System.

BACKGROUND: Recent studies of molecular biology have provided great advances for diagnostic molecular pathology. Automated diagnostic systems with computerized scanning for sampled cells in fluids or smears are now widely utilized. Automated analysis of tissue sections is, however, very difficult because they exhibit a complex mixture of overlapping malignant tumor cells, benign host-derived cells, and extracellular materials. Thus, traditional histological diagnosis is still the most powerful method for diagnosis of diseases. METHODS: We have developed a novel computer-assisted pathology system for rapid, automated histological analysis of hematoxylin and eosin (H and E)-stained sections. It is a multistage recognition system patterned after methods that human pathologists use for diagnosis but harnessing machine learning and image analysis. The system first analyzes an entire H and E-stained section (tissue) at low resolution to search suspicious areas for cancer and then the selected areas are analyzed at high resolution to confirm the initial suspicion. RESULTS: After training the pathology system with gastric tissues samples, we examined its performance using other 1905 gastric tissues. The system's accuracy in detecting malignancies was shown to be almost equal to that of conventional diagnosis by expert pathologists. CONCLUSIONS: Our novel computerized analysis system provides a support for histological diagnosis, which is useful for screening and quality control. We consider that it could be extended to be applicable to many other carcinomas after learning normal and malignant forms of various tissues. Furthermore, we expect it to contribute to the development of more objective grading systems, immunohistochemical staining systems, and fluorescent-stained image analysis systems.

Automatic quantification of morphological features for hepatic trabeculae analysis in stained liver specimens.

This paper proposes a digital image analysis method to support quantitative pathology by automatically segmenting the hepatocyte structure and quantifying its morphological features. To structurally analyze histopathological hepatic images, we isolate the trabeculae by extracting the sinusoids, fat droplets, and stromata. We then measure the morphological features of the extracted trabeculae, divide the image into cords, and calculate the feature values of the local cords. We propose a method of calculating the nuclear-cytoplasmic ratio, nuclear density, and number of layers using the local cords. Furthermore, we evaluate the effectiveness of the proposed method using surgical specimens. The proposed method was found to be an effective method for the quantification of the Edmondson grade.

Enhancing automatic classification of hepatocellular carcinoma images through image masking, tissue changes and trabecular features.

BACKGROUND: Recent breakthroughs in computer vision and digital microscopy have prompted the application of such technologies in cancer diagnosis, especially in histopathological image analysis. Earlier, an attempt to classify hepatocellular carcinoma images based on nuclear and structural features has been carried out on a set of surgical resected samples. Here, we proposed methods to enhance the process and improve the classification performance. METHODS: First, we segmented the histological components of the liver tissues and generated several masked images. By utilizing the masked images, some set of new features were introduced, producing three sets of features consisting nuclei, trabecular and tissue changes features. Furthermore, we extended the classification process by using biopsy resected samples in addition to the surgical samples. RESULTS: Experiments by using support vector machine (SVM) classifier with combinations of features and sample types showed that the proposed methods improve the classification rate in HCC detection for about 1-3%. Moreover, detection rate of low-grades cancer increased when the new features were appended in the classification process, although the rate was worsen in the case of undifferentiated tumors. CONCLUSIONS: The masking process increased the reliability of extracted nuclei features. The additional of new features improved the system especially for early HCC detection. Likewise, the combination of surgical and biopsy samples as training data could also improve the classification rates. Therefore, the methods will extend the support for pathologists in the HCC diagnosis.

Changes in chromatin structure during processing of wax-embedded tissue sections.

The use of immunofluorescence (IF) and fluorescence in situ hybridisation (FISH) underpins much of our understanding of how chromatin is organised in the nucleus. However, there has only recently been an appreciation that these types of study need to move away from cells grown in culture and towards an investigation of nuclear organisation in cells in situ in their normal tissue architecture. Such analyses, however, especially of archival clinical samples, often requires use of formalin-fixed paraffin wax-embedded tissue sections which need addition steps of processing prior to IF or FISH. Here we quantify the changes in nuclear and chromatin structure that may be caused by these additional processing steps. Treatments, especially the microwaving to reverse fixation, do significantly alter nuclear architecture and chromatin texture, and these must be considered when inferring the original organisation of the nucleus from data collected from wax-embedded tissue sections.

Dioxin interferes in chromosomal positioning through the aryl hydrocarbon receptor.

Each chromosome occupies its own-specific space called a 'territory' within the interphase nucleus, and the arrangement of chromosome territories (CTs) is important in epigenetic mechanisms. The molecular mechanism to determine the positioning of CTs, however, remains unknown. On the other hand, dioxin is known to be the typical environmental pollutant that affects a wide variety of biological events in many species. Here, we show that dioxin enlarges the minimum distance between chromosome 12 and chromosome 16 territories in human preadipocyte cells, and the alteration of chromosome positioning is canceled by an aryl hydrocarbon receptor (AhR) antagonist alpha-naphthoflavone. Thus, AhR may be a key molecule to regulate chromosome positioning. Our results suggest a novel effect of dioxin toxicity, and demonstrate a clue to reveal the novel molecular mechanism for the arrangement of CTs.

Alteration of chromosome positioning during adipocyte differentiation.

Chromosomes are highly restricted to specific chromosome territories within the interphase nucleus. The arrangement of chromosome territories is non-random, exhibiting a defined radial distribution as well as a preferential association with specific nuclear compartments, which indicates a functional role for chromosome-territory organization in the regulation of gene expression. In this report, we focus on changes in adipocyte differentiation that are related to a specific chromosomal translocation associated with liposarcoma tumorigenesis, t(12;16). We have examined the relative and radial positioning of the chromosome territories of human chromosomes 12 and 16 during adipocyte differentiation, and detected a close association between the territories of chromosomes 12 and 16 in differentiated adipocytes, an association not observed in preadipocytes. Although further studies are required to elucidate the underlying reasons for the adipocyte-specific translocation of chromosomes 12 and 16, our observations indicate that alteration of relative chromosome positioning might play a key role in the tumorigenesis of human liposarcomas. In addition, these results demonstrate the potential impact of higher order chromatin organization on the epigenetic mechanisms that control gene expression and gene silencing during cell differentiation.

Visual event-related potentials during movement imagery and the dipole analysis.

Visual event-related potentials during an oddball paradigm with movement imagery tasks were recorded in 10 right-handed subjects from 32 scalp electrodes. Rare targets and non-targets elicited early (P3e) and late (P31) P300 components. In the P3e there was no difference between the rare target and non-target. In the right-imagery task the rare target P31 amplitude was larger than the rare non-target one, whereas the rare non-target P31 amplitude was larger than the rare target one in the left-imagery task. Some of the 4 equivalent current dipole (ECD) sources were located at the subcortical regions, the cerebellum and the cingulate cortex, common to the P3e and the P31. Moreover, another P3e dipole was localized to the parietal regions, while that of the P31 dipoles to the contralateral premotor cortex. This difference between the P3e and P31 dipoles might reflect two different neural networks related with the transformation of coordinates from visual to motor space.

Electroencephalographic dipoles of spikes with and without myoclonic jerks caused by epilepsia partialis continua.

We used electroencephalographic (EEG) dipole analysis to investigate the generators of spikes with and without myoclonic jerks in a 12-year-old patient with epilepsia partialis continua secondary to left parietal cortical dysplasia. We recorded EEG and right wrist extensor electromyography (EMG) and collected 42 spikes with jerks (jerking spikes) and 42 spikes without jerks (nonjerking spikes). We applied a single moving dipole model to the individual and averaged spikes. Dipoles at the negative peak of individual jerking and nonjerking spikes were localized in the dysplastic area. At the onset of the averaged jerking spike that preceded the EMG discharges by 20 ms, the dipole was in the motor cortex, whereas for the averaged nonjerking spike, the dipole was in the sensory cortex. The dipole moment at averaged jerking spike onset was twice that of the averaged nonjerking spike. Electroencephalographic dipole analysis of averaged spikes differentiated the generator of jerking and nonjerking spikes in epilepsia partialis continua. Individual dipoles demonstrated the area of epileptogenic cortical dysplasia.