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.

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.

Transgenic rice overproducing Rubisco exhibits increased yields with improved nitrogen-use efficiency in an experimental paddy field.

The green revolution's breeding of semi-dwarf rice cultivars in the 1960s improved crop yields, with large increases in the use of nitrogen (N) fertilizer. However, excess N application has caused serious environmental problems, including acid rain and the eutrophication of rivers and oceans. To use N to improve crop yields, while minimizing the associated environmental costs, there is a need to produce crops with higher N-use efficiency and higher yield components. Here we show that transgenic rice overproducing ribulose 1,5-bisphosphate carboxylase-oxygenase (Rubisco)-the key enzyme of photosynthesis-exhibits increased yields with improved N-use efficiency for increasing biomass production when receiving sufficient N fertilization in an experimental paddy field. This field experiment demonstrates an improvement in photosynthesis linked to yield increase due to a higher N-use efficiency in a major crop.

Quantitative analysis of nuclear shape in oral squamous cell carcinoma is useful for predicting the chemotherapeutic response.

The number of people afflicted with oral carcinoma in Japan has increased in recent years. Although preoperative neoadjuvant therapy with cisplatin and 5-fluorouracil are performed, chemotherapeutic response varies widely among the patients. With the aim of establishing novel indices to predict the therapeutic response to chemotherapy, we investigated the relationship between morphological features of pre-treatment oral carcinoma nuclei and the chemotherapeutic response using quantifying morphology of cell nuclei in pathological specimen images. We measured 4 morphological features of the nucleus of oral squamous cell carcinoma cases classified by the response to chemotherapy: No Change (NC) group, Partial Response (PR) group and Complete Response (CR) group. Furthermore, we performed immunohistochemical staining for p53 and Ki67 and calculated their positive rates in cancer tissues. Compactness and symmetry of the nucleus were significantly higher and nuclear edge response was significantly lower in cancer cells with lower chemotherapeutic responses compared high chemotherapeutic responders. As for positive rates of p53 and Ki67, there were no significant differences between any of the response groups. Morphological features of cancer cell nuclei in pathological specimens are sensitive predictive factors for the chemotherapeutic response to oral squamous cell carcinoma.

Age-related decrease of the retinal vasculature area identified with a novel computer-aided analysis system.

Fundus photographs enable non-invasive analysis of the status of the microcirculation by directly observing the retinal vasculature. Retinal microvascular abnormalities are important clinical markers of hypertension and arteriosclerosis, but retinal microvascular changes can be observed in older individuals without hypertension. In this study, our goal is to elucidate the effects of aging on fundus vessels in the retinal photograph. We analyzed retinal vessels of 161 healthy volunteers (49.5 ± 18.7 years, range 18-87) using in-house computer-aided measurement system to measure areas and diameters of all retinal vessels across the entire area of a retinal photograph. The vessels were segmented according to color, and then their area, size, length and thickness were measured by image processing. We also analyzed the correlation between total blood vessel area, age and mean arterial blood pressure (MABP). The decrease in total blood vessel area was dependent on both age and MABP. Moreover, decrease in blood vessel area was also correlated with age for the normotensive group. Furthermore, the slope of the regression line for retinal vessel area with MABP was significantly higher in participants aged ≤ 60 years than in those aged over 60 years. Changes in retinal vessel area with aging were observed in both arterioles and venules. In conclusion, we found the significant decrease in retinal vessel area that is correlated well with calendar age. Therefore, we need to carefully apply traditional classifications of fundus examination for hypertensive retinopathy in older individuals.

An algorithm for cancer nest feature extraction from pathological images.

Here, we propose an algorithm to automatically obtain extraction filters for the affected regions from cancer images. The proposed algorithm consists of two steps: extraction of affected region candidates and elimination of false positives. Useful features of cancer images, such as the area and degree of circularity of cancer nests, etc., are extracted using the derived filters. These features are useful for supporting pathological diagnosis. Automatic Construction of Tree-structural Image Transformation (ACTIT) was used to construct these filters to extract the affected regions from the image. The proposed algorithm was applied to a mouth cancer pathological image. The results confirmed that the proposed algorithm can obtain good filters capable of extracting cancer nests. The derived filters were also applied to other images from the same specimen. The results also indicated that the generated filters show general versatility in extracting cancer nest candidates. The area and degree of circularity of the cancer nets were also derived automatically.

Degradation of natural estrogen and identification of the metabolites produced by soil isolates of Rhodococcus sp. and Sphingomonas sp.

Five bacterial strains capable of utilizing 17beta-estradiol (E2) and estrone (E1) were isolated from soil samples. Using their morphological and physiological features and 16S rDNA sequences, we classified these isolates into two groups: Group A (Rhodococcus sp. strains ED6, ED7, and ED10) and Group B (Sphingomonas sp. strains ED8 and ED9). All isolates used E2 and E1 as the sole carbon sources and showed high E1 and E2 degradation activities. In all strains, more than 50% of 0.8 mg of E1 or E2 was degraded in 4 mL of inorganic medium over 24 h, and 90% was degraded over 120 h. By incubating the resting ED8 cells with E2 and the meta-cleavage inhibitor 3-chlorocatechol, we identified two metabolites, 4-hydroxyestrone (4-OH-E1) and 4-hydroxyestradiol (4-OH-E2), and confirmed their identity using authentic chemicals. The 4-OH-E1 and 4-OH-E2 compounds were assumed to be intermediate metabolites formed before meta-cleavage, as they were not identified in culture without 3-chlorocatechol. Degradation of E2 by strain ED8 can be initiated by hydroxylation of the C-4 position, followed by meta-cleavage of the benzene ring. When strains ED8 degraded E2, we further identified hydroxy-E2, keto-E1 and -E2, and an additional degradation product via mass spectrometry. The presence of these compounds implied degradation through a second pathway initiated through an attack of the saturated ring.

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.