Cytopathology : official journal of the British Society for Clinical Cytology · 2026
A Two-Dimensional Plot of Cell Aggregates and Their Largest Nuclei Distinguishes Benign From Malignant Pleural Effusion Cytology Specimens.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Kaneko Rio, Kobayashi Sayaka, Ikota Hayato, Shibanuma Rio, Nishijima Yoshimi, Hisada Takeshi, Yokoo Hideaki, Saio Masanao
Аннотация
OBJECTIVE: This study aimed to analyze the morphological characteristics of cells observed in pleural effusion cytology specimens using computer-assisted image analysis (CAIA).
METHODS: We examined 166 pleural effusion cytology specimens obtained for suspected lung cancer, including 80 negative, 22 suspicious and 64 positive cases. Whole-slide images (WSIs) were generated from Papanicolaou-stained specimens, and image analysis was performed using virtual slide cytology image analysis software. A scatter plot was then created, with the x-axis representing the area of each cell or cell cluster and the y-axis representing the maximum nuclear area within that cluster. The resulting plot type and the positive rate (PR) were subsequently evaluated.
RESULTS: Four distinct plot types were defined from the scatter plots: small cluster type (S-type), horizontal type (H-type), vertical type (V-type) and diagonal type (D-type). Overall, S-type and H-type patterns were commonly observed in non-cancer or cytologically negative cases, whereas V-type and D-type patterns predominated in cytologically positive cases. In suspicious cases, S-type and V-type plots each accounted for roughly half of the samples. The PR was significantly higher in cytologically positive cases relative to non-cancer and cytologically negative cases (p < 0.0001).
CONCLUSIONS: In pleural cytology specimens from patients with lung cancer, the degree of cell aggregation and nuclear overlap is an important factor for distinguishing benign from malignant lesions. Moreover, although AI-based image analysis has advanced rapidly in recent years, this study emphasizes the continued value of CAIA approaches that employ algorithms readily interpretable by humans.
METHODS: We examined 166 pleural effusion cytology specimens obtained for suspected lung cancer, including 80 negative, 22 suspicious and 64 positive cases. Whole-slide images (WSIs) were generated from Papanicolaou-stained specimens, and image analysis was performed using virtual slide cytology image analysis software. A scatter plot was then created, with the x-axis representing the area of each cell or cell cluster and the y-axis representing the maximum nuclear area within that cluster. The resulting plot type and the positive rate (PR) were subsequently evaluated.
RESULTS: Four distinct plot types were defined from the scatter plots: small cluster type (S-type), horizontal type (H-type), vertical type (V-type) and diagonal type (D-type). Overall, S-type and H-type patterns were commonly observed in non-cancer or cytologically negative cases, whereas V-type and D-type patterns predominated in cytologically positive cases. In suspicious cases, S-type and V-type plots each accounted for roughly half of the samples. The PR was significantly higher in cytologically positive cases relative to non-cancer and cytologically negative cases (p < 0.0001).
CONCLUSIONS: In pleural cytology specimens from patients with lung cancer, the degree of cell aggregation and nuclear overlap is an important factor for distinguishing benign from malignant lesions. Moreover, although AI-based image analysis has advanced rapidly in recent years, this study emphasizes the continued value of CAIA approaches that employ algorithms readily interpretable by humans.