Automated recognition and segmentation of lung cancer cytological images based on deep learning.
Compared with histological examination of lung cancer, cytology is less invasive and provides better preservation of complete morphology and detail. However, traditional cytological diagnosis requires an experienced pathologist to evaluate all sections individually under a microscope, which is a tim...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0317996 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540228571627520 |
|---|---|
| author | Qingyang Wang Yazhi Luo Ying Zhao Shuhao Wang Yiru Niu Jinxi Di Jia Guo Guorong Lan Lei Yang Yu Shan Mao Yuan Tu Dingrong Zhong Pei Zhang |
| author_facet | Qingyang Wang Yazhi Luo Ying Zhao Shuhao Wang Yiru Niu Jinxi Di Jia Guo Guorong Lan Lei Yang Yu Shan Mao Yuan Tu Dingrong Zhong Pei Zhang |
| author_sort | Qingyang Wang |
| collection | DOAJ |
| description | Compared with histological examination of lung cancer, cytology is less invasive and provides better preservation of complete morphology and detail. However, traditional cytological diagnosis requires an experienced pathologist to evaluate all sections individually under a microscope, which is a time-consuming process with low interobserver consistency. With the development of deep neural networks, the You Only Look Once (YOLO) object-detection model has been recognized for its impressive speed and accuracy. Thus, in this study, we developed a model for intraoperative cytological segmentation of pulmonary lesions based on the YOLOv8 algorithm, which labels each instance by segmenting the image at the pixel level. The model achieved a mean pixel accuracy and mean intersection over union of 0.80 and 0.70, respectively, on the test set. At the image level, the accuracy and area under the receiver operating characteristic curve values for malignant and benign (or normal) lesions were 91.0% and 0.90, respectively. In addition, the model was deemed suitable for diagnosing pleural fluid cytology and bronchoalveolar lavage fluid cytology images. The model predictions were strongly correlated with pathologist diagnoses and the gold standard, indicating the model's ability to make clinical-level decisions during initial diagnosis. Thus, the proposed method is useful for rapidly localizing lung cancer cells based on microscopic images and outputting image interpretation results. |
| format | Article |
| id | doaj-art-08ffa9357c4d47eaa1e2b076fb1eb965 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-08ffa9357c4d47eaa1e2b076fb1eb9652025-02-05T05:31:39ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e031799610.1371/journal.pone.0317996Automated recognition and segmentation of lung cancer cytological images based on deep learning.Qingyang WangYazhi LuoYing ZhaoShuhao WangYiru NiuJinxi DiJia GuoGuorong LanLei YangYu Shan MaoYuan TuDingrong ZhongPei ZhangCompared with histological examination of lung cancer, cytology is less invasive and provides better preservation of complete morphology and detail. However, traditional cytological diagnosis requires an experienced pathologist to evaluate all sections individually under a microscope, which is a time-consuming process with low interobserver consistency. With the development of deep neural networks, the You Only Look Once (YOLO) object-detection model has been recognized for its impressive speed and accuracy. Thus, in this study, we developed a model for intraoperative cytological segmentation of pulmonary lesions based on the YOLOv8 algorithm, which labels each instance by segmenting the image at the pixel level. The model achieved a mean pixel accuracy and mean intersection over union of 0.80 and 0.70, respectively, on the test set. At the image level, the accuracy and area under the receiver operating characteristic curve values for malignant and benign (or normal) lesions were 91.0% and 0.90, respectively. In addition, the model was deemed suitable for diagnosing pleural fluid cytology and bronchoalveolar lavage fluid cytology images. The model predictions were strongly correlated with pathologist diagnoses and the gold standard, indicating the model's ability to make clinical-level decisions during initial diagnosis. Thus, the proposed method is useful for rapidly localizing lung cancer cells based on microscopic images and outputting image interpretation results.https://doi.org/10.1371/journal.pone.0317996 |
| spellingShingle | Qingyang Wang Yazhi Luo Ying Zhao Shuhao Wang Yiru Niu Jinxi Di Jia Guo Guorong Lan Lei Yang Yu Shan Mao Yuan Tu Dingrong Zhong Pei Zhang Automated recognition and segmentation of lung cancer cytological images based on deep learning. PLoS ONE |
| title | Automated recognition and segmentation of lung cancer cytological images based on deep learning. |
| title_full | Automated recognition and segmentation of lung cancer cytological images based on deep learning. |
| title_fullStr | Automated recognition and segmentation of lung cancer cytological images based on deep learning. |
| title_full_unstemmed | Automated recognition and segmentation of lung cancer cytological images based on deep learning. |
| title_short | Automated recognition and segmentation of lung cancer cytological images based on deep learning. |
| title_sort | automated recognition and segmentation of lung cancer cytological images based on deep learning |
| url | https://doi.org/10.1371/journal.pone.0317996 |
| work_keys_str_mv | AT qingyangwang automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT yazhiluo automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT yingzhao automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT shuhaowang automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT yiruniu automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT jinxidi automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT jiaguo automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT guoronglan automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT leiyang automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT yushanmao automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT yuantu automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT dingrongzhong automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning AT peizhang automatedrecognitionandsegmentationoflungcancercytologicalimagesbasedondeeplearning |