Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder Cancer
Although the tumor-stroma ratio (TSR) has prognostic value in many cancers, the traditional semi-quantitative visual assessment method has inter-observer variability, making it impossible for clinical practice. We aimed to develop a machine learning (ML) algorithm for accurately quantifying TSR in h...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/24/3/2746 |
| _version_ | 1797624203523915776 |
|---|---|
| author | Qingyuan Zheng Zhengyu Jiang Xinmiao Ni Song Yang Panpan Jiao Jiejun Wu Lin Xiong Jingping Yuan Jingsong Wang Jun Jian Lei Wang Rui Yang Zhiyuan Chen Xiuheng Liu |
| author_facet | Qingyuan Zheng Zhengyu Jiang Xinmiao Ni Song Yang Panpan Jiao Jiejun Wu Lin Xiong Jingping Yuan Jingsong Wang Jun Jian Lei Wang Rui Yang Zhiyuan Chen Xiuheng Liu |
| author_sort | Qingyuan Zheng |
| collection | DOAJ |
| description | Although the tumor-stroma ratio (TSR) has prognostic value in many cancers, the traditional semi-quantitative visual assessment method has inter-observer variability, making it impossible for clinical practice. We aimed to develop a machine learning (ML) algorithm for accurately quantifying TSR in hematoxylin-and-eosin (H&E)-stained whole slide images (WSI) and further investigate its prognostic effect in patients with muscle-invasive bladder cancer (MIBC). We used an optimal cell classifier previously built based on QuPath open-source software and ML algorithm for quantitative calculation of TSR. We retrospectively analyzed data from two independent cohorts to verify the prognostic significance of ML-based TSR in MIBC patients. WSIs from 133 MIBC patients were used as the discovery set to identify the optimal association of TSR with patient survival outcomes. Furthermore, we performed validation in an independent external cohort consisting of 261 MIBC patients. We demonstrated a significant prognostic association of ML-based TSR with survival outcomes in MIBC patients (<i>p</i> < 0.001 for all comparisons), with higher TSR associated with better prognosis. Uni- and multivariate Cox regression analyses showed that TSR was independently associated with overall survival (<i>p</i> < 0.001 for all analyses) after adjusting for clinicopathological factors including age, gender, and pathologic stage. TSR was found to be a strong prognostic factor that was not redundant with the existing staging system in different subgroup analyses (<i>p</i> < 0.05 for all analyses). Finally, the expression of six genes (DACH1, DEEND2A, NOTCH4, DTWD1, TAF6L, and MARCHF5) were significantly associated with TSR, revealing possible potential biological relevance. In conclusion, we developed an ML algorithm based on WSIs of MIBC patients to accurately quantify TSR and demonstrated its prognostic validity for MIBC patients in two independent cohorts. This objective quantitative method allows application in clinical practice while reducing the workload of pathologists. Thus, it might be of significant aid in promoting precise pathology services in MIBC. |
| first_indexed | 2024-03-11T09:39:37Z |
| format | Article |
| id | doaj.art-28a3d15997c440768175d9701a46be9e |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-11T09:39:37Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-28a3d15997c440768175d9701a46be9e2023-11-16T17:01:45ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672023-02-01243274610.3390/ijms24032746Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder CancerQingyuan Zheng0Zhengyu Jiang1Xinmiao Ni2Song Yang3Panpan Jiao4Jiejun Wu5Lin Xiong6Jingping Yuan7Jingsong Wang8Jun Jian9Lei Wang10Rui Yang11Zhiyuan Chen12Xiuheng Liu13Department of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Pathology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Pathology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaDepartment of Urology, Renmin Hospital of Wuhan University, Wuhan 430060, ChinaAlthough the tumor-stroma ratio (TSR) has prognostic value in many cancers, the traditional semi-quantitative visual assessment method has inter-observer variability, making it impossible for clinical practice. We aimed to develop a machine learning (ML) algorithm for accurately quantifying TSR in hematoxylin-and-eosin (H&E)-stained whole slide images (WSI) and further investigate its prognostic effect in patients with muscle-invasive bladder cancer (MIBC). We used an optimal cell classifier previously built based on QuPath open-source software and ML algorithm for quantitative calculation of TSR. We retrospectively analyzed data from two independent cohorts to verify the prognostic significance of ML-based TSR in MIBC patients. WSIs from 133 MIBC patients were used as the discovery set to identify the optimal association of TSR with patient survival outcomes. Furthermore, we performed validation in an independent external cohort consisting of 261 MIBC patients. We demonstrated a significant prognostic association of ML-based TSR with survival outcomes in MIBC patients (<i>p</i> < 0.001 for all comparisons), with higher TSR associated with better prognosis. Uni- and multivariate Cox regression analyses showed that TSR was independently associated with overall survival (<i>p</i> < 0.001 for all analyses) after adjusting for clinicopathological factors including age, gender, and pathologic stage. TSR was found to be a strong prognostic factor that was not redundant with the existing staging system in different subgroup analyses (<i>p</i> < 0.05 for all analyses). Finally, the expression of six genes (DACH1, DEEND2A, NOTCH4, DTWD1, TAF6L, and MARCHF5) were significantly associated with TSR, revealing possible potential biological relevance. In conclusion, we developed an ML algorithm based on WSIs of MIBC patients to accurately quantify TSR and demonstrated its prognostic validity for MIBC patients in two independent cohorts. This objective quantitative method allows application in clinical practice while reducing the workload of pathologists. Thus, it might be of significant aid in promoting precise pathology services in MIBC.https://www.mdpi.com/1422-0067/24/3/2746tumor-stroma ratiowhole slide imagemachine learningprognosis predictionmuscle-invasive bladder cancer |
| spellingShingle | Qingyuan Zheng Zhengyu Jiang Xinmiao Ni Song Yang Panpan Jiao Jiejun Wu Lin Xiong Jingping Yuan Jingsong Wang Jun Jian Lei Wang Rui Yang Zhiyuan Chen Xiuheng Liu Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder Cancer International Journal of Molecular Sciences tumor-stroma ratio whole slide image machine learning prognosis prediction muscle-invasive bladder cancer |
| title | Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder Cancer |
| title_full | Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder Cancer |
| title_fullStr | Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder Cancer |
| title_full_unstemmed | Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder Cancer |
| title_short | Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder Cancer |
| title_sort | machine learning quantified tumor stroma ratio is an independent prognosticator in muscle invasive bladder cancer |
| topic | tumor-stroma ratio whole slide image machine learning prognosis prediction muscle-invasive bladder cancer |
| url | https://www.mdpi.com/1422-0067/24/3/2746 |
| work_keys_str_mv | AT qingyuanzheng machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT zhengyujiang machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT xinmiaoni machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT songyang machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT panpanjiao machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT jiejunwu machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT linxiong machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT jingpingyuan machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT jingsongwang machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT junjian machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT leiwang machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT ruiyang machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT zhiyuanchen machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer AT xiuhengliu machinelearningquantifiedtumorstromaratioisanindependentprognosticatorinmuscleinvasivebladdercancer |