Accurate Prediction of Metachronous Liver Metastasis in Stage I-III Colorectal Cancer Patients Using Deep Learning With Digital Pathological Images
ObjectivesMetachronous liver metastasis (LM) significantly impacts the prognosis of stage I-III colorectal cancer (CRC) patients. An effective biomarker to predict LM after surgery is urgently needed. We aimed to develop deep learning-based models to assist in predicting LM in stage I-III CRC patien...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.844067/full |
| _version_ | 1818309089298481152 |
|---|---|
| author | Chanchan Xiao Chanchan Xiao Meihua Zhou Xihua Yang Haoyun Wang Zhen Tang Zheng Zhou Zeyu Tian Qi Liu Xiaojie Li Wei Jiang Wei Jiang Jihui Luo |
| author_facet | Chanchan Xiao Chanchan Xiao Meihua Zhou Xihua Yang Haoyun Wang Zhen Tang Zheng Zhou Zeyu Tian Qi Liu Xiaojie Li Wei Jiang Wei Jiang Jihui Luo |
| author_sort | Chanchan Xiao |
| collection | DOAJ |
| description | ObjectivesMetachronous liver metastasis (LM) significantly impacts the prognosis of stage I-III colorectal cancer (CRC) patients. An effective biomarker to predict LM after surgery is urgently needed. We aimed to develop deep learning-based models to assist in predicting LM in stage I-III CRC patients using digital pathological images.MethodsSix-hundred eleven patients were retrospectively included in the study and randomly divided into training (428 patients) and validation (183 patients) cohorts according to the 7:3 ratio. Digital HE images from training cohort patients were used to construct the LM risk score based on a 50-layer residual convolutional neural network (ResNet-50). An LM prediction model was established by multivariable Cox analysis and confirmed in the validation cohort. The performance of the integrated nomogram was assessed with respect to its calibration, discrimination, and clinical application value.ResultsPatients were divided into low- and high-LM risk score groups according to the cutoff value and significant differences were observed in the LM of the different risk score groups in the training and validation cohorts (P<0.001). Multivariable analysis revealed that the LM risk score, VELIPI, pT stage and pN stage were independent predictors of LM. Then, the prediction model was developed and presented as a nomogram to predict the 1-, 2-, and 3-year probability of LM. The integrated nomogram achieved satisfactory discrimination, with C-indexes of 0.807 (95% CI: 0.787, 0.827) and 0.812 (95% CI: 0.773, 0.850) and AUCs of 0.840 (95% CI: 0.795, 0.885) and 0.848 (95% CI: 0.766, 0.931) in the training and validation cohorts, respectively. Favorable calibration of the nomogram was confirmed in the training and validation cohorts. Integrated discrimination improvement and net reclassification index indicated that the integrated nomogram was superior to the traditional clinicopathological model. Decision curve analysis confirmed that the nomogram has clinical application value.ConclusionsThe LM risk score based on ResNet-50 and digital HE images was significantly associated with LM. The integrated nomogram could identify stage I-III CRC patients at high risk of LM after primary colectomy, so it may serve as a potential tool to choose the appropriate treatment to improve the prognosis of stage I-III CRC patients. |
| first_indexed | 2024-12-13T07:24:37Z |
| format | Article |
| id | doaj.art-62ae1439024f44308c460f2ad1d7d12a |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-13T07:24:37Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-62ae1439024f44308c460f2ad1d7d12a2022-12-21T23:55:19ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-04-011210.3389/fonc.2022.844067844067Accurate Prediction of Metachronous Liver Metastasis in Stage I-III Colorectal Cancer Patients Using Deep Learning With Digital Pathological ImagesChanchan Xiao0Chanchan Xiao1Meihua Zhou2Xihua Yang3Haoyun Wang4Zhen Tang5Zheng Zhou6Zeyu Tian7Qi Liu8Xiaojie Li9Wei Jiang10Wei Jiang11Jihui Luo12Department of General Surgery, Hunan Provincial People’s Hospital (The First-Affiliated Hospital of Hunan Normal University), Changsha, ChinaDepartment of Microbiology and Immunology, Institute of Geriatric Immunology, School of Medicine, Jinan University, Guangzhou, ChinaDepartment of General Surgery, Hunan Provincial People’s Hospital (The First-Affiliated Hospital of Hunan Normal University), Changsha, ChinaDepartment of Surgical Oncology, Chenzhou No. 1 People’s Hospital, Chenzhou, ChinaDepartment of Microbiology and Immunology, Institute of Geriatric Immunology, School of Medicine, Jinan University, Guangzhou, ChinaDepartment of General Surgery, Hunan Provincial People’s Hospital (The First-Affiliated Hospital of Hunan Normal University), Changsha, ChinaDepartment of General Surgery, Hunan Provincial People’s Hospital (The First-Affiliated Hospital of Hunan Normal University), Changsha, ChinaDepartment of General Surgery, Hunan Provincial People’s Hospital (The First-Affiliated Hospital of Hunan Normal University), Changsha, ChinaDepartment of General Surgery, Hunan Provincial People’s Hospital (The First-Affiliated Hospital of Hunan Normal University), Changsha, ChinaDepartment of Pathology, Chenzhou No. 1 People’s Hospital, Chenzhou, ChinaDepartment of General Surgery, Hunan Provincial People’s Hospital (The First-Affiliated Hospital of Hunan Normal University), Changsha, ChinaDepartment of Surgical Oncology, Chenzhou No. 1 People’s Hospital, Chenzhou, ChinaDepartment of General Surgery, Hunan Provincial People’s Hospital (The First-Affiliated Hospital of Hunan Normal University), Changsha, ChinaObjectivesMetachronous liver metastasis (LM) significantly impacts the prognosis of stage I-III colorectal cancer (CRC) patients. An effective biomarker to predict LM after surgery is urgently needed. We aimed to develop deep learning-based models to assist in predicting LM in stage I-III CRC patients using digital pathological images.MethodsSix-hundred eleven patients were retrospectively included in the study and randomly divided into training (428 patients) and validation (183 patients) cohorts according to the 7:3 ratio. Digital HE images from training cohort patients were used to construct the LM risk score based on a 50-layer residual convolutional neural network (ResNet-50). An LM prediction model was established by multivariable Cox analysis and confirmed in the validation cohort. The performance of the integrated nomogram was assessed with respect to its calibration, discrimination, and clinical application value.ResultsPatients were divided into low- and high-LM risk score groups according to the cutoff value and significant differences were observed in the LM of the different risk score groups in the training and validation cohorts (P<0.001). Multivariable analysis revealed that the LM risk score, VELIPI, pT stage and pN stage were independent predictors of LM. Then, the prediction model was developed and presented as a nomogram to predict the 1-, 2-, and 3-year probability of LM. The integrated nomogram achieved satisfactory discrimination, with C-indexes of 0.807 (95% CI: 0.787, 0.827) and 0.812 (95% CI: 0.773, 0.850) and AUCs of 0.840 (95% CI: 0.795, 0.885) and 0.848 (95% CI: 0.766, 0.931) in the training and validation cohorts, respectively. Favorable calibration of the nomogram was confirmed in the training and validation cohorts. Integrated discrimination improvement and net reclassification index indicated that the integrated nomogram was superior to the traditional clinicopathological model. Decision curve analysis confirmed that the nomogram has clinical application value.ConclusionsThe LM risk score based on ResNet-50 and digital HE images was significantly associated with LM. The integrated nomogram could identify stage I-III CRC patients at high risk of LM after primary colectomy, so it may serve as a potential tool to choose the appropriate treatment to improve the prognosis of stage I-III CRC patients.https://www.frontiersin.org/articles/10.3389/fonc.2022.844067/fulldeep learningcolorectal cancermetachronous liver metastasisprediction modelnomogram |
| spellingShingle | Chanchan Xiao Chanchan Xiao Meihua Zhou Xihua Yang Haoyun Wang Zhen Tang Zheng Zhou Zeyu Tian Qi Liu Xiaojie Li Wei Jiang Wei Jiang Jihui Luo Accurate Prediction of Metachronous Liver Metastasis in Stage I-III Colorectal Cancer Patients Using Deep Learning With Digital Pathological Images Frontiers in Oncology deep learning colorectal cancer metachronous liver metastasis prediction model nomogram |
| title | Accurate Prediction of Metachronous Liver Metastasis in Stage I-III Colorectal Cancer Patients Using Deep Learning With Digital Pathological Images |
| title_full | Accurate Prediction of Metachronous Liver Metastasis in Stage I-III Colorectal Cancer Patients Using Deep Learning With Digital Pathological Images |
| title_fullStr | Accurate Prediction of Metachronous Liver Metastasis in Stage I-III Colorectal Cancer Patients Using Deep Learning With Digital Pathological Images |
| title_full_unstemmed | Accurate Prediction of Metachronous Liver Metastasis in Stage I-III Colorectal Cancer Patients Using Deep Learning With Digital Pathological Images |
| title_short | Accurate Prediction of Metachronous Liver Metastasis in Stage I-III Colorectal Cancer Patients Using Deep Learning With Digital Pathological Images |
| title_sort | accurate prediction of metachronous liver metastasis in stage i iii colorectal cancer patients using deep learning with digital pathological images |
| topic | deep learning colorectal cancer metachronous liver metastasis prediction model nomogram |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.844067/full |
| work_keys_str_mv | AT chanchanxiao accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT chanchanxiao accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT meihuazhou accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT xihuayang accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT haoyunwang accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT zhentang accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT zhengzhou accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT zeyutian accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT qiliu accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT xiaojieli accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT weijiang accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT weijiang accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages AT jihuiluo accuratepredictionofmetachronouslivermetastasisinstageiiiicolorectalcancerpatientsusingdeeplearningwithdigitalpathologicalimages |