2
|
Huang KB, Gui CP, Xu YZ, Li XS, Zhao HW, Cao JZ, Chen YH, Pan YH, Liao B, Cao Y, Zhang XK, Han H, Zhou FJ, Liu RY, Chen WF, Jiang ZY, Feng ZH, Jiang FN, Yu YF, Xiong SW, Han GP, Tang Q, Ouyang K, Qu GM, Wu JT, Cao M, Dong BJ, Huang YR, Zhang J, Li CX, Li PX, Chen W, Zhong WD, Guo JP, Liu ZP, Hsieh JT, Xie D, Cai MY, Xue W, Wei JH, Luo JH. A multi-classifier system integrated by clinico-histology-genomic analysis for predicting recurrence of papillary renal cell carcinoma. Nat Commun 2024; 15:6215. [PMID: 39043664 PMCID: PMC11266571 DOI: 10.1038/s41467-024-50369-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2023] [Accepted: 07/02/2024] [Indexed: 07/25/2024] Open
Abstract
Integrating genomics and histology for cancer prognosis demonstrates promise. Here, we develop a multi-classifier system integrating a lncRNA-based classifier, a deep learning whole-slide-image-based classifier, and a clinicopathological classifier to accurately predict post-surgery localized (stage I-III) papillary renal cell carcinoma (pRCC) recurrence. The multi-classifier system demonstrates significantly higher predictive accuracy for recurrence-free survival (RFS) compared to the three single classifiers alone in the training set and in both validation sets (C-index 0.831-0.858 vs. 0.642-0.777, p < 0.05). The RFS in our multi-classifier-defined high-risk stage I/II and grade 1/2 groups is significantly worse than in the low-risk stage III and grade 3/4 groups (p < 0.05). Our multi-classifier system is a practical and reliable predictor for recurrence of localized pRCC after surgery that can be used with the current staging system to more accurately predict disease course and inform strategies for individualized adjuvant therapy.
Collapse
Affiliation(s)
- Kang-Bo Huang
- Department of Urology, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
- Department of Urology, Sun Yat-sen University Cancer center, Guangzhou, China
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer center, Guangzhou, China
| | - Cheng-Peng Gui
- Department of Urology, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Yun-Ze Xu
- Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Xue-Song Li
- Department of Urology, Peking University First Hospital, Institute of Urology, Peking University, National Urological Cancer Center, Beijing, China
| | - Hong-Wei Zhao
- Department of Urology, Affiliated Yantai Yuhuangding Hospital, Qingdao University, Yantai, China
| | - Jia-Zheng Cao
- Department of Urology, Jiangmen Hospital, Sun Yat-sen University, Jiangmen, China
| | - Yu-Hang Chen
- Department of Urology, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Yi-Hui Pan
- Department of Urology, The Third Affiliated Hospital of Soochow University, Changzhou, China
| | - Bing Liao
- Department of Pathology, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Yun Cao
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer center, Guangzhou, China
- Department of Pathology, Sun Yat-sen University Cancer center, Guangzhou, China
| | - Xin-Ke Zhang
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer center, Guangzhou, China
- Department of Pathology, Sun Yat-sen University Cancer center, Guangzhou, China
| | - Hui Han
- Department of Urology, Sun Yat-sen University Cancer center, Guangzhou, China
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer center, Guangzhou, China
| | - Fang-Jian Zhou
- Department of Urology, Sun Yat-sen University Cancer center, Guangzhou, China
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer center, Guangzhou, China
| | - Ran-Yi Liu
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer center, Guangzhou, China
| | - Wen-Fang Chen
- Department of Pathology, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Ze-Ying Jiang
- Department of Pathology, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Zi-Hao Feng
- Department of Urology, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Fu-Neng Jiang
- Department of Urology, Guangdong Key Laboratory of Clinical Molecular Medicine and Diagnostics, Guangzhou First People's Hospital, School of Medicine, South China University of Technology, Guangzhou, China
| | - Yan-Fei Yu
- Department of Urology, Peking University First Hospital, Institute of Urology, Peking University, National Urological Cancer Center, Beijing, China
| | - Sheng-Wei Xiong
- Department of Urology, Peking University First Hospital, Institute of Urology, Peking University, National Urological Cancer Center, Beijing, China
| | - Guan-Peng Han
- Department of Urology, Peking University First Hospital, Institute of Urology, Peking University, National Urological Cancer Center, Beijing, China
| | - Qi Tang
- Department of Urology, Peking University First Hospital, Institute of Urology, Peking University, National Urological Cancer Center, Beijing, China
| | - Kui Ouyang
- Department of Urology, Affiliated Yantai Yuhuangding Hospital, Qingdao University, Yantai, China
| | - Gui-Mei Qu
- Department of Pathology, Affiliated Yantai Yuhuangding Hospital, Qingdao University, Yantai, China
| | - Ji-Tao Wu
- Department of Urology, Affiliated Yantai Yuhuangding Hospital, Qingdao University, Yantai, China
| | - Ming Cao
- Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Bai-Jun Dong
- Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Yi-Ran Huang
- Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Jin Zhang
- Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Cai-Xia Li
- School of Mathematics and Computational Science, Sun Yat-sen University, Guangzhou, China
| | - Pei-Xing Li
- School of Mathematics and Computational Science, Sun Yat-sen University, Guangzhou, China
| | - Wei Chen
- Department of Urology, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Wei-De Zhong
- Department of Urology, Guangdong Key Laboratory of Clinical Molecular Medicine and Diagnostics, Guangzhou First People's Hospital, School of Medicine, South China University of Technology, Guangzhou, China
| | - Jian-Ping Guo
- Institute of Precision Medicine, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Zhi-Ping Liu
- Department of Internal Medicine and Department of Molecular Biology, University of Texas Southwestern Medical Center at Dallas, Dallas, TX, USA
| | - Jer-Tsong Hsieh
- Department of Urology, University of Texas Southwestern Medical Center at Dallas, Dallas, TX, USA
| | - Dan Xie
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer center, Guangzhou, China
- Department of Pathology, Sun Yat-sen University Cancer center, Guangzhou, China
| | - Mu-Yan Cai
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer center, Guangzhou, China
- Department of Pathology, Sun Yat-sen University Cancer center, Guangzhou, China
| | - Wei Xue
- Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China.
| | - Jin-Huan Wei
- Department of Urology, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
| | - Jun-Hang Luo
- Department of Urology, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
- Institute of Precision Medicine, First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
| |
Collapse
|
3
|
Liu Y, Zhen T, Fu Y, Wang Y, He Y, Han A, Shi H. AI-Powered Segmentation of Invasive Carcinoma Regions in Breast Cancer Immunohistochemical Whole-Slide Images. Cancers (Basel) 2023; 16:167. [PMID: 38201594 PMCID: PMC10778369 DOI: 10.3390/cancers16010167] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2023] [Revised: 12/24/2023] [Accepted: 12/26/2023] [Indexed: 01/12/2024] Open
Abstract
AIMS The automation of quantitative evaluation for breast immunohistochemistry (IHC) plays a crucial role in reducing the workload of pathologists and enhancing the objectivity of diagnoses. However, current methods face challenges in achieving fully automated immunohistochemistry quantification due to the complexity of segmenting the tumor area into distinct ductal carcinoma in situ (DCIS) and invasive carcinoma (IC) regions. Moreover, the quantitative analysis of immunohistochemistry requires a specific focus on invasive carcinoma regions. METHODS AND RESULTS In this study, we propose an innovative approach to automatically identify invasive carcinoma regions in breast cancer immunohistochemistry whole-slide images (WSIs). Our method leverages a neural network that combines multi-scale morphological features with boundary features, enabling precise segmentation of invasive carcinoma regions without the need for additional H&E and P63 staining slides. In addition, we introduced an advanced semi-supervised learning algorithm, allowing efficient training of the model using unlabeled data. To evaluate the effectiveness of our approach, we constructed a dataset consisting of 618 IHC-stained WSIs from 170 cases, including four types of staining (ER, PR, HER2, and Ki-67). Notably, the model demonstrated an impressive intersection over union (IoU) score exceeding 80% on the test set. Furthermore, to ascertain the practical utility of our model in IHC quantitative evaluation, we constructed a fully automated Ki-67 scoring system based on the model's predictions. Comparative experiments convincingly demonstrated that our system exhibited high consistency with the scores given by experienced pathologists. CONCLUSIONS Our developed model excels in accurately distinguishing between DCIS and invasive carcinoma regions in breast cancer immunohistochemistry WSIs. This method paves the way for a clinically available, fully automated immunohistochemistry quantitative scoring system.
Collapse
Affiliation(s)
- Yiqing Liu
- Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China; (Y.L.); (Y.F.); (Y.W.); (Y.H.)
| | - Tiantian Zhen
- Department of Pathology, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou 510080, China;
| | - Yuqiu Fu
- Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China; (Y.L.); (Y.F.); (Y.W.); (Y.H.)
| | - Yizhi Wang
- Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China; (Y.L.); (Y.F.); (Y.W.); (Y.H.)
| | - Yonghong He
- Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China; (Y.L.); (Y.F.); (Y.W.); (Y.H.)
| | - Anjia Han
- Department of Pathology, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou 510080, China;
| | - Huijuan Shi
- Department of Pathology, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou 510080, China;
| |
Collapse
|
5
|
Gong Z, Li X, Shi M, Cai G, Chen S, Ye Z, Gan X, Yang R, Wang R, Chen Z. Measuring the binary thickness of buccal bone of anterior maxilla in low-resolution cone-beam computed tomography via a bilinear convolutional neural network. Quant Imaging Med Surg 2023; 13:8053-8066. [PMID: 38106266 PMCID: PMC10722026 DOI: 10.21037/qims-23-744] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Accepted: 08/28/2023] [Indexed: 12/19/2023]
Abstract
Background The thickness of the buccal bone of the anterior maxilla is an important aesthetic-determining factor for dental implant, which is divided into the thick (≥1 mm) and thin type (<1 mm). However, as a micro-scale structure that is evaluated through low-resolution cone-beam computed tomography (CBCT), its thickness measurement is error-prone under the circumstance of enormous patients and relatively inexperienced primary dentists. Further, the challenges of deep learning-based analysis of the binary thickness of buccal bone include the substantial real-world variance caused by pixel error, the extraction of fine-grained features, and burdensome annotations. Methods This study built bilinear convolutional neural network (BCNN) with 2 convolutional neural network (CNN) backbones and a bilinear pooling module to predict the binary thickness of buccal bone (thick or thin) of the anterior maxilla in an end-to-end manner. The methods of 5-fold cross-validation and model ensemble were adopted at the training and testing stages. The visualization methods of Gradient Weighted Class Activation Mapping (Grad-CAM), Guided Grad-CAM, and layer-wise relevance propagation (LRP) were used for revealing the important features on which the model focused. The performance metrics and efficacy were compared between BCNN, dentists of different clinical experience (i.e., dental student, junior dentist, and senior dentist), and the fusion of BCNN and dentists to investigate the clinical feasibility of BCNN. Results Based on the dataset of 4,000 CBCT images from 1,000 patients (aged 36.15±13.09 years), the BCNN with visual geometry group (VGG)16 backbone achieved an accuracy of 0.870 [95% confidence interval (CI): 0.838-0.902] and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.924 (95% CI: 0.896-0.948). Compared with the conventional CNNs, BCNN precisely located the buccal bone wall over irrelevant regions. The BCNN generally outperformed the expert-level dentists. The clinical diagnostic performance of the dentists was improved with the assistance of BCNN. Conclusions The application of BCNN to the quantitative analysis of binary buccal bone thickness validated the model's excellent ability of subtle feature extraction and achieved expert-level performance. This work signals the potential of fine-grained image recognition networks to the precise quantitative analysis of micro-scale structures.
Collapse
Affiliation(s)
- Zhuohong Gong
- Hospital of Stomatology, Guanghua School of Stomatology, Guangdong Provincial Key Laboratory of Stomatology, Sun Yat-sen University, Guangzhou, China
| | - Xiaohui Li
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
| | - Mengru Shi
- Hospital of Stomatology, Guanghua School of Stomatology, Guangdong Provincial Key Laboratory of Stomatology, Sun Yat-sen University, Guangzhou, China
| | - Gengbin Cai
- Hospital of Stomatology, Guanghua School of Stomatology, Guangdong Provincial Key Laboratory of Stomatology, Sun Yat-sen University, Guangzhou, China
| | - Shijie Chen
- Hospital of Stomatology, Guanghua School of Stomatology, Guangdong Provincial Key Laboratory of Stomatology, Sun Yat-sen University, Guangzhou, China
| | - Zejun Ye
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
| | - Xuejing Gan
- Hospital of Stomatology, Guanghua School of Stomatology, Guangdong Provincial Key Laboratory of Stomatology, Sun Yat-sen University, Guangzhou, China
| | - Ruihan Yang
- Hospital of Stomatology, Guanghua School of Stomatology, Guangdong Provincial Key Laboratory of Stomatology, Sun Yat-sen University, Guangzhou, China
| | - Ruixuan Wang
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
| | - Zetao Chen
- Hospital of Stomatology, Guanghua School of Stomatology, Guangdong Provincial Key Laboratory of Stomatology, Sun Yat-sen University, Guangzhou, China
| |
Collapse
|
6
|
Ashurov A, Chelloug SA, Tselykh A, Muthanna MSA, Muthanna A, Al-Gaashani MSAM. Improved Breast Cancer Classification through Combining Transfer Learning and Attention Mechanism. Life (Basel) 2023; 13:1945. [PMID: 37763348 PMCID: PMC10532552 DOI: 10.3390/life13091945] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Revised: 09/16/2023] [Accepted: 09/17/2023] [Indexed: 09/29/2023] Open
Abstract
Breast cancer, a leading cause of female mortality worldwide, poses a significant health challenge. Recent advancements in deep learning techniques have revolutionized breast cancer pathology by enabling accurate image classification. Various imaging methods, such as mammography, CT, MRI, ultrasound, and biopsies, aid in breast cancer detection. Computer-assisted pathological image classification is of paramount importance for breast cancer diagnosis. This study introduces a novel approach to breast cancer histopathological image classification. It leverages modified pre-trained CNN models and attention mechanisms to enhance model interpretability and robustness, emphasizing localized features and enabling accurate discrimination of complex cases. Our method involves transfer learning with deep CNN models-Xception, VGG16, ResNet50, MobileNet, and DenseNet121-augmented with the convolutional block attention module (CBAM). The pre-trained models are finetuned, and the two CBAM models are incorporated at the end of the pre-trained models. The models are compared to state-of-the-art breast cancer diagnosis approaches and tested for accuracy, precision, recall, and F1 score. The confusion matrices are used to evaluate and visualize the results of the compared models. They help in assessing the models' performance. The test accuracy rates for the attention mechanism (AM) using the Xception model on the "BreakHis" breast cancer dataset are encouraging at 99.2% and 99.5%. The test accuracy for DenseNet121 with AMs is 99.6%. The proposed approaches also performed better than previous approaches examined in the related studies.
Collapse
Affiliation(s)
- Asadulla Ashurov
- School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
| | - Samia Allaoua Chelloug
- Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
| | - Alexey Tselykh
- Institute of Computer Technologies and Information Security, Southern Federal University, Taganrog 347922, Russia; (A.T.); (M.S.A.M.)
| | - Mohammed Saleh Ali Muthanna
- Institute of Computer Technologies and Information Security, Southern Federal University, Taganrog 347922, Russia; (A.T.); (M.S.A.M.)
| | - Ammar Muthanna
- RUDN University, 6 Miklukho-Maklaya Street, Moscow 117198, Russia;
| | - Mehdhar S. A. M. Al-Gaashani
- College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
| |
Collapse
|