1
|
Kildal W, Cyll K, Kalsnes J, Islam R, Julbø FM, Pradhan M, Ersvær E, Shepherd N, Vlatkovic L, Tekpli X, Garred Ø, Kristensen GB, Askautrud HA, Hveem TS, Danielsen HE. Deep learning for automated scoring of immunohistochemically stained tumour tissue sections - Validation across tumour types based on patient outcomes. Heliyon 2024; 10:e32529. [PMID: 39040241 PMCID: PMC11261074 DOI: 10.1016/j.heliyon.2024.e32529] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2024] [Accepted: 06/05/2024] [Indexed: 07/24/2024] Open
Abstract
We aimed to develop deep learning (DL) models to detect protein expression in immunohistochemically (IHC) stained tissue-sections, and to compare their accuracy and performance with manually scored clinically relevant proteins in common cancer types. Five cancer patient cohorts (colon, two prostate, breast, and endometrial) were included. We developed separate DL models for scoring IHC-stained tissue-sections with nuclear, cytoplasmic, and membranous staining patterns. For training, we used images with annotations of cells with positive and negative staining from the colon cohort stained for Ki-67 and PMS2 (nuclear model), the prostate cohort 1 stained for PTEN (cytoplasmic model) and β-catenin (membranous model). The nuclear DL model was validated for MSH6 in the colon, MSH6 and PMS2 in the endometrium, Ki-67 and CyclinB1 in prostate, and oestrogen and progesterone receptors in the breast cancer cohorts. The cytoplasmic DL model was validated for PTEN and Mapre2, and the membranous DL model for CD44 and Flotillin1, all in prostate cohorts. When comparing the results of manual and DL scores in the validation sets, using manual scores as the ground truth, we observed an average correct classification rate of 91.5 % (76.9-98.5 %) for the nuclear model, 85.6 % (73.3-96.6 %) for the cytoplasmic model, and 78.4 % (75.5-84.3 %) for the membranous model. In survival analyses, manual and DL scores showed similar prognostic impact, with similar hazard ratios and p-values for all DL models. Our findings demonstrate that DL models offer a promising alternative to manual IHC scoring, providing efficiency and reproducibility across various data sources and markers.
Collapse
Affiliation(s)
- Wanja Kildal
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Karolina Cyll
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Joakim Kalsnes
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Rakibul Islam
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Frida M. Julbø
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Manohar Pradhan
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Elin Ersvær
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Neil Shepherd
- Gloucestershire Cellular Pathology Laboratory, Gloucester, GL53 7AN, UK
| | - Ljiljana Vlatkovic
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - OSBREAC
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
- Gloucestershire Cellular Pathology Laboratory, Gloucester, GL53 7AN, UK
- Department of Medical Genetics, Institute of Clinical Medicine, Faculty of Medicine, University of Oslo and Oslo University Hospital, NO-0450, Oslo, Norway
- Department of Pathology, Oslo University Hospital, NO-0424, Oslo, Norway
- Nuffield Division of Clinical Laboratory Sciences, University of Oxford, Oxford, OX3 9DU, UK
| | - Xavier Tekpli
- Department of Medical Genetics, Institute of Clinical Medicine, Faculty of Medicine, University of Oslo and Oslo University Hospital, NO-0450, Oslo, Norway
| | - Øystein Garred
- Department of Pathology, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Gunnar B. Kristensen
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Hanne A. Askautrud
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Tarjei S. Hveem
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
| | - Håvard E. Danielsen
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, NO-0424, Oslo, Norway
- Nuffield Division of Clinical Laboratory Sciences, University of Oxford, Oxford, OX3 9DU, UK
| |
Collapse
|
2
|
Zhao J, Ding X, Peng C, Tian X, Wang M, Fu Y, Guo H, Bai X, Zhai X, Huang Q, Liu K, Li L, Ye H, Zhang X, Ma X, Wang H. Assessment of Ki-67 proliferation index in prognosis prediction in patients with nonmetastatic clear cell renal cell carcinoma and tumor thrombus. Urol Oncol 2024; 42:23.e5-23.e13. [PMID: 38030468 DOI: 10.1016/j.urolonc.2023.11.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2023] [Revised: 10/29/2023] [Accepted: 11/02/2023] [Indexed: 12/01/2023]
Abstract
PURPOSE To determine the optimal cut-off value of Ki-67 for predicting the survival of patients with clear cell renal cell carcinoma (ccRCC) and tumor thrombus and to explore the correlation between Ki-67 expression and pathological features. PATIENTS AND METHODS We retrospectively analyzed Ki-67 immunohistochemical staining of ccRCC and tumor thrombus resected from February 2006 to February 2022. The survival rate was evaluated using the Kaplan-Meier method. The optimal cut-off value of the Ki-67 expression for predicting survival was determined by the minimum P-value method. Clinicopathological data were compared based on Ki-67 status (low versus high expression). Univariate and multivariate Cox regression analysis was used to explore independent predictors. RESULTS A total of 202 patients (median age, 58 years [IQR, 52-65 years], 147 men) with ccRCC and tumor thrombus were included in the study. The optimal cut-off value of Ki-67 for predicting survival was 30%. 159 (78.7%) and 43 (21.3%) patients were included in the low-expression and high-expression groups. Patients with Ki-67 high expression had significantly worse recurrence-free survival (P < 0.001) and cancer-specific survival (P < 0.001). Ki-67 high expression was associated with adverse pathological features, including tumor necrosis, ISUP nuclear grade, sarcomatoid differentiation, perirenal fat invasion, renal pelvis invasion, and inferior vena cava wall invasion (all P < 0.050). Ki-67 expression ≥ 30% (P = 0.016), tumor side (P = 0.003), diabetes (P = 0.040), blood loss (P = 0.016), inferior vena cava wall invasion (P = 0.016), and sarcomatoid differentiation (P = 0.014) were independent predictors of cancer-specific survival. CONCLUSION The optimal cut-off level of Ki-67 in predicting the prognosis of ccRCC and tumor thrombus was 30%. The high expression of Ki-67 was associated with the aggressive pathological phenotype and poor prognosis.
Collapse
Affiliation(s)
- Jian Zhao
- Department of Radiology, First Medical Center, Chinese PLA General Hospital, Haidian District, Beijing, PR China; Department of Radiology, Armed Police Force Hospital of Sichuan, Leshan, PR China
| | - Xiaohui Ding
- Department of Pathology, First Medical Center, Chinese PLA General Hospital, Beijing, PR China
| | - Cheng Peng
- Department of Urology, Chinese PLA General Hospital, Beijing, PR China
| | - Xia Tian
- Department of Pathology, First Medical Center, Chinese PLA General Hospital, Beijing, PR China
| | - Meifeng Wang
- Department of Radiology, Sixth Medical Center, Chinese PLA General Hospital, Beijing, PR China
| | - Yonggui Fu
- Department of Radiology, Sixth Medical Center, Chinese PLA General Hospital, Beijing, PR China
| | - Huiping Guo
- Department of Radiology, First Medical Center, Chinese PLA General Hospital, Haidian District, Beijing, PR China
| | - Xu Bai
- Department of Radiology, First Medical Center, Chinese PLA General Hospital, Haidian District, Beijing, PR China
| | - Xue Zhai
- Department of Radiology, First Medical Center, Chinese PLA General Hospital, Haidian District, Beijing, PR China
| | - Qingbo Huang
- Department of Urology, Chinese PLA General Hospital, Beijing, PR China
| | - Kan Liu
- Department of Urology, Chinese PLA General Hospital, Beijing, PR China
| | - Lin Li
- Department of Innovative Medical Research, Hospital Management Institute, Chinese PLA General Hospital, Beijing, PR China
| | - Huiyi Ye
- Department of Radiology, First Medical Center, Chinese PLA General Hospital, Haidian District, Beijing, PR China
| | - Xu Zhang
- Department of Urology, Chinese PLA General Hospital, Beijing, PR China
| | - Xin Ma
- Department of Urology, Chinese PLA General Hospital, Beijing, PR China
| | - Haiyi Wang
- Department of Radiology, First Medical Center, Chinese PLA General Hospital, Haidian District, Beijing, PR China.
| |
Collapse
|
3
|
Yang Y, Sun K, Gao Y, Wang K, Yu G. Preparing Data for Artificial Intelligence in Pathology with Clinical-Grade Performance. Diagnostics (Basel) 2023; 13:3115. [PMID: 37835858 PMCID: PMC10572440 DOI: 10.3390/diagnostics13193115] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2023] [Revised: 09/27/2023] [Accepted: 09/28/2023] [Indexed: 10/15/2023] Open
Abstract
The pathology is decisive for disease diagnosis but relies heavily on experienced pathologists. In recent years, there has been growing interest in the use of artificial intelligence in pathology (AIP) to enhance diagnostic accuracy and efficiency. However, the impressive performance of deep learning-based AIP in laboratory settings often proves challenging to replicate in clinical practice. As the data preparation is important for AIP, the paper has reviewed AIP-related studies in the PubMed database published from January 2017 to February 2022, and 118 studies were included. An in-depth analysis of data preparation methods is conducted, encompassing the acquisition of pathological tissue slides, data cleaning, screening, and subsequent digitization. Expert review, image annotation, dataset division for model training and validation are also discussed. Furthermore, we delve into the reasons behind the challenges in reproducing the high performance of AIP in clinical settings and present effective strategies to enhance AIP's clinical performance. The robustness of AIP depends on a randomized collection of representative disease slides, incorporating rigorous quality control and screening, correction of digital discrepancies, reasonable annotation, and sufficient data volume. Digital pathology is fundamental in clinical-grade AIP, and the techniques of data standardization and weakly supervised learning methods based on whole slide image (WSI) are effective ways to overcome obstacles of performance reproduction. The key to performance reproducibility lies in having representative data, an adequate amount of labeling, and ensuring consistency across multiple centers. Digital pathology for clinical diagnosis, data standardization and the technique of WSI-based weakly supervised learning will hopefully build clinical-grade AIP.
Collapse
Affiliation(s)
- Yuanqing Yang
- Department of Biomedical Engineering, School of Basic Medical Sciences, Central South University, Changsha 410013, China; (Y.Y.); (K.S.)
- Department of Biomedical Engineering, School of Medical, Tsinghua University, Beijing 100084, China
| | - Kai Sun
- Department of Biomedical Engineering, School of Basic Medical Sciences, Central South University, Changsha 410013, China; (Y.Y.); (K.S.)
- Furong Laboratory, Changsha 410013, China
| | - Yanhua Gao
- Department of Ultrasound, Shaanxi Provincial People’s Hospital, Xi’an 710068, China;
| | - Kuansong Wang
- Department of Pathology, School of Basic Medical Sciences, Central South University, Changsha 410013, China;
- Department of Pathology, Xiangya Hospital, Central South University, Changsha 410013, China
| | - Gang Yu
- Department of Biomedical Engineering, School of Basic Medical Sciences, Central South University, Changsha 410013, China; (Y.Y.); (K.S.)
| |
Collapse
|
4
|
He Q, Liu Y, Pan F, Duan H, Guan J, Liang Z, Zhong H, Wang X, He Y, Huang W, Guan T. Unsupervised domain adaptive tumor region recognition for Ki67 automated assisted quantification. Int J Comput Assist Radiol Surg 2023; 18:629-640. [PMID: 36371746 DOI: 10.1007/s11548-022-02781-2] [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: 05/31/2022] [Accepted: 10/13/2022] [Indexed: 11/15/2022]
Abstract
PURPOSE Ki67 is a protein associated with tumor proliferation and metastasis in breast cancer and acts as an essential prognostic factor. Clinical work requires recognizing tumor regions on Ki67-stained whole-slide images (WSIs) before quantitation. Deep learning has the potential to provide assistance but largely relies on massive annotations and consumes a huge amount of time and energy. Hence, a novel tumor region recognition approach is proposed for more precise Ki67 quantification. METHODS An unsupervised domain adaptive method is proposed, which combines adversarial and self-training. The model trained on labeled hematoxylin and eosin (H&E) data and unlabeled Ki67 data can recognize tumor regions in Ki67 WSIs. Based on the UDA method, a Ki67 automated assisted quantification system is developed, which contains foreground segmentation, tumor region recognition, cell counting, and WSI-level score calculation. RESULTS The proposed UDA method achieves high performance in tumor region recognition and Ki67 quantification. The AUC reached 0.9915, 0.9352, and 0.9689 on the validation set and internal and external test sets, respectively, substantially exceeding baseline (0.9334, 0.9167, 0.9408) and rivaling the fully supervised method (0.9950, 0.9284, 0.9652). The evaluation of automated quantification on 148 WSIs illustrated statistical agreement with pathological reports. CONCLUSION The model trained by the proposed method is capable of accurately recognizing Ki67 tumor regions. The proposed UDA method can be readily extended to other types of immunohistochemical staining images. The results of automated assisted quantification are accurate and interpretable to provide assistance to both junior and senior pathologists in their interpretation.
Collapse
Affiliation(s)
- Qiming He
- Department of Life and Health, Tsinghua Shenzhen International Graduate School, Shenzhen, China
| | - Yiqing Liu
- Department of Life and Health, Tsinghua Shenzhen International Graduate School, Shenzhen, China
| | - Feiyang Pan
- Department of Life and Health, Tsinghua Shenzhen International Graduate School, Shenzhen, China
| | - Hufei Duan
- Department of Life and Health, Tsinghua Shenzhen International Graduate School, Shenzhen, China
| | - Jian Guan
- Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Zhendong Liang
- Department of Life and Health, Tsinghua Shenzhen International Graduate School, Shenzhen, China
| | - Hui Zhong
- Huaibei Maternal and Child Health Care Hospital, Huaibei, China
| | - Xing Wang
- New H3C Technologies Co., Ltd., Hangzhou, China
| | - Yonghong He
- New H3C Technologies Co., Ltd., Hangzhou, China
| | - Wenting Huang
- Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
| | - Tian Guan
- Department of Life and Health, Tsinghua Shenzhen International Graduate School, Shenzhen, China.
| |
Collapse
|
5
|
Li L, Wang C, Qiu Z, Deng D, Chen X, Wang Q, Meng Y, Zhang B, Zheng G, Hu J. Triptolide inhibits intrahepatic cholangiocarcinoma growth by suppressing glycolysis via the AKT/mTOR pathway. PHYTOMEDICINE : INTERNATIONAL JOURNAL OF PHYTOTHERAPY AND PHYTOPHARMACOLOGY 2023; 109:154575. [PMID: 36610163 DOI: 10.1016/j.phymed.2022.154575] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/20/2022] [Revised: 11/04/2022] [Accepted: 11/20/2022] [Indexed: 06/17/2023]
Abstract
BACKGROUND High levels of glycolysis supply large quantities of energy and biological macromolecular raw materials for cell proliferation. Triptolide (TP) is a kind of epoxy diterpene lactone extracted from the roots, flowers, leaves, or grains of the Celastraceae plant, Tripterygium wilfordii. TP has multiple biological activities, including anti-inflammatory, immunologic suppression, and anti-cancer effects. Nevertheless, it is little known regarding its anti-intrahepatic cholangiocarcinoma (ICC) growth, and the mechanism still require exploration. PURPOSE This research explored the effect of TP on ICC growth and investigated whether TP inhibits glycolysis via the AKT/mTOR pathway. METHODS Cell proliferation was analyzed by Cell Counting Kit-8 (CCK-8), clonogenic assay, and flow cytometry. The underlying molecular mechanism was identified by determining glucose consumption, ATP production, lactate production, hexokinase (HK) and pyruvate kinase (PK) activity, and Western blot analysis. A rapid ICC model of AKT/YapS127A oncogene coactivation in mice was used to clarify the effect of TP treatment on tumor growth and glycolysis. RESULTS The results showed that TP treatment significantly inhibited ICC cell proliferation and glycolysis in a dose- and time-dependent manner(P < 0.05). Further analysis suggested that TP suppressed ICC cell glycolysis by targeting AKT/mTOR signaling. Additionally, we found that TP inhibits tumor growth and glycolysis in AKT/YapS127A mice(P < 0.05). CONCLUSION Taken together, we revealed that TP suppressed ICC growth by suppressing glycolysis via the AKT/mTOR pathway and may provide a potential therapeutic target for ICC treatment.
Collapse
Affiliation(s)
- Li Li
- College of Pharmacy, Hubei University of Chinese Medicine, Wuhan 430065, China
| | - Chuting Wang
- College of Pharmacy, Hubei University of Chinese Medicine, Wuhan 430065, China
| | - Zhenpeng Qiu
- College of Pharmacy, Hubei University of Chinese Medicine, Wuhan 430065, China
| | - Dongjie Deng
- College of Pharmacy, Hubei University of Chinese Medicine, Wuhan 430065, China
| | - Xin Chen
- College of Pharmacy, Hubei University of Chinese Medicine, Wuhan 430065, China
| | - Qi Wang
- College of Pharmacy, Hubei University of Chinese Medicine, Wuhan 430065, China
| | - Yan Meng
- College of Pharmacy, Hubei University of Chinese Medicine, Wuhan 430065, China
| | - Baohui Zhang
- College of Pharmacy, Hubei University of Chinese Medicine, Wuhan 430065, China
| | - Guohua Zheng
- College of Pharmacy, Hubei University of Chinese Medicine, Wuhan 430065, China; Key Laboratory of Chinese Medicine Resource and Compound Prescription, Ministry of Education, Hubei University of Chinese Medicine, Wuhan 430065, China.
| | - Junjie Hu
- College of Pharmacy, Hubei University of Chinese Medicine, Wuhan 430065, China.
| |
Collapse
|
6
|
Catteau X, Zindy E, Bouri S, Noël JC, Salmon I, Decaestecker C. Comparison Between Manual and Automated Assessment of Ki-67 in Breast Carcinoma: Test of a Simple Method in Daily Practice. Technol Cancer Res Treat 2023; 22:15330338231169603. [PMID: 37559526 PMCID: PMC10416654 DOI: 10.1177/15330338231169603] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/11/2023] Open
Abstract
BACKGROUND In the era of "precision medicine," the availability of high-quality tumor biomarker tests is critical and tumor proliferation evaluated by Ki-67 antibody is one of the most important prognostic factors in breast cancer. But the evaluation of Ki-67 index has been shown to suffer from some interobserver variability. The goal of the study is to develop an easy, automated, and reliable Ki-67 assessment approach for invasive breast carcinoma in routine practice. PATIENTS AND METHODS A total of 151 biopsies of invasive breast carcinoma were analyzed. The Ki-67 index was evaluated by 2 pathologists with MIB-1 antibody as a global tumor index and also in a hotspot. These 2 areas were also analyzed by digital image analysis (DIA). RESULTS For Ki-67 index assessment, in the global and hotspot tumor area, the concordances were very good between DIA and pathologists when DIA focused on the annotations made by pathologist (0.73 and 0.83, respectively). However, this was definitely not the case when DIA was not constrained within the pathologist's annotations and automatically established its global or hotspot area in the whole tissue sample (concordance correlation coefficients between 0.28 and 0.58). CONCLUSIONS The DIA technique demonstrated a meaningful concordance with the indices evaluated by pathologists when the tumor area is previously identified by a pathologist. In contrast, basing Ki-67 assessment on automatic tissue detection was not satisfactory and provided bad concordance results. A representative tumoral zone must therefore be manually selected prior to the measurement made by the DIA.
Collapse
Affiliation(s)
- Xavier Catteau
- Department of Pathology, Erasme's Hospital, Université Libre de Bruxelles, Brussels, Belgium
- Curepath laboratory, CHU Tivoli and CHIREC institute, Jumet, Belgium
| | - Egor Zindy
- Laboratory of Image Synthesis and Analysis (LISA), Université Libre de Bruxelles, Bruxelles, Belgium
- Digital Pathology Platform of the CMMI (DIAPath), Université Libre de Bruxelles, Gosselies, Belgium
| | - Sarah Bouri
- Department of Pathology, Erasme's Hospital, Université Libre de Bruxelles, Brussels, Belgium
- Curepath laboratory, CHU Tivoli and CHIREC institute, Jumet, Belgium
| | - Jean-Christophe Noël
- Department of Pathology, Erasme's Hospital, Université Libre de Bruxelles, Brussels, Belgium
- Curepath laboratory, CHU Tivoli and CHIREC institute, Jumet, Belgium
| | - Isabelle Salmon
- Department of Pathology, Erasme's Hospital, Université Libre de Bruxelles, Brussels, Belgium
- Digital Pathology Platform of the CMMI (DIAPath), Université Libre de Bruxelles, Gosselies, Belgium
| | - Christine Decaestecker
- Laboratory of Image Synthesis and Analysis (LISA), Université Libre de Bruxelles, Bruxelles, Belgium
- Digital Pathology Platform of the CMMI (DIAPath), Université Libre de Bruxelles, Gosselies, Belgium
| |
Collapse
|
7
|
Zhong Z, Wang X, Li J, Zhang B, Yan L, Xu S, Chen G, Gao H. A study on the diagnosis of the Helicobacter pylori coccoid form with artificial intelligence technology. Front Microbiol 2022; 13:1008346. [PMID: 36386698 PMCID: PMC9651970 DOI: 10.3389/fmicb.2022.1008346] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2022] [Accepted: 10/10/2022] [Indexed: 09/05/2023] Open
Abstract
BACKGROUND Helicobacter pylori (H. pylori) is an important pathogenic microorganism that causes gastric cancer, peptic ulcers and dyspepsia, and infects more than half of the world's population. Eradicating H. pylori is the most effective means to prevent and treat these diseases. H. pylori coccoid form (HPCF) causes refractory H. pylori infection and should be given more attention in infection management. However, manual HPCF recognition on slides is time-consuming and labor-intensive and depends on experienced pathologists; thus, HPCF diagnosis is rarely performed and often overlooked. Therefore, simple HPCF diagnostic methods need to be developed. MATERIALS AND METHODS We manually labeled 4,547 images from anonymized paraffin-embedded samples in the China Center for H. pylori Molecular Medicine (CCHpMM, Shanghai), followed by training and optimizing the Faster R-CNN and YOLO v5 models to identify HPCF. Mean average precision (mAP) was applied to evaluate and select the model. The artificial intelligence (AI) model interpretation results were compared with those of the pathologists with senior, intermediate, and junior experience levels, using the mean absolute error (MAE) of the coccoid rate as an evaluation metric. RESULTS For the HPCF detection task, the YOLO v5 model was superior to the Faster R-CNN model (0.688 vs. 0.568, mean average precision, mAP); the optimized YOLO v5 model had a better performance (0.803 mAP). The MAE of the optimized YOLO v5 model (3.25 MAE) was superior to that of junior pathologists (4.14 MAE, p < 0.05), no worse than intermediate pathologists (3.40 MAE, p > 0.05), and equivalent to a senior pathologist (3.07 MAE, p > 0.05). CONCLUSION HPCF identification using AI has the advantage of high accuracy and efficiency with the potential to assist or replace pathologists in clinical practice for HPCF identification.
Collapse
Affiliation(s)
- Zishao Zhong
- School of Medicine, Institute of Digestive Disease, Tongji University, Shanghai, China
- China Center for Helicobacter pylori Molecular Medicine, Shanghai, China
- The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China
- Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Xin Wang
- School of Medicine, Institute of Digestive Disease, Tongji University, Shanghai, China
- China Center for Helicobacter pylori Molecular Medicine, Shanghai, China
- School of Chemical Engineering and Technology, China University of Mining and Technology, Xuzhou, China
| | - Jianmin Li
- Unicom Guangdong Industrial Internet Co., Ltd, Guangzhou, China
| | - Beiping Zhang
- China Center for Helicobacter pylori Molecular Medicine, Shanghai, China
- The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Lijuan Yan
- China Center for Helicobacter pylori Molecular Medicine, Shanghai, China
| | - Shuchang Xu
- School of Medicine, Institute of Digestive Disease, Tongji University, Shanghai, China
- Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Guangxia Chen
- Department of Gastroenterology, Xuzhou Municipal Hospital Affiliated to Xuzhou Medical University, Xuzhou, China
| | - Hengjun Gao
- School of Medicine, Institute of Digestive Disease, Tongji University, Shanghai, China
- China Center for Helicobacter pylori Molecular Medicine, Shanghai, China
- Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
- National Engineering Center for Biochips, Shanghai, China
| |
Collapse
|
8
|
DeepHistoClass: A Novel Strategy for Confident Classification of Immunohistochemistry Images Using Deep Learning. Mol Cell Proteomics 2021; 20:100140. [PMID: 34425263 PMCID: PMC8476775 DOI: 10.1016/j.mcpro.2021.100140] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2021] [Revised: 08/13/2021] [Accepted: 08/18/2021] [Indexed: 11/20/2022] Open
Abstract
A multitude of efforts worldwide aim to create a single-cell reference map of the human body, for fundamental understanding of human health, molecular medicine, and targeted treatment. Antibody-based proteomics using immunohistochemistry (IHC) has proven to be an excellent technology for integration with large-scale single-cell transcriptomics datasets. The golden standard for evaluation of IHC staining patterns is manual annotation, which is expensive and may lead to subjective errors. Artificial intelligence holds much promise for efficient and accurate pattern recognition, but confidence in prediction needs to be addressed. Here, the aim was to present a reliable and comprehensive framework for automated annotation of IHC images. We developed a multilabel classification of 7848 complex IHC images of human testis corresponding to 2794 unique proteins, generated as part of the Human Protein Atlas (HPA) project. Manual annotation data for eight different cell types was generated as a basis for training and testing a proposed Hybrid Bayesian Neural Network. By combining the deep learning model with a novel uncertainty metric, DeepHistoClass (DHC) Confidence Score, the average diagnostic performance improved from 86.9% to 96.3%. This metric not only reveals which images are reliably classified by the model, but can also be utilized for identification of manual annotation errors. The proposed streamlined workflow can be developed further for other tissue types in health and disease and has important implications for digital pathology initiatives or large-scale protein mapping efforts such as the HPA project. A novel method for automated annotation of immunohistochemistry images. Introduction of an uncertainty metric, the DeepHistoClass (DHC) confidence score. Increased accuracy of automated image predictions. Identification of manual annotation errors.
Collapse
|
9
|
Song J, Yu Z, Dong B, Zhu M, Guo X, Ma Y, Zhao S, Yang T. Clinical significance of circulating tumour cells and Ki-67 in renal cell carcinoma. World J Surg Oncol 2021; 19:156. [PMID: 34034739 PMCID: PMC8152311 DOI: 10.1186/s12957-021-02268-5] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2021] [Accepted: 05/18/2021] [Indexed: 12/27/2022] Open
Abstract
Background Renal cell carcinoma (RCC) is a common malignant tumour of the genitourinary system. We aimed to analyse the potential value of metastasis-related biomarkers, circulating tumour cells (CTCs) and the proliferative marker Ki-67 in the diagnosis of RCC. Methods Data from 24 laparoscopic radical nephrectomies (RNs) and 17 laparoscopic partial nephrectomies (PNs) were collected in 2018. The numbers and positive rates of CTCs and circulating tumour microemboli (CTM) in the peripheral blood were obtained at three different time points: just before surgery, immediately after surgery and 1 week after surgery. Ki-67 protein expression was evaluated in the RCC tissue by immunohistochemistry. Results Except for the statistically significant association between the preoperative CTC counts and tumour size, no association between the number and positive rate of perioperative CTCs and clinicopathological features was found. The CTC counts gradually decreased during the perioperative period, and at 1 week after surgery, they were significantly lower than those before surgery. High Ki-67 expression was significantly positively correlated with preoperative CTC counts. In addition, Ki-67 expression was higher in the high CTC group (≥ 5 CTCs). Conclusion Our results suggest that surgical nephrectomy is associated with a decrease in CTC counts in RCC patients. CTCs can act as a potential biomarker for the diagnosis and prognosis of RCC. A careful and sufficient long-term follow-up is needed for patients with high preoperative CTC counts. Supplementary Information The online version contains supplementary material available at 10.1186/s12957-021-02268-5.
Collapse
Affiliation(s)
- Jinbo Song
- Department of Urology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, Zhengzhou, China
| | - Zhe Yu
- Department of Urology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, Zhengzhou, China
| | - Bingqi Dong
- Department of Urology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, Zhengzhou, China
| | - Mingkai Zhu
- Department of Urology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, Zhengzhou, China
| | - Xiaofeng Guo
- Department of Urology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, Zhengzhou, China
| | - Yongkang Ma
- Department of Urology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, Zhengzhou, China
| | - Shiming Zhao
- Department of Urology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, Zhengzhou, China
| | - Tiejun Yang
- Department of Urology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, Zhengzhou, China.
| |
Collapse
|
10
|
Hu Z, Cheng C, Wang Y, Chen T, Tu J, Niu C, Xing R, Wang Y, Xu Y. Synergistic Effect of Statins and Abiraterone Acetate on the Growth Inhibition of Neuroblastoma via Targeting Androgen Receptor. Front Oncol 2021; 11:595285. [PMID: 34041015 PMCID: PMC8141582 DOI: 10.3389/fonc.2021.595285] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2020] [Accepted: 03/03/2021] [Indexed: 12/19/2022] Open
Abstract
Neuroblastoma is the most common extracranial neuroendocrine tumor in childhood. Although many studies have tried to find effective treatments, there are still numerous limitations in current clinical targeted therapy. So, it is important to find new therapeutic targets and strategies from a new perspective. Our previous study reported that the androgen receptor (AR) promotes the growth of neuroblastoma in vitro and in vivo. Based on documentary investigation, we postulated that the AR–SCAP–SREBPs-CYP17/HMGCR axis may regulate cholesterol and androgens synthesis and form a positive enhancement loop promoting NB progression. Clinical samples and Oncomine database analysis proved the activation of AR–SCAP–SREBPs-CYP17/HMGCR axis in neuroblastoma. The combination of inhibitors of HMGCR (statins) and CYP17A1 (abiraterone acetate) showed synergistic effect that significantly inhibited the proliferation and migration with decreased expression of related genes detected in vitro and in vivo suggesting the dual-targeted therapy had the potential to inhibit the progression of neuroblastoma in spite of its MYCN status. This study provides new ideas for clinical treatment of neuroblastoma with efficacy and reduced toxicity.
Collapse
Affiliation(s)
- Zengchun Hu
- Dalian Medical University, Dalian, China.,Department of Neurosurgery, 2nd Affiliated Hospital of Dalian Medical University, Dalian, China
| | - Chuandong Cheng
- Anhui Provincial Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China.,Division of Life Sciences and Medicine, Department of Neurosurgery, 1st Affiliated Hospital of University of Science and Technology of China, Hefei, China
| | - Yue Wang
- Dalian Medical University, Dalian, China.,Department of Pathophysiology, College of Basic Medical Sciences, Dalian Medical University, Dalian, China
| | - Tianrui Chen
- Department of Bone Tumor Surgery, Changzheng Hospital, Second Military Medical University, Shanghai, China
| | - Junhong Tu
- Dalian Medical University, Dalian, China.,Department of Pathophysiology, College of Basic Medical Sciences, Dalian Medical University, Dalian, China
| | - Chaoshi Niu
- Anhui Provincial Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China.,Division of Life Sciences and Medicine, Department of Neurosurgery, 1st Affiliated Hospital of University of Science and Technology of China, Hefei, China
| | - Rong Xing
- Dalian Medical University, Dalian, China.,Department of Pathophysiology, College of Basic Medical Sciences, Dalian Medical University, Dalian, China
| | - Yang Wang
- Dalian Medical University, Dalian, China.,Department of Pathophysiology, College of Basic Medical Sciences, Dalian Medical University, Dalian, China
| | - Yinghui Xu
- Department of Neurosurgery, 1st Affiliated Hospital of Dalian Medical University, Dalian, China
| |
Collapse
|
11
|
Geread RS, Sivanandarajah A, Brouwer ER, Wood GA, Androutsos D, Faragalla H, Khademi A. piNET-An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images. Cancers (Basel) 2020; 13:E11. [PMID: 33375043 PMCID: PMC7792768 DOI: 10.3390/cancers13010011] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2020] [Revised: 12/15/2020] [Accepted: 12/17/2020] [Indexed: 12/16/2022] Open
Abstract
In this work, a novel proliferation index (PI) calculator for Ki67 images called piNET is proposed. It is successfully tested on four datasets, from three scanners comprised of patches, tissue microarrays (TMAs) and whole slide images (WSI), representing a diverse multi-centre dataset for evaluating Ki67 quantification. Compared to state-of-the-art methods, piNET consistently performs the best over all datasets with an average PI difference of 5.603%, PI accuracy rate of 86% and correlation coefficient R = 0.927. The success of the system can be attributed to several innovations. Firstly, this tool is built based on deep learning, which can adapt to wide variability of medical images-and it was posed as a detection problem to mimic pathologists' workflow which improves accuracy and efficiency. Secondly, the system is trained purely on tumor cells, which reduces false positives from non-tumor cells without needing the usual pre-requisite tumor segmentation step for Ki67 quantification. Thirdly, the concept of learning background regions through weak supervision is introduced, by providing the system with ideal and non-ideal (artifact) patches that further reduces false positives. Lastly, a novel hotspot analysis is proposed to allow automated methods to score patches from WSI that contain "significant" activity.
Collapse
Affiliation(s)
- Rokshana Stephny Geread
- Electrical, Computer and Biomedical Engineering Department, Ryerson University, Toronto, ON M5B 2K3, Canada; (A.S.); (D.A.)
| | - Abishika Sivanandarajah
- Electrical, Computer and Biomedical Engineering Department, Ryerson University, Toronto, ON M5B 2K3, Canada; (A.S.); (D.A.)
| | - Emily Rita Brouwer
- Department of Pathobiology, Ontario Veterinarian College, University of Guelph, Guelph, ON NIG 2W1, Canada; (E.R.B.); (G.A.W.)
| | - Geoffrey A. Wood
- Department of Pathobiology, Ontario Veterinarian College, University of Guelph, Guelph, ON NIG 2W1, Canada; (E.R.B.); (G.A.W.)
| | - Dimitrios Androutsos
- Electrical, Computer and Biomedical Engineering Department, Ryerson University, Toronto, ON M5B 2K3, Canada; (A.S.); (D.A.)
| | - Hala Faragalla
- Department of Laboratory Medicine & Pathobiology, St. Michael’s Hospital, Unity Health Network, Toronto, ON M5B 1W8, Canada;
| | - April Khademi
- Electrical, Computer and Biomedical Engineering Department, Ryerson University, Toronto, ON M5B 2K3, Canada; (A.S.); (D.A.)
- Keenan Research Center for Biomedical Science, St. Michael’s Hospital, Unity Health Network, Toronto, ON M5B 1W8, Canada
| |
Collapse
|
12
|
Liu W, Juhas M, Zhang Y. Fine-Grained Breast Cancer Classification With Bilinear Convolutional Neural Networks (BCNNs). Front Genet 2020; 11:547327. [PMID: 33101377 PMCID: PMC7500315 DOI: 10.3389/fgene.2020.547327] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2020] [Accepted: 08/17/2020] [Indexed: 12/24/2022] Open
Abstract
Classification of histopathological images of cancer is challenging even for well-trained professionals, due to the fine-grained variability of the disease. Deep Convolutional Neural Networks (CNNs) showed great potential for classification of a number of the highly variable fine-grained objects. In this study, we introduce a Bilinear Convolutional Neural Networks (BCNNs) based deep learning method for fine-grained classification of breast cancer histopathological images. We evaluated our model by comparison with several deep learning algorithms for fine-grained classification. We used bilinear pooling to aggregate a large number of orderless features without taking into consideration the disease location. The experimental results on BreaKHis, a publicly available breast cancer dataset, showed that our method is highly accurate with 99.24% and 95.95% accuracy in binary and in fine-grained classification, respectively.
Collapse
Affiliation(s)
- Weihuang Liu
- College of Science, Harbin Institute of Technology, Shenzhen, China
| | - Mario Juhas
- Faculty of Science and Medicine, University of Fribourg, Fribourg, Switzerland
| | - Yang Zhang
- College of Science, Harbin Institute of Technology, Shenzhen, China
| |
Collapse
|
13
|
Serna G, Simonetti S, Fasani R, Pagliuca F, Guardia X, Gallego P, Jimenez J, Peg V, Saura C, Eppenberger-Castori S, Ramon Y Cajal S, Terracciano L, Nuciforo P. Sequential immunohistochemistry and virtual image reconstruction using a single slide for quantitative KI67 measurement in breast cancer. Breast 2020; 53:102-110. [PMID: 32707454 PMCID: PMC7375667 DOI: 10.1016/j.breast.2020.07.002] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2020] [Revised: 06/12/2020] [Accepted: 07/08/2020] [Indexed: 12/22/2022] Open
Abstract
Objective Ki67 is a prognostic and predictive marker in breast cancer (BC). However, manual scoring (MS) by visual assessment suffers from high inter-observer variability which limits its clinical use. Here, we developed a new digital image analysis (DIA) workflow, named KiQuant for automated scoring of Ki67 and investigated its equivalence with standard pathologist's assessment. Methods Sequential immunohistochemistry of Ki67 and cytokeratin, for precise tumor cell recognition, were performed in the same section of 5 tissue microarrays containing 329 tumor cores from different breast cancer subtypes. Slides were digitalized and subjected to DIA and MS for Ki67 assessment. The intraclass correlation coefficient (ICC) and Bland-Altman plot were used to evaluate inter-observer reproducibility. The Kaplan-Meier analysis was used to determine the prognostic potential. Results KiQuant showed an excellent correlation with MS (ICC:0.905,95%CI:0.878–0.926) with satisfactory inter-run (ICC:0.917,95%CI:0.884–0.942) and inter-antibody reproducibilities (ICC:0.886,95%CI:0.820–0.929). The distance between KiQuant and MS increased with the magnitude of Ki67 measurement and positively correlated with analyzed tumor area and breast cancer subtype. Agreement rates between KiQuant and MS within the clinically relevant 14% and 30% cut-off points ranged from 33% to 44% with modest interobserver reproducibility below the 20% cut-off (0.606, 95%CI:0.467–0.727). High Ki67 by KiQuant correlated with worse outcome in all BC and in the luminal subtype (P = 0.028 and P = 0.043, respectively). For MS, the association with survival was significant only in 1 out of 3 observers. Conclusions KiQuant represents an easy and accurate methodology for Ki67 measurement providing a step toward utilizing Ki67 in the clinical setting. Automated Ki67 scoring workflow improved reproducibility. Sequential immunohistochemistry in the same section for precise cell recognition. Use of a tumor mask for automatic tumor region selection. Outperform pathologist-based Ki67 scoring in prognostic prediction.
Collapse
Affiliation(s)
- Garazi Serna
- Molecular Oncology Group, Vall D'Hebron Institute of Oncology, Barcelona, Spain
| | - Sara Simonetti
- Molecular Oncology Group, Vall D'Hebron Institute of Oncology, Barcelona, Spain
| | - Roberta Fasani
- Molecular Oncology Group, Vall D'Hebron Institute of Oncology, Barcelona, Spain
| | - Francesca Pagliuca
- University of Naples Federico II, Department of Advanced Biomedical Sciences, Pathology Section, Naples, Italy
| | - Xavier Guardia
- Molecular Oncology Group, Vall D'Hebron Institute of Oncology, Barcelona, Spain
| | - Paqui Gallego
- Molecular Oncology Group, Vall D'Hebron Institute of Oncology, Barcelona, Spain
| | - Jose Jimenez
- Molecular Oncology Group, Vall D'Hebron Institute of Oncology, Barcelona, Spain
| | - Vicente Peg
- Department of Pathology, Vall D'Hebron University Hospital, Barcelona, Spain
| | - Cristina Saura
- Breast Cancer and Melanoma Group, Vall D'Hebron Institute of Oncology, Barcelona, Spain
| | | | | | - Luigi Terracciano
- Institute of Pathology, University Hospital Basel, Basel, Switzerland
| | - Paolo Nuciforo
- Molecular Oncology Group, Vall D'Hebron Institute of Oncology, Barcelona, Spain.
| |
Collapse
|
14
|
Panayides AS, Amini A, Filipovic ND, Sharma A, Tsaftaris SA, Young A, Foran D, Do N, Golemati S, Kurc T, Huang K, Nikita KS, Veasey BP, Zervakis M, Saltz JH, Pattichis CS. AI in Medical Imaging Informatics: Current Challenges and Future Directions. IEEE J Biomed Health Inform 2020; 24:1837-1857. [PMID: 32609615 PMCID: PMC8580417 DOI: 10.1109/jbhi.2020.2991043] [Citation(s) in RCA: 105] [Impact Index Per Article: 26.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
This paper reviews state-of-the-art research solutions across the spectrum of medical imaging informatics, discusses clinical translation, and provides future directions for advancing clinical practice. More specifically, it summarizes advances in medical imaging acquisition technologies for different modalities, highlighting the necessity for efficient medical data management strategies in the context of AI in big healthcare data analytics. It then provides a synopsis of contemporary and emerging algorithmic methods for disease classification and organ/ tissue segmentation, focusing on AI and deep learning architectures that have already become the de facto approach. The clinical benefits of in-silico modelling advances linked with evolving 3D reconstruction and visualization applications are further documented. Concluding, integrative analytics approaches driven by associate research branches highlighted in this study promise to revolutionize imaging informatics as known today across the healthcare continuum for both radiology and digital pathology applications. The latter, is projected to enable informed, more accurate diagnosis, timely prognosis, and effective treatment planning, underpinning precision medicine.
Collapse
|