1
|
Dunenova G, Kalmataeva Z, Kaidarova D, Dauletbaev N, Semenova Y, Mansurova M, Grjibovski A, Kassymbekova F, Sarsembayev A, Semenov D, Glushkova N. The Performance and Clinical Applicability of HER2 Digital Image Analysis in Breast Cancer: A Systematic Review. Cancers (Basel) 2024; 16:2761. [PMID: 39123488 PMCID: PMC11311684 DOI: 10.3390/cancers16152761] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2024] [Revised: 07/28/2024] [Accepted: 07/30/2024] [Indexed: 08/12/2024] Open
Abstract
This systematic review aims to address the research gap in the performance of computational algorithms for the digital image analysis of HER2 images in clinical settings. While numerous studies have explored various aspects of these algorithms, there is a lack of comprehensive evaluation regarding their effectiveness in real-world clinical applications. We conducted a search of the Web of Science and PubMed databases for studies published from 31 December 2013 to 30 June 2024, focusing on performance effectiveness and components such as dataset size, diversity and source, ground truth, annotation, and validation methods. The study was registered with PROSPERO (CRD42024525404). Key questions guiding this review include the following: How effective are current computational algorithms at detecting HER2 status in digital images? What are the common validation methods and dataset characteristics used in these studies? Is there standardization of algorithm evaluations of clinical applications that can improve the clinical utility and reliability of computational tools for HER2 detection in digital image analysis? We identified 6833 publications, with 25 meeting the inclusion criteria. The accuracy rate with clinical datasets varied from 84.19% to 97.9%. The highest accuracy was achieved on the publicly available Warwick dataset at 98.8% in synthesized datasets. Only 12% of studies used separate datasets for external validation; 64% of studies used a combination of accuracy, precision, recall, and F1 as a set of performance measures. Despite the high accuracy rates reported in these studies, there is a notable absence of direct evidence supporting their clinical application. To facilitate the integration of these technologies into clinical practice, there is an urgent need to address real-world challenges and overreliance on internal validation. Standardizing study designs on real clinical datasets can enhance the reliability and clinical applicability of computational algorithms in improving the detection of HER2 cancer.
Collapse
Affiliation(s)
- Gauhar Dunenova
- Department of Epidemiology, Biostatistics and Evidence-Based Medicine, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan
| | - Zhanna Kalmataeva
- Rector Office, Asfendiyarov Kazakh National Medical University, Almaty 050000, Kazakhstan;
| | - Dilyara Kaidarova
- Kazakh Research Institute of Oncology and Radiology, Almaty 050022, Kazakhstan;
| | - Nurlan Dauletbaev
- Department of Internal, Respiratory and Critical Care Medicine, Philipps University of Marburg, 35037 Marburg, Germany;
- Department of Pediatrics, Faculty of Medicine and Health Sciences, McGill University, Montreal, QC H4A 3J1, Canada
- Faculty of Medicine and Health Care, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan
| | - Yuliya Semenova
- School of Medicine, Nazarbayev University, Astana 010000, Kazakhstan;
| | - Madina Mansurova
- Department of Artificial Intelligence and Big Data, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan;
| | - Andrej Grjibovski
- Central Scientific Research Laboratory, Northern State Medical University, Arkhangelsk 163000, Russia;
- Department of Epidemiology and Modern Vaccination Technologies, I.M. Sechenov First Moscow State Medical University, Moscow 105064, Russia
- Department of Biology, Ecology and Biotechnology, Northern (Arctic) Federal University, Arkhangelsk 163000, Russia
- Department of Health Policy and Management, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan
| | - Fatima Kassymbekova
- Department of Public Health and Social Sciences, Kazakhstan Medical University “KSPH”, Almaty 050060, Kazakhstan;
| | - Aidos Sarsembayev
- School of Digital Technologies, Almaty Management University, Almaty 050060, Kazakhstan;
- Health Research Institute, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan;
| | - Daniil Semenov
- Computer Science and Engineering Program, Astana IT University, Astana 020000, Kazakhstan;
| | - Natalya Glushkova
- Department of Epidemiology, Biostatistics and Evidence-Based Medicine, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan
- Health Research Institute, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan;
| |
Collapse
|
2
|
Al Zorgani MM, Ugail H, Pors K, Dauda AM. Deep Transfer Learning-Based Approach for Glucose Transporter-1 (GLUT1) Expression Assessment. J Digit Imaging 2023; 36:2367-2381. [PMID: 37670181 PMCID: PMC10584776 DOI: 10.1007/s10278-023-00859-0] [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: 11/21/2021] [Revised: 05/20/2023] [Accepted: 05/22/2023] [Indexed: 09/07/2023] Open
Abstract
Glucose transporter-1 (GLUT-1) expression level is a biomarker of tumour hypoxia condition in immunohistochemistry (IHC)-stained images. Thus, the GLUT-1 scoring is a routine procedure currently employed for predicting tumour hypoxia markers in clinical practice. However, visual assessment of GLUT-1 scores is subjective and consequently prone to inter-pathologist variability. Therefore, this study proposes an automated method for assessing GLUT-1 scores in IHC colorectal carcinoma images. For this purpose, we leverage deep transfer learning methodologies for evaluating the performance of six different pre-trained convolutional neural network (CNN) architectures: AlexNet, VGG16, GoogleNet, ResNet50, DenseNet-201 and ShuffleNet. The target CNNs are fine-tuned as classifiers or adapted as feature extractors with support vector machine (SVM) to classify GLUT-1 scores in IHC images. Our experimental results show that the winning model is the trained SVM classifier on the extracted deep features fusion Feat-Concat from DenseNet201, ResNet50 and GoogLeNet extractors. It yields the highest prediction accuracy of 98.86%, thus outperforming the other classifiers on our dataset. We also conclude, from comparing the methodologies, that the off-the-shelf feature extraction is better than the fine-tuning model in terms of time and resources required for training.
Collapse
Affiliation(s)
- Maisun Mohamed Al Zorgani
- Faculty of Engineering and Informatics, School of Media, Design and Technology, University of Bradford, Richmond Road, Bradford, BD7 1DP, UK.
| | - Hassan Ugail
- Faculty of Engineering and Informatics, School of Media, Design and Technology, University of Bradford, Richmond Road, Bradford, BD7 1DP, UK
| | - Klaus Pors
- Institute of Cancer Therapeutics, University of Bradford, Richmond Road, Bradford, BD7 1DP, UK
| | - Abdullahi Magaji Dauda
- Institute of Cancer Therapeutics, University of Bradford, Richmond Road, Bradford, BD7 1DP, UK
| |
Collapse
|
3
|
Pham TD. Prediction of Five-Year Survival Rate for Rectal Cancer Using Markov Models of Convolutional Features of RhoB Expression on Tissue Microarray. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2023; 20:3195-3204. [PMID: 37155403 DOI: 10.1109/tcbb.2023.3274211] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/10/2023]
Abstract
The ability to predict survival in cancer is clinically important because the finding can help patients and physicians make optimal treatment decisions. Artificial intelligence in the context of deep learning has been increasingly realized by the informatics-oriented medical community as a powerful machine-learning technology for cancer research, diagnosis, prediction, and treatment. This paper presents the combination of deep learning, data coding, and probabilistic modeling for predicting five-year survival in a cohort of patients with rectal cancer using images of RhoB expression on biopsies. Using about one-third of the patients' data for testing, the proposed approach achieved 90% prediction accuracy, which is much higher than the direct use of the best pretrained convolutional neural network (70%) and the best coupling of a pretrained model and support vector machines (70%).
Collapse
|
4
|
Predicting the HER2 status in oesophageal cancer from tissue microarrays using convolutional neural networks. Br J Cancer 2023; 128:1369-1376. [PMID: 36717673 PMCID: PMC10050393 DOI: 10.1038/s41416-023-02143-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2022] [Revised: 12/21/2022] [Accepted: 01/05/2023] [Indexed: 02/01/2023] Open
Abstract
BACKGROUND Fast and accurate diagnostics are key for personalised medicine. Particularly in cancer, precise diagnosis is a prerequisite for targeted therapies, which can prolong lives. In this work, we focus on the automatic identification of gastroesophageal adenocarcinoma (GEA) patients that qualify for a personalised therapy targeting epidermal growth factor receptor 2 (HER2). We present a deep-learning method for scoring microscopy images of GEA for the presence of HER2 overexpression. METHODS Our method is based on convolutional neural networks (CNNs) trained on a rich dataset of 1602 patient samples and tested on an independent set of 307 patient samples. We additionally verified the CNN's generalisation capabilities with an independent dataset with 653 samples from a separate clinical centre. We incorporated an attention mechanism in the network architecture to identify the tissue regions, which are important for the prediction outcome. Our solution allows for direct automated detection of HER2 in immunohistochemistry-stained tissue slides without the need for manual assessment and additional costly in situ hybridisation (ISH) tests. RESULTS We show accuracy of 0.94, precision of 0.97, and recall of 0.95. Importantly, our approach offers accurate predictions in cases that pathologists cannot resolve and that require additional ISH testing. We confirmed our findings in an independent dataset collected in a different clinical centre. The attention-based CNN exploits morphological information in microscopy images and is superior to a predictive model based on the staining intensity only. CONCLUSIONS We demonstrate that our approach not only automates an important diagnostic process for GEA patients but also paves the way for the discovery of new morphological features that were previously unknown for GEA pathology.
Collapse
|
5
|
Baez-Navarro X, van Bockstal MR, Nawawi D, Broeckx G, Colpaert C, Doebar SC, Hogenes MCH, Koop E, Lambein K, Peeters DJE, Sinke RHJA, Bastiaan van Brakel J, van der Starre-Gaal J, van der Vegt B, van de Vijver K, Vreuls CPH, Vreuls W, Westenend PJ, van Deurzen CHM. Interobserver Variation in the Assessment of Immunohistochemistry Expression Levels in HER2-Negative Breast Cancer: Can We Improve the Identification of Low Levels of HER2 Expression by Adjusting the Criteria? An International Interobserver Study. Mod Pathol 2023; 36:100009. [PMID: 36788064 DOI: 10.1016/j.modpat.2022.100009] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2022] [Revised: 08/03/2022] [Accepted: 09/16/2022] [Indexed: 01/19/2023]
Abstract
The classification of human epidermal growth factor receptor 2 (HER2) expression is optimized to detect HER2-amplified breast cancer (BC). However, novel HER2-targeting agents are also effective for BCs with low levels of HER2. This raises the question whether the current guidelines for HER2 testing are sufficiently reproducible to identify HER2-low BC. The aim of this multicenter international study was to assess the interobserver agreement of specific HER2 immunohistochemistry scores in cases with negative HER2 results (0, 1+, or 2+/in situ hybridization negative) according to the current American Society of Clinical Oncology/College of American Pathologists (ASCO/CAP) guidelines. Furthermore, we evaluated whether the agreement improved by redefining immunohistochemistry (IHC) scoring criteria or by adding fluorescent in situ hybridization (FISH). We conducted a 2-round study of 105 nonamplified BCs. During the first assessment, 16 pathologists used the latest version of the ASCO/CAP guidelines. After a consensus meeting, the same pathologists scored the same digital slides using modified IHC scoring criteria based on the 2007 ASCO/CAP guidelines, and an extra "ultralow" category was added. Overall, the interobserver agreement was limited (4.7% of cases with 100% agreement) in the first round, but this was improved by clustering IHC categories. In the second round, the highest reproducibility was observed when comparing IHC 0 with the ultralow/1+/2+ grouped cluster (74.3% of cases with 100% agreement). The FISH results were not statistically different between HER2-0 and HER2-low cases, regardless of the IHC criteria used. In conclusion, our study suggests that the modified 2007 ASCO/CAP criteria were more reproducible in distinguishing HER2-0 from HER2-low cases than the 2018 ASCO/CAP criteria. However, the reproducibility was still moderate, which was not improved by adding FISH. This could lead to a suboptimal selection of patients eligible for novel HER2-targeting agents. If the threshold between HER2 IHC 0 and 1+ is to be clinically actionable, there is a need for clearer, more reproducible IHC definitions, training, and/or development of more accurate methods to detect this subtle difference in protein expression levels.
Collapse
Affiliation(s)
- Ximena Baez-Navarro
- Department of Pathology, Erasmus University Medical Center, Rotterdam, The Netherlands.
| | | | - Diënna Nawawi
- Department of Pathology, Erasmus University Medical Center, Rotterdam, The Netherlands
| | - Glenn Broeckx
- Department of Pathology, Antwerp University Hospital, Edegem, Belgium
| | - Cecile Colpaert
- Department of Pathology, General Hospital Turnhout, Turnhout, Belgium; Department of Pathology, University Hospital Leuven, Leuven, Belgium
| | - Shusma C Doebar
- Department of Pathology, Spaarne Gasthuis, Haarlem Zuid, The Netherlands
| | - Marieke C H Hogenes
- Department of Pathology, Laboratory Pathology East Netherlands, Hengelo, The Netherlands
| | - Esther Koop
- Department of Pathology, Gelre Hospital, Apeldoorn, The Netherlands
| | - Kathleen Lambein
- Department of Surgical Oncology, Leuven University Hospitals, Leuven, Belgium; Department of Pathology, Ghent University Hospital, Ghent, Belgium
| | - Dieter J E Peeters
- Department of Pathology, Sint-Maarten General Hospital, Mechelen, Belgium; Department of Pathology, CellCarta NV, Antwerp, Belgium
| | | | | | | | - Bert van der Vegt
- Department of Pathology & Medical Biology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Koen van de Vijver
- Department of Surgical Oncology, Leuven University Hospitals, Leuven, Belgium; Division of Diagnostic Sciences, Cancer Research Institute Ghent, Ghent University, Ghent, Belgium
| | - Celien P H Vreuls
- Department of Pathology, Utrecht University Medical Center, Utrecht, The Netherlands
| | - Willem Vreuls
- Department of Pathology, CWZ Hospital, Nijmegen, The Netherlands
| | - Pieter J Westenend
- Department of Pathology, PAL Laboratory of Pathology, Dordrecht, The Netherlands
| | | |
Collapse
|
6
|
Using Deep Learning to Predict Final HER2 Status in Invasive Breast Cancers That are Equivocal (2+) by Immunohistochemistry. Appl Immunohistochem Mol Morphol 2022; 30:668-673. [PMID: 36251973 DOI: 10.1097/pai.0000000000001079] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2022] [Accepted: 09/17/2022] [Indexed: 11/25/2022]
Abstract
Invasive breast carcinomas are routinely tested for HER2 using immunohistochemistry (IHC), with reflex in situ hybridization (ISH) for those scored as equivocal (2+). ISH testing is expensive, time-consuming, and not universally available. In this study, we trained a deep learning algorithm to directly predict HER2 gene amplification status from HER2 2+ IHC slides. Data included 115 consecutive cases of invasive breast carcinoma scored as 2+ by IHC that had follow-up HER2 ISH testing. An external validation data set was created from 36 HER2 IHC slides prepared at an outside institution. All internal IHC slides were digitized and divided into training (80%), and test (20%) sets with 5-fold cross-validation. Small patches (256×256 pixels) were randomly extracted and used to train convolutional neural networks with EfficientNet B0 architecture using a transfer learning approach. Predictions for slides in the test set were made on individual patches, and these predictions were aggregated to generate an overall prediction for each slide. This resulted in a receiver operating characteristic area under the curve of 0.83 with an overall accuracy of 79% (sensitivity=0.70, specificity=0.82). Analysis of external validation slides resulted in a receiver operating characteristic area under the curve of 0.79 with an overall accuracy of 81% (sensitivity=0.50, specificity=0.82). Although the sensitivity and specificity are not high enough to negate the need for reflexive ISH testing entirely, this approach may be useful for triaging cases more likely to be HER2 positive and initiating treatment planning in centers where HER2 ISH testing is not readily available.
Collapse
|
7
|
Yiming A, Wubulikasimu M, Yusuying N. Analysis on factors behind sentinel lymph node metastasis in breast cancer by color ultrasonography, molybdenum target, and pathological detection. World J Surg Oncol 2022; 20:72. [PMID: 35255911 PMCID: PMC8902784 DOI: 10.1186/s12957-022-02531-3] [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: 10/11/2021] [Accepted: 02/18/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND This study aimed to identify the factors underlying the metastasis of breast cancer and sentinel lymph nodes and to screen and analyze the risk factors of sentinel lymph node metastasis to provide a reference and basis for clinical work. METHODS A total of 99 patients with breast cancer were enrolled in this study. These patients received treatment in our hospital between May 2017 and May 2020. The general information, characteristics of the color Doppler echocardiography, molybdenum, conventional pathology, and molecular pathology of the patients were collected. Factors influencing sentinel lymph node metastasis in breast cancer patients were retrospectively analyzed. RESULTS In this study, age, tumor diameter, BI-RADS category, pathology type, expression profiles of CK5/6, EGFR, and CK19, and TP53 and BRAC1/2 mutations were independent risk factors for sentinel lymph node metastasis in breast cancer (P < 0.05). The number and locations of tumors, quadrant of tumors, regularity of tumor margins, presence of blood flow signals, presence of posterior echo attenuation, presence of calcification, histological grade, molecular typing, and mutations of BRAF, ATM, and PALB2 were irrelevant factors (P > 0.05). CONCLUSIONS In conclusion, age, tumor diameter, BI-RADS category, invasive type, expression of CK5/6, EGFR, and CK19, and mutations in TP53 and BRAC1/2 were positively correlated with sentinel lymph node metastasis. These independent risk factors should be given more attention in clinical studies to strengthen the management and control of sentinel lymph node metastasis in high-risk breast cancer and support early chemotherapy or targeted therapy.
Collapse
Affiliation(s)
- Aibibai Yiming
- Department of General Surgery, The Second People's Hospital of Kashgar, Room 3 Building 3, No. 1 Sagelamu Road, Kashgar, Xinjiang, 844000, China
| | - Muhetaer Wubulikasimu
- Department of General Surgery, The Second People's Hospital of Kashgar, Room 3 Building 3, No. 1 Sagelamu Road, Kashgar, Xinjiang, 844000, China
| | - Nuermaimaiti Yusuying
- Department of General Surgery, The Second People's Hospital of Kashgar, Room 3 Building 3, No. 1 Sagelamu Road, Kashgar, Xinjiang, 844000, China.
| |
Collapse
|