1
|
Ou DX, Lu CW, Chen LW, Lee WY, Hu HW, Chuang JH, Lin MW, Chen KY, Chiu LY, Chen JS, Chen CM, Hsieh MS. Deep Learning Analysis for Predicting Tumor Spread through Air Space in Early-Stage Lung Adenocarcinoma Pathology Images. Cancers (Basel) 2024; 16:2132. [PMID: 38893251 PMCID: PMC11172106 DOI: 10.3390/cancers16112132] [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: 04/19/2024] [Revised: 05/25/2024] [Accepted: 06/01/2024] [Indexed: 06/21/2024] Open
Abstract
The presence of spread through air spaces (STASs) in early-stage lung adenocarcinoma is a significant prognostic factor associated with disease recurrence and poor outcomes. Although current STAS detection methods rely on pathological examinations, the advent of artificial intelligence (AI) offers opportunities for automated histopathological image analysis. This study developed a deep learning (DL) model for STAS prediction and investigated the correlation between the prediction results and patient outcomes. To develop the DL-based STAS prediction model, 1053 digital pathology whole-slide images (WSIs) from the competition dataset were enrolled in the training set, and 227 WSIs from the National Taiwan University Hospital were enrolled for external validation. A YOLOv5-based framework comprising preprocessing, candidate detection, false-positive reduction, and patient-based prediction was proposed for STAS prediction. The model achieved an area under the curve (AUC) of 0.83 in predicting STAS presence, with 72% accuracy, 81% sensitivity, and 63% specificity. Additionally, the DL model demonstrated a prognostic value in disease-free survival compared to that of pathological evaluation. These findings suggest that DL-based STAS prediction could serve as an adjunctive screening tool and facilitate clinical decision-making in patients with early-stage lung adenocarcinoma.
Collapse
Affiliation(s)
- De-Xiang Ou
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei 10617, Taiwan; (D.-X.O.); (L.-W.C.); (K.-Y.C.)
| | - Chao-Wen Lu
- Division of Thoracic Surgery, Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan; (C.-W.L.); (J.-H.C.)
- Graduate Institute of Pathology, National Taiwan University College of Medicine, Taipei 100, Taiwan
| | - Li-Wei Chen
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei 10617, Taiwan; (D.-X.O.); (L.-W.C.); (K.-Y.C.)
| | - Wen-Yao Lee
- Division of Thoracic Surgery, Department of Surgery, Fu Jen Catholic University Hospital, No. 69, Guizi Road, Taishan District, New Taipei City 24352, Taiwan;
| | - Hsiang-Wei Hu
- Department of Pathology, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan;
| | - Jen-Hao Chuang
- Division of Thoracic Surgery, Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan; (C.-W.L.); (J.-H.C.)
| | - Mong-Wei Lin
- Division of Thoracic Surgery, Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan; (C.-W.L.); (J.-H.C.)
| | - Kuan-Yu Chen
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei 10617, Taiwan; (D.-X.O.); (L.-W.C.); (K.-Y.C.)
| | - Ling-Ying Chiu
- Institute of Medicine, Chung Shan Medical University, Taichung 40201, Taiwan;
| | - Jin-Shing Chen
- Division of Thoracic Surgery, Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan; (C.-W.L.); (J.-H.C.)
| | - Chung-Ming Chen
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei 10617, Taiwan; (D.-X.O.); (L.-W.C.); (K.-Y.C.)
| | - Min-Shu Hsieh
- Graduate Institute of Pathology, National Taiwan University College of Medicine, Taipei 100, Taiwan
- Department of Pathology, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan;
| |
Collapse
|
2
|
Karageorgos GM, Cho S, McDonough E, Chadwick C, Ghose S, Owens J, Jung KJ, Machiraju R, West R, Brooks JD, Mallick P, Ginty F. Deep learning-based automated pipeline for blood vessel detection and distribution analysis in multiplexed prostate cancer images. FRONTIERS IN BIOINFORMATICS 2024; 3:1296667. [PMID: 38323039 PMCID: PMC10844485 DOI: 10.3389/fbinf.2023.1296667] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2023] [Accepted: 12/18/2023] [Indexed: 02/08/2024] Open
Abstract
Introduction: Prostate cancer is a highly heterogeneous disease, presenting varying levels of aggressiveness and response to treatment. Angiogenesis is one of the hallmarks of cancer, providing oxygen and nutrient supply to tumors. Micro vessel density has previously been correlated with higher Gleason score and poor prognosis. Manual segmentation of blood vessels (BVs) In microscopy images is challenging, time consuming and may be prone to inter-rater variabilities. In this study, an automated pipeline is presented for BV detection and distribution analysis in multiplexed prostate cancer images. Methods: A deep learning model was trained to segment BVs by combining CD31, CD34 and collagen IV images. In addition, the trained model was used to analyze the size and distribution patterns of BVs in relation to disease progression in a cohort of prostate cancer patients (N = 215). Results: The model was capable of accurately detecting and segmenting BVs, as compared to ground truth annotations provided by two reviewers. The precision (P), recall (R) and dice similarity coefficient (DSC) were equal to 0.93 (SD 0.04), 0.97 (SD 0.02) and 0.71 (SD 0.07) with respect to reviewer 1, and 0.95 (SD 0.05), 0.94 (SD 0.07) and 0.70 (SD 0.08) with respect to reviewer 2, respectively. BV count was significantly associated with 5-year recurrence (adjusted p = 0.0042), while both count and area of blood vessel were significantly associated with Gleason grade (adjusted p = 0.032 and 0.003 respectively). Discussion: The proposed methodology is anticipated to streamline and standardize BV analysis, offering additional insights into the biology of prostate cancer, with broad applicability to other cancers.
Collapse
Affiliation(s)
| | | | | | | | | | | | - Kyeong Joo Jung
- Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, United States
| | - Raghu Machiraju
- Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, United States
| | - Robert West
- Department of Pathology, Stanford University School of Medicine, Stanford, CA, United States
| | - James D. Brooks
- Department of Urology, Stanford University School of Medicine, Stanford, CA, United States
| | - Parag Mallick
- Canary Center for Cancer Early Detection, Department of Radiology, Stanford University School of Medicine, Stanford, CA, United States
| | | |
Collapse
|
3
|
Doğan RS, Yılmaz B. Histopathology image classification: highlighting the gap between manual analysis and AI automation. Front Oncol 2024; 13:1325271. [PMID: 38298445 PMCID: PMC10827850 DOI: 10.3389/fonc.2023.1325271] [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: 10/20/2023] [Accepted: 12/19/2023] [Indexed: 02/02/2024] Open
Abstract
The field of histopathological image analysis has evolved significantly with the advent of digital pathology, leading to the development of automated models capable of classifying tissues and structures within diverse pathological images. Artificial intelligence algorithms, such as convolutional neural networks, have shown remarkable capabilities in pathology image analysis tasks, including tumor identification, metastasis detection, and patient prognosis assessment. However, traditional manual analysis methods have generally shown low accuracy in diagnosing colorectal cancer using histopathological images. This study investigates the use of AI in image classification and image analytics using histopathological images using the histogram of oriented gradients method. The study develops an AI-based architecture for image classification using histopathological images, aiming to achieve high performance with less complexity through specific parameters and layers. In this study, we investigate the complicated state of histopathological image classification, explicitly focusing on categorizing nine distinct tissue types. Our research used open-source multi-centered image datasets that included records of 100.000 non-overlapping images from 86 patients for training and 7180 non-overlapping images from 50 patients for testing. The study compares two distinct approaches, training artificial intelligence-based algorithms and manual machine learning models, to automate tissue classification. This research comprises two primary classification tasks: binary classification, distinguishing between normal and tumor tissues, and multi-classification, encompassing nine tissue types, including adipose, background, debris, stroma, lymphocytes, mucus, smooth muscle, normal colon mucosa, and tumor. Our findings show that artificial intelligence-based systems can achieve 0.91 and 0.97 accuracy in binary and multi-class classifications. In comparison, the histogram of directed gradient features and the Random Forest classifier achieved accuracy rates of 0.75 and 0.44 in binary and multi-class classifications, respectively. Our artificial intelligence-based methods are generalizable, allowing them to be integrated into histopathology diagnostics procedures and improve diagnostic accuracy and efficiency. The CNN model outperforms existing machine learning techniques, demonstrating its potential to improve the precision and effectiveness of histopathology image analysis. This research emphasizes the importance of maintaining data consistency and applying normalization methods during the data preparation stage for analysis. It particularly highlights the potential of artificial intelligence to assess histopathological images.
Collapse
Affiliation(s)
- Refika Sultan Doğan
- Department of Bioengineering, Abdullah Gül University, Kayseri, Türkiye
- Biomedical Instrumentation and Signal Analysis Laboratory, Abdullah Gül University, Kayseri, Türkiye
| | - Bülent Yılmaz
- Biomedical Instrumentation and Signal Analysis Laboratory, Abdullah Gül University, Kayseri, Türkiye
- Department of Electrical and Computer Engineering, Abdullah Gul University, Kayseri, Türkiye
- Department of Electrical Engineering, Gulf University for Science and Technology, Mishref, Kuwait
| |
Collapse
|
4
|
Terada K, Yoshizawa A, Liu X, Ito H, Hamaji M, Menju T, Date H, Bise R, Haga H. Deep Learning for Predicting Effect of Neoadjuvant Therapies in Non-Small Cell Lung Carcinomas With Histologic Images. Mod Pathol 2023; 36:100302. [PMID: 37580019 DOI: 10.1016/j.modpat.2023.100302] [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: 04/06/2023] [Revised: 06/23/2023] [Accepted: 08/02/2023] [Indexed: 08/16/2023]
Abstract
Neoadjuvant therapies are used for locally advanced non-small cell lung carcinomas, whereby pathologists histologically evaluate the effect using resected specimens. Major pathological response (MPR) has recently been used for treatment evaluation and as an economical survival surrogate; however, interobserver variability and poor reproducibility are often noted. The aim of this study was to develop a deep learning (DL) model to predict MPR from hematoxylin and eosin-stained tissue images and to validate its utility for clinical use. We collected data on 125 primary non-small cell lung carcinoma cases that were resected after neoadjuvant therapy. The cases were randomly divided into 55 for training/validation and 70 for testing. A total of 261 hematoxylin and eosin-stained slides were obtained from the maximum tumor beds, and whole slide images were prepared. We used a multiscale patch model that can adaptively weight multiple convolutional neural networks trained with different field-of-view images. We performed 3-fold cross-validation to evaluate the model. During testing, we compared the percentages of viable tumor evaluated by annotator pathologists (reviewed data), those evaluated by nonannotator pathologists (primary data), and those predicted by the DL-based model using 2-class confusion matrices and receiver operating characteristic curves and performed a survival analysis between MPR-achieved and non-MPR cases. In cross-validation, accuracy and mean F1 score were 0.859 and 0.805, respectively. During testing, accuracy and mean F1 score with reviewed data and those with primary data were 0.986, 0.985, 0.943, and 0.943, respectively. The areas under the receiver operating characteristic curve with reviewed and primary data were 0.999 and 0.978, respectively. The disease-free survival of MPR-achieved cases with reviewed and primary data was significantly better than that of the non-MPR cases (P<.001 and P=.001), and that predicted by the DL-based model was almost identical (P=.005). The DL model may support pathologist evaluations and can offer accurate determinations of MPR in patients.
Collapse
Affiliation(s)
- Kazuhiro Terada
- Department of Diagnostic Pathology, Kyoto University Hospital, Kyoto, Japan
| | - Akihiko Yoshizawa
- Department of Diagnostic Pathology, Kyoto University Hospital, Kyoto, Japan.
| | - Xiaoqing Liu
- Department of Advanced Information Technology, Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan
| | - Hiroaki Ito
- Department of Diagnostic Pathology, Kyoto University Hospital, Kyoto, Japan
| | - Masatsugu Hamaji
- Department of Thoracic Surgery, Kyoto University Hospital, Kyoto, Japan
| | - Toshi Menju
- Department of Thoracic Surgery, Kyoto University Hospital, Kyoto, Japan
| | - Hiroshi Date
- Department of Thoracic Surgery, Kyoto University Hospital, Kyoto, Japan
| | - Ryoma Bise
- Department of Advanced Information Technology, Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan
| | - Hironori Haga
- Department of Diagnostic Pathology, Kyoto University Hospital, Kyoto, Japan
| |
Collapse
|
5
|
Timakova A, Ananev V, Fayzullin A, Makarov V, Ivanova E, Shekhter A, Timashev P. Artificial Intelligence Assists in the Detection of Blood Vessels in Whole Slide Images: Practical Benefits for Oncological Pathology. Biomolecules 2023; 13:1327. [PMID: 37759727 PMCID: PMC10526383 DOI: 10.3390/biom13091327] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Revised: 08/23/2023] [Accepted: 08/28/2023] [Indexed: 09/29/2023] Open
Abstract
The analysis of the microvasculature and the assessment of angiogenesis have significant prognostic value in various diseases, including cancer. The search for invasion into the blood and lymphatic vessels and the assessment of angiogenesis are important aspects of oncological diagnosis. These features determine the prognosis and aggressiveness of the tumor. Traditional manual evaluation methods are time consuming and subject to inter-observer variability. Blood vessel detection is a perfect task for artificial intelligence, which is capable of rapid analyzing thousands of tissue structures in whole slide images. The development of computer vision solutions requires the segmentation of tissue regions, the extraction of features and the training of machine learning models. In this review, we focus on the methodologies employed by researchers to identify blood vessels and vascular invasion across a range of tumor localizations, including breast, lung, colon, brain, renal, pancreatic, gastric and oral cavity cancers. Contemporary models herald a new era of computational pathology in morphological diagnostics.
Collapse
Affiliation(s)
- Anna Timakova
- Institute for Regenerative Medicine, Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya St., 119991 Moscow, Russia; (A.T.); (A.F.); (E.I.); (P.T.)
| | - Vladislav Ananev
- Medical Informatics Laboratory, Yaroslav-the-Wise Novgorod State University, 41 B. St. Petersburgskaya, 173003 Veliky Novgorod, Russia; (V.A.); (V.M.)
| | - Alexey Fayzullin
- Institute for Regenerative Medicine, Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya St., 119991 Moscow, Russia; (A.T.); (A.F.); (E.I.); (P.T.)
| | - Vladimir Makarov
- Medical Informatics Laboratory, Yaroslav-the-Wise Novgorod State University, 41 B. St. Petersburgskaya, 173003 Veliky Novgorod, Russia; (V.A.); (V.M.)
| | - Elena Ivanova
- Institute for Regenerative Medicine, Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya St., 119991 Moscow, Russia; (A.T.); (A.F.); (E.I.); (P.T.)
- B.V. Petrovsky Russian Research Center of Surgery, 2 Abrikosovskiy Lane, 119991 Moscow, Russia
| | - Anatoly Shekhter
- Institute for Regenerative Medicine, Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya St., 119991 Moscow, Russia; (A.T.); (A.F.); (E.I.); (P.T.)
| | - Peter Timashev
- Institute for Regenerative Medicine, Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya St., 119991 Moscow, Russia; (A.T.); (A.F.); (E.I.); (P.T.)
- World-Class Research Center “Digital Biodesign and Personalized Healthcare”, Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya St., 119991 Moscow, Russia
| |
Collapse
|
6
|
Zhu C, Hu P, Wang X, Zeng X, Shi L. A real-time computer-aided diagnosis method for hydatidiform mole recognition using deep neural network. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 234:107510. [PMID: 37003042 DOI: 10.1016/j.cmpb.2023.107510] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/13/2022] [Revised: 02/20/2023] [Accepted: 03/22/2023] [Indexed: 06/19/2023]
Abstract
BACKGROUND AND OBJECTIVE Hydatidiform mole (HM) is one of the most common gestational trophoblastic diseases with malignant potential. Histopathological examination is the primary method for diagnosing HM. However, due to the obscure and confusing pathology features of HM, significant observer variability exists among pathologists, leading to over- and misdiagnosis in clinical practice. Efficient feature extraction can significantly improve the accuracy and speed of the diagnostic process. Deep neural network (DNN) has been proven to have excellent feature extraction and segmentation capabilities, which is widely used in clinical practice for many other diseases. We constructed a deep learning-based CAD method to recognize HM hydrops lesions under the microscopic view in real-time. METHODS To solve the challenge of lesion segmentation due to difficulties in extracting effective features from HM slide images, we proposed a hydrops lesion recognition module that employs DeepLabv3+ with our novel compound loss function and a stepwise training strategy to achieve great performance in recognizing hydrops lesions at both pixel and lesion level. Meanwhile, a Fourier transform-based image mosaic module and an edge extension module for image sequences were developed to make the recognition model more applicable to the case of moving slides in clinical practice. Such an approach also addresses the situation where the model has poor results for image edge recognition. RESULTS We evaluated our method using widely adopted DNNs on an HM dataset and chose DeepLabv3+ with our compound loss function as the segmentation model. The comparison experiments show that the edge extension module is able to improve the model performance by at most 3.4% regarding pixel-level IoU and 9.0% regarding lesion-level IoU. As for the final result, our method is able to achieve a pixel-level IoU of 77.0%, a precision of 86.0%, and a lesion-level recall of 86.2% while having a response time of 82 ms per frame. Experiments show that our method is able to display the full microscopic view with accurately labeled HM hydrops lesions following the movement of slides in real-time. CONCLUSIONS To the best of our knowledge, this is the first method to utilize deep neural networks in HM lesion recognition. This method provides a robust and accurate solution with powerful feature extraction and segmentation capabilities for auxiliary diagnosis of HM.
Collapse
Affiliation(s)
- Chengze Zhu
- Department of Automation, Tsinghua University, Beijing, 100084, China
| | - Pingge Hu
- Department of Automation, Tsinghua University, Beijing, 100084, China
| | - Xingtong Wang
- Department of Automation, Tsinghua University, Beijing, 100084, China
| | - Xianxu Zeng
- Department of Pathology, the Third Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
| | - Li Shi
- Department of Automation, Tsinghua University, Beijing, 100084, China.
| |
Collapse
|
7
|
Copeland-Hardin L, Paunesku T, Murley JS, Crentsil J, Antipova O, Li L, Maxey E, Jin Q, Hooper D, Lai B, Chen S, Woloschak GE. Proof of principle study: synchrotron X-ray fluorescence microscopy for identification of previously radioactive microparticles and elemental mapping of FFPE tissues. Sci Rep 2023; 13:7806. [PMID: 37179410 PMCID: PMC10183016 DOI: 10.1038/s41598-023-34890-6] [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: 02/02/2023] [Accepted: 05/09/2023] [Indexed: 05/15/2023] Open
Abstract
Biobanks containing formalin-fixed, paraffin-embedded (FFPE) tissues from animals and human atomic-bomb survivors exposed to radioactive particulates remain a vital resource for understanding the molecular effects of radiation exposure. These samples are often decades old and prepared using harsh fixation processes which limit sample imaging options. Optical imaging of hematoxylin and eosin (H&E) stained tissues may be the only feasible processing option, however, H&E images provide no information about radioactive microparticles or radioactive history. Synchrotron X-ray fluorescence microscopy (XFM) is a robust, non-destructive, semi-quantitative technique for elemental mapping and identifying candidate chemical element biomarkers in FFPE tissues. Still, XFM has never been used to uncover distribution of formerly radioactive micro-particulates in FFPE canine specimens collected more than 30 years ago. In this work, we demonstrate the first use of low-, medium-, and high-resolution XFM to generate 2D elemental maps of ~ 35-year-old, canine FFPE lung and lymph node specimens stored in the Northwestern University Radiobiology Archive documenting distribution of formerly radioactive micro-particulates. Additionally, we use XFM to identify individual microparticles and detect daughter products of radioactive decay. The results of this proof-of-principle study support the use of XFM to map chemical element composition in historic FFPE specimens and conduct radioactive micro-particulate forensics.
Collapse
Affiliation(s)
- Letonia Copeland-Hardin
- Department of Radiation Oncology and Department of Radiology, Feinberg School of Medicine, Northwestern University, 300 E. Superior St., Tarry 4-713, Chicago, IL, 60611, USA
| | - Tatjana Paunesku
- Department of Radiation Oncology and Department of Radiology, Feinberg School of Medicine, Northwestern University, 300 E. Superior St., Tarry 4-713, Chicago, IL, 60611, USA
| | - Jeffrey S Murley
- Department of Radiation Oncology and Department of Radiology, Feinberg School of Medicine, Northwestern University, 300 E. Superior St., Tarry 4-713, Chicago, IL, 60611, USA
| | - Jasson Crentsil
- Department of Radiation Oncology and Department of Radiology, Feinberg School of Medicine, Northwestern University, 300 E. Superior St., Tarry 4-713, Chicago, IL, 60611, USA
| | - Olga Antipova
- X-Ray Science Division, Advanced Photon Source, Argonne National Laboratory, Lemont, IL, USA
| | - LuXi Li
- X-Ray Science Division, Advanced Photon Source, Argonne National Laboratory, Lemont, IL, USA
| | - Evan Maxey
- X-Ray Science Division, Advanced Photon Source, Argonne National Laboratory, Lemont, IL, USA
| | - Qiaoling Jin
- X-Ray Science Division, Advanced Photon Source, Argonne National Laboratory, Lemont, IL, USA
| | - David Hooper
- Nuclear Nonproliferation Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
| | - Barry Lai
- X-Ray Science Division, Advanced Photon Source, Argonne National Laboratory, Lemont, IL, USA
| | - Si Chen
- X-Ray Science Division, Advanced Photon Source, Argonne National Laboratory, Lemont, IL, USA
| | - Gayle E Woloschak
- Department of Radiation Oncology and Department of Radiology, Feinberg School of Medicine, Northwestern University, 300 E. Superior St., Tarry 4-713, Chicago, IL, 60611, USA.
| |
Collapse
|
8
|
Franco PIR, Pereira JX, Ferreira HH, de Menezes LB, Miguel MP. Low-grade mammary gland tumours in dogs have greater VEGF-A and BMP2 immunostaining and higher CD31 blood vessel density. Top Companion Anim Med 2023; 53-54:100778. [PMID: 37011834 DOI: 10.1016/j.tcam.2023.100778] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Revised: 03/22/2023] [Accepted: 03/27/2023] [Indexed: 04/03/2023]
Abstract
Tumor angiogenesis is an important process in tumor growth, and different molecules are involved in its regulation including VEGF-A, BMP2, and CD31, which can be considered possible prognostic markers. The aim of this study was to verify whether the VEGF-A and BMP2 immunostaining area, and microvascular density (MVD) might be associated with the degree of malignancy in malignant mammary neoplasms of dogs. For this purpose, samples of mammary malignancies from female dogs embedded in wax were used and separated into four main histomorphological types: tubulopapillary carcinomas, solid, complex, and carcinosarcoma, which were separated based on high and low degrees of malignancy. Immunohistochemical analysis was performed on tissue microarray blocks using anti-CD31 antibodies for evaluation of MVD and vascular lumen area, and with anti-VEGF-A and anti-BMP2 to determine the immunostaining area using the DAKO EnVision™ FLEX+ kit. MVD and vascular lumen area were higher in tubulopapillary carcinomas as were the areas stained by VEGF-A and BMP2. Immunostaining for CD31 was higher in low-grade carcinomas as well as in areas immunostained by VEGF-A and BMP2. There was a positive correlation between VEGF and BMP2 in high (r = 0.556, p < 0.0001) and low-grade (r = 0.287, p<0.0001) carcinomas and between MVD and VEGF-A in low-grade carcinomas (r = 0.267, p = 0.0064). Thus, the markers evaluated showed greater immunostaining in canine mammary tumors with a lower degree of malignancy.
Collapse
|
9
|
Huang S, Yang J, Shen N, Xu Q, Zhao Q. Artificial intelligence in lung cancer diagnosis and prognosis: Current application and future perspective. Semin Cancer Biol 2023; 89:30-37. [PMID: 36682439 DOI: 10.1016/j.semcancer.2023.01.006] [Citation(s) in RCA: 20] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2022] [Revised: 01/18/2023] [Accepted: 01/18/2023] [Indexed: 01/22/2023]
Abstract
Lung cancer is one of the malignant tumors with the highest incidence and mortality in the world. The overall five-year survival rate of lung cancer is relatively lower than many leading cancers. Early diagnosis and prognosis of lung cancer are essential to improve the patient's survival rate. With artificial intelligence (AI) approaches widely applied in lung cancer, early diagnosis and prediction have achieved excellent performance in recent years. This review summarizes various types of AI algorithm applications in lung cancer, including natural language processing (NLP), machine learning and deep learning, and reinforcement learning. In addition, we provides evidence regarding the application of AI in lung cancer diagnostic and clinical prognosis. This review aims to elucidate the value of AI in lung cancer diagnosis and prognosis as the novel screening decision-making for the precise treatment of lung cancer patients.
Collapse
Affiliation(s)
- Shigao Huang
- Department of Radiation Oncology, The First Affiliated Hospital, Air Force Medical University, Xi'an, Shanxi, China
| | - Jie Yang
- Chongqing Industry&Trade Polytechnic, Chongqing, China
| | - Na Shen
- Hong Kong Shue Yan University, Hong Kong, China
| | - Qingsong Xu
- Faculty of Science and Technology, University of Macau, Taipa, Macau SAR, China
| | - Qi Zhao
- Cancer Center, Institute of Translational Medicine, Faculty of Health Sciences, University of Macau, Taipa, Macau SAR, China; MoE Frontiers Science Center for Precision Oncology, University of Macau, Taipa, Macau SAR, China.
| |
Collapse
|
10
|
Wu B, Moeckel G. Application of digital pathology and machine learning in the liver, kidney and lung diseases. J Pathol Inform 2023; 14:100184. [PMID: 36714454 PMCID: PMC9874068 DOI: 10.1016/j.jpi.2022.100184] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2022] [Revised: 11/28/2022] [Accepted: 12/28/2022] [Indexed: 01/05/2023] Open
Abstract
The development of rapid and accurate Whole Slide Imaging (WSI) has paved the way for the application of Artificial Intelligence (AI) to digital pathology. The availability of WSI in the recent years allowed the rapid development of various AI technologies to blossom. WSI-based digital pathology combined with neural networks can automate arduous and time-consuming tasks of slide evaluation. Machine Learning (ML)-based AI has been demonstrated to outperform pathologists by eliminating inter- and intra-observer subjectivity, obtaining quantitative data from slide images, and extracting hidden image patterns that are relevant to disease subtype and progression. In this review, we outline the functionality of different AI technologies such as neural networks and deep learning and discover how aspects of different diseases make them benefit from the implementation of AI. AI has proven to be valuable in many different organs, with this review focusing on the liver, kidney, and lungs. We also discuss how AI and image analysis not only can grade diseases objectively but also discover aspects of diseases that have prognostic value. In the end, we review the current status of the integration of AI in pathology and share our vision on the future of digital pathology.
Collapse
Affiliation(s)
- Benjamin Wu
- Horace Mann School, Bronx, NY, USA,Corresponding author at: 950 Post Rd., Scarsdale, NY 10583, USA.
| | - Gilbert Moeckel
- Department of Pathology, Yale University School of Medicine, New Haven, CT, USA
| |
Collapse
|
11
|
Chen J, Yang Y, Luo B, Wen Y, Chen Q, Ma R, Huang Z, Zhu H, Li Y, Chen Y, Qian D. Further predictive value of lymphovascular invasion explored via supervised deep learning for lymph node metastases in breast cancer. Hum Pathol 2023; 131:26-37. [PMID: 36481204 DOI: 10.1016/j.humpath.2022.11.007] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/04/2022] [Revised: 11/22/2022] [Accepted: 11/27/2022] [Indexed: 12/12/2022]
Abstract
Lymphovascular invasion, specifically lymph-blood vessel invasion (LBVI), is a risk factor for metastases in breast invasive ductal carcinoma (IDC) and is routinely screened using hematoxylin-eosin histopathological images. However, routine reports only describe whether LBVI is present and does not provide other potential prognostic information of LBVI. This study aims to evaluate the clinical significance of LBVI in 685 IDC cases and explore the added predictive value of LBVI on lymph node metastases (LNM) via supervised deep learning (DL), an expert-experience embedded knowledge transfer learning (EEKT) model in 40 LBVI-positive cases signed by the routine report. Multivariate logistic regression and propensity score matching analysis demonstrated that LBVI (OR 4.203, 95% CI 2.809-6.290, P < 0.001) was a significant risk factor for LNM. Then, the EEKT model trained on 5780 image patches automatically segmented LBVI with a patch-wise Dice similarity coefficient of 0.930 in the test set and output counts, location, and morphometric features of the LBVIs. Some morphometric features were beneficial for further stratification within the 40 LBVI-positive cases. The results showed that LBVI in cases with LNM had a higher short-to-long side ratio of the minimum rectangle (MR) (0.686 vs. 0.480, P = 0.001), LBVI-to-MR area ratio (0.774 vs. 0.702, P = 0.002), and solidity (0.983 vs. 0.934, P = 0.029) compared to LBVI in cases without LNM. The results highlight the potential of DL to assist pathologists in quantifying LBVI and, more importantly, in exploring added prognostic information from LBVI.
Collapse
Affiliation(s)
- Jiamei Chen
- Center of Oncology, Renmin Hospital of Wuhan University, Wuhan, 430060, China
| | - Yang Yang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200000, China
| | - Bo Luo
- Department of Pathology, The Central Hospital of Wuhan, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430014, China
| | - Yaofeng Wen
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200000, China
| | - Qingzhong Chen
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200000, China
| | - Ru Ma
- Department of Peritoneal Cancer Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital, Beijing, 100038, China
| | - Zhen Huang
- Center of Oncology, Renmin Hospital of Wuhan University, Wuhan, 430060, China
| | - Hangjia Zhu
- Center of Oncology, Renmin Hospital of Wuhan University, Wuhan, 430060, China
| | - Yan Li
- Department of Peritoneal Cancer Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital, Beijing, 100038, China; Department of Pathology, Capital Medical University Affiliated Beijing Shijitan Hospital, Beijing, 100038, China.
| | - Yongshun Chen
- Center of Oncology, Renmin Hospital of Wuhan University, Wuhan, 430060, China.
| | - Dahong Qian
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200000, China.
| |
Collapse
|
12
|
Brancato V, Cavaliere C, Garbino N, Isgrò F, Salvatore M, Aiello M. The relationship between radiomics and pathomics in Glioblastoma patients: Preliminary results from a cross-scale association study. Front Oncol 2022; 12:1005805. [PMID: 36276163 PMCID: PMC9582951 DOI: 10.3389/fonc.2022.1005805] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2022] [Accepted: 09/21/2022] [Indexed: 12/01/2022] Open
Abstract
Glioblastoma multiforme (GBM) typically exhibits substantial intratumoral heterogeneity at both microscopic and radiological resolution scales. Diffusion Weighted Imaging (DWI) and dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) are two functional MRI techniques that are commonly employed in clinic for the assessment of GBM tumor characteristics. This work presents initial results aiming at determining if radiomics features extracted from preoperative ADC maps and post-contrast T1 (T1C) images are associated with pathomic features arising from H&E digitized pathology images. 48 patients from the public available CPTAC-GBM database, for which both radiology and pathology images were available, were involved in the study. 91 radiomics features were extracted from ADC maps and post-contrast T1 images using PyRadiomics. 65 pathomic features were extracted from cell detection measurements from H&E images. Moreover, 91 features were extracted from cell density maps of H&E images at four different resolutions. Radiopathomic associations were evaluated by means of Spearman's correlation (ρ) and factor analysis. p values were adjusted for multiple correlations by using a false discovery rate adjustment. Significant cross-scale associations were identified between pathomics and ADC, both considering features (n = 186, 0.45 < ρ < 0.74 in absolute value) and factors (n = 5, 0.48 < ρ < 0.54 in absolute value). Significant but fewer ρ values were found concerning the association between pathomics and radiomics features (n = 53, 0.5 < ρ < 0.65 in absolute value) and factors (n = 2, ρ = 0.63 and ρ = 0.53 in absolute value). The results of this study suggest that cross-scale associations may exist between digital pathology and ADC and T1C imaging. This can be useful not only to improve the knowledge concerning GBM intratumoral heterogeneity, but also to strengthen the role of radiomics approach and its validation in clinical practice as "virtual biopsy", introducing new insights for omics integration toward a personalized medicine approach.
Collapse
Affiliation(s)
| | | | | | - Francesco Isgrò
- Department of Electrical Engineering and Information Technologies, University of Napoli Federico II, Napoli, Italy
| | | | | |
Collapse
|
13
|
Microvessel quantification by fully convolutional neural networks associated with type 2 inflammation in chronic rhinosinusitis. Ann Allergy Asthma Immunol 2022; 128:697-704.e1. [PMID: 35257872 DOI: 10.1016/j.anai.2022.02.025] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2021] [Revised: 02/08/2022] [Accepted: 02/27/2022] [Indexed: 12/29/2022]
Abstract
BACKGROUND The pathogenesis of chronic rhinosinusitis (CRS) is still unclear, and little is known about angiogenesis in this disease. We utilized a fully convolutional network (FCN), which has been extensively used in image processing to study angiogenesis in CRS. OBJECTIVE To explore the tissue quantification of microvessels and their potential association with inflammation in CRS by using FCN to reflect the angiogenesis condition in CRS. METHODS For endotyping of CRS, tissue homogenates of 79 patients with CRS who had undergone functional endoscopic sinus surgery and 17 control subjects were analyzed for interferon gamma, transforming growth factor beta, interleukin (IL)-1β, IL-5, IL-6, IL-8, IL-10, IL-17, tumor necrosis factor alpha, eosinophilic cationic protein, immunoglobulin E, and Staphylococcus aureus-immunoglobulin E(SE-IgE). A total of 552 hematoxylin and eosin-stained images of 27 CRS tissue samples were used to develop an FCN, going through training, validation, and evaluation processes. An optimized FCN was applied to quantify the microvessels of tissue samples of all subjects. Correlation analysis between microvessel quantification with phenotype, endotype, clinical characteristics, and cytokine expression of CRS was carried out. RESULTS Quantification of microvessels in type 2 and non-type 2 CRS demonstrated considerable differences, with a higher expression in type 2 CRS. There was a strong negative correlation between the area ratio of microvessels with tissue tumor necrosis factor alpha and transforming growth factor beta levels and a mildly positive correlation with tissue IL-5 and eosinophilic cationic protein concentration. CONCLUSION FCN proved to facilitate the analysis of microvessels in airway tissue samples. This study elucidated the close association of angiogenesis with endotyping, suggesting that treatment aiming at antagonizing angiogenesis may assist to the therapy for the recrudescent and refractory CRS.
Collapse
|
14
|
Liu YH, To M, Okudera T, Wada-Takahashi S, Takahashi SS, Su CY, Matsuo M. Advanced platelet-rich fibrin (A-PRF) has an impact on the initial healing of gingival regeneration after tooth extraction. J Oral Biosci 2021; 64:141-147. [PMID: 34808363 DOI: 10.1016/j.job.2021.11.001] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2021] [Revised: 11/11/2021] [Accepted: 11/15/2021] [Indexed: 11/30/2022]
Abstract
OBJECTIVES Platelet-rich fibrin (PRF) is widely used in wound healing because it contains several growth factors, including vascular endothelial growth factor (VEGF). In this study, we investigated the effects of advanced PRF (A-PRF) in early-stage gingival regeneration after tooth extraction. METHODS Blood sample was collected from females beagle dogs (age: 12 months) before tooth extraction for A-PRF preparation. All animals were sacrificed by perfusion-fixation on postoperative days 1, 3, and 7. The upper jaws were prepared for hematoxylin and eosin staining and immunostaining (for CD34 and VEGF). The lower jaw samples were prepared for scanning electron microscope observations. Blood flow in the gingiva before and after surgery was measured using laser Doppler flowmetry. RESULTS In the A-PRF group, a large number of microvessels were observed in the gingival tissue on postoperative day 1. The microvessels in the control group were fewer and sparse. Regarding the vascular resin cast, a large number of new blood vessels were observed on postoperative day 1 in the A-PRF group. A stronger CD34-positive signal was obtained around the blood vessels in the A-PRF group than in the control group. Further, a strong VEGF-positive signal was observed in the perivascular tissue in the A-PRF group. Gingival blood flow was significantly higher in the A-PRF group after surgery. CONCLUSION A-PRF had a positive impact on angiogenesis in the gingiva through the induction of VEGF expression. Thus, A-PRF may be beneficial for gingival tissue regeneration.
Collapse
Affiliation(s)
- Yu-Hao Liu
- Department of Clinical Oral Anatomy, Kanagawa Dental University, 82, Inaoka, Yokosuka, Kanagawa, 238-8580, Japan
| | - Masahiro To
- Department of Physiology, Kanagawa Dental University, 82, Inaoka, Yokosuka, Kanagawa, 238-8580, Japan
| | - Toshimitsu Okudera
- Department of Clinical Oral Anatomy, Kanagawa Dental University, 82, Inaoka, Yokosuka, Kanagawa, 238-8580, Japan
| | - Satoko Wada-Takahashi
- Department of Physiology, Kanagawa Dental University, 82, Inaoka, Yokosuka, Kanagawa, 238-8580, Japan
| | - Shun-Suke Takahashi
- Department of Pharmacology, Kanagawa Dental University, 82, Inaoka, Yokosuka, Kanagawa, 238-8580, Japan
| | - Chen-Yao Su
- Department of Clinical Oral Anatomy, Kanagawa Dental University, 82, Inaoka, Yokosuka, Kanagawa, 238-8580, Japan; International Society of Blood Biomaterials (ISBB), Sec.2, Linong Street, Taipei, 112 Taiwan
| | - Masato Matsuo
- Department of Clinical Oral Anatomy, Kanagawa Dental University, 82, Inaoka, Yokosuka, Kanagawa, 238-8580, Japan.
| |
Collapse
|
15
|
Olianti C, Giardini F, Lazzeri E, Costantini I, Silvestri L, Coppini R, Cerbai E, Pavone FS, Sacconi L. Optical clearing in cardiac imaging: A comparative study. PROGRESS IN BIOPHYSICS AND MOLECULAR BIOLOGY 2021; 168:10-17. [PMID: 34358555 DOI: 10.1016/j.pbiomolbio.2021.07.012] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/14/2021] [Accepted: 07/29/2021] [Indexed: 10/20/2022]
Abstract
The optical clearing of the cardiac tissue has always been a challenging goal to obtain successful three-dimensional reconstructions of entire hearts. Typically, the developed protocols are targeted at the clearing of the brain; cardiac tissue requires proper arrangements to the original protocols, which are usually tough and time-consuming to figure out. Here, we present the application of three different clearing methodologies on mouse hearts: uDISCO, CLARITY, and SHIELD. For each approach, we describe the required optimizations that we have developed to improve the outcome; in particular, we focus on comparing the features of the tissue after the application of each methodology, especially in terms of tissue preservation, transparency, and staining. We found that the uDISCO protocol induces strong fiber delamination of the cardiac tissue, thus reducing the reliability of structural analyses. The CLARITY protocol confers a high level of transparency to the heart and allows deep penetration of the fluorescent dyes; however, it requires long times for the clearing and the tissue loses its robustness. The SHIELD methodology, indeed, is very promising for tissue maintenance since it preserves its consistency and provides ideal transparency, but further approaches are needed to obtain homogeneous staining of the whole heart. Since the CLARITY procedure, despite the disadvantages in terms of tissue preservation and timings, is actually the most suitable approach to image labeled samples in depth, we optimized and performed the methodology also on human cardiac tissue from control hearts and hearts with hypertrophic cardiomyopathy.
Collapse
Affiliation(s)
- Camilla Olianti
- European Laboratory for Non-Linear Spectroscopy, Sesto Fiorentino, 50019, Italy
| | - Francesco Giardini
- European Laboratory for Non-Linear Spectroscopy, Sesto Fiorentino, 50019, Italy
| | - Erica Lazzeri
- European Laboratory for Non-Linear Spectroscopy, Sesto Fiorentino, 50019, Italy
| | - Irene Costantini
- European Laboratory for Non-Linear Spectroscopy, Sesto Fiorentino, 50019, Italy; National Institute of Optics, National Research Council, Florence, 50125, Italy; Department of Biology, University of Florence, Sesto Fiorentino, 50019, Italy
| | - Ludovico Silvestri
- European Laboratory for Non-Linear Spectroscopy, Sesto Fiorentino, 50019, Italy; National Institute of Optics, National Research Council, Florence, 50125, Italy; Department of Physics and Astronomy, University of Florence, Sesto Fiorentino, 50019, Italy
| | - Raffaele Coppini
- Department of Neurosciences, Psychology, Drugs and Child Health, University of Florence, Italy
| | - Elisabetta Cerbai
- European Laboratory for Non-Linear Spectroscopy, Sesto Fiorentino, 50019, Italy; Department of Neurosciences, Psychology, Drugs and Child Health, University of Florence, Italy
| | - Francesco S Pavone
- European Laboratory for Non-Linear Spectroscopy, Sesto Fiorentino, 50019, Italy; National Institute of Optics, National Research Council, Florence, 50125, Italy; Department of Physics and Astronomy, University of Florence, Sesto Fiorentino, 50019, Italy
| | - Leonardo Sacconi
- European Laboratory for Non-Linear Spectroscopy, Sesto Fiorentino, 50019, Italy; National Institute of Optics, National Research Council, Florence, 50125, Italy; Institute for Experimental Cardiovascular Medicine, Faculty of Medicine, University of Freiburg, Freiburg, Germany.
| |
Collapse
|
16
|
DeepRePath: Identifying the Prognostic Features of Early-Stage Lung Adenocarcinoma Using Multi-Scale Pathology Images and Deep Convolutional Neural Networks. Cancers (Basel) 2021; 13:cancers13133308. [PMID: 34282757 PMCID: PMC8268823 DOI: 10.3390/cancers13133308] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2021] [Revised: 06/10/2021] [Accepted: 06/28/2021] [Indexed: 12/12/2022] Open
Abstract
Simple Summary Pathology images are vital for understanding solid cancers. In this study, we created DeepRePath using multi-scale pathology images with two-channel deep learning to predict the prognosis of patients with early-stage lung adenocarcinoma (LUAD). DeepRePath demonstrated that it could predict the recurrence of early-stage LUAD with average area under the curve scores of 0.77 and 0.76 in cohort I and cohort II (external validation set), respectively. Pathological features found to be associated with a high probability of recurrence included tumor necrosis, discohesive tumor cells, and atypical nuclei. In conclusion, DeepRePath can improve the treatment modality for patients with early-stage LUAD through recurrence prediction. Abstract The prognosis of patients with lung adenocarcinoma (LUAD), especially early-stage LUAD, is dependent on clinicopathological features. However, its predictive utility is limited. In this study, we developed and trained a DeepRePath model based on a deep convolutional neural network (CNN) using multi-scale pathology images to predict the prognosis of patients with early-stage LUAD. DeepRePath was pre-trained with 1067 hematoxylin and eosin-stained whole-slide images of LUAD from the Cancer Genome Atlas. DeepRePath was further trained and validated using two separate CNNs and multi-scale pathology images of 393 resected lung cancer specimens from patients with stage I and II LUAD. Of the 393 patients, 95 patients developed recurrence after surgical resection. The DeepRePath model showed average area under the curve (AUC) scores of 0.77 and 0.76 in cohort I and cohort II (external validation set), respectively. Owing to low performance, DeepRePath cannot be used as an automated tool in a clinical setting. When gradient-weighted class activation mapping was used, DeepRePath indicated the association between atypical nuclei, discohesive tumor cells, and tumor necrosis in pathology images showing recurrence. Despite the limitations associated with a relatively small number of patients, the DeepRePath model based on CNNs with transfer learning could predict recurrence after the curative resection of early-stage LUAD using multi-scale pathology images.
Collapse
|
17
|
Puttagunta M, Ravi S. Medical image analysis based on deep learning approach. MULTIMEDIA TOOLS AND APPLICATIONS 2021; 80:24365-24398. [PMID: 33841033 PMCID: PMC8023554 DOI: 10.1007/s11042-021-10707-4] [Citation(s) in RCA: 43] [Impact Index Per Article: 14.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/25/2020] [Revised: 11/28/2020] [Accepted: 02/10/2021] [Indexed: 05/05/2023]
Abstract
Medical imaging plays a significant role in different clinical applications such as medical procedures used for early detection, monitoring, diagnosis, and treatment evaluation of various medical conditions. Basicsof the principles and implementations of artificial neural networks and deep learning are essential for understanding medical image analysis in computer vision. Deep Learning Approach (DLA) in medical image analysis emerges as a fast-growing research field. DLA has been widely used in medical imaging to detect the presence or absence of the disease. This paper presents the development of artificial neural networks, comprehensive analysis of DLA, which delivers promising medical imaging applications. Most of the DLA implementations concentrate on the X-ray images, computerized tomography, mammography images, and digital histopathology images. It provides a systematic review of the articles for classification, detection, and segmentation of medical images based on DLA. This review guides the researchers to think of appropriate changes in medical image analysis based on DLA.
Collapse
Affiliation(s)
- Muralikrishna Puttagunta
- Department of Computer Science, School of Engineering and Technology, Pondicherry University, Pondicherry, India
| | - S. Ravi
- Department of Computer Science, School of Engineering and Technology, Pondicherry University, Pondicherry, India
| |
Collapse
|
18
|
Sakamoto T, Furukawa T, Lami K, Pham HHN, Uegami W, Kuroda K, Kawai M, Sakanashi H, Cooper LAD, Bychkov A, Fukuoka J. A narrative review of digital pathology and artificial intelligence: focusing on lung cancer. Transl Lung Cancer Res 2020; 9:2255-2276. [PMID: 33209648 PMCID: PMC7653145 DOI: 10.21037/tlcr-20-591] [Citation(s) in RCA: 43] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022]
Abstract
The emergence of whole slide imaging technology allows for pathology diagnosis on a computer screen. The applications of digital pathology are expanding, from supporting remote institutes suffering from a shortage of pathologists to routine use in daily diagnosis including that of lung cancer. Through practice and research large archival databases of digital pathology images have been developed that will facilitate the development of artificial intelligence (AI) methods for image analysis. Currently, several AI applications have been reported in the field of lung cancer; these include the segmentation of carcinoma foci, detection of lymph node metastasis, counting of tumor cells, and prediction of gene mutations. Although the integration of AI algorithms into clinical practice remains a significant challenge, we have implemented tumor cell count for genetic analysis, a helpful application for routine use. Our experience suggests that pathologists often overestimate the contents of tumor cells, and the use of AI-based analysis increases the accuracy and makes the tasks less tedious. However, there are several difficulties encountered in the practical use of AI in clinical diagnosis. These include the lack of sufficient annotated data for the development and validation of AI systems, the explainability of black box AI models, such as those based on deep learning that offer the most promising performance, and the difficulty in defining the ground truth data for training and validation owing to inherent ambiguity in most applications. All of these together present significant challenges in the development and clinical translation of AI methods in the practice of pathology. Additional research on these problems will help in resolving the barriers to the clinical use of AI. Helping pathologists in developing knowledge of the working and limitations of AI will benefit the use of AI in both diagnostics and research.
Collapse
Affiliation(s)
- Taro Sakamoto
- Department of Pathology, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan
| | - Tomoi Furukawa
- Department of Pathology, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan
| | - Kris Lami
- Department of Pathology, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan
| | - Hoa Hoang Ngoc Pham
- Department of Pathology, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan
| | - Wataru Uegami
- Department of Pathology, Kameda Medical Center, Kamogawa, Chiba, Japan
| | - Kishio Kuroda
- Department of Pathology, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan
| | - Masataka Kawai
- Department of Pathology, Interdisciplinary Graduate School of Medicine and Engineering, University of Yamanashi, Yamanashi, Japan
| | - Hidenori Sakanashi
- Configurable Learning Mechanism Research Team, National Institute of Advanced Industrial Science and Technology, Tokyo, Japan
| | | | - Andrey Bychkov
- Department of Pathology, Kameda Medical Center, Kamogawa, Chiba, Japan
| | - Junya Fukuoka
- Department of Pathology, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan.,Department of Pathology, Kameda Medical Center, Kamogawa, Chiba, Japan
| |
Collapse
|
19
|
Yin PN, Kc K, Wei S, Yu Q, Li R, Haake AR, Miyamoto H, Cui F. Histopathological distinction of non-invasive and invasive bladder cancers using machine learning approaches. BMC Med Inform Decis Mak 2020; 20:162. [PMID: 32680493 PMCID: PMC7367328 DOI: 10.1186/s12911-020-01185-z] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2019] [Accepted: 07/13/2020] [Indexed: 01/18/2023] Open
Abstract
Background One of the most challenging tasks for bladder cancer diagnosis is to histologically differentiate two early stages, non-invasive Ta and superficially invasive T1, the latter of which is associated with a significantly higher risk of disease progression. Indeed, in a considerable number of cases, Ta and T1 tumors look very similar under microscope, making the distinction very difficult even for experienced pathologists. Thus, there is an urgent need for a favoring system based on machine learning (ML) to distinguish between the two stages of bladder cancer. Methods A total of 1177 images of bladder tumor tissues stained by hematoxylin and eosin were collected by pathologists at University of Rochester Medical Center, which included 460 non-invasive (stage Ta) and 717 invasive (stage T1) tumors. Automatic pipelines were developed to extract features for three invasive patterns characteristic to the T1 stage bladder cancer (i.e., desmoplastic reaction, retraction artifact, and abundant pinker cytoplasm), using imaging processing software ImageJ and CellProfiler. Features extracted from the images were analyzed by a suite of machine learning approaches. Results We extracted nearly 700 features from the Ta and T1 tumor images. Unsupervised clustering analysis failed to distinguish hematoxylin and eosin images of Ta vs. T1 tumors. With a reduced set of features, we successfully distinguished 1177 Ta or T1 images with an accuracy of 91–96% by six supervised learning methods. By contrast, convolutional neural network (CNN) models that automatically extract features from images produced an accuracy of 84%, indicating that feature extraction driven by domain knowledge outperforms CNN-based automatic feature extraction. Further analysis revealed that desmoplastic reaction was more important than the other two patterns, and the number and size of nuclei of tumor cells were the most predictive features. Conclusions We provide a ML-empowered, feature-centered, and interpretable diagnostic system to facilitate the accurate staging of Ta and T1 diseases, which has a potential to apply to other types of cancer.
Collapse
Affiliation(s)
- Peng-Nien Yin
- Thomas H. Gosnell School of Life Sciences, Rochester Institute of Technology, 1 Lomb Memorial Drive, Rochester, NY, 14623, USA
| | - Kishan Kc
- Golisano College of Computing and Information Sciences, Rochester Institute of Technology, 20 Lomb Memorial Drive, Rochester, NY, 14623, USA
| | - Shishi Wei
- Golisano College of Computing and Information Sciences, Rochester Institute of Technology, 20 Lomb Memorial Drive, Rochester, NY, 14623, USA
| | - Qi Yu
- Golisano College of Computing and Information Sciences, Rochester Institute of Technology, 20 Lomb Memorial Drive, Rochester, NY, 14623, USA
| | - Rui Li
- Golisano College of Computing and Information Sciences, Rochester Institute of Technology, 20 Lomb Memorial Drive, Rochester, NY, 14623, USA
| | - Anne R Haake
- Golisano College of Computing and Information Sciences, Rochester Institute of Technology, 20 Lomb Memorial Drive, Rochester, NY, 14623, USA
| | - Hiroshi Miyamoto
- Department of Pathology and Laboratory Medicine, University of Rochester Medical Center, 601 Elmwood Avenue, Rochester, NY, 14642, USA.
| | - Feng Cui
- Thomas H. Gosnell School of Life Sciences, Rochester Institute of Technology, 1 Lomb Memorial Drive, Rochester, NY, 14623, USA.
| |
Collapse
|
20
|
Cong L, Feng W, Yao Z, Zhou X, Xiao W. Deep Learning Model as a New Trend in Computer-aided Diagnosis of Tumor Pathology for Lung Cancer. J Cancer 2020; 11:3615-3622. [PMID: 32284758 PMCID: PMC7150458 DOI: 10.7150/jca.43268] [Citation(s) in RCA: 18] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2019] [Accepted: 03/05/2020] [Indexed: 01/01/2023] Open
Abstract
Lung cancer is one of the main causes of cancer-related death in the world. The identification and characteristics of malignant cells are essential for the diagnosis and treatment of primary or metastatic cancers. Deep learning is a new field of artificial intelligence, which can be used for computer aided diagnosis and scientific research of lung cancer pathology by analyzing and learning through establishment and simulation of human brain. In this review, we will introduce the application, progress and problems of deep learning in pathology of lung cancer and make prospects for its future development.
Collapse
Affiliation(s)
- Lei Cong
- Department of Oncology, Shandong Provincial Hospital affiliated to Shandong University, Jinan, China
| | - Wanbing Feng
- Cheeloo College of Medicine, Shandong University, Jinan, China
| | - Zhigang Yao
- Department of Pathology, Shandong Provincial Hospital affiliated to Shandong University, Jinan, China
| | - Xiaoming Zhou
- Department of Scientific Research, Shandong Provincial Hospital affiliated to Shandong University, Jinan, China
| | - Wei Xiao
- Department of Scientific Research, Shandong Provincial Hospital affiliated to Shandong University, Jinan, China
| |
Collapse
|
21
|
Wang S, Wang T, Yang L, Yang DM, Fujimoto J, Yi F, Luo X, Yang Y, Yao B, Lin S, Moran C, Kalhor N, Weissferdt A, Minna J, Xie Y, Wistuba II, Mao Y, Xiao G. ConvPath: A software tool for lung adenocarcinoma digital pathological image analysis aided by a convolutional neural network. EBioMedicine 2019; 50:103-110. [PMID: 31767541 PMCID: PMC6921240 DOI: 10.1016/j.ebiom.2019.10.033] [Citation(s) in RCA: 55] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2019] [Revised: 10/16/2019] [Accepted: 10/16/2019] [Indexed: 12/20/2022] Open
Abstract
BACKGROUND The spatial distributions of different types of cells could reveal a cancer cell's growth pattern, its relationships with the tumor microenvironment and the immune response of the body, all of which represent key "hallmarks of cancer". However, the process by which pathologists manually recognize and localize all the cells in pathology slides is extremely labor intensive and error prone. METHODS In this study, we developed an automated cell type classification pipeline, ConvPath, which includes nuclei segmentation, convolutional neural network-based tumor cell, stromal cell, and lymphocyte classification, and extraction of tumor microenvironment-related features for lung cancer pathology images. To facilitate users in leveraging this pipeline for their research, all source scripts for ConvPath software are available at https://qbrc.swmed.edu/projects/cnn/. FINDINGS The overall classification accuracy was 92.9% and 90.1% in training and independent testing datasets, respectively. By identifying cells and classifying cell types, this pipeline can convert a pathology image into a "spatial map" of tumor, stromal and lymphocyte cells. From this spatial map, we can extract features that characterize the tumor micro-environment. Based on these features, we developed an image feature-based prognostic model and validated the model in two independent cohorts. The predicted risk group serves as an independent prognostic factor, after adjusting for clinical variables that include age, gender, smoking status, and stage. INTERPRETATION The analysis pipeline developed in this study could convert the pathology image into a "spatial map" of tumor cells, stromal cells and lymphocytes. This could greatly facilitate and empower comprehensive analysis of the spatial organization of cells, as well as their roles in tumor progression and metastasis.
Collapse
Affiliation(s)
- Shidan Wang
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX
| | - Tao Wang
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX; Center for the Genetics of Host Defense, University of Texas Southwestern Medical Center, Dallas, TX
| | - Lin Yang
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX; Department of Pathology, National Cancer Center/Cancer Hospital, Chinese Academy of Medical Sciences (CHCAMS), China
| | - Donghan M Yang
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX
| | - Junya Fujimoto
- Department of Translational Molecular Pathology, University of Texas MD Anderson Cancer Center, Houston, TX
| | - Faliu Yi
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX
| | - Xin Luo
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX
| | - Yikun Yang
- Department of Thoracic Surgery, National Cancer Center/Cancer Hospital, Chinese Academy of Medical Sciences (CHCAMS), China
| | - Bo Yao
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX
| | - ShinYi Lin
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX
| | - Cesar Moran
- Department of Pathology, Division of Pathology/Lab Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Neda Kalhor
- Department of Pathology, Division of Pathology/Lab Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Annikka Weissferdt
- Department of Pathology, Division of Pathology/Lab Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - John Minna
- Hamon Center for Therapeutic Oncology Research, Department of Internal Medicine and Department of Pharmacology, University of Texas Southwestern Medical Center, Dallas, TX; Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX
| | - Yang Xie
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX; Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX; Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX
| | - Ignacio I Wistuba
- Department of Translational Molecular Pathology, University of Texas MD Anderson Cancer Center, Houston, TX
| | - Yousheng Mao
- Department of Thoracic Surgery, National Cancer Center/Cancer Hospital, Chinese Academy of Medical Sciences (CHCAMS), China
| | - Guanghua Xiao
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX; Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX; Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX.
| |
Collapse
|
22
|
FABnet: feature attention-based network for simultaneous segmentation of microvessels and nerves in routine histology images of oral cancer. Neural Comput Appl 2019. [DOI: 10.1007/s00521-019-04516-y] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
|
23
|
Bukenya F, Nerissa C, Serres S, Pardon MC, Bai L. An automated method for segmentation and quantification of blood vessels in histology images. Microvasc Res 2019; 128:103928. [PMID: 31676310 DOI: 10.1016/j.mvr.2019.103928] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2018] [Revised: 09/11/2019] [Accepted: 09/16/2019] [Indexed: 02/01/2023]
Abstract
Alzheimer's disease (AD) is a chronic neuro-degenerative disease that adversely affect many people on a global scale. Despite different diagnostic and therapeutic treatment, there is no cure for AD. The brain is one of the most complex organ and researchers are still trying to understand so as to find a cure. OBJECTIVE To complement the efforts of clinical researchers engaged in research in alzheimer's disease, accurate segmentation and quantification of blood vessels in brain images is required. METHOD For robust segmentation of blood vessels even in the presence of colour variation, we introduce a fully automated morphological tool that can extract and quantify vessels from haematoxylin and diaminobenzidine stained histology brain image. The method, exploits saturation channel of stained image slides, ISODATA threshold method is applied to obtain a binary image. This helps in eliminating background and remaining with only blood vessels. A one-stage procedure that includes eliminating small artefacts is performed on the binary mask. The intensity of the image is transformed. Joining is performed to deal with fragmentation of intact blood vessels on the images, and artefactual appearance of the blood vessel structures. The artefactual fragments based on measured incoherence with neighbouring tissue are removed. The vessels are then labelled to facilitate quantification. Morphometric measurements are used during the vessel quantification assess both vessels with lumen and vessels without lumen. We have quantified the diameter of blood vessels. RESULTS The image processing technique is developed in close collaboration with neuroscientist experts to help clinician. We have evaluated our proposed approach qualitatively. The method was validated against their manual quantification results. Qualitative results show that the method can indeed segment the blood vessels in the presence of colour variations and artefacts. The quantitative method produces fairly better results.
Collapse
Affiliation(s)
- Faiza Bukenya
- School of Computer Science, University of Nottingham, Nottingham NG8 1BB, United Kingdom.
| | - Culi Nerissa
- School of Life Sciences, University of Nottingham, Nottingham NG7 2UH, United Kingdom.
| | - Sébastien Serres
- School of Life Sciences, University of Nottingham, Nottingham NG7 2UH, United Kingdom.
| | | | - Li Bai
- School of Computer Science, University of Nottingham, Nottingham NG8 1BB, United Kingdom.
| |
Collapse
|
24
|
Wang S, Yang DM, Rong R, Zhan X, Fujimoto J, Liu H, Minna J, Wistuba II, Xie Y, Xiao G. Artificial Intelligence in Lung Cancer Pathology Image Analysis. Cancers (Basel) 2019; 11:E1673. [PMID: 31661863 PMCID: PMC6895901 DOI: 10.3390/cancers11111673] [Citation(s) in RCA: 97] [Impact Index Per Article: 19.4] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2019] [Revised: 10/17/2019] [Accepted: 10/21/2019] [Indexed: 12/12/2022] Open
Abstract
OBJECTIVE Accurate diagnosis and prognosis are essential in lung cancer treatment selection and planning. With the rapid advance of medical imaging technology, whole slide imaging (WSI) in pathology is becoming a routine clinical procedure. An interplay of needs and challenges exists for computer-aided diagnosis based on accurate and efficient analysis of pathology images. Recently, artificial intelligence, especially deep learning, has shown great potential in pathology image analysis tasks such as tumor region identification, prognosis prediction, tumor microenvironment characterization, and metastasis detection. MATERIALS AND METHODS In this review, we aim to provide an overview of current and potential applications for AI methods in pathology image analysis, with an emphasis on lung cancer. RESULTS We outlined the current challenges and opportunities in lung cancer pathology image analysis, discussed the recent deep learning developments that could potentially impact digital pathology in lung cancer, and summarized the existing applications of deep learning algorithms in lung cancer diagnosis and prognosis. DISCUSSION AND CONCLUSION With the advance of technology, digital pathology could have great potential impacts in lung cancer patient care. We point out some promising future directions for lung cancer pathology image analysis, including multi-task learning, transfer learning, and model interpretation.
Collapse
Affiliation(s)
- Shidan Wang
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
| | - Donghan M Yang
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
| | - Ruichen Rong
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
| | - Xiaowei Zhan
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
| | - Junya Fujimoto
- Department of Translational Molecular Pathology, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA.
| | - Hongyu Liu
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
| | - John Minna
- Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
- Hamon Center for Therapeutic Oncology Research, UT Southwestern Medical Center, Dallas, TX 75390, USA.
- Departments of Internal Medicine and Pharmacology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
| | - Ignacio Ivan Wistuba
- Department of Translational Molecular Pathology, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA.
| | - Yang Xie
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
- Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
- Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
| | - Guanghua Xiao
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
- Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
- Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
| |
Collapse
|
25
|
Wang S, Yang DM, Rong R, Zhan X, Xiao G. Pathology Image Analysis Using Segmentation Deep Learning Algorithms. THE AMERICAN JOURNAL OF PATHOLOGY 2019; 189:1686-1698. [PMID: 31199919 PMCID: PMC6723214 DOI: 10.1016/j.ajpath.2019.05.007] [Citation(s) in RCA: 154] [Impact Index Per Article: 30.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/19/2018] [Revised: 05/01/2019] [Accepted: 05/09/2019] [Indexed: 12/16/2022]
Abstract
With the rapid development of image scanning techniques and visualization software, whole slide imaging (WSI) is becoming a routine diagnostic method. Accelerating clinical diagnosis from pathology images and automating image analysis efficiently and accurately remain significant challenges. Recently, deep learning algorithms have shown great promise in pathology image analysis, such as in tumor region identification, metastasis detection, and patient prognosis. Many machine learning algorithms, including convolutional neural networks, have been proposed to automatically segment pathology images. Among these algorithms, segmentation deep learning algorithms such as fully convolutional networks stand out for their accuracy, computational efficiency, and generalizability. Thus, deep learning-based pathology image segmentation has become an important tool in WSI analysis. In this review, the pathology image segmentation process using deep learning algorithms is described in detail. The goals are to provide quick guidance for implementing deep learning into pathology image analysis and to provide some potential ways of further improving segmentation performance. Although there have been previous reviews on using machine learning methods in digital pathology image analysis, this is the first in-depth review of the applications of deep learning algorithms for segmentation in WSI analysis.
Collapse
Affiliation(s)
- Shidan Wang
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Donghan M Yang
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Ruichen Rong
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Xiaowei Zhan
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, Texas.
| | - Guanghua Xiao
- Quantitative Biomedical Research Center, Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Dallas, Texas; Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas; Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, Texas.
| |
Collapse
|