1
|
Seesawad N, Ittichaiwong P, Sudhawiyangkul T, Sawangjai P, Thuwajit P, Boonsakan P, Sripodok S, Veerakanjana K, Charngkaew K, Pongpaibul A, Angkathunyakul N, Hnoohom N, Yuenyong S, Thuwajit C, Wilaiprasitporn T. PseudoCell: Hard Negative Mining as Pseudo Labeling for Deep Learning-Based Centroblast Cell Detection. IEEE OPEN JOURNAL OF ENGINEERING IN MEDICINE AND BIOLOGY 2024; 5:514-523. [PMID: 39050971 PMCID: PMC11268940 DOI: 10.1109/ojemb.2024.3407351] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/18/2024] [Revised: 05/08/2024] [Accepted: 05/27/2024] [Indexed: 07/27/2024] Open
Abstract
Background: Deep learning models for patch classification in whole-slide images (WSIs) have shown promise in assisting follicular lymphoma grading. However, these models often require pathologists to identify centroblasts and manually provide refined labels for model optimization. Objective: To address this limitation, we propose PseudoCell, an object detection framework for automated centroblast detection in WSI, eliminating the need for extensive pathologist's refined labels. Methods: PseudoCell leverages a combination of pathologist-provided centroblast labels and pseudo-negative labels generated from undersampled false-positive predictions based on cell morphology features. This approach reduces the reliance on time-consuming manual annotations. Results: Our framework significantly reduces the workload for pathologists by accurately identifying and narrowing down areas of interest containing centroblasts. Depending on the confidence threshold, PseudoCell can eliminate 58.18-99.35% of irrelevant tissue areas on WSI, streamlining the diagnostic process. Conclusion: This study presents PseudoCell as a practical and efficient prescreening method for centroblast detection, eliminating the need for refined labels from pathologists. The discussion section provides detailed guidance for implementing PseudoCell in clinical practice.
Collapse
Affiliation(s)
- Narongrid Seesawad
- Bio-inspired Robotics and Neural Engineering (BRAIN) Lab, School of Information Science and Technology (IST)Vidyasirimedhi Institute of Science & Technology (VISTEC)Rayong21210Thailand
| | - Piyalitt Ittichaiwong
- Siriraj Informatics and Data Innovation Center, Faculty of Medicine Siriraj HospitalMahidol UniversityBangkok10700Thailand
| | - Thapanun Sudhawiyangkul
- Bio-inspired Robotics and Neural Engineering (BRAIN) Lab, School of Information Science and Technology (IST)Vidyasirimedhi Institute of Science & Technology (VISTEC)Rayong21210Thailand
| | - Phattarapong Sawangjai
- Bio-inspired Robotics and Neural Engineering (BRAIN) Lab, School of Information Science and Technology (IST)Vidyasirimedhi Institute of Science & Technology (VISTEC)Rayong21210Thailand
| | - Peti Thuwajit
- Department of Immunology, Faculty of Medicine Siriraj HospitalMahidol UniversityBangkok10700Thailand
| | - Paisarn Boonsakan
- Department of Pathology, Faculty of Medicine Ramathibodi HospitalMahidol UniversityBangkok10400Thailand
| | - Supasan Sripodok
- Department of Pathology, Faculty of Medicine Siriraj HospitalMahidol UniversityBangkok10700Thailand
| | - Kanyakorn Veerakanjana
- Siriraj Informatics and Data Innovation Center, Faculty of Medicine Siriraj HospitalMahidol UniversityBangkok10700Thailand
| | - Komgrid Charngkaew
- Department of Pathology, Faculty of Medicine Siriraj HospitalMahidol UniversityBangkok10700Thailand
| | - Ananya Pongpaibul
- Department of Pathology, Faculty of Medicine Siriraj HospitalMahidol UniversityBangkok10700Thailand
| | - Napat Angkathunyakul
- Department of Pathology, Faculty of Medicine Siriraj HospitalMahidol UniversityBangkok10700Thailand
| | - Narit Hnoohom
- Department of Computer Engineering, Faculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand
| | - Sumeth Yuenyong
- Department of Computer Engineering, Faculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand
| | - Chanitra Thuwajit
- Department of Immunology, Faculty of Medicine Siriraj HospitalMahidol UniversityBangkok10700Thailand
| | - Theerawit Wilaiprasitporn
- Bio-inspired Robotics and Neural Engineering (BRAIN) Lab, School of Information Science and Technology (IST)Vidyasirimedhi Institute of Science & Technology (VISTEC)Rayong21210Thailand
| |
Collapse
|
2
|
Yuenyong S, Boonsakan P, Sripodok S, Thuwajit P, Charngkaew K, Pongpaibul A, Angkathunyakul N, Hnoohom N, Thuwajit C. Detection of centroblast cells in H&E stained whole slide image based on object detection. Front Med (Lausanne) 2024; 11:1303982. [PMID: 38384407 PMCID: PMC10879397 DOI: 10.3389/fmed.2024.1303982] [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: 09/28/2023] [Accepted: 01/18/2024] [Indexed: 02/23/2024] Open
Abstract
Introduction Detection and counting of Centroblast cells (CB) in hematoxylin & eosin (H&E) stained whole slide image (WSI) is an important workflow in grading Lymphoma. Each high power field (HPF) patch of a WSI is inspected for the number of CB cells and compared with the World Health Organization (WHO) guideline that organizes lymphoma into 3 grades. Spotting and counting CBs is time-consuming and labor intensive. Moreover, there is often disagreement between different readers, and even a single reader may not be able to perform consistently due to many factors. Method We propose an artificial intelligence system that can scan patches from a WSI and detect CBs automatically. The AI system works on the principle of object detection, where the CB is the single class of object of interest. We trained the AI model on 1,669 example instances of CBs that originate from WSI of 5 different patients. The data was split 80%/20% for training and validation respectively. Result The best performance was from YOLOv5x6 model that used the preprocessed CB dataset achieved precision of 0.808, recall of 0.776, mAP at 0.5 IoU of 0.800 and overall mAP of 0.647. Discussion The results show that centroblast cells can be detected in WSI with relatively high precision and recall.
Collapse
Affiliation(s)
- Sumeth Yuenyong
- Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom, Thailand
| | - Paisarn Boonsakan
- Department of Pathology, Faculty of Medicine Ramathibodi Hospital, Mahidol University, Bangkok, Thailand
| | - Supasan Sripodok
- Department of Pathology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Peti Thuwajit
- Department of Immunology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Komgrid Charngkaew
- Department of Pathology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Ananya Pongpaibul
- Department of Pathology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Napat Angkathunyakul
- Department of Pathology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Narit Hnoohom
- Image Information and Intelligence Laboratory, Department of Computer Engineering, Faculty of Engineering, Mahidol University, Nakhon Pathom, Thailand
| | - Chanitra Thuwajit
- Department of Immunology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
| |
Collapse
|
3
|
El Achi H, Khoury JD. Artificial Intelligence and Digital Microscopy Applications in Diagnostic Hematopathology. Cancers (Basel) 2020; 12:cancers12040797. [PMID: 32224980 PMCID: PMC7226574 DOI: 10.3390/cancers12040797] [Citation(s) in RCA: 37] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2020] [Revised: 03/20/2020] [Accepted: 03/24/2020] [Indexed: 12/15/2022] Open
Abstract
Digital Pathology is the process of converting histology glass slides to digital images using sophisticated computerized technology to facilitate acquisition, evaluation, storage, and portability of histologic information. By its nature, digitization of analog histology data renders it amenable to analysis using deep learning/artificial intelligence (DL/AI) techniques. The application of DL/AI to digital pathology data holds promise, even if the scope of use cases and regulatory framework for deploying such applications in the clinical environment remains in the early stages. Recent studies using whole-slide images and DL/AI to detect histologic abnormalities in general and cancer in particular have shown encouraging results. In this review, we focus on these emerging technologies intended for use in diagnostic hematology and the evaluation of lymphoproliferative diseases.
Collapse
Affiliation(s)
- Hanadi El Achi
- Department of Pathology and Laboratory Medicine, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA;
| | - Joseph D. Khoury
- Department of Hematopathology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Correspondence:
| |
Collapse
|
4
|
Classification of Nuclei in Follicular Lyphoma Tissue Sections Using Different Stains and Bayesian Networks. ACTA ACUST UNITED AC 2016. [DOI: 10.1007/978-3-319-32703-7_47] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register]
|
5
|
|
6
|
Fauzi MFA, Pennell M, Sahiner B, Chen W, Shana'ah A, Hemminger J, Gru A, Kurt H, Losos M, Joehlin-Price A, Kavran C, Smith SM, Nowacki N, Mansor S, Lozanski G, Gurcan MN. Classification of follicular lymphoma: the effect of computer aid on pathologists grading. BMC Med Inform Decis Mak 2015; 15:115. [PMID: 26715518 PMCID: PMC4696238 DOI: 10.1186/s12911-015-0235-6] [Citation(s) in RCA: 22] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2015] [Accepted: 12/15/2015] [Indexed: 11/28/2022] Open
Abstract
Background Follicular lymphoma (FL) is one of the most common lymphoid malignancies in the western world. FL cases are stratified into three histological grades based on the average centroblast count per high power field (HPF). The centroblast count is performed manually by the pathologist using an optical microscope and hematoxylin and eosin (H&E) stained tissue section. Although this is the current clinical practice, it suffers from high inter- and intra-observer variability and is vulnerable to sampling bias. Methods In this paper, we present a system, called Follicular Lymphoma Grading System (FLAGS), to assist the pathologist in grading FL cases. We also assess the effect of FLAGS on accuracy of expert and inexperienced readers. FLAGS automatically identifies possible HPFs for examination by analyzing H&E and CD20 stains, before classifying them into low or high risk categories. The pathologist is first asked to review the slides according to the current routine clinical practice, before being presented with FLAGS classification via color-coded map. The accuracy of the readers with and without FLAGS assistance is measured. Results FLAGS was used by four experts (board-certified hematopathologists) and seven pathology residents on 20 FL slides. Access to FLAGS improved overall reader accuracy with the biggest improvement seen among residents. An average AUC value of 0.75 was observed which generally indicates “acceptable” diagnostic performance. Conclusions The results of this study show that FLAGS can be useful in increasing the pathologists’ accuracy in grading the tissue. To the best of our knowledge, this study measure, for the first time, the effect of computerized image analysis on pathologists’ grading of follicular lymphoma. When fully developed, such systems have the potential to reduce sampling bias by examining an increased proportion of HPFs within follicle regions, as well as to reduce inter- and intra-reader variability. Electronic supplementary material The online version of this article (doi:10.1186/s12911-015-0235-6) contains supplementary material, which is available to authorized users.
Collapse
Affiliation(s)
| | - Michael Pennell
- Division of Biostatistics, College of Public Health, The Ohio State University, Columbus, OH, USA
| | - Berkman Sahiner
- Center for Devices and Radiological Health, US Food and Drug Administration, Silver Spring, MD, USA
| | - Weijie Chen
- Center for Devices and Radiological Health, US Food and Drug Administration, Silver Spring, MD, USA
| | - Arwa Shana'ah
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Jessica Hemminger
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Alejandro Gru
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Habibe Kurt
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Michael Losos
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Amy Joehlin-Price
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Christina Kavran
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Stephen M Smith
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Nicholas Nowacki
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Sharmeen Mansor
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Gerard Lozanski
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Metin N Gurcan
- Department of Biomedical Informatics, The Ohio State University, 250 Lincoln Tower, 1800 Cannon Drive, Columbus, OH, 43210, USA.
| |
Collapse
|
7
|
Fauzi MFA, Gokozan HN, Elder B, Puduvalli VK, Pierson CR, Otero JJ, Gurcan MN. A multi-resolution textural approach to diagnostic neuropathology reporting. J Neurooncol 2015; 124:393-402. [PMID: 26255070 PMCID: PMC4782607 DOI: 10.1007/s11060-015-1872-4] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2015] [Accepted: 07/27/2015] [Indexed: 10/23/2022]
Abstract
We present a computer aided diagnostic workflow focusing on two diagnostic branch points in neuropathology (intraoperative consultation and p53 status in tumor biopsy specimens) by means of texture analysis via discrete wavelet frames decomposition. For intraoperative consultation, our methodology is capable of classifying glioblastoma versus metastatic cancer by extracting textural features from the non-nuclei region of cytologic preparations based on the imaging characteristics of glial processes, which appear as anisotropic thin linear structures. For metastasis, these are homogeneous in appearance, thus suitable and extractable texture features distinguish the two tissue types. Experiments on 53 images (29 glioblastomas and 24 metastases) resulted in average accuracy as high as 89.7 % for glioblastoma, 87.5 % for metastasis and 88.7 % overall. For p53 interpretation, we detect and classify p53 status by classifying staining intensity into strong, moderate, weak and negative sub-classes. We achieved this by developing a novel adaptive thresholding for detection, a two-step rule based on weighted color and intensity for the classification of positively and negatively stained nuclei, followed by texture classification to classify the positively stained nuclei into the strong, moderate and weak intensity sub-classes. Our detection method is able to correctly locate and distinguish the four types of cells, at 85 % average precision and 88 % average sensitivity rate. These classification methods on the other hand recorded 81 % accuracy in classifying the positive and negative cells, and 60 % accuracy in further classifying the positive cells into the three intensity groups, which is comparable with neuropathologists' markings.
Collapse
Affiliation(s)
| | | | - Brad Elder
- Department of Neurological Surgery, The Ohio State University, Columbus, OH, USA
| | - Vinay K. Puduvalli
- Division of Neuro-oncology, The Ohio State University Wexner Medical Center, Columbus, OH, USA
| | - Christopher R. Pierson
- Department of Pathology, The Ohio State University, Columbus, OH, USA
- Department of Pathology and Laboratory Medicine, Nationwide Children’s Hospital, Columbus, OH, USA
- Division of Anatomy, The Ohio State University, Columbus, OH, USA
| | - José Javier Otero
- Department of Pathology, The Ohio State University, Columbus, OH, USA
- Department of Pathology, Division of Neuropathology, The Ohio State University College of Medicine, 4169 Graves Hall, 333 W 10th Avenue, Columbus, OH 43210, USA
| | - Metin N. Gurcan
- Department of Biomedical Informatics, The Ohio State University, Columbus, OH, USA
- 250 Lincoln Tower, 1800 Cannon Drive, Columbus, OH 43210, USA
- 320-K Lincoln Tower, Columbus, USA
| |
Collapse
|
8
|
Kornaropoulos EN, Niazi MKK, Lozanski G, Gurcan MN. Histopathological image analysis for centroblasts classification through dimensionality reduction approaches. Cytometry A 2013; 85:242-55. [PMID: 24376080 DOI: 10.1002/cyto.a.22432] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2013] [Revised: 11/30/2013] [Accepted: 12/03/2013] [Indexed: 11/10/2022]
Abstract
We present two novel automated image analysis methods to differentiate centroblast (CB) cells from noncentroblast (non-CB) cells in digital images of H&E-stained tissues of follicular lymphoma. CB cells are often confused by similar looking cells within the tissue, therefore a system to help their classification is necessary. Our methods extract the discriminatory features of cells by approximating the intrinsic dimensionality from the subspace spanned by CB and non-CB cells. In the first method, discriminatory features are approximated with the help of singular value decomposition (SVD), whereas in the second method they are extracted using Laplacian Eigenmaps. Five hundred high-power field images were extracted from 17 slides, which are then used to compose a database of 213 CB and 234 non-CB region of interest images. The recall, precision, and overall accuracy rates of the developed methods were measured and compared with existing classification methods. Moreover, the reproducibility of both classification methods was also examined. The average values of the overall accuracy were 99.22% ± 0.75% and 99.07% ± 1.53% for COB and CLEM, respectively. The experimental results demonstrate that both proposed methods provide better classification accuracy of CB/non-CB in comparison with the state of the art methods.
Collapse
Affiliation(s)
- Evgenios N Kornaropoulos
- Informatics and Telematics Institute-Centre for Research and Technology Hellas (ITI-CERTH), Thessaloniki, Greece
| | | | | | | |
Collapse
|
9
|
Lozanski G, Pennell M, Shana'ah A, Zhao W, Gewirtz A, Racke F, Hsi E, Simpson S, Mosse C, Alam S, Swierczynski S, Hasserjian RP, Gurcan MN. Inter-reader variability in follicular lymphoma grading: Conventional and digital reading. J Pathol Inform 2013; 4:30. [PMID: 24392244 PMCID: PMC3869955 DOI: 10.4103/2153-3539.120747] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2013] [Accepted: 09/03/2013] [Indexed: 11/04/2022] Open
Abstract
CONTEXT Pathologists grade follicular lymphoma (FL) cases by selecting 10, random high power fields (HPFs), counting the number of centroblasts (CBs) in these HPFs under the microscope and then calculating the average CB count for the whole slide. Previous studies have demonstrated that there is high inter-reader variability among pathologists using this methodology in grading. AIMS The objective of this study was to explore if newly available digital reading technologies can reduce inter-reader variability. SETTINGS AND DESIGN IN THIS STUDY, WE CONSIDERED THREE DIFFERENT READING CONDITIONS (RCS) IN GRADING FL: (1) Conventional (glass-slide based) to establish the baseline, (2) digital whole slide viewing, (3) digital whole slide viewing with selected HPFs. Six board-certified pathologists from five different institutions read 17 FL slides in these three different RCs. RESULTS Although there was relative poor consensus in conventional reading, with lack of consensus in 41.2% of cases, which was similar to previously reported studies; we found that digital reading with pre-selected fields improved the inter-reader agreement, with only 5.9% lacking consensus among pathologists. CONCLUSIONS Digital whole slide RC resulted in the worst concordance among pathologists while digital whole slide reading selected HPFs improved the concordance. Further studies are underway to determine if this performance can be sustained with a larger dataset and our automated HPF and CB detection algorithms can be employed to further improve the concordance.
Collapse
Affiliation(s)
- Gerard Lozanski
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Michael Pennell
- Division of Biostatistics, College of Public Health, The Ohio State University, Columbus, OH, USA
| | - Arwa Shana'ah
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Weiqiang Zhao
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Amy Gewirtz
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Frederick Racke
- Department of Pathology, The Ohio State University, Columbus, OH, USA
| | - Eric Hsi
- Cleveland Clinic, Cleveland, OH, USA
| | - Sabrina Simpson
- Department of Pathology, Central Ohio Pathology Associates, Westerville, OH, USA
| | | | - Shadia Alam
- Department of Pathology, Battle Creek, MI, USA
| | | | | | - Metin N Gurcan
- Department of Biomedical Informatics, Ohio State University, Columbus, OH, USA
| |
Collapse
|
10
|
Belkacem-Boussaid K, Samsi S, Lozanski G, Gurcan MN. Automatic detection of follicular regions in H&E images using iterative shape index. Comput Med Imaging Graph 2011; 35:592-602. [PMID: 21511436 DOI: 10.1016/j.compmedimag.2011.03.001] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2010] [Revised: 02/16/2011] [Accepted: 03/16/2011] [Indexed: 10/18/2022]
Abstract
Follicular Lymphoma (FL) accounts for 20-25% of non-Hodgkin lymphomas in the United States. The first step in grading FL is identifying follicles. Our paper discusses a novel technique to segment follicular regions in H&E stained images. The method is based on three successive steps: (1) region-based segmentation, (2) iterative shape index (concavity index) calculation, (3) and recursive watershed. A novel aspect of this method is the use of iterative Concavity Index (CI) to control the follicular splitting process in recursive watershed. CI takes into consideration the convex hull of the object and the closest area surrounding it. The mean Zijbendos similarity index (ZSI) final segmentation score on fifteen cases was 78.33%, with a standard deviation of 2.83.
Collapse
Affiliation(s)
- K Belkacem-Boussaid
- Department of Biomedical Informatics, Ohio State University, Columbus, OH 43210, USA.
| | | | | | | |
Collapse
|
11
|
|