1
|
Ghezloo F, Chang OH, Knezevich SR, Shaw KC, Thigpen KG, Reisch LM, Shapiro LG, Elmore JG. Robust ROI Detection in Whole Slide Images Guided by Pathologists' Viewing Patterns. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01202-x. [PMID: 39122892 DOI: 10.1007/s10278-024-01202-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/01/2024] [Revised: 06/24/2024] [Accepted: 07/05/2024] [Indexed: 08/12/2024]
Abstract
Deep learning techniques offer improvements in computer-aided diagnosis systems. However, acquiring image domain annotations is challenging due to the knowledge and commitment required of expert pathologists. Pathologists often identify regions in whole slide images with diagnostic relevance rather than examining the entire slide, with a positive correlation between the time spent on these critical image regions and diagnostic accuracy. In this paper, a heatmap is generated to represent pathologists' viewing patterns during diagnosis and used to guide a deep learning architecture during training. The proposed system outperforms traditional approaches based on color and texture image characteristics, integrating pathologists' domain expertise to enhance region of interest detection without needing individual case annotations. Evaluating our best model, a U-Net model with a pre-trained ResNet-18 encoder, on a skin biopsy whole slide image dataset for melanoma diagnosis, shows its potential in detecting regions of interest, surpassing conventional methods with an increase of 20%, 11%, 22%, and 12% in precision, recall, F1-score, and Intersection over Union, respectively. In a clinical evaluation, three dermatopathologists agreed on the model's effectiveness in replicating pathologists' diagnostic viewing behavior and accurately identifying critical regions. Finally, our study demonstrates that incorporating heatmaps as supplementary signals can enhance the performance of computer-aided diagnosis systems. Without the availability of eye tracking data, identifying precise focus areas is challenging, but our approach shows promise in assisting pathologists in improving diagnostic accuracy and efficiency, streamlining annotation processes, and aiding the training of new pathologists.
Collapse
Affiliation(s)
- Fatemeh Ghezloo
- Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA.
| | - Oliver H Chang
- Department of Laboratory Medicine and Pathology, University of Washington, Seattle, WA, USA
| | | | | | | | - Lisa M Reisch
- Department of Biostatistics, University of Washington, Seattle, WA, USA
| | - Linda G Shapiro
- Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA
| | - Joann G Elmore
- Department of Medicine, David Geffen School of Medicine, University of California, Los AngelesLos Angeles, CA, USA
| |
Collapse
|
2
|
Khan S, Ali H, Shah Z. Identifying the role of vision transformer for skin cancer-A scoping review. Front Artif Intell 2023; 6:1202990. [PMID: 37529760 PMCID: PMC10388102 DOI: 10.3389/frai.2023.1202990] [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: 04/10/2023] [Accepted: 07/03/2023] [Indexed: 08/03/2023] Open
Abstract
Introduction Detecting and accurately diagnosing early melanocytic lesions is challenging due to extensive intra- and inter-observer variabilities. Dermoscopy images are widely used to identify and study skin cancer, but the blurred boundaries between lesions and besieging tissues can lead to incorrect identification. Artificial Intelligence (AI) models, including vision transformers, have been proposed as a solution, but variations in symptoms and underlying effects hinder their performance. Objective This scoping review synthesizes and analyzes the literature that uses vision transformers for skin lesion detection. Methods The review follows the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Revise) guidelines. The review searched online repositories such as IEEE Xplore, Scopus, Google Scholar, and PubMed to retrieve relevant articles. After screening and pre-processing, 28 studies that fulfilled the inclusion criteria were included. Results and discussions The review found that the use of vision transformers for skin cancer detection has rapidly increased from 2020 to 2022 and has shown outstanding performance for skin cancer detection using dermoscopy images. Along with highlighting intrinsic visual ambiguities, irregular skin lesion shapes, and many other unwanted challenges, the review also discusses the key problems that obfuscate the trustworthiness of vision transformers in skin cancer diagnosis. This review provides new insights for practitioners and researchers to understand the current state of knowledge in this specialized research domain and outlines the best segmentation techniques to identify accurate lesion boundaries and perform melanoma diagnosis. These findings will ultimately assist practitioners and researchers in making more authentic decisions promptly.
Collapse
|
3
|
Doeleman T, Hondelink LM, Vermeer MH, van Dijk MR, Schrader AMR. Artificial intelligence in digital pathology of cutaneous lymphomas: a review of the current state and future perspectives. Semin Cancer Biol 2023:S1044-579X(23)00095-0. [PMID: 37331571 DOI: 10.1016/j.semcancer.2023.06.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2022] [Revised: 06/01/2023] [Accepted: 06/12/2023] [Indexed: 06/20/2023]
Abstract
Primary cutaneous lymphomas (CLs) represent a heterogeneous group of T-cell lymphomas and B-cell lymphomas that present in the skin without evidence of extracutaneous involvement at time of diagnosis. CLs are largely distinct from their systemic counterparts in clinical presentation, histopathology, and biological behavior and, therefore, require different therapeutic management. Additional diagnostic burden is added by the fact that several benign inflammatory dermatoses mimic CL subtypes, requiring clinicopathological correlation for definitive diagnosis. Due to the heterogeneity and rarity of CL, adjunct diagnostic tools are welcomed, especially by pathologists without expertise in this field or with limited access to a centralized specialist panel. The transition into digital pathology workflows enables artificial intelligence (AI)-based analysis of patients' whole-slide pathology images (WSIs). AI can be used to automate manual processes in histopathology but, more importantly, can be applied to complex diagnostic tasks, especially suitable for rare disease like CL. To date, AI-based applications for CL have been minimally explored in literature. However, in other skin cancers and systemic lymphomas, disciplines that are recognized here as the building blocks for CLs, several studies demonstrated promising results using AI for disease diagnosis and subclassification, cancer detection, specimen triaging, and outcome prediction. Additionally, AI allows discovery of novel biomarkers or may help to quantify established biomarkers. This review summarizes and blends applications of AI in pathology of skin cancer and lymphoma and proposes how these findings can be applied to diagnostics of CL.
Collapse
Affiliation(s)
- Thom Doeleman
- Department of Pathology, Leiden University Medical Centre, Leiden, the Netherlands; Department of Pathology, University Medical Center Utrecht, Utrecht, the Netherlands.
| | - Liesbeth M Hondelink
- Department of Pathology, Leiden University Medical Centre, Leiden, the Netherlands
| | - Maarten H Vermeer
- Department of Dermatology, Leiden University Medical Center, Leiden, the Netherlands
| | - Marijke R van Dijk
- Department of Pathology, University Medical Center Utrecht, Utrecht, the Netherlands
| | - Anne M R Schrader
- Department of Pathology, Leiden University Medical Centre, Leiden, the Netherlands
| |
Collapse
|
4
|
Tsuneki M. Editorial on Special Issue "Artificial Intelligence in Pathological Image Analysis". Diagnostics (Basel) 2023; 13:diagnostics13050828. [PMID: 36899972 PMCID: PMC10000562 DOI: 10.3390/diagnostics13050828] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2023] [Accepted: 02/20/2023] [Indexed: 02/25/2023] Open
Abstract
The artificial intelligence (AI), especially deep learning models, is highly compatible with medical images and natural language processing and is expected to be applied to pathological image analysis and other medical fields [...].
Collapse
Affiliation(s)
- Masayuki Tsuneki
- Medmain Research, Medmain Inc., 2-4-5-104, Akasaka, Chuo-ku, Fukuoka 810-0042, Japan
| |
Collapse
|
5
|
Nofallah S, Wu W, Liu K, Ghezloo F, Elmore JG, Shapiro LG. Automated analysis of whole slide digital skin biopsy images. Front Artif Intell 2022; 5:1005086. [PMID: 36204597 PMCID: PMC9531680 DOI: 10.3389/frai.2022.1005086] [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: 07/27/2022] [Accepted: 08/25/2022] [Indexed: 11/23/2022] Open
Abstract
A rapidly increasing rate of melanoma diagnosis has been noted over the past three decades, and nearly 1 in 4 skin biopsies are diagnosed as melanocytic lesions. The gold standard for diagnosis of melanoma is the histopathological examination by a pathologist to analyze biopsy material at both the cellular and structural levels. A pathologist's diagnosis is often subjective and prone to variability, while deep learning image analysis methods may improve and complement current diagnostic and prognostic capabilities. Mitoses are important entities when reviewing skin biopsy cases as their presence carries prognostic information; thus, their precise detection is an important factor for clinical care. In addition, semantic segmentation of clinically important structures in skin biopsies might help the diagnosis pipeline with an accurate classification. We aim to provide prognostic and diagnostic information on skin biopsy images, including the detection of cellular level entities, segmentation of clinically important tissue structures, and other important factors toward the accurate diagnosis of skin biopsy images. This paper is an overview of our work on analysis of digital whole slide skin biopsy images, including mitotic figure (mitosis) detection, semantic segmentation, diagnosis, and analysis of pathologists' viewing patterns, and with new work on melanocyte detection. Deep learning has been applied to our methods for all the detection, segmentation, and diagnosis work. In our studies, deep learning is proven superior to prior approaches to skin biopsy analysis. Our work on analysis of pathologists' viewing patterns is the only such work in the skin biopsy literature. Our work covers the whole spectrum from low-level entities through diagnosis and understanding what pathologists do in performing their diagnoses.
Collapse
Affiliation(s)
- Shima Nofallah
- Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, United States
| | - Wenjun Wu
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States
| | - Kechun Liu
- Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, United States
| | - Fatemeh Ghezloo
- Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, United States
| | - Joann G. Elmore
- David Geffen School of Medicine, University of California Los Angeles (UCLA), Los Angeles, CA, United States
| | - Linda G. Shapiro
- Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, United States
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States
- Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, United States
| |
Collapse
|