1
|
Mirza FN, Haq Z, Abdi P, Diaz MJ, Libby TJ. Artificial Intelligence for Mohs and Dermatologic Surgery: A Systematic Review and Meta-Analysis. Dermatol Surg 2024; 50:799-806. [PMID: 38991503 DOI: 10.1097/dss.0000000000004297] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/13/2024]
Abstract
BACKGROUND Over the past decade, several studies have shown that potential of artificial intelligence (AI) in dermatology. However, there has yet to be a systematic review evaluating the usage of AI specifically within the field of Mohs micrographic surgery (MMS). OBJECTIVE In this review, we aimed to comprehensively evaluate the current state, efficacy, and future implications of AI when applied to MMS for the treatment of nonmelanoma skin cancers (NMSC). MATERIALS AND METHODS A systematic review and meta-analysis was conducted following PRISMA guidelines across several databases, including PubMed/MEDLINE, Embase, and Cochrane libraries. A predefined protocol was registered in PROSPERO, with literature search involving specific keywords related to AI and Mohs surgery for NMSC. RESULTS From 23 studies evaluated, our results find that AI shows promise as a prediction tool for precisely identifying NMSC in tissue sections during MMS. Furthermore, high AUC and concordance values were also found across the various usages of AI in MMS, including margin control, surgical recommendations, similarity metrics, and in the prediction of stage and construction complexity. CONCLUSION The findings of this review suggest promising potential for AI to enhance the accuracy and efficiency of Mohs surgery, particularly for NMSC.
Collapse
Affiliation(s)
- Fatima N Mirza
- Department of Dermatology, Warren Alpert Medical School, Brown University, Providence, Rhode Island
| | - Zaim Haq
- Warren Alpert Medical School, Brown University, Providence, Rhode Island
| | - Parsa Abdi
- Memorial University of Newfoundland, Faculty of Medicine, St. Johns, Newfoundland & Labrador, Canada ; and
| | - Michael J Diaz
- University of Florida, College of Medicine, Gainesville, Florida
| | - Tiffany J Libby
- Department of Dermatology, Warren Alpert Medical School, Brown University, Providence, Rhode Island
| |
Collapse
|
2
|
Siarov J, Kumar D, Paoli J, Mölne J, Gillstedt M, Noora N. Utilizing deep learning model for assessing melanocytic density in resection margins of lentigo maligna. Diagn Pathol 2024; 19:106. [PMID: 39097745 PMCID: PMC11297622 DOI: 10.1186/s13000-024-01532-y] [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: 07/05/2024] [Accepted: 07/29/2024] [Indexed: 08/05/2024] Open
Abstract
BACKGROUND Surgical excision with clear histopathological margins is the preferred treatment to prevent progression of lentigo maligna (LM) to invasive melanoma. However, the assessment of resection margins on sun-damaged skin is challenging. We developed a deep learning model for detection of melanocytes in resection margins of LM. METHODS In total, 353 whole slide images (WSIs) were included. 295 WSIs were used for training and 58 for validation and testing. The algorithm was trained with 3,973 manual pixel-wise annotations. The AI analyses were compared to those of three blinded dermatopathologists and two pathology residents, who performed their evaluations without AI and AI-assisted. Immunohistochemistry (SOX10) served as the reference standard. We used a dichotomized cutoff for low and high risk of recurrence (≤ 25 melanocytes in an area of 0.5 mm for low risk and > 25 for high risk). RESULTS The AI model achieved an area under the receiver operating characteristic curve (AUC) of 0.84 in discriminating margins with low and high recurrence risk. In comparison, the AUC for dermatopathologists ranged from 0.72 to 0.90 and for the residents in pathology, 0.68 to 0.80. Additionally, with aid of the AI model the performance of two pathologists significantly improved. CONCLUSIONS The deep learning showed notable accuracy in detecting resection margins of LM with a high versus low risk of recurrence. Furthermore, the use of AI improved the performance of 2/5 pathologists. This automated tool could aid pathologists in the assessment or pre-screening of LM margins.
Collapse
Affiliation(s)
- Jan Siarov
- Department of Laboratory Medicine, Institute of Biomedicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.
- Department of Clinical Pathology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden.
| | | | - John Paoli
- Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Johan Mölne
- Department of Laboratory Medicine, Institute of Biomedicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Clinical Pathology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Martin Gillstedt
- Department of Dermatology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Neittaanmäki Noora
- Department of Laboratory Medicine, Institute of Biomedicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Clinical Pathology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden
| |
Collapse
|
3
|
Murphree DH, Kim YH, Sidey KA, Comfere NI, Vidal NY. Artificial intelligence for automatic detection of basal cell carcinoma from frozen tissue tangential biopsies. Clin Exp Dermatol 2024; 49:719-721. [PMID: 37317975 DOI: 10.1093/ced/llad209] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2022] [Revised: 05/20/2023] [Accepted: 06/12/2023] [Indexed: 06/16/2023]
Abstract
Evaluation of basal cell carcinoma (BCC) involves tangential biopsies of a suspicious lesion that is sent for frozen sections and evaluated by a Mohs micrographic surgeon. Advances in artificial intelligence (AI) have made possible the development of sophisticated clinical decision support systems to provide real-time feedback to clinicians that could have a role in optimizing the diagnostic workup of BCC. There were 287 annotated whole-slide images of frozen sections from tangential biopsies, of which 121 contained BCC, that were used to train and test an AI pipeline to recognize BCC. Regions of interest were annotated by a senior dermatology resident, an experienced dermatopathologist and an experienced Mohs surgeon, with concordance of annotations noted on final review. Final performance metrics included a sensitivity and specificity of 0.73 and 0.88, respectively. Our results on a relatively small dataset suggest the feasibility of developing an AI system to aid in the workup and management of BCC.
Collapse
Affiliation(s)
- Dennis H Murphree
- Department of Dermatology
- Department of Artificial Intelligence and Informatics
- Mayo Clinical Dermatology Digital Health
| | | | - Kirk A Sidey
- Department of Dermatology, University of Iowa Hospitals and Clinics, Iowa City, IA, USA
| | - Nneka I Comfere
- Department of Dermatology
- Mayo Clinical Dermatology Digital Health
- Department of Laboratory Medicine & Pathology
| | - Nahid Y Vidal
- Department of Dermatology
- Mayo Clinical Dermatology Digital Health
- Division of Dermatologic Surgery, Mayo Clinic, Rochester, MN, USA
| |
Collapse
|
4
|
Trager MH, Gordon ER, Breneman A, Weng C, Samie FH. Artificial intelligence for nonmelanoma skin cancer. Clin Dermatol 2024:S0738-081X(24)00100-7. [PMID: 38925444 DOI: 10.1016/j.clindermatol.2024.06.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/28/2024]
Abstract
Nonmelanoma skin cancers (NMSCs) are among the top five most common cancers globally. NMSC is an area with great potential for novel application of diagnostic tools including artificial intelligence (AI). In this scoping review, we aimed to describe the applications of AI in the diagnosis and treatment of NMSC. Twenty-nine publications described AI applications to dermatopathology including lesion classification and margin assessment. Twenty-five publications discussed AI use in clinical image analysis, showing that algorithms are not superior to dermatologists and may rely on unbalanced, nonrepresentative, and nontransparent training data sets. Sixteen publications described the use of AI in cutaneous surgery for NMSC including use in margin assessment during excisions and Mohs surgery, as well as predicting procedural complexity. Eleven publications discussed spectroscopy, confocal microscopy, thermography, and the AI algorithms that analyze and interpret their data. Ten publications pertained to AI applications for the discovery and use of NMSC biomarkers. Eight publications discussed the use of smartphones and AI, specifically how they enable clinicians and patients to have increased access to instant dermatologic assessments but with varying accuracies. Five publications discussed large language models and NMSC, including how they may facilitate or hinder patient education and medical decision-making. Three publications pertaining to the skin of color and AI for NMSC discussed concerns regarding limited diverse data sets for the training of convolutional neural networks. AI demonstrates tremendous potential to improve diagnosis, patient and clinician education, and management of NMSC. Despite excitement regarding AI, data sets are often not transparently reported, may include low-quality images, and may not include diverse skin types, limiting generalizability. AI may serve as a tool to increase access to dermatology services for patients in rural areas and save health care dollars. These benefits can only be achieved, however, with consideration of potential ethical costs.
Collapse
Affiliation(s)
- Megan H Trager
- Department of Dermatology, Columbia University Irving Medical Center, New York, NY, USA
| | - Emily R Gordon
- Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA
| | - Alyssa Breneman
- Department of Dermatology, Columbia University Irving Medical Center, New York, NY, USA
| | - Chunhua Weng
- Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA
| | - Faramarz H Samie
- Department of Dermatology, Columbia University Irving Medical Center, New York, NY, USA.
| |
Collapse
|
5
|
Wei ML, Tada M, So A, Torres R. Artificial intelligence and skin cancer. Front Med (Lausanne) 2024; 11:1331895. [PMID: 38566925 PMCID: PMC10985205 DOI: 10.3389/fmed.2024.1331895] [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: 11/01/2023] [Accepted: 02/26/2024] [Indexed: 04/04/2024] Open
Abstract
Artificial intelligence is poised to rapidly reshape many fields, including that of skin cancer screening and diagnosis, both as a disruptive and assistive technology. Together with the collection and availability of large medical data sets, artificial intelligence will become a powerful tool that can be leveraged by physicians in their diagnoses and treatment plans for patients. This comprehensive review focuses on current progress toward AI applications for patients, primary care providers, dermatologists, and dermatopathologists, explores the diverse applications of image and molecular processing for skin cancer, and highlights AI's potential for patient self-screening and improving diagnostic accuracy for non-dermatologists. We additionally delve into the challenges and barriers to clinical implementation, paths forward for implementation and areas of active research.
Collapse
Affiliation(s)
- Maria L. Wei
- Department of Dermatology, University of California, San Francisco, San Francisco, CA, United States
- Dermatology Service, San Francisco VA Health Care System, San Francisco, CA, United States
| | - Mikio Tada
- Institute for Neurodegenerative Diseases, University of California, San Francisco, San Francisco, CA, United States
| | - Alexandra So
- School of Medicine, University of California, San Francisco, San Francisco, CA, United States
| | - Rodrigo Torres
- Dermatology Service, San Francisco VA Health Care System, San Francisco, CA, United States
| |
Collapse
|
6
|
Levy JJ, Davis MJ, Chacko RS, Davis MJ, Fu LJ, Goel T, Pamal A, Nafi I, Angirekula A, Suvarna A, Vempati R, Christensen BC, Hayden MS, Vaickus LJ, LeBoeuf MR. Intraoperative margin assessment for basal cell carcinoma with deep learning and histologic tumor mapping to surgical site. NPJ Precis Oncol 2024; 8:2. [PMID: 38172524 PMCID: PMC10764333 DOI: 10.1038/s41698-023-00477-7] [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: 09/12/2022] [Accepted: 11/14/2023] [Indexed: 01/05/2024] Open
Abstract
Successful treatment of solid cancers relies on complete surgical excision of the tumor either for definitive treatment or before adjuvant therapy. Intraoperative and postoperative radial sectioning, the most common form of margin assessment, can lead to incomplete excision and increase the risk of recurrence and repeat procedures. Mohs Micrographic Surgery is associated with complete removal of basal cell and squamous cell carcinoma through real-time margin assessment of 100% of the peripheral and deep margins. Real-time assessment in many tumor types is constrained by tissue size, complexity, and specimen processing / assessment time during general anesthesia. We developed an artificial intelligence platform to reduce the tissue preprocessing and histological assessment time through automated grossing recommendations, mapping and orientation of tumor to the surgical specimen. Using basal cell carcinoma as a model system, results demonstrate that this approach can address surgical laboratory efficiency bottlenecks for rapid and complete intraoperative margin assessment.
Collapse
Affiliation(s)
- Joshua J Levy
- Department of Pathology and Laboratory Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, 90048, USA.
- Department of Computational Biomedicine, Cedars-Sinai Medical Center, Los Angeles, CA, 90048, USA.
- Department of Dermatology, Geisel School of Medicine at Dartmouth, Hanover, NH, 03756, USA.
- Emerging Diagnostic and Investigative Technologies, Clinical Genomics and Advanced Technologies, Department of Pathology and Laboratory Medicine, Dartmouth Hitchcock Medical Center, Lebanon, NH, 03756, USA.
- Department of Epidemiology, Geisel School of Medicine at Dartmouth, Hanover, NH, 03756, USA.
- Program in Quantitative Biomedical Sciences, Geisel School of Medicine at Dartmouth, Hanover, NH, 03756, USA.
| | - Matthew J Davis
- Department of Dermatology, Geisel School of Medicine at Dartmouth, Hanover, NH, 03756, USA
| | | | - Michael J Davis
- Department of Dermatology, Geisel School of Medicine at Dartmouth, Hanover, NH, 03756, USA
| | - Lucy J Fu
- Geisel School of Medicine at Dartmouth, Hanover, NH, 03755, USA
| | - Tarushii Goel
- Thomas Jefferson High School for Science and Technology, Alexandria, VA, 22312, USA
- Massachusetts Institute of Technology, Cambridge, MA, 02139, USA
| | - Akash Pamal
- Thomas Jefferson High School for Science and Technology, Alexandria, VA, 22312, USA
- University of Virginia, Charlottesville, VA, 22903, USA
| | - Irfan Nafi
- Thomas Jefferson High School for Science and Technology, Alexandria, VA, 22312, USA
- Stanford University, Palo Alto, CA, 94305, USA
| | - Abhinav Angirekula
- Thomas Jefferson High School for Science and Technology, Alexandria, VA, 22312, USA
- University of Illinois Urbana-Champaign, Champaign, IL, 61820, USA
| | - Anish Suvarna
- Thomas Jefferson High School for Science and Technology, Alexandria, VA, 22312, USA
| | - Ram Vempati
- Thomas Jefferson High School for Science and Technology, Alexandria, VA, 22312, USA
| | - Brock C Christensen
- Department of Dermatology, Geisel School of Medicine at Dartmouth, Hanover, NH, 03756, USA
- Department of Molecular and Systems Biology, Geisel School of Medicine at Dartmouth, Hanover, NH, 03756, USA
- Department of Community and Family Medicine, Geisel School of Medicine at Dartmouth, Hanover, NH, 03756, USA
| | - Matthew S Hayden
- Department of Dermatology, Geisel School of Medicine at Dartmouth, Hanover, NH, 03756, USA
| | - Louis J Vaickus
- Emerging Diagnostic and Investigative Technologies, Clinical Genomics and Advanced Technologies, Department of Pathology and Laboratory Medicine, Dartmouth Hitchcock Medical Center, Lebanon, NH, 03756, USA
| | - Matthew R LeBoeuf
- Department of Dermatology, Geisel School of Medicine at Dartmouth, Hanover, NH, 03756, USA
| |
Collapse
|
7
|
Duschner N, Baguer DO, Schmidt M, Griewank KG, Hadaschik E, Hetzer S, Wiepjes B, Le'Clerc Arrastia J, Jansen P, Maass P, Schaller J. Applying an artificial intelligence deep learning approach to routine dermatopathological diagnosis of basal cell carcinoma. J Dtsch Dermatol Ges 2023; 21:1329-1337. [PMID: 37814387 DOI: 10.1111/ddg.15180] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2023] [Accepted: 06/15/2023] [Indexed: 10/11/2023]
Abstract
BACKGROUND Institutes of dermatopathology are faced with considerable challenges including a continuously rising numbers of submitted specimens and a shortage of specialized health care practitioners. Basal cell carcinoma (BCC) is one of the most common tumors in the fair-skinned western population and represents a major part of samples submitted for histological evaluation. Digitalizing glass slides has enabled the application of artificial intelligence (AI)-based procedures. To date, these methods have found only limited application in routine diagnostics. The aim of this study was to establish an AI-based model for automated BCC detection. PATIENTS AND METHODS In three dermatopathological centers, daily routine practice BCC cases were digitalized. The diagnosis was made both conventionally by analog microscope and digitally through an AI-supported algorithm based on a U-Net architecture neural network. RESULTS In routine practice, the model achieved a sensitivity of 98.23% (center 1) and a specificity of 98.51%. The model generalized successfully without additional training to samples from the other centers, achieving similarly high accuracies in BCC detection (sensitivities of 97.67% and 98.57% and specificities of 96.77% and 98.73% in centers 2 and 3, respectively). In addition, automated AI-based basal cell carcinoma subtyping and tumor thickness measurement were established. CONCLUSIONS AI-based methods can detect BCC with high accuracy in a routine clinical setting and significantly support dermatopathological work.
Collapse
Affiliation(s)
| | - Daniel Otero Baguer
- Center for Technical Mathematics (ZeTeM), University of Bremen, Bremen, Germany
| | - Maximilian Schmidt
- Center for Technical Mathematics (ZeTeM), University of Bremen, Bremen, Germany
| | - Klaus Georg Griewank
- Dermatopathologie bei Mainz, Nieder-Olm, Germany
- Department of Dermatology, University Hospital Essen, Essen, Germany
| | - Eva Hadaschik
- MVZ Dermatopathology Duisburg Essen, Essen, Germany
- Department of Dermatology, University Hospital Essen, Essen, Germany
| | - Sonja Hetzer
- MVZ Dermatopathology Duisburg Essen, Essen, Germany
| | | | | | - Philipp Jansen
- Department of Dermatology and Allergology, University Hospital Bonn, Bonn, Germany
| | - Peter Maass
- Center for Technical Mathematics (ZeTeM), University of Bremen, Bremen, Germany
| | | |
Collapse
|
8
|
Duschner N, Baguer DO, Schmidt M, Griewank KG, Hadaschik E, Hetzer S, Wiepjes B, Le'Clerc Arrastia J, Jansen P, Maass P, Schaller J. Einsatz künstlicher Intelligenz mittels Deep Learning in der dermatopathologischen Routinediagnostik des Basalzellkarzinoms: Applying an artificial intelligence deep learning approach to routine dermatopathological diagnosis of basal cell carcinoma. J Dtsch Dermatol Ges 2023; 21:1329-1338. [PMID: 37946648 DOI: 10.1111/ddg.15180_g] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2023] [Accepted: 06/15/2023] [Indexed: 11/12/2023]
Abstract
ZusammenfassungHintergrundDermatopathologische Institute stehen aufgrund immer höherer Anforderungen bei andererseits schwindenden Ressourcen vor zunehmenden Herausforderungen. Basalzellkarzinome stellen einen Großteil des Einsendeguts mit entsprechendem Arbeitsaufwand dar. Gleichzeitig ermöglicht die Digitalisierung von Glasobjektträgern den Einsatz künstlicher Intelligenz (KI)‐basierter Verfahren in der Dermatopathologie. Bislang haben diese Verfahren keinen Einzug in die Routinediagnostik gefunden. Ziel dieser Studie war daher, den Einsatz eines KI‐basierten Modells zur automatisierten Basalzellkarzinom‐Erkennung zu etablieren.Patienten und MethodikIn drei dermatopathologischen Zentren wurden während des täglichen Routinebetriebs Basalzellkarzinom‐Fälle digitalisiert und sowohl klassisch am Mikroskop als auch mittels KI‐basierter Methodik basierend auf neuronalen Netzen mit U‐Net‐Architektur befundet.ErgebnisseIm Routinebetrieb erzielte das Modell eine Sensitivität von 98,23 % und eine Spezifität von 98,51 % (Zentrum 1). Das Modell konnte übergangslos in den anderen Zentren Einsatz finden und erreichte ähnlich hohe Genauigkeiten in der Basalzellkarzinom‐Erkennung (Sensitivität von 97,67 % beziehungsweise 98,57 %, Spezifität von 96,77 % beziehungsweise 98,73 %). Zusätzlich wurden eine automatisierte, KI‐basierte Basalzellkarzinom‐Subtypisierung und Tumordickenmessung etabliert.SchlussfolgerungenKI‐basierte Verfahren können mit einer hohen Genauigkeit im Routinebetrieb Basalzellkarzinome erkennen und signifikant die dermatopathologische Arbeit unterstützen.
Collapse
Affiliation(s)
| | | | | | - Klaus Georg Griewank
- Dermatopathologie bei Mainz, Nieder-Olm
- Klinik für Dermatologie, Universitätsklinikum Essen
| | - Eva Hadaschik
- MVZ Dermatopathologie Duisburg Essen GmbH, Essen
- Klinik für Dermatologie, Universitätsklinikum Essen
| | - Sonja Hetzer
- MVZ Dermatopathologie Duisburg Essen GmbH, Essen
| | | | | | - Philipp Jansen
- Klinik und Poliklinik für Dermatologie und Allergologie, Universitätsklinikum Bonn
| | - Peter Maass
- Zentrum für Technomathematik (ZeTeM), Universität Bremen
| | | |
Collapse
|
9
|
Omiye JA, Gui H, Daneshjou R, Cai ZR, Muralidharan V. Principles, applications, and future of artificial intelligence in dermatology. Front Med (Lausanne) 2023; 10:1278232. [PMID: 37901399 PMCID: PMC10602645 DOI: 10.3389/fmed.2023.1278232] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2023] [Accepted: 09/27/2023] [Indexed: 10/31/2023] Open
Abstract
This paper provides an overview of artificial-intelligence (AI), as applied to dermatology. We focus our discussion on methodology, AI applications for various skin diseases, limitations, and future opportunities. We review how the current image-based models are being implemented in dermatology across disease subsets, and highlight the challenges facing widespread adoption. Additionally, we discuss how the future of AI in dermatology might evolve and the emerging paradigm of large language, and multi-modal models to emphasize the importance of developing responsible, fair, and equitable models in dermatology.
Collapse
Affiliation(s)
| | - Haiwen Gui
- Department of Dermatology, Stanford University, Stanford, CA, United States
| | - Roxana Daneshjou
- Department of Dermatology, Stanford University, Stanford, CA, United States
- Department of Biomedical Data Science, Stanford University, Stanford, CA, United States
| | - Zhuo Ran Cai
- Department of Dermatology, Stanford University, Stanford, CA, United States
| | | |
Collapse
|
10
|
Gorman BG, Lifson MA, Vidal NY. Artificial intelligence and frozen section histopathology: A systematic review. J Cutan Pathol 2023; 50:852-859. [PMID: 37394789 DOI: 10.1111/cup.14481] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2022] [Revised: 05/14/2023] [Accepted: 05/29/2023] [Indexed: 07/04/2023]
Abstract
Frozen sections are a useful pathologic tool, but variable image quality may impede the use of artificial intelligence and machine learning in their interpretation. We aimed to identify the current research on machine learning models trained or tested on frozen section images. We searched PubMed and Web of Science for articles presenting new machine learning models published in any year. Eighteen papers met all inclusion criteria. All papers presented at least one novel model trained or tested on frozen section images. Overall, convolutional neural networks tended to have the best performance. When physicians were able to view the output of the model, they tended to perform better than either the model or physicians alone at the tested task. Models trained on frozen sections performed well when tested on other slide preparations, but models trained on only formalin-fixed tissue performed significantly worse across other modalities. This suggests not only that machine learning can be applied to frozen section image processing, but also use of frozen section images may increase model generalizability. Additionally, expert physicians working in concert with artificial intelligence may be the future of frozen section histopathology.
Collapse
Affiliation(s)
- Benjamin G Gorman
- Mayo Clinic Alix School of Medicine, Rochester, Minnesota, USA
- Mayo Clinic Graduate School of Biomedical Sciences, Rochester, Minnesota, USA
| | - Mark A Lifson
- Center for Digital Health, Mayo Clinic, Rochester, Minnesota, USA
| | - Nahid Y Vidal
- Department of Dermatology, Mayo Clinic, Rochester, Minnesota, USA
- Division of Dermatologic Surgery, Mayo Clinic, Rochester, Minnesota, USA
| |
Collapse
|
11
|
Esmaeili S, Faraji N, Bahrami S, Shaddeli S, Ahmadi A, Mostafaei B. Deep excision surgery of face due to cruel invasion of basal cell carcinoma: A case report study. Int J Surg Case Rep 2023; 109:108551. [PMID: 37487354 PMCID: PMC10374954 DOI: 10.1016/j.ijscr.2023.108551] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2023] [Revised: 07/14/2023] [Accepted: 07/16/2023] [Indexed: 07/26/2023] Open
Abstract
INTRODUCTION AND IMPORTANCE The predominant variant of skin cancer is Basal cell carcinoma (BCC), constituting about 80 % of all non-melanoma skin cancers on a global scale. Typically, it manifests on skin surfaces that are frequently exposed to sunlight, such as the neck, face, and ears. CASE PRESENTATION A 65-year-old man presented to a specialized cancer hospital with a large pigmented lesion on the left cheek that had gradually increased in size for about a year. The tumor had become raised and ulcerated, which necessitated deep surgery on his face due to extensive invasion of BCC was done. CLINICAL DISCUSSION Basal cell carcinoma is a slow-growing, locally invasive cancerous tumor of the basal cells of the skin, which line the deepest layer of the epidermis. BCC often occurs on areas of the body that are exposed to the sun. It develops in response to cumulative UV irradiation and sporadic UV irradiation, as occurs with sunburns. CONCLUSION BCC is a common and potentially devastating skin cancer that primarily affects fair-skinned people over the age of 50. Lesions on the face can be particularly challenging. Early detection and treatment is critical to minimize the need for extensive excision and reconstruction.
Collapse
Affiliation(s)
- Sogand Esmaeili
- Department of Laboratory Sciences, School of Paramedical, Urmia University of Medical Sciences, Nursing and Midwifery Faculty, Campus Nazlu, 11 KM Road Seru, Urmia, West Azerbaijan 575611-5111, Iran
| | - Navid Faraji
- Department of Medical-Surgical Nursing, School of Nursing and Midwifery, Urmia University of Medical Sciences, Nursing and Midwifery Faculty, Campus Nazlu, 11 KM Road Seru, Urmia, West Azerbaijan 575611-5111, Iran
| | - Soheyla Bahrami
- Department of Nursing, School of Nursing and Midwifery Bonab, Nursing and Midwifery Faculty, Velayat Highway, Bonab, West Azerbaijan 5551785176, Iran
| | - Sevda Shaddeli
- School of Medicine, Urmia University of Medical Sciences, Medicine Faculty, Campus Nazlu, 11 KM Road Seru, Urmia, West Azerbaijan 575611-5111, Iran
| | - Abdolhadi Ahmadi
- Department of Nursing, School of Nursing and Midwifery, Urmia University of Medical Sciences, Nursing and Midwifery Faculty, Campus Nazlu, 11 KM Road Seru, Urmia, West Azerbaijan 575611-5111, Iran
| | - Behnam Mostafaei
- Department of Nursing, School of Nursing and Midwifery, Urmia University of Medical Sciences, Nursing and Midwifery Faculty, Campus Nazlu, 11 KM Road Seru, Urmia, West Azerbaijan 575611-5111, Iran.
| |
Collapse
|
12
|
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
|
13
|
Bonnefille H, Abbas M, Roger P, Habib F, Masset F, Chaumont M, Subsol G, Stoebner PE. A deep-learning algorithm to localize basal cell carcinoma foci on Mohs surgery frozen sections. J Eur Acad Dermatol Venereol 2023; 37:e631-e632. [PMID: 36645807 DOI: 10.1111/jdv.18859] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2022] [Accepted: 01/05/2023] [Indexed: 01/17/2023]
Affiliation(s)
- Hugo Bonnefille
- Department of Dermatology, CHU Carémeau, Montpellier University, Nîmes, France
| | - Marwan Abbas
- LIRMM, Montpellier University, CNRS, Montpellier, France
| | - Pascal Roger
- Department of Pathology, CHU Carémeau, Montpellier University, Nîmes, France
| | - François Habib
- Department of Dermatology, CHU Carémeau, Montpellier University, Nîmes, France
| | - Farzaneh Masset
- Department of Pathology, CHU Carémeau, Montpellier University, Nîmes, France
| | - Marc Chaumont
- LIRMM, Montpellier University, CNRS, Montpellier, France.,Université de Nîmes, Nîmes, France
| | - Gerard Subsol
- LIRMM, Montpellier University, CNRS, Montpellier, France
| | - Pierre E Stoebner
- Department of Dermatology, CHU Carémeau, Montpellier University, Nîmes, France.,IRCM, INSERM U1194, Montpellier, France
| |
Collapse
|
14
|
Șerbănescu MS, Bungărdean RM, Georgiu C, Crișan M. Nodular and Micronodular Basal Cell Carcinoma Subtypes Are Different Tumors Based on Their Morphological Architecture and Their Interaction with the Surrounding Stroma. Diagnostics (Basel) 2022; 12:diagnostics12071636. [PMID: 35885545 PMCID: PMC9323345 DOI: 10.3390/diagnostics12071636] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Revised: 06/29/2022] [Accepted: 07/02/2022] [Indexed: 11/16/2022] Open
Abstract
Basal cell carcinoma (BCC) is the most frequent cancer of the skin and comprises low-risk and high-risk subtypes. We selected a low-risk subtype, namely, nodular (N), and a high-risk subtype, namely, micronodular (MN), with the aim to identify differences between them using a classical morphometric approach through a gray-level co-occurrence matrix and histogram analysis, as well as an approach based on deep learning semantic segmentation. From whole-slide images, pathologists selected 216 N and 201 MN BCC images. The two groups were then manually segmented and compared based on four morphological areas: center of the BCC islands (tumor, T), peripheral palisading of the BCC islands (touching tumor, TT), peritumoral cleft (PC) and surrounding stroma (S). We found that the TT pattern varied the least, while the PC pattern varied the most between the two subtypes. The combination of two distinct analysis approaches yielded fresh insights into the characterization of BCC, and thus, we were able to describe two different morphological patterns for the T component of the two subtypes.
Collapse
Affiliation(s)
- Mircea-Sebastian Șerbănescu
- Department of Medical Informatics and Biostatistics, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania;
| | - Raluca Maria Bungărdean
- Department of Pathology, Iuliu Haţieganu University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania;
- Correspondence:
| | - Carmen Georgiu
- Department of Pathology, Iuliu Haţieganu University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania;
| | - Maria Crișan
- Department of Histology, Iuliu Haţieganu University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania;
| |
Collapse
|
15
|
Ruini C, Schlingmann S, Jonke Ž, Avci P, Padrón-Laso V, Neumeier F, Koveshazi I, Ikeliani IU, Patzer K, Kunrad E, Kendziora B, Sattler E, French LE, Hartmann D. Machine Learning Based Prediction of Squamous Cell Carcinoma in Ex Vivo Confocal Laser Scanning Microscopy. Cancers (Basel) 2021; 13:cancers13215522. [PMID: 34771684 PMCID: PMC8583634 DOI: 10.3390/cancers13215522] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2021] [Revised: 10/22/2021] [Accepted: 10/29/2021] [Indexed: 01/02/2023] Open
Abstract
Image classification with convolutional neural networks (CNN) offers an unprecedented opportunity to medical imaging. Regulatory agencies in the USA and Europe have already cleared numerous deep learning/machine learning based medical devices and algorithms. While the field of radiology is on the forefront of artificial intelligence (AI) revolution, conventional pathology, which commonly relies on examination of tissue samples on a glass slide, is falling behind in leveraging this technology. On the other hand, ex vivo confocal laser scanning microscopy (ex vivo CLSM), owing to its digital workflow features, has a high potential to benefit from integrating AI tools into the assessment and decision-making process. Aim of this work was to explore a preliminary application of CNN in digitally stained ex vivo CLSM images of cutaneous squamous cell carcinoma (cSCC) for automated detection of tumor tissue. Thirty-four freshly excised tissue samples were prospectively collected and examined immediately after resection. After the histologically confirmed ex vivo CLSM diagnosis, the tumor tissue was annotated for segmentation by experts, in order to train the MobileNet CNN. The model was then trained and evaluated using cross validation. The overall sensitivity and specificity of the deep neural network for detecting cSCC and tumor free areas on ex vivo CLSM slides compared to expert evaluation were 0.76 and 0.91, respectively. The area under the ROC curve was equal to 0.90 and the area under the precision-recall curve was 0.85. The results demonstrate a high potential of deep learning models to detect cSCC regions on digitally stained ex vivo CLSM slides and to distinguish them from tumor-free skin.
Collapse
Affiliation(s)
- Cristel Ruini
- Department of Dermatology and Allergy, University Hospital, LMU Munich, 80337 Munich, Germany; (S.S.); (P.A.); (K.P.); (E.K.); (B.K.); (E.S.); (L.E.F.); (D.H.)
- PhD School in Clinical and Experimental Medicine, University of Modena and Reggio Emilia, 41125 Modena, Italy
- Correspondence:
| | - Sophia Schlingmann
- Department of Dermatology and Allergy, University Hospital, LMU Munich, 80337 Munich, Germany; (S.S.); (P.A.); (K.P.); (E.K.); (B.K.); (E.S.); (L.E.F.); (D.H.)
| | - Žan Jonke
- Munich Innovation Labs GmbH, 80336 Munich, Germany; (Ž.J.); (V.P.-L.)
| | - Pinar Avci
- Department of Dermatology and Allergy, University Hospital, LMU Munich, 80337 Munich, Germany; (S.S.); (P.A.); (K.P.); (E.K.); (B.K.); (E.S.); (L.E.F.); (D.H.)
| | | | - Florian Neumeier
- M3i Industry-in-Clinic-Platform GmbH, 80336 Munich, Germany; (F.N.); (I.K.); (I.U.I.)
| | - Istvan Koveshazi
- M3i Industry-in-Clinic-Platform GmbH, 80336 Munich, Germany; (F.N.); (I.K.); (I.U.I.)
| | - Ikenna U. Ikeliani
- M3i Industry-in-Clinic-Platform GmbH, 80336 Munich, Germany; (F.N.); (I.K.); (I.U.I.)
| | - Kathrin Patzer
- Department of Dermatology and Allergy, University Hospital, LMU Munich, 80337 Munich, Germany; (S.S.); (P.A.); (K.P.); (E.K.); (B.K.); (E.S.); (L.E.F.); (D.H.)
| | - Elena Kunrad
- Department of Dermatology and Allergy, University Hospital, LMU Munich, 80337 Munich, Germany; (S.S.); (P.A.); (K.P.); (E.K.); (B.K.); (E.S.); (L.E.F.); (D.H.)
| | - Benjamin Kendziora
- Department of Dermatology and Allergy, University Hospital, LMU Munich, 80337 Munich, Germany; (S.S.); (P.A.); (K.P.); (E.K.); (B.K.); (E.S.); (L.E.F.); (D.H.)
| | - Elke Sattler
- Department of Dermatology and Allergy, University Hospital, LMU Munich, 80337 Munich, Germany; (S.S.); (P.A.); (K.P.); (E.K.); (B.K.); (E.S.); (L.E.F.); (D.H.)
| | - Lars E. French
- Department of Dermatology and Allergy, University Hospital, LMU Munich, 80337 Munich, Germany; (S.S.); (P.A.); (K.P.); (E.K.); (B.K.); (E.S.); (L.E.F.); (D.H.)
- Dr. Phillip Frost Department of Dermatology & Cutaneous Surgery, Miller School of Medicine, University of Miami, Miami, FL 33136, USA
| | - Daniela Hartmann
- Department of Dermatology and Allergy, University Hospital, LMU Munich, 80337 Munich, Germany; (S.S.); (P.A.); (K.P.); (E.K.); (B.K.); (E.S.); (L.E.F.); (D.H.)
| |
Collapse
|
16
|
Janssen BV, Theijse R, van Roessel S, de Ruiter R, Berkel A, Huiskens J, Busch OR, Wilmink JW, Kazemier G, Valkema P, Farina A, Verheij J, de Boer OJ, Besselink MG. Artificial Intelligence-Based Segmentation of Residual Tumor in Histopathology of Pancreatic Cancer after Neoadjuvant Treatment. Cancers (Basel) 2021; 13:cancers13205089. [PMID: 34680241 PMCID: PMC8533716 DOI: 10.3390/cancers13205089] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2021] [Revised: 10/07/2021] [Accepted: 10/09/2021] [Indexed: 12/31/2022] Open
Abstract
Simple Summary The use of neoadjuvant therapy (NAT) in patients with pancreatic ductal adenocarcinoma (PDAC) is increasing. Objective quantification of the histopathological response to NAT may be used to guide adjuvant treatment and compare the efficacy of neoadjuvant regimens. However, current tumor response scoring (TRS) systems suffer from interobserver variability, originating from subjective definitions, the sometimes challenging histology, and response heterogeneity throughout the tumor bed. This study investigates if artificial intelligence-based segmentation of residual tumor burden in histopathology of PDAC after NAT may offer a more objective and reproducible TRS solution. Abstract Background: Histologic examination of resected pancreatic cancer after neoadjuvant therapy (NAT) is used to assess the effect of NAT and may guide the choice for adjuvant treatment. However, evaluating residual tumor burden in pancreatic cancer is challenging given tumor response heterogeneity and challenging histomorphology. Artificial intelligence techniques may offer a more reproducible approach. Methods: From 64 patients, one H&E-stained slide of resected pancreatic cancer after NAT was digitized. Three separate classes were manually outlined in each slide (i.e., tumor, normal ducts, and remaining epithelium). Corresponding segmentation masks and patches were generated and distributed over training, validation, and test sets. Modified U-nets with varying encoders were trained, and F1 scores were obtained to express segmentation accuracy. Results: The highest mean segmentation accuracy was obtained using modified U-nets with a DenseNet161 encoder. Tumor tissue was segmented with a high mean F1 score of 0.86, while the overall multiclass average F1 score was 0.82. Conclusions: This study shows that artificial intelligence-based assessment of residual tumor burden is feasible given the promising obtained F1 scores for tumor segmentation. This model could be developed into a tool for the objective evaluation of the response to NAT and may potentially guide the choice for adjuvant treatment.
Collapse
Affiliation(s)
- Boris V. Janssen
- Department of Surgery, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (B.V.J.); (R.T.); (S.v.R.); (O.R.B.)
- Department of Pathology, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (P.V.); (A.F.); (J.V.); (O.J.d.B.)
| | - Rutger Theijse
- Department of Surgery, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (B.V.J.); (R.T.); (S.v.R.); (O.R.B.)
- Department of Pathology, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (P.V.); (A.F.); (J.V.); (O.J.d.B.)
| | - Stijn van Roessel
- Department of Surgery, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (B.V.J.); (R.T.); (S.v.R.); (O.R.B.)
| | - Rik de Ruiter
- SAS Institute Besloten Vennootschap, 1272 PC Huizen, The Netherlands; (R.d.R.); (A.B.); (J.H.)
| | - Antonie Berkel
- SAS Institute Besloten Vennootschap, 1272 PC Huizen, The Netherlands; (R.d.R.); (A.B.); (J.H.)
| | - Joost Huiskens
- SAS Institute Besloten Vennootschap, 1272 PC Huizen, The Netherlands; (R.d.R.); (A.B.); (J.H.)
| | - Olivier R. Busch
- Department of Surgery, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (B.V.J.); (R.T.); (S.v.R.); (O.R.B.)
| | - Johanna W. Wilmink
- Department of Medical Oncology, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands;
| | - Geert Kazemier
- Department of Surgery, Amsterdam UMC, Cancer Center Amsterdam, Vrije Universiteit, 1081 HV Amsterdam, The Netherlands;
| | - Pieter Valkema
- Department of Pathology, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (P.V.); (A.F.); (J.V.); (O.J.d.B.)
| | - Arantza Farina
- Department of Pathology, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (P.V.); (A.F.); (J.V.); (O.J.d.B.)
| | - Joanne Verheij
- Department of Pathology, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (P.V.); (A.F.); (J.V.); (O.J.d.B.)
| | - Onno J. de Boer
- Department of Pathology, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (P.V.); (A.F.); (J.V.); (O.J.d.B.)
| | - Marc G. Besselink
- Department of Surgery, Amsterdam UMC, Cancer Center Amsterdam, University of Amsterdam, 1081 HV Amsterdam, The Netherlands; (B.V.J.); (R.T.); (S.v.R.); (O.R.B.)
- Correspondence: ; Tel.: +31-20-444-4444
| |
Collapse
|