Development of an AI-Assisted Diagnostic Tool for Mycosis Fungoides and Other Cutaneous Lymphoproliferative Diseases Using Microscopic Image Analysis: A Training and Validation Study

NCT07705386 | Active Not Recruiting

• 1 other identifier: MD-152-2025
• Study Type: observational
• Target: 463
• Locations: 1 country
• Sites: 1

Brief Summary

Cutaneous lymphoproliferative diseases (CLPDs) are a group of skin disorders that range from benign conditions, such as pseudolymphomas, to malignant forms like cutaneous T-cell and B-cell lymphomas. Mycosis fungoides is the most common malignant type, but diagnosis is often difficult because many benign skin conditions can mimic lymphoma. Current diagnostic methods rely on microscopic examination of biopsies, which can be subjective and vary between pathologists. This study aims to develop and validate a deep learning model that uses digitized biopsy images and clinical data to distinguish malignant CLPDs from benign ones. By applying artificial intelligence to dermatopathology, the project seeks to improve diagnostic accuracy, reduce variability, and support clinicians in making timely treatment decisions. The novelty of this work lies in applying advanced AI methods to a rare and challenging group of skin diseases, with the potential to enhance patient care in both specialized centers and resource-limited settings.

Conditions

Cutaneous Lymphoproliferative Diseases; Mycosis Fungoides of Skin (Diagnosis); Pseudolymphoma; Primary Cutaneous B-Cell Lymphoma (CBCL); T Cell Dyscrasia; PLEVA-PLC Spectrum

Outcome Measures

Primary Outcomes (1)

• Diagnostic accuracy of AI model

  Accuracy, sensitivity, specificity, and positive predictive value of the trained AI models in differentiating benign CLPDs from malignant types.

  Baseline (In retrospective diagnostic studies, the moment the AI evaluates the historical slide is considered the patients's baseline).

Secondary Outcomes (2)

• Comparison with dermatopathologists

  Baseline (In retrospective diagnostic studies, the moment the AI evaluates the historical slide is considered the patients's baseline).

• Smartphone imaging feasibility

  Baseline (In retrospective diagnostic studies, the moment the AI evaluates the historical slide is considered the patients's baseline).

Study Arms (5)

MF

Patients diagnosed histopathologically as mycosis fungoides

Diagnostic Test: AI-assisted histopathology image analysis

PLC/PLEVA

Patients diagnosed histopathologically as PLC or PLEVA

Diagnostic Test: AI-assisted histopathology image analysis

TCD

Patients diagnosed histopathologically as T cell dyscrasia

Diagnostic Test: AI-assisted histopathology image analysis

BCL

Patients diagnosed histopathologically as B cell lymphoma

Diagnostic Test: AI-assisted histopathology image analysis

Pseudolymphoma

Patients diagnosed histopathologically as pseudo lymphoma

Diagnostic Test: AI-assisted histopathology image analysis

Interventions

AI-assisted histopathology image analysis DIAGNOSTIC_TEST

Development and validation of a deep learning model using digitized hematoxylin and eosin (H\&E) stained slides and clinical data to differentiate malignant CLPDs from benign mimickers. Comparator: Standard histopathological diagnosis by experienced dermatopathologists.

BCL; MF; PLC/PLEVA; Pseudolymphoma; TCD

Eligibility Criteria

• Sex: all
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Archived slides of patients diagnosed with malignant CLPDs (e.g., mycosis fungoides, cutaneous B-cell lymphoma) and benign mimickers (e.g., pseudolymphoma, pityriasis lichenoides chronica, PLEVA) were identified from the pathology database of Kasr Al-Aini Hospitals, Cairo University. Cases were selected based on WHO-EORTC diagnostic criteria and availability of adequate quality H\&E slides plus relevant clinical data.

You may qualify if:

• Archived slides of patients with a confirmed histopathological diagnosis of malignant CLPDs (e.g., mycosis fungoides at all stages, cutaneous B-cell lymphoma, primary cutaneous anaplastic large cell lymphoma, lymphomatoid papulosis), based on WHO-EORTC criteria.
• Archived slides of patients with benign CLPDs that mimic MF clinically and histologically (e.g., pseudolymphoma, pityriasis lichenoides chronica, pityriasis lichenoides et varioliformis acuta \[PLEVA\]).
• Availability of adequate quality hematoxylin and eosin (H\&E) stained slides.
• Availability of relevant clinical data (age, sex, disease duration, distribution of lesions, drug history).

You may not qualify if:

• Slides with significant artifacts (folding, tearing, poor staining) that prevent adequate image analysis.
• Cases with insufficient clinical or pathological data for definitive diagnosis.
• Cases with secondary cutaneous CLPDs

Sponsors & Collaborators

• Cairo University: lead

Study Sites (1)

Kasr Al-Aini Hospitals, Cairo University

Cairo, Egypt

Location

Related Publications (20)

• Zama D, Borghesi A, Ranieri A, Manieri E, Pierantoni L, Andreozzi L, Dondi A, Neri I, Lanari M, Calegari R. Perspectives and Challenges of Telemedicine and Artificial Intelligence in Pediatric Dermatology. Children (Basel). 2024 Nov 19;11(11):1401. doi: 10.3390/children11111401.

  PMID: 39594976 BACKGROUND

• Valencia Ocampo OJ, Julio L, Zapata V, Correa LA, Vasco C, Correa S, Velasquez-Lopera MM. Mycosis Fungoides in Children and Adolescents: A Series of 23 Cases. Actas Dermosifiliogr (Engl Ed). 2020 Mar;111(2):149-156. doi: 10.1016/j.ad.2019.04.004. Epub 2019 Jul 2. English, Spanish.

  PMID: 31277835 BACKGROUND

• Rashad, N. M., Abdelnapi, N. Mm., Seddik, A. F., & Sayedelahl, M. A. (2025). Automating skin cancer screening: A deep learning. Journal of Engineering and Applied Science, 72(1), 6. https://doi.org/10.1186/s44147-024-00573-w

  BACKGROUND

• Floridi, L. (2019). Establishing the rules for building trustworthy AI. Nature Machine Intelligence, 1(6), 261-262. https://doi.org/10.1038/s42256-019-0055-y

  BACKGROUND

• Foss FM, Girardi M. Mycosis Fungoides and Sezary Syndrome. Hematol Oncol Clin North Am. 2017 Apr;31(2):297-315. doi: 10.1016/j.hoc.2016.11.008.

  PMID: 28340880 BACKGROUND

• Gomolin A, Netchiporouk E, Gniadecki R, Litvinov IV. Artificial Intelligence Applications in Dermatology: Where Do We Stand? Front Med (Lausanne). 2020 Mar 31;7:100. doi: 10.3389/fmed.2020.00100. eCollection 2020.

  PMID: 32296706 BACKGROUND

• Hodak E, Geskin L, Guenova E, Ortiz-Romero PL, Willemze R, Zheng J, Cowan R, Foss F, Mangas C, Querfeld C. Real-Life Barriers to Diagnosis of Early Mycosis Fungoides: An International Expert Panel Discussion. Am J Clin Dermatol. 2023 Jan;24(1):5-14. doi: 10.1007/s40257-022-00732-w. Epub 2022 Nov 18.

  PMID: 36399227 BACKGROUND

• Jartarkar SR. Artificial intelligence: Its role in dermatopathology. Indian J Dermatol Venereol Leprol. 2023 Jul-Aug;89(4):549-552. doi: 10.25259/IJDVL_725_2021.

  PMID: 36688886 BACKGROUND

• Kempf W, Mitteldorf C, Cerroni L, Willemze R, Berti E, Guenova E, Scarisbrick JJ, Battistella M. Classifications of cutaneous lymphomas and lymphoproliferative disorders: An update from the EORTC cutaneous lymphoma histopathology group. J Eur Acad Dermatol Venereol. 2024 Aug;38(8):1491-1503. doi: 10.1111/jdv.19987. Epub 2024 Apr 6.

  PMID: 38581201 BACKGROUND

• Kent MN, Olsen TG, Feeser TA, Tesno KC, Moad JC, Conroy MP, Kendrick MJ, Stephenson SR, Murchland MR, Khan AU, Peacock EA, Brumfiel A, Bottomley MA. Diagnostic Accuracy of Virtual Pathology vs Traditional Microscopy in a Large Dermatopathology Study. JAMA Dermatol. 2017 Dec 1;153(12):1285-1291. doi: 10.1001/jamadermatol.2017.3284.

  PMID: 29049424 BACKGROUND

• Ottevanger R, de Bruin DT, Willemze R, Jansen PM, Bekkenk MW, de Haas ERM, Horvath B, van Rossum MM, Sanders CJG, Veraart JCJM, Vermeer MH, Quint KD. Incidence of mycosis fungoides and Sezary syndrome in the Netherlands between 2000 and 2020. Br J Dermatol. 2021 Aug;185(2):434-435. doi: 10.1111/bjd.20048. Epub 2021 May 4. No abstract available.

  PMID: 33690948 BACKGROUND

• Polesie S, McKee PH, Gardner JM, Gillstedt M, Siarov J, Neittaanmaki N, Paoli J. Attitudes Toward Artificial Intelligence Within Dermatopathology: An International Online Survey. Front Med (Lausanne). 2020 Oct 20;7:591952. doi: 10.3389/fmed.2020.591952. eCollection 2020.

  PMID: 33195357 BACKGROUND

• Tsianakas A, Kienast AK, Hoeger PH. Infantile-onset cutaneous T-cell lymphoma. Br J Dermatol. 2008 Dec;159(6):1338-41. doi: 10.1111/j.1365-2133.2008.08794.x. Epub 2008 Aug 19.

  PMID: 18717674 BACKGROUND

• Willemze R. Cutaneous lymphoproliferative disorders: Back to the future. J Cutan Pathol. 2024 Jun;51(6):468-476. doi: 10.1111/cup.14609. Epub 2024 Mar 18.

  PMID: 38499969 BACKGROUND

• Fatima S, Siddiqui S, Tariq MU, Ishtiaque H, Idrees R, Ahmed Z, Ahmed A. Mycosis Fungoides: A Clinicopathological Study of 60 Cases from a Tertiary Care Center. Indian J Dermatol. 2020 Mar-Apr;65(2):123-129. doi: 10.4103/ijd.IJD_602_18.

  PMID: 32180598 BACKGROUND

• Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, Cui C, Corrado G, Thrun S, Dean J. A guide to deep learning in healthcare. Nat Med. 2019 Jan;25(1):24-29. doi: 10.1038/s41591-018-0316-z. Epub 2019 Jan 7.

  PMID: 30617335 BACKGROUND

• 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 Sep;94:81-88. doi: 10.1016/j.semcancer.2023.06.004. Epub 2023 Jun 17.

  PMID: 37331571 BACKGROUND

• Chan S, Reddy V, Myers B, Thibodeaux Q, Brownstone N, Liao W. Machine Learning in Dermatology: Current Applications, Opportunities, and Limitations. Dermatol Ther (Heidelb). 2020 Jun;10(3):365-386. doi: 10.1007/s13555-020-00372-0. Epub 2020 Apr 6.

  PMID: 32253623 BACKGROUND

• Cazzato G, Rongioletti F. Artificial intelligence in dermatopathology: Updates, strengths, and challenges. Clin Dermatol. 2024 Sep-Oct;42(5):437-442. doi: 10.1016/j.clindermatol.2024.06.010. Epub 2024 Jun 21.

  PMID: 38909860 BACKGROUND

• Amorim GM, Quintella DC, Niemeyer-Corbellini JP, Ferreira LC, Ramos-E-Silva M, Cuzzi T. Validation of an algorithm based on clinical, histopathological and immunohistochemical data for the diagnosis of early-stage mycosis fungoides. An Bras Dermatol. 2020 May-Jun;95(3):326-331. doi: 10.1016/j.abd.2020.01.002. Epub 2020 Mar 20.

  PMID: 32317132 BACKGROUND

MeSH Terms

Conditions

Disease; Pseudolymphoma

Condition Hierarchy (Ancestors)

Pathologic Processes; Pathological Conditions, Signs and Symptoms; Lymphatic Diseases; Hemic and Lymphatic Diseases

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Assistant lecturer of Dermatology & Dermatopathology, Cairo university

Study Record Dates

• First Submitted: June 30, 2026
• First Posted: July 15, 2026
• Study Start: January 1, 2026
• Primary Completion (Estimated): November 30, 2026
• Study Completion (Estimated): December 30, 2026
• Last Updated: July 15, 2026

Record last verified: 2026-01

Locations

EG (1)