1
|
Lv H, Li W, Lu Z, Gao X, Zhang Q, Bao Y, Fu Y, Xiao J. SPMLD: A skin pathological image dataset for non-melanoma with detailed lesion area annotation. Comput Biol Med 2024; 179:108793. [PMID: 38955126 DOI: 10.1016/j.compbiomed.2024.108793] [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: 12/15/2023] [Revised: 06/05/2024] [Accepted: 06/18/2024] [Indexed: 07/04/2024]
Abstract
Skin tumors are the most common tumors in humans and the clinical characteristics of three common non-melanoma tumors (IDN, SK, BCC) are similar, resulting in a high misdiagnosis rate. The accurate differential diagnosis of these tumors needs to be judged based on pathological images. However, a shortage of experienced dermatological pathologists leads to bias in the diagnostic accuracy of these skin tumors in China. In this paper, we establish a skin pathological image dataset, SPMLD, for three non-melanoma to achieve automatic and accurate intelligent identification for them. Meanwhile, we propose a lesion-area-based enhanced classification network with the KLS module and an attention module. Specifically, we first collect thousands of H&E-stained tissue sections from patients with clinically and pathologically confirmed IDN, SK, and BCC from a single-center hospital. Then, we scan them to construct a pathological image dataset of these three skin tumors. Furthermore, we mark the complete lesion area of the entire pathology image to better learn the pathologist's diagnosis process. In addition, we applied the proposed network for lesion classification prediction on the SPMLD dataset. Finally, we conduct a series of experiments to demonstrate that this annotation and our network can effectively improve the classification results of various networks. The source dataset and code are available at https://github.com/efss24/SPMLD.git.
Collapse
Affiliation(s)
- Haozhen Lv
- Department of Dermatology, Beijing Hospital, National Center of Gerontology, Beijing, China; Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 101408, China
| | - Wentao Li
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 101408, China
| | - Zhengda Lu
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 101408, China
| | - Xiaoman Gao
- Department of Dermatology, Beijing Hospital, National Center of Gerontology, Beijing, China; Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China
| | - Qiuli Zhang
- Department of Dermatology, Beijing Hospital, National Center of Gerontology, Beijing, China; Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China
| | - Yingqiu Bao
- Department of Dermatology, Beijing Hospital, National Center of Gerontology, Beijing, China; Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China.
| | - Yu Fu
- Department of Dermatology, Beijing Hospital, National Center of Gerontology, Beijing, China; Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China
| | - Jun Xiao
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 101408, China
| |
Collapse
|
2
|
Russo GM, Russo A, Urraro F, Cioce F, Gallo L, Belfiore MP, Sangiovanni A, Napolitano S, Troiani T, Verolino P, Sica A, Brancaccio G, Briatico G, Nardone V, Reginelli A. Management of Non-Melanoma Skin Cancer: Radiologists Challenging and Risk Assessment. Diagnostics (Basel) 2023; 13:diagnostics13040793. [PMID: 36832281 PMCID: PMC9955870 DOI: 10.3390/diagnostics13040793] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Revised: 02/16/2023] [Accepted: 02/17/2023] [Indexed: 02/22/2023] Open
Abstract
Basal cell carcinoma, squamous cell carcinoma, and Merkel cell carcinoma are the three main types of nonmelanoma skin cancers and their rates of occurrence and mortality have been steadily rising over the past few decades. For radiologists, it is still difficult to treat patients with advanced nonmelanoma skin cancer. Nonmelanoma skin cancer patients would benefit greatly from an improved diagnostic imaging-based risk stratification and staging method that takes into account patient characteristics. The risk is especially elevated among those who previously received systemic treatment or phototherapy. Systemic treatments, including biologic therapies and methotrexate (MTX), are effective in managing immune-mediated diseases; however, they may increase susceptibility to NMSC due to immunosuppression or other factors. Risk stratification and staging tools are crucial in treatment planning and prognostic evaluation. PET/CT appears more sensitive and superior to CT and MRI for nodal and distant metastasis as well as in surveillance after surgery. The patient treatment response improved with advent and utilization of immunotherapy and different immune-specific criteria are established to standardized evaluation criteria of clinical trials but none of them have been utilized routinely with immunotherapy. The advent of immunotherapy has also arisen new critical issues for radiologists, such as atypical response pattern, pseudo-progression, as well as immune-related adverse events that require early identification to optimize and improve patient prognosis and management. It is important for radiologists to have knowledge of the radiologic features site of the tumor, clinical stage, histological subtype, and any high-risk features to assess immunotherapy treatment response and immune-related adverse events.
Collapse
Affiliation(s)
- Gaetano Maria Russo
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
- Correspondence:
| | - Anna Russo
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Fabrizio Urraro
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Fabrizio Cioce
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Luigi Gallo
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Maria Paola Belfiore
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Angelo Sangiovanni
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Stefania Napolitano
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Teresa Troiani
- Unit of Plastic Surgery, Multidisciplinary Department of Medical Surgical and Dental Specialties, University of Campania “Luigi Vanvitelli”, 80120 Naples, Italy
| | - Pasquale Verolino
- Unit of Plastic Surgery, Multidisciplinary Department of Medical Surgical and Dental Specialties, University of Campania “Luigi Vanvitelli”, 80120 Naples, Italy
| | - Antonello Sica
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Gabriella Brancaccio
- Unit of Dermatology, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Giulia Briatico
- Unit of Dermatology, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Valerio Nardone
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| | - Alfonso Reginelli
- Department of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80123 Naples, Italy
| |
Collapse
|
3
|
Mahdar I, Lembarki G, Jamil J, Safi-eddine H, Najib B, Sabiri M, Labied M, El Manjra S, Samira L, Diouri M, Essodegui F. Eccrine porocarcinoma: an extremely rare cutaneous tumor from a radiological point of view - case report and review of the literature. BJR Case Rep 2022; 8:20220044. [PMID: 36632555 PMCID: PMC9809907 DOI: 10.1259/bjrcr.20220044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2022] [Revised: 07/27/2022] [Accepted: 08/19/2022] [Indexed: 01/14/2023] Open
Abstract
Eccrine porocarcinoma is a rare type of skin neoplasm. It represents less than 0.01% of all epithelial cutaneous tumors. Early diagnosis is the only way to minimize the mortality rate, given its aggressive nature and the high rate of local recurrence and metastasis. Clinical diagnosis is challenging and the confirmation is histological. Few studies have been published about the radiological features of eccrine porocarcinoma. We report a case of a localized eccrine porocarcinoma along with ultrasound, MRI features, and a review of the literature to highlight the role of imaging in the diagnosis and treatment plan.
Collapse
Affiliation(s)
- Imane Mahdar
- Central Unit of Radiology, Ibn Rochd University Hospital, Casablanca, Morocco
| | - Ghizlane Lembarki
- Central Unit of Radiology, Ibn Rochd University Hospital, Casablanca, Morocco
| | - Jihad Jamil
- Central Unit of Radiology, Ibn Rochd University Hospital, Casablanca, Morocco
| | - Hiba Safi-eddine
- Central Unit of Radiology, Ibn Rochd University Hospital, Casablanca, Morocco
| | - Belmoudden Najib
- Plastic Surgery Center, Ibn Rochd University Hospital, Casablanca, Morocco
| | - Mouna Sabiri
- Central Unit of Radiology, Ibn Rochd University Hospital, Casablanca, Morocco
| | - Mohamed Labied
- Central Unit of Radiology, Ibn Rochd University Hospital, Casablanca, Morocco
| | - Samia El Manjra
- Central Unit of Radiology, Ibn Rochd University Hospital, Casablanca, Morocco
| | - Lezar Samira
- Central Unit of Radiology, Ibn Rochd University Hospital, Casablanca, Morocco
| | - Mounia Diouri
- Plastic Surgery Center, Ibn Rochd University Hospital, Casablanca, Morocco
| | - Fatiha Essodegui
- Central Unit of Radiology, Ibn Rochd University Hospital, Casablanca, Morocco
| |
Collapse
|
4
|
Kawaguchi M, Kato H, Noda Y, Kobayashi K, Miyazaki T, Hyodo F, Matsuo M. Imaging findings of malignant skin tumors: radiological-pathological correlation. Insights Imaging 2022; 13:52. [PMID: 35316414 PMCID: PMC8941041 DOI: 10.1186/s13244-022-01205-8] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2022] [Accepted: 03/04/2022] [Indexed: 11/11/2022] Open
Abstract
Sometimes, radiologists encounter malignant skin tumors (MSTs) during image interpretation. As MSTs require different clinical management modalities for each histological subtype, accurate preoperative diagnosis is essential. The histological subtypes of MST can be easily assessed by visual inspection or biopsy. Therefore, the significant role of radiological imaging in MSTs is to evaluate the extent of local invasion, nodal involvement, and distant metastasis, and the histological estimation of MSTs by radiological imaging has not been reported until a few years ago. However, recent studies have revealed characteristic radiological features for differential diagnosis of MSTs, such as configuration, intratumoral homogeneity, signal intensity, cyst formation, and hemorrhage. Other important clinical data for determining the histological subtype of MST include age, gender, and site of occurrence. MSTs can be categorized as epidermal, melanocytic, adnexal, and mesenchymal tumors based on the origin and have distinctive characteristics. Hence, this review article was designed to describe the clinical and radiological features of MSTs.
Collapse
Affiliation(s)
- Masaya Kawaguchi
- Department of Radiology, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan.
| | - Hiroki Kato
- Department of Radiology, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan
| | - Yoshifumi Noda
- Department of Radiology, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan
| | | | | | - Fuminori Hyodo
- Department of Radiology, Frontier Science for Imaging, Gifu University, Gifu, Japan
| | - Masayuki Matsuo
- Department of Radiology, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan
| |
Collapse
|
5
|
Abstract
PURPOSE The purpose of this study was to evaluate magnetic resonance (MR) imaging findings of poroma and porocarcinoma. METHODS Six patients (3 male, 3 female; age range, 40-84 years; mean age, 61 years) with histologically confirmed skin appendage tumors with apocrine and eccrine differentiation (2 poromas and 4 porocarcinomas) were enrolled. All patients underwent preoperative MR imaging and the MR images were retrospectively reviewed. RESULTS The configurations were classified as pedunculated solid in 5 lesions and subcutaneous cystic with mural nodules in 1. Well-demarcated deep tumor margins and smooth skin surfaces were observed in all 6 lesions, and peritumoral fat stranding was observed in 2. In all 5 pedunculated solid lesions, T2-hyperintense foci, T1 hyperintensity, and homogeneous solid components were observed within the lesions. CONCLUSIONS Poroma and porocarcinoma usually exhibited pedunculated solid homogeneous lesion. Intratumoral T2-hyperintense foci and T1 hyperintensity were observed in pedunculated solid lesions.
Collapse
|