Small Cell Variant of Metastatic Melanoma: A Mimicker of Lymphoblastic Leukemia/Lymphoma

Ronen, Shira; Czaja, Rebecca; Ronen, Natali; Pantazis, Cooley G.; Iczkowski, Kenneth A.

doi:10.1159/000503703

Cited by 10 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This feature was maximized in specimen with small to intermediate sized melanocytes (Figure 7). Small cell melanoma has been associated with a poor prognosis previously in case series and case reports (32,33), and our feature of Major axis length bin 4 is consistent with this finding. Small cell melanoma, however is exceedingly rare, and though some IHC staining patterns of this variant have been described in patients with metastatic disease but of unknown primary lesions, it has not been systematically studied (34).…”

Section: Visualization and Interpretation Of Identified Image Featuressupporting

confidence: 92%

Predicting melanoma survival and metastasis with interpretable histopathological features and machine learning models

Couetil

Liu²,

Huang³

et al. 2023

Front. Med.

View full text Add to dashboard Cite

IntroductionMelanoma is the fifth most common cancer in US, and the incidence is increasing 1.4% annually. The overall survival rate for early-stage disease is 99.4%. However, melanoma can recur years later (in the same region of the body or as distant metastasis), and results in a dramatically lower survival rate. Currently there is no reliable method to predict tumor recurrence and metastasis on early primary tumor histological images.MethodsTo identify rapid, accurate, and cost-effective predictors of metastasis and survival, in this work, we applied various interpretable machine learning approaches to analyze melanoma histopathological H&E images. The result is a set of image features that can help clinicians identify high-risk-of-metastasis patients for increased clinical follow-up and precision treatment. We use simple models (i.e., logarithmic classification and KNN) and “human-interpretable” measures of cell morphology and tissue architecture (e.g., cell size, staining intensity, and cell density) to predict the melanoma survival on public and local Stage I–III cohorts as well as the metastasis risk on a local cohort.ResultsWe use penalized survival regression to limit features available to downstream classifiers and investigate the utility of convolutional neural networks in isolating tumor regions to focus morphology extraction on only the tumor region. This approach allows us to predict survival and metastasis with a maximum F1 score of 0.72 and 0.73, respectively, and to visualize several high-risk cell morphologies.DiscussionThis lays the foundation for future work, which will focus on using our interpretable pipeline to predict metastasis in Stage I & II melanoma.

show abstract

Section: Visualization and Interpretation Of Identified Image Featuressupporting

confidence: 92%

Predicting melanoma survival and metastasis with interpretable histopathological features and machine learning models

Couetil

Liu²,

Huang³

et al. 2023

Front. Med.

View full text Add to dashboard Cite

show abstract

“…There are few reports of recurrent malignant melanoma mainly presenting with pleural effusions in the literature (5)(6)(7)(8)(9)(10)(11)(12)(13)(14)(15)(16)(17)(18) (Table 1); all were con rmed by pathology.…”

Section: Discussionmentioning

confidence: 99%

Pleural effusion as the initial manifestation of metastatic melanoma: a case report and literature review

Quan

Qiu

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Malignant melanoma (MM) is a highly invasive form of skin cancer with poor prognosis. Pleural metastatic melanoma is rare, with only a few reported cases.Case presentation: A 47-year-old woman with a medical history of right heel melanoma was diagnosed with left-sided pleural effusion, with pleural thickening and calcified mediastinal lymph nodes, using chest computed tomography (CT). A video-assisted thoracoscopic biopsy was performed which revealed numerous pink lumps arising from the parietal pleura and viscera along the diaphragmatic surface. The pathological diagnosis was pleural metastatic melanoma and the tumor cells were immunocytochemically positive for S100, SOX10, and Melan-A.Conclusions: The clinical manifestations of metastatic pleural melanoma are nonspecific. Pleural effusion cytology combined with thoracoscopy is an effective diagnostic method. The presence of melanocytes has improved the diagnosis of this condition.

show abstract

“…MM is known for its wide range of histologic variants and cytomorphologic features, which can mimic various poorly differentiated carcinomas like neuroendocrine tumors, germ cell tumors, and different types of soft tissue sarcomas. [7][8][9][10][11] Moreover, The primary and metastatic MM can also assume different histological patterns, making the light-microscopic identification of the tumors difficult. [12][13][14] And metastases from a primary cutaneous MM of the classical type may present a divergent histological appearance.…”

Section: Discussionmentioning

confidence: 99%

Neurosarcomatous amelanotic transformation of malignant melanoma presenting as malignant periopheral nerve sheath tumor: Rare case report

Bofan,

Xiaofei,

Jingwen

et al. 2023

Medicine

View full text Add to dashboard Cite

Rationale: Malignant melanoma (MM) is notorious for its remarkable morphological variation and aberrant histopathological patterns. In addition, Malignant Periopheral Nerve Sheath Tumor (MPNST) is an uncommon but aggressive soft tissue sarcoma. Because of the common embryological origin of melanocytes and Schwann cells in the neural crest, discriminating between a particular type of MM and MPNST can be difficult, particularly when they are amelanotic. Our goal is to increase awareness among clinicians of the rare variations of MM and the importance of medical history in improving the accuracy of the final clinical diagnosis. Patient concerns: A 68-year-old man was admitted to the hospital due to pain in his right ankle, which had persisted for 8 months, along with swelling for 4 months. Medical history revealed delayed healing of right plantar for 5 years after a traumatic injury. Diagnoses: The ankle mass was initially diagnosed as MPNST through biopsy. After reviewing the patient’s medical history and receiving the final pathological report following amputation, we have revised the diagnosis to metastatic amelanotic desmoplastic melanoma in the ankle part and lentigo maligna melanoma in the plantar part. This is due to both lesions displaying positive markers or mutated genes in immunohistology and Gene Mutation Detection, indicating homology between the 2 tumors. Interventions: Due to the malignant characteristics of the tumor and the patient’s wishes, amputation of the right lower leg was carried out. Outcomes: Subsequently, the patient was treated with interferon-γ and immunosuppressant PD-1 inhibitor, and survived for 1 year after amputation. Lessons: Clinical data, immunohistochemisty biomarkers and genes detection results can serve as valuable evidence for pathologists and clinicians in identifying the disease process. Collaborative efforts between clinicians and scientists are crucial in order to identify specific markers that can effectively differentiate between the 2 tumors, thereby enhancing the conclusiveness of the diagnosis.

show abstract

Small Cell Variant of Metastatic Melanoma: A Mimicker of Lymphoblastic Leukemia/Lymphoma

Cited by 10 publications

References 22 publications

Predicting melanoma survival and metastasis with interpretable histopathological features and machine learning models

Predicting melanoma survival and metastasis with interpretable histopathological features and machine learning models

Pleural effusion as the initial manifestation of metastatic melanoma: a case report and literature review

Neurosarcomatous amelanotic transformation of malignant melanoma presenting as malignant periopheral nerve sheath tumor: Rare case report

Contact Info

Product

Resources

About