ABSTRACT
BACKGROUND: Infantile hemangiomas (IHs) of the anogenital region remain poorly characterized. OBJECTIVE: To examine the distribution, ulceration rate, and associated congenital anomalies of anogenital IHs. METHODS: Retrospective study at 8 tertiary referral centers. RESULTS: A total of 435 infants with an IH of the anogenital region were enrolled (of which, 319 [73%] were girls). Congenital anomalies were present in 6.4% (n = 28) of infants with an anogenital IH. Segmental or partial segmental anogenital IHs ulcerated in 72% (n = 99 of 138) of infants, whereas 45% (n = 133 of 297) of focal anogenital IHs experienced ulceration (P < .001). In a multivariable logistic regression analysis, segmental or partial segmental morphology (adjusted odds ratio [aOR], 2.70; 95% CI, 1.60-4.64), mixed type (aOR, 3.44; 95% CI, 2.01-6.07), and perianal (aOR, 3.01; 95% CI, 1.53-6.12) and buttocks location (aOR, 2.08; 95% CI, 1.17-3.76) had increased odds of ulceration. Segmental or partial segmental IHs of the genitalia were confined to distinct anatomic territories and were predominantly distributed unilaterally, with a linear demarcation at the perineal raphe. LIMITATIONS: Possible selection bias, given recruitment at tertiary referral centers. CONCLUSION: This study improves our understanding of high-risk features of anogenital IHs and demonstrates that genital segmental or partial segmental IHs develop within distinct anatomic territories.
ABSTRACT
OBJECTIVE: The integration of an artificial intelligence tool into pathologists' workflow may lead to a more accurate and timely diagnosis of melanocytic lesions, directly patient care. The objective of this study was to create and evaluate the performance of such a model in achieving clinical-grade diagnoses of Spitz nevi, dermal and junctional melanocytic nevi, and melanomas. METHODS: We created a beginner-level training environment by teaching our algorithm to perform cytologic inferences on 136,216 manually annotated tiles of hematoxylin and eosin-stained slides consisting of unequivocal melanocytic nevi, Spitz nevi, and invasive melanoma cases. We sequentially trained and tested our network to provide a final diagnosis-classification on 39 cases in total. Positive predictive value (precision) and sensitivity (recall) were used to measure our performance. RESULTS: The tile-classification algorithm predicted the 136,216 irrelevant, melanoma, melanocytic nevi, and Spitz nevi tiles at sensitivities of 96%, 93%, 94% and 73%, respectively. The final trained model was able to correctly classify and predict the correct diagnosis in 85.7% of unseen cases (n = 28), reporting at or near screening-level performances for precision and recall of melanoma (76.2%, 100.0%), melanocytic nevi (100.0%, 75.0%), and Spitz nevi (100.0%, 75.0%). CONCLUSIONS: Our pilot study proves that convolutional networks trained on cellular morphology to classify melanocytic proliferations can be used as a powerful tool to assist pathologists in screening for melanoma versus other benign lesions.
Subject(s)
Deep Learning , Melanoma , Nevus, Epithelioid and Spindle Cell , Nevus, Pigmented , Skin Neoplasms , Artificial Intelligence , Diagnosis, Differential , Humans , Melanoma/diagnosis , Melanoma/pathology , Nevus, Epithelioid and Spindle Cell/diagnosis , Nevus, Pigmented/pathology , Pilot Projects , Skin Neoplasms/diagnosis , Skin Neoplasms/pathology , Melanoma, Cutaneous MalignantSubject(s)
Graft vs Host Disease/radiotherapy , Hematologic Neoplasms/therapy , Hematopoietic Stem Cell Transplantation/adverse effects , Phototherapy/methods , Skin Diseases/radiotherapy , Ultraviolet Therapy/methods , Acute Disease , Adolescent , Adult , Child , Child, Preschool , Female , Follow-Up Studies , Graft vs Host Disease/etiology , Graft vs Host Disease/pathology , Hematologic Neoplasms/pathology , Humans , Infant , Male , Prognosis , Retrospective Studies , Skin Diseases/etiology , Skin Diseases/pathology , Transplantation, Homologous , Young AdultSubject(s)
Anti-Infective Agents , Benzophenoneidum , Coloring Agents , Fluorescent Dyes , Mycobacterium Infections/microbiology , Mycobacterium/isolation & purification , Rhodamines , Bacteriological Techniques/methods , Drug Combinations , Female , Humans , Male , Retrospective Studies , Sensitivity and SpecificityABSTRACT
OBJECTIVES: To investigate the progression of coronary atherosclerosis burden by coronary CT angiography (CCTA) and to demonstrate its association with the incidence of major adverse cardiac events (MACE). METHODS: We retrospectively studied patients with stable angina who had undergone repeat CCTA due to recurrent or worsening symptoms. Lipid-rich, fibrous, calcified and total plaque burden as well as coronary diameter stenosis were quantitatively analysed. The incidence of MACE during follow-up was determined. RESULTS: The final cohort consisted of 268 patients (mean age 52.9 ± 9.8 years, 71 % male) with a mean follow-up period of 4.6 ± 0.9 years. Patients with lipid-rich, fibrous, calcified and total plaque burden (%) progression, as well as coronary diameter stenosis (%) progression had a significantly higher incidence of MACE than those without (all p < 0.05). The progression of lipid-rich plaque (HR = 1.601, p = 0.021), total plaque burden (HR = 2.979, p = 0.043) and coronary diameter stenosis (HR = 4.327, p <0.001) were independent predictors of MACE (all p < 0.05). CONCLUSIONS: Patients presenting with recurrent or worsening symptoms associated with coronary artery disease who have coronary atherosclerosis progression on CCTA are at an increased risk of future MACE. KEY POINTS: ⢠Repeat CCTA can provide information regarding the progression of coronary atherosclerosis. ⢠Coronary atherosclerosis progression at CCTA is independently associated with MACE. ⢠CCTA findings could serve as incremental predictors of MACE.
