RESUMO
BACKGROUND: This study aims to develop a stacking model for accurately predicting axillary lymph node (ALN) response to neoadjuvant chemotherapy (NAC) using longitudinal MRI in breast cancer. METHODS: We included patients with node-positive breast cancer who received NAC following surgery from January 2012 to June 2022. We collected MRIs before and after NAC, and extracted radiomics features from the tumour, peritumour, and ALN regions. The Mann-Whitney U test, least absolute shrinkage and selection operator, and Boruta algorithm were used to select features. We utilised machine learning techniques to develop three single-modality models and a stacking model for predicting ALN response to NAC. RESULTS: This study consisted of a training cohort (n = 277), three external validation cohorts (n = 313, 164, and 318), and a prospective cohort (n = 81). Among the 1153 patients, 60.62% achieved ypN0. The stacking model achieved excellent AUCs of 0.926, 0.874, and 0.862 in the training, external validation, and prospective cohort, respectively. It also showed lower false-negative rates (FNRs) compared to radiologists, with rates of 14.40%, 20.85%, and 18.18% (radiologists: 40.80%, 50.49%, and 63.64%) in three cohorts. Additionally, there was a significant difference in disease-free survival between high-risk and low-risk groups (p < 0.05). CONCLUSIONS: The stacking model can accurately predict ALN status after NAC in breast cancer, showing a lower false-negative rate than radiologists. TRIAL REGISTRATION NUMBER: The clinical trial numbers were NCT03154749 and NCT04858529.
Assuntos
Inteligência Artificial , Axila , Neoplasias da Mama , Imageamento por Ressonância Magnética , Terapia Neoadjuvante , Humanos , Feminino , Neoplasias da Mama/tratamento farmacológico , Neoplasias da Mama/patologia , Neoplasias da Mama/diagnóstico por imagem , Pessoa de Meia-Idade , Adulto , Imageamento por Ressonância Magnética/métodos , Estudos Prospectivos , Linfonodos/patologia , Linfonodos/diagnóstico por imagem , Idoso , Metástase Linfática , Aprendizado de Máquina , Quimioterapia AdjuvanteRESUMO
Gasless transaxillary posterior endoscopic thyroidectomy (GTPET) is a new approach for thyroid cancer. It allows en bloc resection of the thyroid and central lymph nodes. Few studies have reported on the learning curve for GTPET.We examined the learning curve of GTPET for thyroid cancer by cumulative sum (CUSUM) analysis by retrospectively analyzing patients who underwent hemithyroidectomy with ipsilateral central neck dissection between December 2020 and September 2021 at a tertiary medical center, including the first patient. Moving average analysis and sequential time-block analysis were used for validation. Data on the clinical factors between the two periods were compared. In the overall cohort, the average time for GTPET for thyroid cancer was 113.25 min to harvest an average of 6.4 central lymph nodes. The CUSUM curve of the operative time indicated an inflection point after 38 patients. Moving average analysis and sequential time-block analysis validated the number of procedures needed for GTPET proficiency. (124.05 min vs. 107.63 min for the unproficient period vs. proficient period, respectively; P < 0.001) The number of retrieved lymph nodes was not associated with a certain level of proficiency per the learning curve. The main complication during the surgeon's unproficient period was transient hoarseness (3/38), which was similar to that in their proficient period (2/73, p = 0.336). Proficiency in GTPET is associated with performing more than 38 procedures. Standard course training and instruction on careful management are required prior to introducing the procedure.
Assuntos
Neoplasias da Glândula Tireoide , Tireoidectomia , Humanos , Tireoidectomia/métodos , Curva de Aprendizado , Estudos Retrospectivos , Endoscopia/métodos , Neoplasias da Glândula Tireoide/cirurgia , Neoplasias da Glândula Tireoide/patologiaRESUMO
Adenomyosis is a benign disease with a malignant behavior, bothering a lot of women at reproductive age who suffer from increased menstruation, prolonged menstruation, progressive dysmenorrhea, and infertility. At present, there is no effective treatment for adenomyosis. It seriously affects the life quality of these patients. However, the pathogenesis of adenomyosis is not yet clear. Recently, uterus junctional zone, defined as the inner 1/3 of myometrium between endometrium and myometrium, has gained broad attention. As is reported, the structure and function disorder of uterus junctional zone may play an important part in the occurrence and development of adenomyosis. In this issue, the present study generally reviews the role of uterine junction zone and the related mechanisms involved in adenomyosis, such as the local micro-damage, the formation of inflammatory and hypoxic microenvironment, changes of cytokines, and abnormalities of miRNA as well as signal pathways. It will provide new insights and potential therapeutic target strategies for clinical strategies in the management of adenomyosis.