RESUMEN
Purpose To describe the design, conduct, and results of the Breast Multiparametric MRI for prediction of neoadjuvant chemotherapy Response (BMMR2) challenge. Materials and Methods The BMMR2 computational challenge opened on May 28, 2021, and closed on December 21, 2021. The goal of the challenge was to identify image-based markers derived from multiparametric breast MRI, including diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI, along with clinical data for predicting pathologic complete response (pCR) following neoadjuvant treatment. Data included 573 breast MRI studies from 191 women (mean age [±SD], 48.9 years ± 10.56) in the I-SPY 2/American College of Radiology Imaging Network (ACRIN) 6698 trial (ClinicalTrials.gov: NCT01042379). The challenge cohort was split into training (60%) and test (40%) sets, with teams blinded to test set pCR outcomes. Prediction performance was evaluated by area under the receiver operating characteristic curve (AUC) and compared with the benchmark established from the ACRIN 6698 primary analysis. Results Eight teams submitted final predictions. Entries from three teams had point estimators of AUC that were higher than the benchmark performance (AUC, 0.782 [95% CI: 0.670, 0.893], with AUCs of 0.803 [95% CI: 0.702, 0.904], 0.838 [95% CI: 0.748, 0.928], and 0.840 [95% CI: 0.748, 0.932]). A variety of approaches were used, ranging from extraction of individual features to deep learning and artificial intelligence methods, incorporating DCE and DWI alone or in combination. Conclusion The BMMR2 challenge identified several models with high predictive performance, which may further expand the value of multiparametric breast MRI as an early marker of treatment response. Clinical trial registration no. NCT01042379 Keywords: MRI, Breast, Tumor Response Supplemental material is available for this article. © RSNA, 2024.
Asunto(s)
Neoplasias de la Mama , Imágenes de Resonancia Magnética Multiparamétrica , Femenino , Humanos , Persona de Mediana Edad , Inteligencia Artificial , Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/tratamiento farmacológico , Imagen por Resonancia Magnética , Terapia Neoadyuvante , Respuesta Patológica Completa , AdultoRESUMEN
Background Computational models based on artificial intelligence (AI) are increasingly used to diagnose malignant breast lesions. However, assessment from radiologic images of the specific pathologic lesion subtypes, as detailed in the results of biopsy procedures, remains a challenge. Purpose To develop an AI-based model to identify breast lesion subtypes with mammograms and linked electronic health records labeled with histopathologic information. Materials and Methods In this retrospective study, 26 569 images were collected in 9234 women who underwent digital mammography to pretrain the algorithms. The training data included individuals who had at least 1 year of clinical and imaging history followed by biopsy-based histopathologic diagnosis from March 2013 to November 2018. A model that combined convolutional neural networks with supervised learning algorithms was independently trained to make breast lesion predictions with data from 2120 women in Israel and 1642 women in the United States. Results were reported using the area under the receiver operating characteristic curve (AUC) with the 95% DeLong approach to estimate CIs. Significance was tested with bootstrapping. Results The Israeli model was validated in 456 women and tested in 441 women (mean age, 51 years ± 11 [SD]). The U.S. model was validated in 350 women and tested in 344 women (mean age, 60 years ± 12). For predicting malignancy in the test sets (consisting of 220 Israeli patient examinations and 126 U.S. patient examinations with ductal carcinoma in situ or invasive cancer), the algorithms obtained an AUC of 0.88 (95% CI: 0.85, 0.91) and 0.80 (95% CI: 0.74, 0.85) for Israeli and U.S. patients, respectively (P = .006). These results may not hold for other cohorts of patients, and generalizability across populations should be further investigated. Conclusion The results offer supporting evidence that artificial intelligence applied to clinical and mammographic images can identify breast lesion subtypes when the data are sufficiently large, which may help assess diagnostic workflow and reduce biopsy sampling errors. Published under a CC BY 4.0 license. Online supplemental material is available for this article.
Asunto(s)
Inteligencia Artificial , Neoplasias de la Mama , Femenino , Humanos , Persona de Mediana Edad , Estudios Retrospectivos , Mamografía/métodos , Mama/diagnóstico por imagen , Biopsia , Neoplasias de la Mama/diagnóstico por imagenRESUMEN
OBJECTIVE: Magnetic resonance-guided focused ultrasound surgery (MRgFUS) was recently introduced as treatment for movement disorders such as essential tremor and advanced Parkinson's disease (PD). Although deep brain target lesions are successfully generated in most patients, the target area temperature fails to increase in some cases. The skull is one of the greatest barriers to ultrasonic energy transmission. The authors analyzed the skull-related factors that may have prevented an increase in target area temperatures in patients who underwent MRgFUS. METHODS: The authors retrospectively reviewed data from clinical trials that involved MRgFUS for essential tremor, idiopathic PD, and obsessive-compulsive disorder. Data from 25 patients were included. The relationships between the maximal temperature during treatment and other factors, including sex, age, skull area of the sonication field, number of elements used, skull volume of the sonication field, and skull density ratio (SDR), were determined. RESULTS: Among the various factors, skull volume and SDR exhibited relationships with the maximum temperature. Skull volume was negatively correlated with maximal temperature (p = 0.023, r(2) = 0.206, y = 64.156 - 0.028x, whereas SDR was positively correlated with maximal temperature (p = 0.009, r(2) = 0.263, y = 49.643 + 11.832x). The other factors correlate with the maximal temperature, although some factors showed a tendency to correlate. CONCLUSIONS: Some skull-related factors correlated with the maximal target area temperature. Although the number of patients in the present study was relatively small, the results offer information that could guide the selection of MRgFUS candidates.
Asunto(s)
Imagen por Resonancia Magnética/métodos , Procedimientos Neuroquirúrgicos/métodos , Cráneo/diagnóstico por imagen , Cráneo/cirugía , Cirugía Asistida por Computador/métodos , Procedimientos Quirúrgicos Ultrasónicos/métodos , Adulto , Factores de Edad , Anciano , Temblor Esencial/cirugía , Femenino , Humanos , Masculino , Persona de Mediana Edad , Trastorno Obsesivo Compulsivo/cirugía , Enfermedad de Parkinson/cirugía , Estudios Retrospectivos , Factores Sexuales , Técnicas Estereotáxicas , Temperatura , Núcleos Talámicos/anatomía & histología , Núcleos Talámicos/cirugía , Resultado del Tratamiento , Ultrasonografía , Adulto JovenRESUMEN
OBJECT: The authors report different MRI patterns in patients with essential tremor (ET) or obsessive-compulsive disorder (OCD) after transcranial MR-guided focused ultrasound (MRgFUS) and discuss possible causes of occasional MRgFUS failure. METHODS: Between March 2012 and August 2013, MRgFUS was used to perform unilateral thalamotomy in 11 ET patients and bilateral anterior limb capsulotomy in 6 OCD patients; in all patients symptoms were refractory to drug therapy. Sequential MR images were obtained in patients across a 6-month follow-up period. RESULTS: For OCD patients, lesion size slowly increased and peaked 1 week after treatment, after which lesion size gradually decreased. For ET patients, lesions were visible immediately after treatment and markedly reduced in size as time passed. In 3 ET patients and 1 OCD patient, there was no or little temperature rise (i.e., < 52°C) during MRgFUS. Successful and failed patient groups showed differences in their ratio of cortical-to-bone marrow thickness (i.e., skull density). CONCLUSIONS: The authors found different MRI pattern evolution after MRgFUS for white matter and gray matter. Their results suggest that skull characteristics, such as low skull density, should be evaluated prior to MRgFUS to successfully achieve thermal rise.