Objective breast symmetry analysis with the breast analyzing tool (BAT): improved tool for clinical trials

Krois, Wilfried; Romar, Alexander Ken; Wild, T. Cameron; Dubsky, Peter; Exner, Ruth; Panhofer, Peter; Jakesz, R.; Gnant, Michael; Fitzal, Florian

doi:10.1007/s10549-017-4255-z

Cited by 28 publications

(19 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…BSI was reproducible and could be used by both experts and non-experts with the same results, while highly correlating with subjective votes from experts and significantly differentiating between good and fair cosmetic outcomes [52]. On the other hand, BSI could not further differentiate between excellent and good or fair and poor cosmetic outcomes, while there was not a correlation between the BSI index and the patients' selfevaluation [20]; even though, Krois et al were able to improve the correlation between subjective and objective BSI values, establishing, thus, new standards on breast symmetry evaluation [4].…”

Section: Objective Methodsmentioning

confidence: 99%

“…The user may consult and change the detection records: it is important that the user has access to the evaluated photos and to the predicted keypoints and he/she should be able to manually correct the model's predictions. 4. The user may erase all the records from the system: once, again, since one is dealing with sensitive clinical data, it is important that the users have the possibility to reset their records.…”

Section: Use-cases and Proposed Architecturementioning

confidence: 99%

See 1 more Smart Citation

Deep Aesthetic Assessment of Breast Cancer Surgery Outcomes

2019

View full text Add to dashboard Cite

Breast cancer is a highly mutable and rapidly evolving disease, with a large worldwide incidence. Even though, it is estimated that approximately 90% of the cases are treatable and curable if detected on early staging and given the best treatment. Nowadays, with the existence of breast cancer routine screening habits, better clinical treatment plans and proper management of the disease, it is possible to treat most cancers with conservative approaches, also known as breast cancer conservative treatments (BCCT). With such a treatment methodology, it is possible to focus on the aesthetic results of the surgery and the patient's Quality of Life, which may influence BCCT outcomes. In the past, this assessment would be done through subjective methods, where a panel of experts would be needed to perform the assessment; however, with the development of computer vision techniques, objective methods, such as BAT c and BCCT.core, which perform the assessment based on asymmetry measurements, have been used. On the other hand, they still require information given by the user and none of them has been considered the gold standard for this task. Recently, with the advent of deep learning techniques, algorithms capable of improving the performance of traditional methods on the detection of breast fiducial points (required for asymmetry measurements) have been proposed and showed promising results. There is still, however, a large margin for investigation on how to integrate such algorithms in a complete application, capable of performing an end-to-end classification of the BCCT outcomes. Taking this into account, this thesis shows a comparative study between deep convolutional networks for image segmentation and two different quality-driven keypoint detection architectures for the detection of the breast contour. One that uses a deep learning model that has learned to predict the quality (given by the mean squared error) of an array of keypoints, and, based on this quality, applies the backpropagation algorithm, with gradient descent, to improve them; another which uses a deep learning model which was trained with the quality as a regularization method and that used iterative refinement, in each training step, to improve the quality of the keypoints that were fed into the network. Although none of the methods surpasses the current state of the art, they present promising results for the creation of alternative methodologies to address other regression problems in which the learning of the quality metric may be easier. Following the current trend in the field of web development and with the objective of transferring BCCT.core to an online format, a prototype of a web application for the automatic keypoint detection was developed and is presented in this document. Currently, the user may upload an image, automatically detect and/or manipulate its keypoints and compute the Breast Retraction Assessment (BRA) value. This prototype is completely scalable and can be upgraded with new functionalities according to the user's needs.iii iv

show abstract

Section: Objective Methodsmentioning

confidence: 99%

Section: Use-cases and Proposed Architecturementioning

confidence: 99%

Deep Aesthetic Assessment of Breast Cancer Surgery Outcomes

2019

View full text Add to dashboard Cite

show abstract

“…Tool ® , una aplicación ejecutable dentro del propio navegador web desarrollada en el artículo de Krois. (22) .…”

Section: -Bsi (Breast Simmetry Index) Para El Cálculo Del Valor Bsunclassified

“…En nuestro trabajo hemos definido un nuevo parámetro numérico que cuantifica las diferencias existentes entre las dos mamas basándonos en el concepto de desplazamiento óptico de imágenes. (26) Para ello, programamos una aplicación (GBAI) en la que el usuario señala la región sobre la que efectuar los cálculos, de forma análoga a otros métodos ya existentes como Breast Analyzing Tool ® , BCCT.core ® y OBCS, (8,22) si bien desde una aproximación completamente diferente: no es necesario trazar puntos de interés ni contornos, sino que en su lugar es el algoritmo el que automáticamente extrae las características de uno y otro lado para luego compararlas.…”

Section: Figura 9 Diagramas De Cajas Y Bigotes Que Muestran Las Difeunclassified

“…(27)(28)(29) . Fitzal y Krois (9,22) validan la última versión de su sistema de dos formas diferentes: por un lado, evalúan las impresiones de un solo observador en una muestra de 50 pacientes frente a la puntuación de su aplicación informática. Por otro lado, correlacionan la opinión de 18 observadores (expertos y no expertos) con su programa en 129 pacientes.…”

Section: Figura 9 Diagramas De Cajas Y Bigotes Que Muestran Las Difeunclassified

See 1 more Smart Citation

Evaluación de la asimetría mamaria mediante algoritmos de desplazamiento óptico

Echeverría

González

Roux

et al. 2019

Cir. plást. iberolatinoam.

View full text Add to dashboard Cite

Evaluación de la asimetría mamaria mediante algoritmos de desplazamiento óptico Breast asymmetry assessment using optical flow algorithms Original / investigación CIRUGÍA MAMARIA Palabras clave Mama, Medidas mama, Asimetría mamaria, Cirugía mamaria Nivel de evidencia científica 3b Diagnóstico Recibido (esta versión) 25 marzo/2019 Aceptado 23 julio/2019 Key words Breast, Breast measures, Breast asymmetry, Breast surgery Level of evidence 3b Diagnostic Received (this version)Antecedentes y Objetivo. La gradación de la simetría es un aspecto fundamental para evaluar un resultado en cirugía mamaria. Los métodos más extendidos de valoración de asimetría se basan en percepciones subjetivas del cirujano o de la paciente, así como en la comparación objetiva de distancias entre puntos de interés tales como la horquilla esternal y el pezón. Utilizar de forma generalizada un método objetivo comportaría ventajas evidentes.El presente trabajo pretende diseñar y contrastar un método de análisis de imagen que permita objetivar el grado de asimetría mamaria en una paciente.Material y método. Basándonos en un algoritmo informático que evalúa el grado de desplazamiento entre dos imágenes similares, desarrollamos una aplicación capaz de cuantificar el grado de desplazamiento que presenta una mama con respecto a la otra, arrojando un resultado numérico que denominamos global breast asymmetry index (GBAI). Calculamos este valor en una serie de 50 pacientes de forma pre y postoperatoria. Comparamos el resultado con otros métodos de evaluación de asimetría tanto objetivos como subjetivos, incluyendo una encuesta a 100 profesionales sanitarios y a un panel de expertos.Resultados. La adaptación de nuestro algoritmo para calcular un índice objetivo de asimetría mamaria muestra un comportamiento similar a la valoración subjetiva de la asimetría por parte del personal sanitario, mejorando otros métodos objetivos y presentándose como una alternativa útil a los métodos tradicionales de comparación de distancias.Conclusiones. El cálculo de desplazamiento óptico es un procedimiento válido y objetivo para cuantificar la asimetría mamaria.Background and Objective. Adequate assessment of symmetry is a critical aspect when evaluating results in breast surgery. Most methods of asymmetry assessment are based on subjective observations by the surgeon or patients, as well as on the objective measurement of distances between key points, such as the sternal notch and the nipple. The widespread use of an objective method would have obvious advantages.We aim to design and test an imaging analysis method that allows to objectively assess the degree of breast asymmetry.Methods. An application has been developed to quantify the degree of disparity between two similar images, based on a computer algorithm. The algorithm was used to compare images of breasts, yielding a numerical result that we named global breast asymmetry index (GBAI). This value was calculated in a series of 50 patients pre-and postoperatively. The result was compared with other asymmetry as...

show abstract

Oncoplastic breast-conserving surgery for women with primary breast cancer

Nanda

Hodgkinson

et al. 2020

Cochrane Database of Systematic Reviews

View full text Add to dashboard Cite

Objective breast symmetry analysis with the breast analyzing tool (BAT): improved tool for clinical trials

Cited by 28 publications

References 14 publications

Deep Aesthetic Assessment of Breast Cancer Surgery Outcomes

Deep Aesthetic Assessment of Breast Cancer Surgery Outcomes

Evaluación de la asimetría mamaria mediante algoritmos de desplazamiento óptico

Oncoplastic breast-conserving surgery for women with primary breast cancer

Contact Info

Product

Resources

About