Towards an intelligent medical system for the aesthetic evaluation of breast cancer conservative treatment

Cardoso, Jaime S.; Cardoso, Maria João

doi:10.1016/j.artmed.2007.02.007

Cited by 143 publications

(152 citation statements)

References 26 publications

(45 reference statements)

Supporting

Mentioning

148

Contrasting

Unclassified

Order By: Relevance

“…On the third and fourth photograph cosmesis was quantitatively scored using the commercially available BCCT.core (Breast Cancer Conservation Treatment. cosmetic results) software of the INESC Porto Breast Research Group (21). This semiautomatic software program also provides an esthetic classification ranging from excellent to poor.…”

Section: Methodsmentioning

confidence: 99%

Does an integrated boost increase acute toxicity in prone hypofractionated breast irradiation? A randomized controlled trial

Paelinck

Gulybán²,

Lakosi³

et al. 2017

Radiotherapy and Oncology

View full text Add to dashboard Cite

SummaryThis is the first randomized trial reporting on the 2-year cosmetic outcome of prone and supine whole-breast irradiation in 94 patients with a cup size of at least C. Better cosmetic outcome was observed in prone-treated patients after 2 years with less skin color changes (PZ.05), less edema (PZ.06), and less worsening of cosmesis assessed by the Breast Cancer Conservation Treatment.cosmetic results software on digital photographs with both arms elevated.Purpose: To report the 2-year cosmetic outcome of a randomized trial comparing prone and supine whole-breast irradiation in large-breasted patients. Methods and Materials: One hundred patients with a (European) cup size C were included. Before and 2 years after radiation therapy, clinical endpoints were scored and digital photographs were taken with the arms alongside the body and with the arms elevated 180 . Three observers rated the photographs using the 4-point Harvard cosmesis scale. Cosmesis was also evaluated with the commercially available Breast Cancer Conservation Treatment.cosmetic results (BCCT.core) software. Results: Two-year follow-up data and photographs were available for 94 patients (47 supine treated and 47 prone treated). Patient and treatment characteristics were not significantly different between the 2 cohorts. Aworsening of color change occurred more frequently in the supine than in the prone cohort (19/46 vs 10/46 patients, respectively, PZ.04). Five patients in the prone group (11%) and 12 patients in the supine group (26%) presented with a worse scoring of edema at 2-year follow-up (PZ.06). For retraction and fibrosis, no significant differences were found between the 2 cohorts, although scores were generally worse in the supine cohort. The cosmetic scoring by 3 observers did not reveal differences between the prone and supine groups. On the photographs with the hands up, 7 patients in the supine group versus none in the prone group had a worsening of cosmesis of 2 categories using the BCCT.org software (PZ.02). Conclusion: With a limited follow-up of 2 years, better cosmetic outcome was observed in prone-treated than in supine-treated patients. Ó

show abstract

Section: Methodsmentioning

confidence: 99%

Does an integrated boost increase acute toxicity in prone hypofractionated breast irradiation? A randomized controlled trial

Paelinck

Gulybán²,

Lakosi³

et al. 2017

Radiotherapy and Oncology

View full text Add to dashboard Cite

show abstract

“…In the presence of a supervised multiclassification problem where the classes are ordered, like for instance the four classes in [15], Excellent > Good > Fair > Poor, if for a particular instance the class with highest a posteriori probability is Fair, then its neighbouring classes, Good and Poor, should have the second and third highest probabilities. This is the unimodal paradigm which states that the probabilities outputted by a prediction method should increase monotonically, until reaching a maximum value, and then decrease monotonically.…”

Section: Unimodal Paradigmmentioning

confidence: 99%

An All-at-once Unimodal SVM Approach for Ordinal Classification

Costa

Sousa

Cardoso

2010

2010 Ninth International Conference on Machine Learning and Applications

Self Cite

View full text Add to dashboard Cite

Abstract-Support vector machines (SVMs) were initially proposed to solve problems with two classes. Despite the myriad of schemes for multiclassification with SVMs proposed since then, little work has been done for the case where the classes are ordered. Usually one constructs a nominal classifier and a posteriori defines the order. The definition of an ordinal classifier leads to a better generalisation. Moreover, most of the techniques presented so far in the literature can generate ambiguous regions. All-at-Once methods have been proposed to solve this issue. In this work we devise a new SVM methodology based on the unimodal paradigm with the All-at-Once scheme for the ordinal classification.

show abstract

“…Trying to overcome the sense that objective asymmetry measurements were insufficient, other groups proposed the sum of the individual scores of subjective and objective individual indices (Al-Ghazal et al, 1999). More recently, a computer-aided medical system was developed to objectively and automatically perform the aesthetic evaluation of BCCT (Cardoso and Cardoso, 2007b). The development of this system entailed the automatic extraction of several features from the photographs (Figure 1), capturing some of the factors considered to have impact on the overall cosmetic result: breast asymmetry, skin colour changes due to the radiotherapy treatment and surgical scar visibility.…”

Section: Introductionmentioning

confidence: 99%

“…The development of this system entailed the automatic extraction of several features from the photographs (Figure 1), capturing some of the factors considered to have impact on the overall cosmetic result: breast asymmetry, skin colour changes due to the radiotherapy treatment and surgical scar visibility. In a second phase, a support vector machine classifier was trained to predict the overall cosmetic result from the recorded features (Cardoso and Cardoso, 2007b). In order to extract the identified relevant features from the image, the detection of the breast contour is necessary.…”

Section: Introductionmentioning

confidence: 99%

Automatic Breast Contour Detection in Digital Photographs

Cardoso

Teixeira

Cardoso

2008

Proceedings of the First International Conference on Health Informatics

View full text Add to dashboard Cite

Keywords:Computer-aided medical system, breast cancer conservative treatment, breast contour, shortest path problem. Abstract:Breast cancer conservative treatment (BCCT), due to its proven oncological safety, is considered, when feasible, the gold standard of breast cancer treatment. However, aesthetic results are heterogeneous and difficult to evaluate in a standardized way, due to the lack of reproducibility of the subjective methods usually applied. The objective assessment methods, considered in the past as being less capable of evaluating all aspects of BCCT, are nowadays being preferred to overcome the drawbacks of the subjective evaluation. A recent computer-aided medical system was developed to objectively and automatically evaluate the aesthetic result of BCCT. In this system, the detection of the breast contour on the digital photograph of the patient is a necessary step to extract the features subsequently used in the evaluation process. In this paper an algorithm based on the shortest path on a graph is proposed to detect automatically the breast contour. The proposed method extends an existing semi-automatic algorithm for the same purpose. A comprehensive comparison with manually-drawn contours reveals the strength of the proposed method.

show abstract

Towards an intelligent medical system for the aesthetic evaluation of breast cancer conservative treatment

Abstract: The results obtained are rather encouraging and the developed tool could be very helpful in assuring objective assessment of the aesthetic outcome of BCCT.

Cited by 143 publications

References 26 publications

Does an integrated boost increase acute toxicity in prone hypofractionated breast irradiation? A randomized controlled trial

Does an integrated boost increase acute toxicity in prone hypofractionated breast irradiation? A randomized controlled trial

An All-at-once Unimodal SVM Approach for Ordinal Classification

Automatic Breast Contour Detection in Digital Photographs

Contact Info

Product

Resources

About