Submitted by Gustavo de Aquino e Aquino (gustavoaqui@gmail.com) on 2022-02-09T21:12:34Z No. of bitstreams: 1 Disserta????o_gustavo_imprimir.pdf: 4362672 bytes, checksum: 96894b93e804014d546a5df1ea425494 (MD5) Rejected by PPGEE Engenharia El??trica (mestrado_engeletrica@ufam.edu.br), reason: Falta inserir os demais documentos, segue as orienta????es que te enviei. on 2022-02-10T14:04:23Z (GMT) Submitted by Gustavo de Aquino e Aquino (gustavoaqui@gmail.com) on 2022-02-10T19:04:40Z No. of bitstreams: 3 Disserta????o_gustavo_imprimir.pdf: 4362672 bytes, checksum: 96894b93e804014d546a5df1ea425494 (MD5) Termo de Autoriza????o - Autodep??sito RIU-TEDE (1).pdf: 674524 bytes, checksum: 1046bf28048b5745178ab811f046b888 (MD5) 2 - Documenta????o defesa disserta????o gustavo (ATA).pdf: 139490 bytes, checksum: 6059c6bd1c5b0b71b1d3779e1aba41ba (MD5) Rejected by PPGEE Engenharia El??trica (mestrado_engeletrica@ufam.edu.br), reason: Boa tarde! Est?? faltando inserir a Carta de Encaminhamento, a ATA de julgamento falta a assinatura do coordenador. on 2022-02-21T18:05:54Z (GMT) Submitted by Gustavo de Aquino e Aquino (gustavoaqui@gmail.com) on 2022-03-16T11:25:28Z No. of bitstreams: 4 Disserta????o_gustavo_imprimir.pdf: 4362672 bytes, checksum: 96894b93e804014d546a5df1ea425494 (MD5) Termo de Autoriza????o - Autodep??sito RIU-TEDE (1).pdf: 674524 bytes, checksum: 1046bf28048b5745178ab811f046b888 (MD5) ATA GUSTAVO AQUINO.pdf: 529745 bytes, checksum: 5e90a9c7edb496ec035b3f7f6d6593b3 (MD5) CartaEncaminhamentoAutodep??sito.pdf: 121737 bytes, checksum: 30cfda3630f8ab503dda8e6e1037791e (MD5) Approved for entry into archive by PPGEE Engenharia El??trica (mestrado_engeletrica@ufam.edu.br) on 2022-03-16T12:46:37Z (GMT) No. of bitstreams: 4 Disserta????o_gustavo_imprimir.pdf: 4362672 bytes, checksum: 96894b93e804014d546a5df1ea425494 (MD5) Termo de Autoriza????o - Autodep??sito RIU-TEDE (1).pdf: 674524 bytes, checksum: 1046bf28048b5745178ab811f046b888 (MD5) ATA GUSTAVO AQUINO.pdf: 529745 bytes, checksum: 5e90a9c7edb496ec035b3f7f6d6593b3 (MD5) CartaEncaminhamentoAutodep??sito.pdf: 121737 bytes, checksum: 30cfda3630f8ab503dda8e6e1037791e (MD5) Rejected by Divis??o de Documenta????o/BC Biblioteca Central (ddbc@ufam.edu.br), reason: No formul??rio da Ficha catalogr??fica, realizar os seguintes ajustes: a) No campo "??ltimo sobrenome" inserir: "Aquino" ; No campo "Nomes e primeiros sobrenomes", inserir: "Gustavo de Aquino e" ; b) O t??tulo deve come??ar com a primeira letra mai??scula e as demais min??sculas, exceto quando forem siglas ou nomes pr??prios. c) No t??tulo, onde se l?? "le??es", leia-se "les??es" ; d) No campo "Quantidade de folhas, inserir o n??mero da ??ltima folha numerada (88) ; e) Ajustar para CoorientadOR, onde consta CoorientadoRA on 2022-03-16T17:47:28Z (GMT) Submitted by Gustavo de Aquino e Aquino (gustavoaqui@gmail.com) on 2022-03-21T11:59:01Z No. of bitstreams: 4 Disserta????o_gustavo_imprimir.pdf: 4362672 bytes, checksum: 96894b93e804014d546a5df1ea425494 (MD5) Termo de Autoriza????o - Autodep??sito RIU-TEDE (1).pdf: 674524 bytes, checksum: 1046bf28048b5745178ab811f046b888 (MD5) ATA GUSTAVO AQUINO.pdf: 529745 bytes, checksum: 5e90a9c7edb496ec035b3f7f6d6593b3 (MD5) CartaEncaminhamentoAutodep??sito.pdf: 121737 bytes, checksum: 30cfda3630f8ab503dda8e6e1037791e (MD5) Approved for entry into archive by PPGEE Engenharia El??trica (mestrado_engeletrica@ufam.edu.br) on 2022-03-21T12:35:47Z (GMT) No. of bitstreams: 4 Disserta????o_gustavo_imprimir.pdf: 4362672 bytes, checksum: 96894b93e804014d546a5df1ea425494 (MD5) Termo de Autoriza????o - Autodep??sito RIU-TEDE (1).pdf: 674524 bytes, checksum: 1046bf28048b5745178ab811f046b888 (MD5) ATA GUSTAVO AQUINO.pdf: 529745 bytes, checksum: 5e90a9c7edb496ec035b3f7f6d6593b3 (MD5) CartaEncaminhamentoAutodep??sito.pdf: 121737 bytes, checksum: 30cfda3630f8ab503dda8e6e1037791e (MD5) Rejected by Divis??o de Documenta????o/BC Biblioteca Central (ddbc@ufam.edu.br), reason: No formul??rio da Ficha catalogr??fica, realizar os seguintes ajustes: a) No campo "??ltimo sobrenome" inserir: Aquino ; No campo "Nomes e primeiros sobrenomes", inserir: Gustavo de Aquino e ; b) O t??tulo deve come??ar com a primeira letra mai??scula e as demais min??sculas, exceto quando forem siglas ou nomes pr??prios. c) No t??tulo, onde se l?? "le??es", leia-se "les??es" ; d) No campo "Quantidade de folhas, inserir o n??mero da ??ltima folha numerada (88) ; e) Ajustar para CoorientadOR, onde consta CoorientadoRA on 2022-03-21T18:03:39Z (GMT) Submitted by Gustavo de Aquino e Aquino (gustavoaqui@gmail.com) on 2022-03-23T15:14:01Z No. of bitstreams: 4 Termo de Autoriza????o - Autodep??sito RIU-TEDE (1).pdf: 674524 bytes, checksum: 1046bf28048b5745178ab811f046b888 (MD5) ATA GUSTAVO AQUINO.pdf: 529745 bytes, checksum: 5e90a9c7edb496ec035b3f7f6d6593b3 (MD5) CartaEncaminhamentoAutodep??sito.pdf: 121737 bytes, checksum: 30cfda3630f8ab503dda8e6e1037791e (MD5) Disserta????o Final TEDE.pdf: 4368227 bytes, checksum: e4aed637488a9c9758becc3cadbe0de0 (MD5) Approved for entry into archive by PPGEE Engenharia El??trica (mestrado_engeletrica@ufam.edu.br) on 2022-03-25T18:07:34Z (GMT) No. of bitstreams: 4 Termo de Autoriza????o - Autodep??sito RIU-TEDE (1).pdf: 674524 bytes, checksum: 1046bf28048b5745178ab811f046b888 (MD5) ATA GUSTAVO AQUINO.pdf: 529745 bytes, checksum: 5e90a9c7edb496ec035b3f7f6d6593b3 (MD5) CartaEncaminhamentoAutodep??sito.pdf: 121737 bytes, checksum: 30cfda3630f8ab503dda8e6e1037791e (MD5) Disserta????o Final TEDE.pdf: 4368227 bytes, checksum: e4aed637488a9c9758becc3cadbe0de0 (MD5) Approved for entry into archive by Divis??o de Documenta????o/BC Biblioteca Central (ddbc@ufam.edu.br) on 2022-03-28T18:02:40Z (GMT) No. of bitstreams: 4 Termo de Autoriza????o - Autodep??sito RIU-TEDE (1).pdf: 674524 bytes, checksum: 1046bf28048b5745178ab811f046b888 (MD5) ATA GUSTAVO AQUINO.pdf: 529745 bytes, checksum: 5e90a9c7edb496ec035b3f7f6d6593b3 (MD5) CartaEncaminhamentoAutodep??sito.pdf: 121737 bytes, checksum: 30cfda3630f8ab503dda8e6e1037791e (MD5) Disserta????o Final TEDE.pdf: 4368227 bytes, checksum: e4aed637488a9c9758becc3cadbe0de0 (MD5) Made available in DSpace on 2022-03-28T18:02:40Z (GMT). No. of bitstreams: 4 Termo de Autoriza????o - Autodep??sito RIU-TEDE (1).pdf: 674524 bytes, checksum: 1046bf28048b5745178ab811f046b888 (MD5) ATA GUSTAVO AQUINO.pdf: 529745 bytes, checksum: 5e90a9c7edb496ec035b3f7f6d6593b3 (MD5) CartaEncaminhamentoAutodep??sito.pdf: 121737 bytes, checksum: 30cfda3630f8ab503dda8e6e1037791e (MD5) Disserta????o Final TEDE.pdf: 4368227 bytes, checksum: e4aed637488a9c9758becc3cadbe0de0 (MD5) Previous issue date: 2020-03-03 FAPEAM - Funda????o de Amparo ?? Pesquisa do Estado do Amazonas Breast cancer can be seen as a worldwide problem, which is responsible for a substantial number of deaths. Diagnosis through image analysis of the lesion is efficient, notably through the use of machine learning techniques. The success achieved in recent years has grown due to the use of convolutional networks. This method is capable of successfully performing computer vision tasks, such as the automatic segmentation of lesions in the most varied modalities of biomedical images. This stage, segmentation, supports later stages of a computer-aided diagnostic imaging system. In this dissertation, the performance of convolutional neural networks with direct acyclic graph architectures in the automatic segmentation of breast lesions in ultrasound images is evaluated. Four convolutional network architectures were implemented and tested, three of them with direct acyclic graphs (DAG) and one sequential. For the development and evaluation of the proposals, two banks of breast ultrasound images (bank A and bank B) were used. Some striking differences between these banks are the size, resolution, and quality of the images. Thus, the images were previously processed and adapted (cropping and resize). The training of these networks with a stop for the number of seasons proved to be unstable. This problem was overcome with the proposal of a training aid function, which allowed us to obtain the best performance point of the model. The best architecture was chosen based on metrics already established in the literature, such as global accuracy and the Dice coefficient. The four architectures tested achieved similar results, with a global accuracy of more than 94% each. The t-student statistical significance test showed that for both databases the best network architecture in the validation was U-net, reaching over 99% of global accuracy for database B and over 96% for the database A. The network with the best performance could be tested, with other input data, and its performance remained the same. It was possible to conclude that the cropping procedure was not crucial for good segmentation accuracy. Besides, the statistical analysis of the performance metrics showed that the use of better resolution images (bank B) did not cause statistically significant performance differences (p