Semantic Segmentation of Urinary Bladder Cancer Masses from CT Images: A Transfer Learning Approach
Urinary bladder cancer is one of the most common cancers of the urinary tract. This cancer is characterized by its high metastatic potential and recurrence rate. Due to the high metastatic potential and recurrence rate, correct and timely diagnosis is crucial for successful treatment and care. With...
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/1b7973215b66493bb56f23ee94f2095c |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Urinary bladder cancer is one of the most common cancers of the urinary tract. This cancer is characterized by its high metastatic potential and recurrence rate. Due to the high metastatic potential and recurrence rate, correct and timely diagnosis is crucial for successful treatment and care. With the aim of increasing diagnosis accuracy, artificial intelligence algorithms are introduced to clinical decision making and diagnostics. One of the standard procedures for bladder cancer diagnosis is computer tomography (CT) scanning. In this research, a transfer learning approach to the semantic segmentation of urinary bladder cancer masses from CT images is presented. The initial data set is divided into three sub-sets according to image planes: frontal (4413 images), axial (4993 images), and sagittal (996 images). First, AlexNet is utilized for the design of a plane recognition system, and it achieved high classification and generalization performances with an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mover><mrow><mi>A</mi><mi>U</mi><msub><mi>C</mi><mrow><mi>m</mi><mi>i</mi><mi>c</mi><mi>r</mi><mi>o</mi></mrow></msub></mrow><mo>¯</mo></mover></semantics></math></inline-formula> of 0.9999 and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>σ</mi><mo>(</mo><mi>A</mi><mi>U</mi><msub><mi>C</mi><mrow><mi>m</mi><mi>i</mi><mi>c</mi><mi>r</mi><mi>o</mi></mrow></msub><mo>)</mo></mrow></semantics></math></inline-formula> of 0.0006. Furthermore, by applying the transfer learning approach, significant improvements in both semantic segmentation and generalization performances were achieved. For the case of the frontal plane, the highest performances were achieved if pre-trained ResNet101 architecture was used as a backbone for U-net with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mover><mrow><mi>D</mi><mi>S</mi><mi>C</mi></mrow><mo>¯</mo></mover></semantics></math></inline-formula> up to 0.9587 and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>σ</mi><mo>(</mo><mi>D</mi><mi>S</mi><mi>C</mi><mo>)</mo></mrow></semantics></math></inline-formula> of 0.0059. When U-net was used for the semantic segmentation of urinary bladder cancer masses from images in the axial plane, the best results were achieved if pre-trained ResNet50 was used as a backbone, with a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mover><mrow><mi>D</mi><mi>S</mi><mi>C</mi></mrow><mo>¯</mo></mover></semantics></math></inline-formula> up to 0.9372 and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>σ</mi><mo>(</mo><mi>D</mi><mi>S</mi><mi>C</mi><mo>)</mo></mrow></semantics></math></inline-formula> of 0.0147. Finally, in the case of images in the sagittal plane, the highest results were achieved with VGG-16 as a backbone. In this case, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mover><mrow><mi>D</mi><mi>S</mi><mi>C</mi></mrow><mo>¯</mo></mover></semantics></math></inline-formula> values up to 0.9660 with a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>σ</mi><mo>(</mo><mi>D</mi><mi>S</mi><mi>C</mi><mo>)</mo></mrow></semantics></math></inline-formula> of 0.0486 were achieved. From the listed results, the proposed semantic segmentation system worked with high performance both from the semantic segmentation and generalization standpoints. The presented results indicate that there is the possibility for the utilization of the semantic segmentation system in clinical practice. |
|---|