Breast Cancer: Model Reconstruction and Image Registration From Segmented Deformed Image Using Visual and Force Based Analysis

Abstract

Breast lesion localization using tactile imaging is a new and developing direction in medical science. To achieve the goal, proper image reconstruction and image registration can be a valuable asset. In this paper, a new approach of the segmentation-based image surface reconstruction algorithm is used to reconstruct the surface of a breast phantom. In breast tissue, the sub-dermal vein network is used as a distinguishable pattern for reconstruction. The proposed image capturing device contacts the surface of the phantom, and surface deformation will occur due to applied force at the time of scanning. A novel force based surface rectification system is used to reconstruct a deformed surface image to its original structure. For the construction of the full surface from rectified images, advanced affine scale-invariant feature transform (A-SIFT) is proposed to reduce the affine effect in time when data capturing. Camera position based image stitching approach is applied to construct the final original non-rigid surface. The proposed model is validated in theoretical models and real scenarios, to demonstrate its advantages with respect to competing methods. The result of the proposed method, applied to path reconstruction, ends with a positioning accuracy of 99.7%.Index Terms-Breast cancer, medical imaging, affine scaleinvariant feature transform (A-SIFT), structure from motion (SfM), force deformation.

Tactile, Orientation, and Optical Sensor Fusion for Tactile Breast Image Mosaicking

“…This idea has been investigated [21], using the vein network of the breast as a reference structure and an integrated infrared (IR) camera for tracking [22], which drew parallels with other works where IR was used for tumor monitoring during chemotherapy [23]. This method was effective in forming a coherent vein structure image, but was not suitable for mosaicking tactile images due to low tactile resolution.…”

“…It is a key challenge in this area to produce an undeformed structure that can be referenced between scans, effectively removing the effect of the tactile imaging process on the breast vein structure. There have been several solutions proposed to this, not just in vein reconstruction but in wider deformable imaging, including: using finite element modelling (FEM) [24] to model deformation, shape from template (SFT) [25] to map images to a known template, structure from motion (SFM) [26] with high affine tolerance matching algorithms [27] or global optimization [28], and using elastic force based deformation approximation [21]. Detailed reviews discuss these [29], however the key takeaway is that authors are faced with a tradeoff between reconstruction accuracy and execution speed with simpler models being suitable for real-time operation [21], and more complex models that may offer better initial deformation reduction only being suitable for post processing activities.…”

Micro Calcification Detection in Mammogram Images Using Contiguous Convolutional Neural Network Algorithm

“…The image is separated into the areola by Srinivasan et al 2014, Zhoupp et al 2015, Kostopoulos et al 2007 of the four focus associated with four different quadrants. A positive estrogen receptor evaluation utilizing a color texture characteristic on IHC images the computer method for determining positive ER receptor status consists of two stages: stage I is nucleus segmentation using Otsu's global image threshold method and morphology operation, and stage II is nucleus classification based on brown and blue color using feature selection and K-Nearest Neighbors weighted averages Bozkurt et [22][23][24][25][26][27][28][29][30].…”

Elementary Methods for Generating Three-Dimensional Coordinate Estimation and Image Reconstruction from Series of Two-Dimensional Images

“…Augmented reality and virtual reality applications are the most commonly observed examples for the same. Off-site controlling and demo of technical work, tutorials for equipment or simulation of medical operations, guides to fit components, and so on [8,9] are some examples. Such generated three-dimensional models play an important role also in multimedia applications where the mock of objects is used.…”