Breast tumor segmentation in medical images is a decisive step for diagnosis and treatment follow-up. Automating this challenging task helps radiologists to reduce the high manual workload of breast cancer analysis. In this paper, we propose two deep learning approaches to automate the breast tumor segmentation in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) by building two fully convolutional neural networks (CNN) based on SegNet and U-Net. The obtained models can handle both detection and segmentation on each single DCE-MRI slice. In this study, we used a dataset of 86 DCE-MRIs, acquired before and after two cycles of chemotherapy, of 43 patients with local advanced breast cancer, a total of 5452 slices were used to train and validate the proposed models. The data were annotated manually by an experienced radiologist. To reduce the training time, a high-performance architecture composed of graphic processing units was used. The model was trained and validated, respectively, on 85% and 15% of the data. A mean intersection over union (IoU) of 68.88 was achieved using SegNet and 76.14% using U-Net architecture.

An automated vertebral identification method was developed and demonstrated to be robust to noise and occlusion. This work presents a first step toward an automated computer-aided diagnosis system for cervical spine trauma detection.

No abstract

Vertebra detection presents the first step of any automatic spinal column diagnosis. This task becomes more difficult in the case of the cervical X-ray images characterized by their low contrasts and noise due to skull bones. In this paper, we describe an efficient modified template matching method for detecting cervical vertebrae using Generalized Hough Transform (GHT). The proposed method consists of three main steps toward vertebrae detection: 1) Offline training to obtain a robust average model of cervical vertebra. 2) Detecting the potential vertebra centers. 3) Adaptive Post-processing filter.X-ray Image data of 40 healthy cases were used to validate our approach by using a total of 200 cervical vertebrae. We obtained an accuracy of 89%.

No abstract