Improved-Mask R-CNN: Towards an Accurate Generic MSK MRI instance segmentation platform (Data from the Osteoarthritis Initiative)

  title={Improved-Mask R-CNN: Towards an Accurate Generic MSK MRI instance segmentation platform (Data from the Osteoarthritis Initiative)},
  author={Banafsheh Felfeliyan and Abhilash Rakkunedeth Hareendranathan and Gregor Kuntze and Jacob Lester Jaremko and Janet Lenore Ronsky},
  journal={Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society},

MRI Knee Domain Translation for Unsupervised Segmentation By CycleGAN (data from Osteoarthritis initiative (OAI))

A domain adaptation (DA) framework using the CycleGAN model for MRI translation that would aid in unsupervised MRI data segmentation is proposed and is validated on five scans from the Osteoarthritis Initiative (OAI) dataset.

Self-Supervised-RCNN for Medical Image Segmentation with Limited Data Annotation

The proposed self-supervised pretraining approach first, randomly applies different distortions to random areas of unlabeled images and then predicts the type of distortions and loss of information and is simple, effective, and suitable for different ranges of medical image analysis tasks including anomaly detection, segmentation, and classification.

Weakly Supervised Medical Image Segmentation With Soft Labels and Noise Robust Loss

The results of this work suggest that the proposed normalized active-passive loss using soft labels successfully mitigated the effects of noisy labels.



Automatic Deep Learning-assisted Detection and Grading of Abnormalities in Knee MRI Studies.

Three-dimensional convolutional neural network had high sensitivity, specificity, and accuracy for knee-lesion-severity scoring and also increased intergrader agreement when used on an external dataset.

Deep Feature Learning for Knee Cartilage Segmentation Using a Triplanar Convolutional Neural Network

A novel system for voxel classification integrating three 2D CNNs, which have a one-to-one association with the xy, yz and zx planes of 3D image, respectively, which performs better than a state-of-the-art method using 3D multi-scale features.

Multiscale Mask R-CNN–Based Lung Tumor Detection Using PET Imaging

Experimental results exhibited strong conviction about the effectiveness of this method in detecting lung tumors, along with the capability of identifying a healthy chest pattern and reducing incorrect identification of tumors to a large extent.

Mask-Refined R-CNN: A Network for Refining Object Details in Instance Segmentation

The proposed Mask-Refined R-CNN (MR R- CNN) is proposed, in which the stride of ROIAlign (region of interest align) is adjusted and the original fully convolutional layer is replaced with a new semantic segmentation layer that realizes feature fusion by constructing a feature pyramid network and summing the forward and backward transmissions of feature maps of the same resolution.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Detection and classification the breast tumors using mask R-CNN on sonograms

A model for automatic detection, segmentation, and classification of breast lesions with ultrasound images based on deep learning and a technique using Mask regions with convolutional neural network was developed for lesion detection and differentiation between benign and malignant.

Computer-aided method for quantification of cartilage thickness and volume changes using MRI: validation study using a synthetic model

A local coordinate system for the femoral and tibial cartilage boundaries that provides a standardized representation of cartilage geometry, thickness, and volume is introduced and is well suited for in vivo follow-up clinical studies of OA knees.

Performance of a Deep Learning Algorithm for Automated Segmentation and Quantification of Traumatic Pelvic Hematomas on CT

A modified coarse-to-fine deep learning approach—the Recurrent Saliency Transformation Network (RSTN) for pelvic hematoma volume segmentation yielded excellent results in pancreas segmentation, where low contrast with adjacent structures, small target volume, variable location, and fine contours are also problematic.