Proposal-Based Instance Segmentation With Point Supervision

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

Rodríguez

Mañas

et al. 2021

Self Cite

Coronavirus Disease 2019 has spread aggressively across the world causing an existential health crisis. Thus, having a system that automatically detects COVID-19 in tomography (CT) images can assist in quantifying the severity of the illness. Unfortunately, labelling chest CT scans requires significant domain expertise, time, and effort. We address these labelling challenges by only requiring point annotations, a single pixel for each infected region on a CT image. This labeling scheme allows annotators to label a pixel in a likely infected region, only taking 1-3 seconds, as opposed to 10-15 seconds to segment a region. Conventionally, segmentation models train on point-level annotations using the crossentropy loss function on these labels. However, these models often suffer from low precision. Thus, we propose a consistency-based (CB) loss function that encourages the output predictions to be consistent with spatial transformations of the input images. The experiments on 3 open-source COVID-19 datasets show that this loss function yields significant improvement over conventional pointlevel loss functions and almost matches the performance of models trained with full supervision with much less human effort.

Section: Related Workmentioning

confidence: 99%

A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

Rodríguez

Mañas

et al. 2021

Self Cite

“…4). While LCFCN was originally designed for counting, it is also able to locate objects and segment them [38]- [42], by refining the activation output that determines the likelihood of a pixel belonging to the localization or segmentation target. In our localization task, we obtain per-pixel probabilities by applying the Softmax activation function to computeŶ , which contains the likelihood that a pixel either belongs to the background or muscle edge.…”

Section: Lcfcn Lossmentioning

confidence: 99%

A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Images

Saleh

IEEE J. Biomed. Health Inform.

Lammie

et al. 2021

Self Cite

Health professionals extensively use Two-Dimensional (2D) Ultrasound (US) videos and images to visualize and measure internal organs for various purposes including evaluation of muscle architectural changes. US images can be used to measure abdominal muscles dimensions for the diagnosis and creation of customized treatment plans for patients with Low Back Pain (LBP), however, they are difficult to interpret. Due to high variability, skilled professionals with specialized training are required to take measurements to avoid low intra-observer reliability. This variability stems from the challenging nature of accurately finding the correct spatial location of measurement endpoints in abdominal US images. In this paper, we use a Deep Learning (DL) approach to automate the measurement of the abdominal muscle thickness in 2D US images. By treating the problem as a localization task, we develop a modified Fully Convolutional Network (FCN) architecture to generate blobs of coordinate locations of measurement endpoints, similar to what a human operator does. We demonstrate that using the TrA400 US image dataset, our network achieves a Mean Absolute Error (MAE) of 0.3125 on the test set, which almost matches the performance of skilled ultrasound technicians. Our approach can facilitate next steps for automating the process of measurements in 2D US images, while reducing inter-observer as well as intra-observer variability for more effective clinical outcomes.

“…In this work, we use point-level annotations since they require a similar acquisition time as image-level annotations, while significantly boosting the segmentation performance 4 . Unfortunately, methods that use point-level supervision either need training a proposal network 33 or tend to output large blobs that do not conform to the segmentation boundaries 4 . Thus, these methods are not well suited to images with objects of specific boundaries like fish.…”

Section: Full Supervision (Conventional)mentioning

confidence: 99%

Weakly Supervised Underwater Fish Segmentation Using Affinity LCFCN

Saleh

Rodríguez

et al. 2021

Preprint

Self Cite

Estimating fish body measurements like length, width, and mass has received considerable research due to its potential in boosting productivity in marine and aquaculture applications. Some methods are based on manual collection of these measurements using tools like a ruler which is time consuming and labour intensive. Others rely on fully-supervised segmentation models to automatically acquire these measurements but require collecting per-pixel labels which are also time consuming. It can take up to 2 minutes per fish to acquire accurate segmentation labels. To address this problem, we propose a segmentation model that can efficiently train on images labeled with point-level supervision, where each fish is annotated with a single click. This labeling scheme takes an average of only 1 second per fish. Our model uses a fully convolutional neural network with one branch that outputs per-pixel scores and another that outputs an affinity matrix. These two outputs are aggregated using a random walk to get the final, refined per-pixel output. The whole model is trained end-to-end using the LCFCN loss and thus we call our method Affinity-LCFCN (A-LCFCN). We conduct experiments on the DeepFish dataset, which contains several fish habitats from north-eastern Australia. The results show that A-LCFCN outperforms a fully-supervised segmentation model when the annotation budget is fixed. They also show that A-LCFCN achieves better segmentation results than LCFCN and a standard baseline.