Automated segmentation of mouse OCT volumes (ASiMOV): Validation & clinical study of a light damage model

PseudoSegRT: efficient pseudo-labelling for intraoperative OCT segmentation

PURPOSE

Robotic ophthalmic microsurgery has significant potential to help improve the success of challenging procedures and overcome the physical limitations of the surgeon. Intraoperative optical coherence tomography (iOCT) has been reported for the visualisation of ophthalmic surgical manoeuvres, where deep learning methods can be used for real-time tissue segmentation and surgical tool tracking. However, many of these methods rely heavily on labelled datasets, where producing annotated segmentation datasets is a time-consuming and tedious task.

METHODS

To address this challenge, we propose a robust and efficient semi-supervised method for boundary segmentation in retinal OCT to guide a robotic surgical system. The proposed method uses U-Net as the base model and implements a pseudo-labelling strategy which combines the labelled data with unlabelled OCT scans during training. After training, the model is optimised and accelerated with the use of TensorRT.

RESULTS

Compared with fully supervised learning, the pseudo-labelling method can improve the generalisability of the model and show better performance for unseen data from a different distribution using only 2% of labelled training samples. The accelerated GPU inference takes less than 1 millisecond per frame with FP16 precision.

CONCLUSION

Our approach demonstrates the potential of using pseudo-labelling strategies in real-time OCT segmentation tasks to guide robotic systems. Furthermore, the accelerated GPU inference of our network is highly promising for segmenting OCT images and guiding the position of a surgical tool (e.g. needle) for sub-retinal injections.

OCT and ERG Techniques in High-Throughput Phenotyping of Mouse Vision

The purpose of the study is to demonstrate coherent optical tomography and electroretinography techniques adopted from the human clinical practice to assess the morphology and function of the mouse retina in a high-throughput phenotyping environment. We present the normal range of wild-type C57Bl/6NCrl retinal parameters in six age groups between 10 and 100 weeks as well as examples of mild and severe pathologies resulting from knocking out a single protein-coding gene. We also show example data obtained by more detailed analysis or additional methods useful in eye research, for example, the angiography of a superficial and deep vascular complex. We discuss the feasibility of these techniques in conditions demanding a high-throughput approach such as the systemic phenotyping carried out by the International Mouse Phenotyping Consortium.

Deep Learning Unlocks X-ray Microtomography Segmentation of Multiclass Microdamage in Heterogeneous Materials

Four-dimensional quantitative characterization of heterogeneous materials using in situ synchrotron radiation computed tomography can reveal 3D sub-micrometer features, particularly damage, evolving under load, leading to improved materials. However, dataset size and complexity increasingly require time-intensive and subjective semi-automatic segmentations. Here, the first deep learning (DL) convolutional neural network (CNN) segmentation of multiclass microscale damage in heterogeneous bulk materials is presented, teaching on advanced aerospace-grade composite damage using ≈65 000 (trained) human-segmented tomograms. The trained CNN machine segments complex and sparse (<<1% of volume) composite damage classes to ≈99.99% agreement, unlocking both objectivity and efficiency, with nearly 100% of the human time eliminated, which traditional rule-based algorithms do not approach. The trained machine is found to perform as well or better than the human due to "machine-discovered" human segmentation error, with machine improvements manifesting primarily as new damage discovery and segmentation augmentation/extension in artifact-rich tomograms. Interrogating a high-level network hyperparametric space on two material configurations, DL is found to be a disruptive approach to quantitative structure-property characterization, enabling high-throughput knowledge creation (accelerated by two orders of magnitude) via generalizable, ultrahigh-resolution feature segmentation.

Retinal layer segmentation in rodent OCT images: Local intensity profiles & fully convolutional neural networks

BACKGROUND AND OBJECTIVE

Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented.

METHODS

One approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture.

RESULTS

After a wide validation, an averaged absolute distance error of 3.77 ± 2.59 and 1.90 ± 0.91 µm is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 ± 1.25 µm is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons.

CONCLUSIONS

Based on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images.

Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis

The Sørensen-Dice index (SDI) is a widely used measure for evaluating medical image segmentation algorithms. It offers a standardized measure of segmentation accuracy which has proven useful. However, it offers diminishing insight when the number of objects is unknown, such as in white matter lesion segmentation of multiple sclerosis (MS) patients. We present a refinement for finer grained parsing of SDI results in situations where the number of objects is unknown. We explore these ideas with two case studies showing what can be learned from our two presented studies. Our first study explores an inter-rater comparison, showing that smaller lesions cannot be reliably identified. In our second case study, we demonstrate fusing multiple MS lesion segmentation algorithms based on the insights into the algorithms provided by our analysis to generate a segmentation that exhibits improved performance. This work demonstrates the wealth of information that can be learned from refined analysis of medical image segmentations.

Longitudinal Analysis of Mouse SDOCT Volumes

Spectral-domain optical coherence tomography (SDOCT), in addition to its routine clinical use in the diagnosis of ocular diseases, has begun to find increasing use in animal studies. Animal models are frequently used to study disease mechanisms as well as to test drug efficacy. In particular, SDOCT provides the ability to study animals longitudinally and non-invasively over long periods of time. However, the lack of anatomical landmarks makes the longitudinal scan acquisition prone to inconsistencies in orientation. Here, we propose a method for the automated registration of mouse SDOCT volumes. The method begins by accurately segmenting the blood vessels and the optic nerve head region in the scans using a pixel classification approach. The segmented vessel maps from follow-up scans were registered using an iterative closest point (ICP) algorithm to the baseline scan to allow for the accurate longitudinal tracking of thickness changes. Eighteen SDOCT volumes from a light damage model study were used to train a random forest utilized in the pixel classification step. The area under the curve (AUC) in a leave-one-out study for the retinal blood vessels and the optic nerve head (ONH) was found to be 0.93 and 0.98, respectively. The complete proposed framework, the retinal vasculature segmentation and the ICP registration, was applied to a secondary set of scans obtained from a light damage model. A qualitative assessment of the registration showed no registration failures.