Mine Your Own Anatomy: Revisiting Medical Image Segmentation With Extremely Limited Labels.

Recent studies on contrastive learning have achieved remarkable performance solely by leveraging few labels in the context of medical image segmentation. Existing methods mainly focus on instance discrimination and invariant mapping (i.e., pulling positive samples closer and negative samples apart in the feature space). However, they face three common pitfalls: (1) tailness: medical image data usually follows an implicit long-tail class distribution. Blindly leveraging all pixels in training hence can lead to the data imbalance issues, and cause deteriorated performance; (2) consistency: it remains unclear whether a segmentation model has learned meaningful and yet consistent anatomical features due to the intra-class variations between different anatomical features; and (3) diversity: the intra-slice correlations within the entire dataset have received significantly less attention. This motivates us to seek a principled approach for strategically making use of the dataset itself to discover similar yet distinct samples from different anatomical views. In this paper, we introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owNAnatomy (MONA), and make three contributions. First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features, mainly due to lacking the supervision signal. We show two simple solutions towards learning invariances-through the use of stronger data augmentations and nearest neighbors. Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features in an unsupervised manner. Lastly, we both empirically and theoretically, demonstrate the efficacy of our MONA on three benchmark datasets with different labeled settings, achieving new state-of-the-art under different labeled semi-supervised settings. MONA makes minimal assumptions on domain expertise, and hence constitutes a practical and versatile solution in medical image analysis. We provide the PyTorch-like pseudo-code in supplementary.

Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-Aware Contrastive Distillation.

Contrastive learning has shown great promise over annotation scarcity problems in the context of medical image segmentation. Existing approaches typically assume a balanced class distribution for both labeled and unlabeled medical images. However, medical image data in reality is commonly imbalanced (i.e., multi-class label imbalance), which naturally yields blurry contours and usually incorrectly labels rare objects. Moreover, it remains unclear whether all negative samples are equally negative. In this work, we present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation. Specifically, we first develop an iterative contrastive distillation algorithm by softly labeling the negatives rather than binary supervision between positive and negative pairs. We also capture more semantically similar features from the randomly chosen negative set compared to the positives to enforce the diversity of the sampled data. Second, we raise a more important question: Can we really handle imbalanced samples to yield better performance? Hence, the key innovation in ACTION is to learn global semantic relationship across the entire dataset and local anatomical features among the neighbouring pixels with minimal additional memory footprint. During the training, we introduce anatomical contrast by actively sampling a sparse set of hard negative pixels, which can generate smoother segmentation boundaries and more accurate predictions. Extensive experiments across two benchmark datasets and different unlabeled settings show that ACTION significantly outperforms the current state-of-the-art semi-supervised methods.

Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective.

For medical image segmentation, contrastive learning is the dominant practice to improve the quality of visual representations by contrasting semantically similar and dissimilar pairs of samples. This is enabled by the observation that without accessing ground truth labels, negative examples with truly dissimilar anatomical features, if sampled, can significantly improve the performance. In reality, however, these samples may come from similar anatomical regions and the models may struggle to distinguish the minority tail-class samples, making the tail classes more prone to misclassification, both of which typically lead to model collapse. In this paper, we propose ARCO, a semi-supervised contrastive learning (CL) framework with stratified group theory for medical image segmentation. In particular, we first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks with extremely limited labels. Furthermore, we theoretically prove these sampling techniques are universal in variance reduction. Finally, we experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings, and our methods consistently outperform state-of-the-art semi-supervised methods. Additionally, we augment the CL frameworks with these sampling techniques and demonstrate significant gains over previous methods. We believe our work is an important step towards semi-supervised medical image segmentation by quantifying the limitation of current self-supervision objectives for accomplishing such challenging safety-critical tasks.

Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts.

Integrating high-level semantically correlated contents and low-level anatomical features is of central importance in medical image segmentation. Towards this end, recent deep learning-based medical segmentation methods have shown great promise in better modeling such information. However, convolution operators for medical segmentation typically operate on regular grids, which inherently blur the high-frequency regions, i.e., boundary regions. In this work, we propose MORSE, a generic implicit neural rendering framework designed at an anatomical level to assist learning in medical image segmentation. Our method is motivated by the fact that implicit neural representation has been shown to be more effective in fitting complex signals and solving computer graphics problems than discrete grid-based representation. The core of our approach is to formulate medical image segmentation as a rendering problem in an end-to-end manner. Specifically, we continuously align the coarse segmentation prediction with the ambiguous coordinate-based point representations and aggregate these features to adaptively refine the boundary region. To parallelly optimize multi-scale pixel-level features, we leverage the idea from Mixture-of-Expert (MoE) to design and train our MORSE with a stochastic gating mechanism. Our experiments demonstrate that MORSE can work well with different medical segmentation backbones, consistently achieving competitive performance improvements in both 2D and 3D supervised medical segmentation methods. We also theoretically analyze the superiority of MORSE.

ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast.

Medical data often exhibits long-tail distributions with heavy class imbalance, which naturally leads to difficulty in classifying the minority classes (i.e., boundary regions or rare objects). Recent work has significantly improved semi-supervised medical image segmentation in long-tailed scenarios by equipping them with unsupervised contrastive criteria. However, it remains unclear how well they will perform in the labeled portion of data where class distribution is also highly imbalanced. In this work, we present ACTION++, an improved contrastive learning framework with adaptive anatomical contrast for semi-supervised medical segmentation. Specifically, we propose an adaptive supervised contrastive loss, where we first compute the optimal locations of class centers uniformly distributed on the embedding space (i.e., off-line), and then perform online contrastive matching training by encouraging different class features to adaptively match these distinct and uniformly distributed class centers. Moreover, we argue that blindly adopting a constant temperature τ in the contrastive loss on long-tailed medical data is not optimal, and propose to use a dynamic τ via a simple cosine schedule to yield better separation between majority and minority classes. Empirically, we evaluate ACTION++ on ACDC and LA benchmarks and show that it achieves state-of-the-art across two semi-supervised settings. Theoretically, we analyze the performance of adaptive anatomical contrast and confirm its superiority in label efficiency.

Can laparoscopic nerve-sparing ultra-radical hysterectomy play a role in locally advanced cervical cancer? A single-center retrospective study.

Background and objectives: The objective of this study is to investigate the outcomes of concurrent platinum-based chemoradiation therapy (CCRT), laparoscopic nerve-sparing ultra-radical hysterectomy (LNSURH), and open radical hysterectomy (ORH) on patients with locally advanced cervical carcinoma (LACC). Methods: A single-center retrospective study was conducted on LACC patients who received CCRT, ORH, or LNSURH from January 2011 to December 2019. Data on age, tumor size, overall survival (OS), disease-free survival (DFS), and early and late morbidities were collected. After 24 months of treatment, patients were asked a series of questions about their urinary, bowel, and sexual activities. Early morbidities were defined as those occurring during or within a month of treatment, whereas late morbidities and complications were defined as those occurring a month after treatment. The postoperative complications were classified with reference to the Clavien-Dindo classification (CD) system. Results: The Kaplan-Meier curves revealed no significant differences in OS and DFS among the three groups (P = 0.106 for DFS and P = 0.190 for OS). The rates of early complications in the CCRT group were comparable with those in the operated groups (P = 0.46). However, late complications were significantly lower in the ORH and LNSURH groups relative to those in the CCRT group. The scores of urinary and bowel functions were restored to the pretreatment state, although the sexual function scores were not satisfactory. Conclusions: The treatments of CCRT, ORH, and LNSURH can be considered options for patients with LACC, as their OS and DFS showed no significant difference. In addition, LNSURH exhibited a lower incidence of late complications and high sexual function scores.

Aptasensing luteinizing hormone to determine gynecological endocrine complications on graphene oxide layered sensor.

Luteinizing hormone (LH)/lutropin is an interstitial cell-stimulating hormone playing a predominant role in the reproductive system, and highly correlated with the infertility treatment in both men and women. This research was concentrated to quantify LH level by using interdigitated electrode sensor. To improve the electric current flow, sensing electrode was modified with graphene oxide (GO) and the aptamer probe was attached on GO through biotin-streptavidin linker. Current responses were measured with aptamer-LH interaction at the target concentrations between 7.5 nM and 1 µM and the detection limit of LH was calculated as 60 nM with the determination coefficient (R2 ) value, 0.9229 [y = 1.296x - 2.8435] on a linear range from 30 nM to 1 µM. Further, biofouling effect on sensing electrode surface was analyzed with complementary aptamer sequence, control proteins (albumin and globulin). The above GO-aptamer-modified interdigitated electrode sensor helps to quantify LH level and diagnose gynecological endocrinology-related complications.

Discontinuous growth of DNA plectonemes due to atomic scale friction.

We develop a model to explain discontinuities in the increase of the length of a DNA plectoneme when the DNA filament is continuously twisted under tension. We account for DNA elasticity, electrostatic interactions and entropic effects due to thermal fluctuation. We postulate that a corrugated energy landscape that contains energy barriers is the cause of jumps in the length of the plectoneme as the number of turns is increased. Thus, our model is similar to the Prandtl-Tomlinson model of atomic scale friction. The existence of a corrugated energy landscape can be justified due to the close proximity of the neighboring pieces of DNA in a plectoneme. We assume the corrugated energy landscape to be sinusoidal since the plectoneme has a periodic helical structure and rotation of the bead is a form of periodic motion. We perform calculations with different tensile forces and ionic concentrations, and show that rotation-extension curves manifest stair-step shapes under relatively high ionic concentrations and high forces. We show that the jump in the plectonemic growth is caused by the flattening of the energy barrier in the corrugated landscape.