This paper proposes a novel noise-shaping (NS) successive approximation register (SAR) based light-to-digital converter (LDC) for continuous multi-wavelength (MW) photoplethysmogram (PPG) monitoring. The proposed NS-SAR LDC employs a single-channel current-integration (CI) SAR quantizer with a three-channel passive NS loop filter performs time-multiplexed, low-power NS readout for MWPPG. The cascade integrator feedforward NS architecture features a passive nested feedback path, which contributes one additional NS order. The LDC enables a wide dynamic range (DR) through the high signal-to-noise-and-distortion ratio (SNDR), inherent AC gain control of the proposed CI NS-SAR, and a predictive threshold filter that compensates for large DC and drifting baseline currents induced by motion artifacts and interference light. Fabricated in a 180-nm standard CMOS process, the NS-SAR LDC consumes$26.5~\mu $W while achieving a SNDR of 95 dB and a total DR of 161.5 dB. The work is validated through finger MWPPG measurements using commercial PPG sensors.

Acquiring high-quality annotated data for medical image segmentation is tedious and costly. Semi-supervised segmentation techniques alleviate this burden by leveraging unlabeled data to generate pseudo labels. Recently, advanced state space models, represented by Mamba, have shown efficient handling of long-range dependencies. This drives us to explore their potential in semi-supervised medical image segmentation. In this paper, we propose a novel Diversity-enhanced Collaborative Mamba framework (namely DCMamba) for semi-supervised medical image segmentation, which explores and utilizes the diversity from data, network, and feature perspectives. Firstly, from the data perspective, we develop patch-level weak-strong mixing augmentation with Mamba's scanning modeling characteristics. Moreover, from the network perspective, we introduce a diverse-scan collaboration module, which could benefit from the prediction discrepancies arising from different scanning directions. Furthermore, from the feature perspective, we adopt an uncertainty-weighted contrastive learning mechanism to enhance the diversity of feature representation. Experiments demonstrate that our DCMamba significantly outperforms other semi-supervised medical image segmentation methods, e.g., yielding the latest SSM-based method by 6.69% on the Synapse dataset with 20% labeled data. The code is available at https://github.com/ShumengLI/DCMamba.

This paper presents a first-order noise shaping (NS) successive approximation register (SAR) analog to digital converter (ADC) utilizing an innovative voltage controlled oscillator (VCO)-based charge-accumulation (CA) integrator. The proposed VCO-CA integrator is highly digital and dynamic, making it energy efficient and compatible with process scaling. Additionally, it can provide a highly linear gain thanks to the small amplitude of residual voltage and the proposed oscillation time control, avoiding the system nonlinearity problem in VCO-based integrators in conventional VCO-based$\mathrm {\Delta \Sigma }$ADCs. Combined with a pulse width (PW)-controlled tunable charge-accumulation circuit, it forms an active loop filter for the first-order NS-SAR ADC, resulting in an innovative fully dynamic VCO-based NS-SAR ADC that achieves a sharp noise transfer function (NTF) without any background gain calibration. The prototype ADC is implemented in a 65-nm GP CMOS process, achieving 77.7 dB SNDR and 79.9 dB DR over a bandwidth of 625 kHz. The total power consumption is$108.3~\mu $W, resulting in a Schreier figure of merit of 175.3 dB.

Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost and maintain satisfactory performance, in this work, we leverage the capabilities of SAM for establishing semi-supervised medical image segmentation models. Rethinking the requirements of effectiveness, efficiency, and compatibility, we propose a three-stage framework, i.e., Stitching, Fine-tuning, and Re-training (SFR). The current fine-tuning approaches mostly involve 2D slice-wise fine-tuning that disregards the contextual information between adjacent slices. Our stitching strategy mitigates the mismatch between natural and 3D medical images. The stitched images are then used for fine-tuning SAM, providing robust initialization of pseudo-labels. Afterwards, we train a 3D semi-supervised segmentation model while maintaining the same parameter size as the conventional segmenter such as V-Net. Our SFR framework is plug-and-play, and easily compatible with various popular semi-supervised methods. We also develop an extended framework SFR+ with selective fine-tuning and re-training through confidence estimation. Extensive experiments validate that our SFR and SFR+ achieve significant improvements in both moderate annotation and scarce annotation across five datasets. In particular, SFR framework improves the Dice score of Mean Teacher from 29.68% to 74.40% with only one labeled data of LA dataset. The code is available at https://github.com/ShumengLI/SFR.

Recent trends in semi-supervised learning have significantly boosted the performance of 3D semi-supervised medical image segmentation. Compared with 2D images, 3D medical volumes involve information from different directions, e.g., transverse, sagittal, and coronal planes, so as to naturally provide complementary views. These complementary views and the intrinsic similarity among adjacent 3D slices inspire us to develop a novel annotation way and its corresponding semi-supervised model for effective segmentation. Specifically, we firstly propose the orthogonal annotation by only labeling two orthogonal slices in a labeled volume, which significantly relieves the burden of annotation. Then, we perform registration to obtain the initial pseudo labels for sparsely labeled volumes. Subsequently, by introducing unlabeled volumes, we propose a dual-network paradigm named Dense-Sparse Co-training (DeSCO) that exploits dense pseudo labels in early stage and sparse labels in later stage and meanwhile forces consistent output of two networks. Experimental results on three benchmark datasets validated our effectiveness in performance and efficiency in annotation. For example, with only 10 annotated slices, our method reaches a Dice up to 86.93% on KiTS19 dataset. Our code and models are available at https://github.com/HengCai-NJU/DeSCO.

It is known that annotations for 3D medical image segmentation tasks are laborious, time-consuming and expensive. Considering the similarities existing in inter-slice and inter-volume, we believe that the delineation way and the model architecture should be tightly coupled. In this paper, by introducing an extremely sparse annotation way of labeling only one slice per 3D image, we investigate a novel barely-supervised segmentation setting with only a few sparsely-labeled images along with a large amount of unlabeled images. To achieve this goal, we present a new parasitic-like network including a registration module (as host) and a semi-supervised segmentation module (as parasite) to deal with inter-slice label propagation and inter-volume segmentation prediction, respectively. Specifically, our parasitism mechanism effectively achieves the collaboration of these two modules through three stages of infection, development and eclosion, providing accurate pseudo-labels for training. Extensive results demonstrate that our framework is capable of achieving high performance on extremely sparse annotation tasks, e.g., we achieve Dice of 84.83% on LA dataset with only 16 labeled slices. The code is available athttps://github.com/ShumengLI/PLN.