In histopathology, tissue sections are typically stained using common H&E staining or special stains (MAS, PAS, PASM, etc. ) to clearly visualize specific tissue structures. The rapid advancement of deep learning offers an effective solution for generating virtually stained images, significantly reducing the time and labor costs associated with traditional histochemical staining. However, a new challenge arises in separating the fundamental visual characteristics of tissue sections from the visual differences induced by staining agents. Additionally, virtual staining often overlooks essential pathological knowledge and the physical properties of staining, resulting in only style-level transfer. To address these issues, we introduce, for the first time in virtual staining tasks, a pathological vision-language large model (VLM) as an auxiliary tool. We integrate contrastive learnable prompts, foundational concept anchors for tissue sections, and staining-specific concept anchors to leverage the extensive knowledge of the pathological VLM. This approach is designed to describe, frame, and enhance the direction of virtual staining. Furthermore, we have developed a data augmentation method based on the constraints of the VLM. This method utilizes the VLM's powerful image interpretation capabilities to further integrate image style and structural information, proving beneficial in high-precision pathological diagnostics. Extensive evaluations on publicly available multi-domain unpaired staining datasets demonstrate that our method can generate highly realistic images and enhance the accuracy of downstream tasks, such as glomerular detection and segmentation. Our code. https://github.com/CZZZZZZZZZZZZZZZZZ/VPGAN-HARBOR is available.

The segmentation of liver tumors using multi-phase computed tomography (CT) images has garnered considerable attention in medical signal processing. However, existing multi-phase liver tumor segmentation methods primarily concentrate on feature integration across various phases, neglecting a comprehensive exploration of synergistic relationships among these phases and constraints on features across different scales. This limitation has led to performance bottlenecks in existing approaches. This article proposes a robust multi-phase liver tumor segmentation framework designed to address the aforementioned challenges. Specifically, we introduce a novel multi-phase and channel-stacked dual attention module, seamlessly integrated within a multi-scale architecture. This module adaptively captures essential semantic information among different phases, enhancing the segmentation network's feature extraction capabilities. A scale-weighted loss function for multi-scale supervision is also designed to mitigate false positives in the segmentation results. To facilitate a systematic evaluation of our model's performance on multi-phase data, we curate a new dataset comprising samples from four distinct phases. Our proposed framework is rigorously assessed through comprehensive quantitative and qualitative experiments, highlighting its compelling performance.

Low-dose CT has been a key diagnostic imaging modality to reduce the potential risk of radiation overdose to patient health. Despite recent advances, CNN-based approaches typically apply filters in a spatially invariant way and adopt similar pixel-level losses, which treat all regions of the CT image equally and can be inefficient when fine-grained structures coexist with non-uniformly distributed noises. To address this issue, we propose a Structure-preserving Kernel Prediction Network (StructKPN) that combines the kernel prediction network with a structure-aware loss function that utilizes the pixel gradient statistics and guides the model towards spatially-variant filters that enhance noise removal, prevent over-smoothing and preserve detailed structures for different regions in CT imaging. Extensive experiments demonstrated that our approach achieved superior performance on both synthetic and non-synthetic datasets, and better preserves structures that are highly desired in clinical screening and low-dose protocol optimization.

The discrete-time amplifier has the property of sample and hold, thus it is difficult to adopt local feedback method to deal with offset and flicker noise. A calibration-free swap-combine noise cancellation technique is proposed to remove the input-pair-introduced mismatch in discrete-time amplifiers with keeping the same external interface so it can directly replace the original amplifier. The proposed method can eliminate the flicker noise by modifying the noise transfer function, as well as achieve significant offset suppression. Simulation of a prototype shows that it can reduce the offset root mean square from 10mV to 0.25mV. Benefiting from avoiding calibration loops, the proposed method can also deal with input common-mode voltage variation and temperature drift, as well as reducing the calibration area cost and initial delay.

A low power column parallel single-slope ADC with power supply noise suppression for CMOS image sensors is proposed. The ADC is composed of a dynamic bias comparator and a novel up/down double-data-rate (DDR) counter in the column. The column ADCs are divided into groups and several control signals are delayed by groups to avoid transient large current from source. A 12-bit current steering DAC with 2-dimension gradient error tolerant switching scheme is adopted as the ramp generator to improve the linearity of the ADC. The proposed techniques are experimentally verified in a prototype chip fabricated in the TSMC 180nm CMOS process. A single-column ADC consumes a total power of 63.2μW and occupies an area of 4.48μm × 310μm. The measured DNL and INL of the ADC are -0.43/+0.46 LSB and -0.84/1.95 LSB.