Computer-aided Diagnosis Research Articles

Medical Image Segmentation

Medical image segmentation is a critical component in the development of computer-aided diagnosis and treatment planning systems. This paper provides a comprehensive survey of recent advances in segmentation techniques applied to various imaging modalities, including Magnetic Resonance Imaging (MRI). Traditional methods such as thresholding, region-growing, and active contours are reviewed alongside contemporary machine learning-based approaches, particularly deep learning models. The survey emphasizes the growing dominance of convolutional neural networks (CNNs) and their variants, including U-Net and Fully Convolutional Networks (FCNs), which have shown remarkable success in handling complex medical imaging challenges. Additionally, the paper discusses hybrid methods that combine classical techniques with artificial intelligence to improve accuracy and robustness in segmentation tasks. Key challenges such as class imbalance, boundary delineation, and computational efficiency are also highlighted. Future directions, including the integration of multi-modal data and advancements in self-supervised learning, are explored as potential solutions to overcome current limitations in medical image segmentation.

Computer-aided diagnosis for China-Japan Friendship Hospital classification of necrotic femurs using statistical shape and appearance model based on CT scans.

The purpose of this study is to quantify the three-dimensional (3D) structural morphology, bone mineral density (BMD) distribution, and mechanical properties of different China-Japan Friendship Hospital (CJFH) classification types and assist clinicians in classifying necrotic femurs accurately. In this study, 41 cases were classified as types L2 and L3 based on CT images. Then, 3D Statistical Shape and Appearance Models (SSM and SAM) were established, and 80 principal component (PC) modes were extracted from the SSM and SAM as the candidate features. The bone strength of each case was also calculated as the candidate feature using finite element analysis (FEA). Support vector machine (SVM) and Extreme Gradient Boosting (XGBoost) were used to establish 10 machine learning models. Feature selection methods were used to screen the candidate features. The performance of each model was evaluated based on sensitivity, specificity, accuracy, and the area under the receiver operating characteristic (ROC) curve. This resulted in a SVM model for CJFH classification with the performance: accuracy of 87.5%, sensitivity of 85.0%, specificity of 76.0%, and AUC of 94.2%. This study provided effective machine learning models for assisting in diagnosing CJFH types, increasing the objectivity of the diagnosis. They may have great potential for application in clinical assessments of CJFH classification.

Automatic Diagnosis of Sleep Apnea and Its Type Using Linear Discriminant Analysis and Support Vector Machine Based on the Characteristics of Two ECG and PPG Signals

Automatic Diagnosis of Sleep Apnea and Its Type Using Linear Discriminant Analysis and Support Vector Machine Based on the Characteristics of Two ECG and PPG Signals

Dual-Attention Multiple Instance Learning Framework for Pathology Whole-Slide Image Classification

Conventional methods for tumor diagnosis suffer from two inherent limitations: they are time-consuming and subjective. Computer-aided diagnosis (CAD) is an important approach for addressing these limitations. Pathology whole-slide images (WSIs) are high-resolution tissue images that have made significant contributions to cancer diagnosis and prognosis assessment. Due to the complexity of WSIs and the availability of only slide-level labels, multiple instance learning (MIL) has become the primary framework for WSI classification. However, most MIL methods fail to capture the interdependence among image patches within a WSI, which is crucial for accurate classification prediction. Moreover, due to the weak supervision of slide-level labels, overfitting may occur during the training process. To address these issues, this paper proposes a dual-attention-based multiple instance learning framework (DAMIL). DAMIL leverages the spatial relationships and channel information between WSI patches for classification prediction, without detailed pixel-level tumor annotations. The output of the model preserves the semantic variations in the latent space, enhances semantic disturbance invariance, and provides reliable class identification for the final slide-level representation. We validate the effectiveness of DAMIL on the most commonly used public dataset, Camelyon16. The results demonstrate that DAMIL outperforms the state-of-the-art methods in terms of classification accuracy (ACC), area under the curve (AUC), and F1-Score. Our model also allows for the examination of its interpretability by visualizing the dual-attention weights. To the best of our knowledge, this is the first attempt to use a dual-attention mechanism, considering both spatial and channel information, for whole-slide image classification.

Computer-Aided Diagnosis of Early-Stage Retinopathy of Prematurity in Neonatal Fundus Images Using Artificial Intelligence.

Retinopathy of Prematurity (ROP) is a retinal disorder affecting preterm babies, which can lead to permanent blindness without treatment. Early-stage ROP diagnosis is vital in providing optimal therapy for the neonates. The proposed study predicts early-stage ROP from neonatal fundus images using Machine Learning (ML) classifiers and Convolution Neural Networks (CNN) based pre-trained networks. The characteristic demarcation lines and ridges in early stage ROP are segmented utilising a novel Swin U-Net. 2000 Scale Invariant Feature Transform (SIFT) descriptors were extracted from the segmented ridges and are dimensionally reduced to 50 features using Principal Component Analysis (PCA). Seven ROP-specific features, including six Gray Level Co-occurrence Matrix (GLCM) and ridge length features, are extracted from the segmented image and are fused with the PCA reduced 50 SIFT features. Finally, three ML classifiers, such as Support Vector Machine (SVM), Random Forest (RF), and k- Nearest Neighbor (k-NN), are used to classify the 50 features to predict the early-stage ROP from Normal images. On the other hand, the raw retinal images are classified directly into normal and early-stage ROP using six pre-trained classifiers, namely ResNet50, ShuffleNet V2, EfficientNet, MobileNet, VGG16, and DarkNet19. It is seen that the ResNet50 network outperformed all other networks in predicting early-stage ROP with 89.5% accuracy, 87.5% sensitivity, 91.5% specificity, 91.1% precision, 88% NPV and an Area Under the Curve (AUC) of 0.92. Swin U-Net Convolutional Neural Networks (CNN) segmented the ridges and demarcation lines with an accuracy of 89.7% with 80.5% precision, 92.6% recall, 75.76% IoU, and 0.86 as the Dice coefficient. The SVM classifier using the 57 features from the segmented images achieved a classification accuracy of 88.75%, sensitivity of 90%, specificity of 87.5%, and an AUC of 0.91. The system can be utilised as a point-of-care diagnostic tool for ROP diagnosis of neonates in remote areas.

Deep learning-based Covid-19 diagnosis: a thorough assessment with a focus on generalization capabilities

The Covid-19 pandemic has significantly spurred the development of deep learning (DL) models for the pathology automatic diagnosis based on CT scan images. However, the assumption about the generalization of the proposed models remains to be assessed and shown for concrete clinical use. In this work, we have investigated the real value of widely used public datasets for the elaboration of DL models that are dedicated to automatic diagnosis of Covid-19 using CT scans. We have collected various international public datasets from 13 countries. Different Convolutional Neural Networks (CNNs) have been trained and their performances carefully assessed. Two evaluations have been conducted: (1) an internal evaluation following a cross-validation procedure, and (2) an external evaluation on real patients coming from new and different sources. The objective is to assess the generalization capabilities considering real-world conditions: different acquisition conditions, devices and configurations. Three families from the most effective CNN models have been selected (ResNet, DenseNet and EfficientNet). These have been fine-tuned, evaluated and used within a training methodology based on transfer learning. The most effective models have been further customized in order to create new models that are dedicated to the task at hand. These models have significantly improved the diagnosis performance.

An open codebase for enhancing transparency in deep learning-based breast cancer diagnosis utilizing CBIS-DDSM data

Accessible mammography datasets and innovative machine learning techniques are at the forefront of computer-aided breast cancer diagnosis. However, the opacity surrounding private datasets and the unclear methodology behind the selection of subset images from publicly available databases for model training and testing, coupled with the arbitrary incompleteness or inaccessibility of code, markedly intensifies the obstacles in replicating and validating the model's efficacy. These challenges, in turn, erect barriers for subsequent researchers striving to learn and advance this field. To address these limitations, we provide a pilot codebase covering the entire process from image preprocessing to model development and evaluation pipeline, utilizing the publicly available Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) mass subset, including both full images and regions of interests (ROIs). We have identified that increasing the input size could improve the detection accuracy of malignant cases within each set of models. Collectively, our efforts hold promise in accelerating global software development for breast cancer diagnosis by leveraging our codebase and structure, while also integrating other advancements in the field.

Development of the continuous ambulatory vestibular assessment (CAVA) system to provide an automatic diagnosis for vestibular conditions: protocol for a multicentre, single-arm, non-randomised clinical trial

IntroductionDizziness is a common symptom that can occur in an unpredictable and episodic manner leading to the imprecise reporting of symptoms. Patients will often see many specialists before receiving a...

Study on artificial intelligence recognition pre-processing algorithm for cervical cancer

INTRODUCTION: Cervical cancer is the most common malignant tumor in the female reproductive system, with the number of deaths due to cervical cancer in developing countries accounting for 80% of the global total. In China, the incidence rate of cervical cancer is increasing year by year. At present, the commonly used methods for cervical cancer screening include TCT, HPV testing, TCT+HPV combined testing, FRD, and VIA/VILI. Among them, although TCT+HPV combined testing has high sensitivity and specificity, it is costly and time-consuming. VIA/VILI screening is cost-effective, easy to operate, and suitable for promotion in economically underdeveloped areas.However, VIA/VILI screening relies on the subjective judgment of doctors, so its accuracy is relatively low in rural areas of China with a large population and a lack of well-trained doctors. To address this issue, computer-aided diagnosis (CAD) technology is needed to improve the accuracy and reliability of VIA/VILI screening. OBJECTIVES: The implementation of artificial intelligence (AI)-based Visual Inspection with Acetic acid (VIA) screening and computer-aided diagnosis has the potential to significantly reduce the cost of cervical cancer screenings and increase the coverage rate of cervical cancer screenings, thus reducing the incidence rate of the disease. To this end, we have developed an AI preprocessing algorithm aimed at improving the accuracy of AI in detecting cervical cancer. METHODS: Initially, the algorithm maps images to the YCrCb and Lab color spaces. Unlike traditional enhancement methods that mainly focus on the luminance channel, our method primarily enhances the Cr channel in the YCrCb color space and a channel in the Lab color space. This paper innovatively proposes the LT_CLAHE algorithm to enhance the Cr channel, obtaining an enhanced image with a bias towards blue-green colors, and uses the WLS algorithm to enhance the a channel, obtaining an enhanced image with a bias towards red colors. Subsequently, the enhanced images from both color spaces are fused to eliminate color distortion. RESULTS: Experimental results show that our method significantly enhances the texture of lesions and outperforms traditional methods across various objective indicators. When the enhanced images from this paper are used as input for neural networks, there is also a significant increase in the accuracy of neural network detection.

CAD-PsorNet: deep transfer learning for computer-assisted diagnosis of skin psoriasis

Psoriasis, being a chronic, inflammatory, lifelong skin disorder, has become a major threat to the human population. The precise and effective diagnosis of psoriasis continues to be difficult for clinicians due to its varied nature. In northern India, the prevalence of psoriasis among adult population ranges from 0.44 to 2.8%. Chronic plaque psoriasis accounts for over 90% of cases. This study utilized a dataset of 325 raw images collected from a reputable local hospital using a digital camera under uniform lighting conditions. These images were processed to generate 496 image patches (both diseased and normal), which were then normalized and resized for model training. An automated psoriasis image recognition framework was developed using four state-of-the-art deep transfer learning models: VGG16, VGG19, MobileNetV1, and ResNet-50. The convolutional layers adopted various edge, shape, and color filters to generate the feature map for psoriasis detection. Each pre-trained model was adapted with two dense layers, one dropout layer, and one output layer to classify input images. Among these models, MobileNetV1 achieved the best performance, with 94.84% sensitivity, 89.37% specificity, and 97.24% overall accuracy. Hyper-parameter tuning was performed using grid search to optimize learning rates, batch sizes, and dropout rates. The AdaGrad (Adaptive gradient)) optimizer was chosen for its adaptive learning rate capabilities, facilitating quicker convergence in model performance. Consequently, the methodology’s performance improved to 94.25% sensitivity, 96.42% specificity, and 99.13% overall accuracy. The model’s performance was also compared with non-machine learning-based diagnostic methods, yielding a Dice coefficient of 0.98. However, the model’s effectiveness is dependent upon high-quality input images, as poor image conditions may affect accuracy, and it may not generalize well across diverse demographics or psoriasis variations, highlighting the need for varied training datasets for robustness.

Differences in regions of interest to identify deeply invasive colorectal cancers: Computer-aided diagnosis vs expert endoscopists.

Background and study aims Diagnostic performance of a computer-aided diagnosis (CAD) system for deep submucosally invasive (T1b) colorectal cancer was excellent, but the "regions of interest" (ROI) within images are not obvious. Class activation mapping (CAM) enables identification of the ROI that CAD utilizes for diagnosis. The purpose of this study was a quantitative investigation of the difference between CAD and endoscopists. Patients and methods Endoscopic images collected for validation of a previous study were used, including histologically proven T1b colorectal cancers (n = 82; morphology: flat 36, polypoid 46; median maximum diameter 20 mm, interquartile range 15-25 mm; histological subtype: papillary 5, well 51, moderate 24, poor 2; location: proximal colon 26, distal colon 27, rectum 29). Application of CAM was limited to one white light endoscopic image (per lesion) to demonstrate findings of T1b cancers. The CAM images were generated from the weights of the previously fine-tuned ResNet50. Two expert endoscopists depicted the ROI in identical images. Concordance of the ROI was rated by intersection over union (IoU) analysis. Results Pixel counts of ROIs were significantly lower using 165K[x103] [108K-227K] than by endoscopists (300K [208K-440K]; P < 0.0001) and median [interquartile] of the IoU was 0.198 [0.024-0.349]. IoU was significantly higher in correctly identified lesions (n = 54, 0.213 [0.116-0.364]) than incorrect ones (n=28, 0.070 [0.000-0.2750, P = 0.033). Concusions IoU was larger in correctly diagnosed T1b colorectal cancers. Optimal annotation of the ROI may be the key to improving diagnostic sensitivity of CAD for T1b colorectal cancers.

Automated lung cancer detection using novel genetic TPOT feature optimization with deep learning techniques

Automated lung cancer detection using novel genetic TPOT feature optimization with deep learning techniques

Deep Learning and Handcrafted Features for Thyroid Nodule Classification

ABSTRACTIn this research, we present a refined image‐based computer‐aided diagnosis (CAD) system for thyroid cancer detection using ultrasound imagery. This system integrates a specialized convolutional neural network (CNN) architecture designed to address the unique aspects of thyroid image datasets. Additionally, it incorporates a novel statistical model that utilizes a two‐dimensional random coefficient autoregressive (2D‐RCA) method to precisely analyze the textural characteristics of thyroid images, thereby capturing essential texture‐related information. The classification framework relies on a composite feature vector that combines deep learning features from the CNN and handcrafted features from the 2D‐RCA model, processed through a support vector machine (SVM) algorithm. Our evaluation methodology is structured in three phases: initial assessment of the 2D‐RCA features, analysis of the CNN‐derived features, and a final evaluation of their combined effect on classification performance. Comparative analyses with well‐known networks such as VGG16, VGG19, ResNet50, and AlexNet highlight the superior performance of our approach. The outcomes indicate a significant enhancement in diagnostic accuracy, achieving a classification accuracy of 97.2%, a sensitivity of 84.42%, and a specificity of 95.23%. These results not only demonstrate a notable advancement in the classification of thyroid nodules but also establish a new standard in the efficiency of CAD systems.

Integrating VGG 19 U‐Net for Breast Thermogram Segmentation and Hybrid Enhancement With Optimized Classifier Selection: A Novel Approach to Breast Cancer Diagnosis

ABSTRACTEarly diagnosis of breast cancer is essential for improving patient survival rates and reducing treatment costs. Despite breast thermogram images having high quality, doctors in developing countries often struggle with early diagnosis due to difficulties in interpreting subtle details. Implementing a Computer‐Aided Diagnosis (CAD) system can assist doctors in accurately analyzing these details. This article presents an innovative approach to breast cancer diagnosis using thermal images. The proposed method enhances the quality and clarity of relevant features while preserving sharp and curved edges through U‐Net‐based segmentation for automatic selection of the ROI, advanced hybrid image enhancement techniques, and a machine learning classifier. Subjective analysis compares the processed images with five conventional enhancement techniques, demonstrating the efficiency of the proposed method. The quantitative analysis further validates the effectiveness of the proposed method against five conventional methods using four quality measures. The proposed method achieves superior performance with PSNR of 15.27 for normal and 14.31 for malignant images, AMBE of 6.594 for normal and 7.46 for malignant images, SSIM of 0.829 for normal and 0.80 for malignant images, and DSSIM of 0.084 for normal and 0.14 for malignant images. The classification phase evaluates four classifiers using 13 features from three categories. The Random Forest (RF) classifier with Discrete Wavelet Transform (DWT) based features initially outperformed other classifier features but had limited performance, with accuracy, sensitivity and specificity of 81.8%, 88.8%, and 91%, respectively. To improve this, three categories of features were normalized and converted into two principal components using Principal Component Analysis (PCA) to train the RF classifier, which then showed superior performance with 97.7% accuracy, 96.5% sensitivity, and 98.2% specificity. The dataset utilized in this article is obtained from the Indira Gandhi Centre for Atomic Research (IGCAR), Kalpakkam, India. The entire proposed model is implemented in a Jupyter notebook.

ChatCAD+: Toward a Universal and Reliable Interactive CAD Using LLMs.

The integration of Computer-Aided Diagnosis (CAD) with Large Language Models (LLMs) presents a promising frontier in clinical applications, notably in automating diagnostic processes akin to those performed by radiologists and providing consultations similar to a virtual family doctor. Despite the promising potential of this integration, current works face at least two limitations: (1) From the perspective of a radiologist, existing studies typically have a restricted scope of applicable imaging domains, failing to meet the diagnostic needs of different patients. Also, the insufficient diagnostic capability of LLMs further undermine the quality and reliability of the generated medical reports. (2) Current LLMs lack the requisite depth in medical expertise, rendering them less effective as virtual family doctors due to the potential unreliability of the advice provided during patient consultations. To address these limitations, we introduce ChatCAD+, to be universal and reliable. Specifically, it is featured by two main modules: (1) Reliable Report Generation and (2) Reliable Interaction. The Reliable Report Generation module is capable of interpreting medical images from diverse domains and generate high-quality medical reports via our proposed hierarchical in-context learning. Concurrently, the interaction module leverages up-to-date information from reputable medical websites to provide reliable medical advice. Together, these designed modules synergize to closely align with the expertise of human medical professionals, offering enhanced consistency and reliability for interpretation and advice. The source code is available at GitHub.

Clustering classifier of FRP strengthened concrete beams using superpixels and principal component analysis

Nowadays, the application of Fiber Reinforced Polymer (FRP) materials in concrete structures is more and more extended because of their advantages. However, premature and brittle failure caused by debonding of FRP materials from the concrete surface may be critical and needs to be detected at its earliest stages to avoid possible catastrophic events. Digital image correlation (DIC) has been used in the past for the detection of abnormalities from surface digital images. In this work, an efficient computer-aided diagnosis (CAD) system for damage identification for this type of FRP strengthening is developed. It is based on the combination of cells of strain maps built with a DIC system and an automated clustering classifier optimized with the use of superpixels and principal component analysis. Additionally, preprocessing of the images is also done with some filters to enhance the accuracy of the methodology. The procedure has been validated with experimental results on a progressively damaged FRP externally strengthened beam. Results show that the proposed detection scheme achieves an effective automated classification method for the damage detection of this kind of strengthened specimens. Furthermore, the optimal choice of the subset size, number of superpixels and principal components contributed to the success of the method. Simultaneously, an attempt to quantify damage from the proposed method and its validation with electromechanical impedance method has been developed.

Vocal cord anomaly detection based on Local Fine-Grained Contour Features

Laryngoscopy is a popular examination for vocal cord disease diagnosis. The conventional screening of laryngoscopic images is labor-intensive and depends heavily on the experience of the medical specialists. Automatic detection of vocal cord diseases from laryngoscopic images is highly sought to assist regular image reading. In laryngoscopic images, the symptoms of vocal cord diseases are concentrated in the inner vocal cord contour, which is often characterized as vegetation and small protuberances. The existing classification methods pay little, if any, attention to the role of vocal cord contour in the diagnosis of vocal cord diseases and fail to effectively capture the fine-grained features. In this paper, we propose a novel Local Fine-grained Contour Feature extraction method for vocal cord anomaly detection. Our proposed method consists of four stages: image segmentation to obtain the overall vocal cord contour, inner vocal cord contour isolation to obtain the inner contour curve by comparing the changes of adjacent pixel values, extraction of the latent feature in the inner vocal cord contour by taking the tangent inclination angle of each point on the contour as the latent feature, and the classification module. Our experimental results demonstrate that the proposed method improves the detection performance of vocal cord anomaly and achieves an accuracy of 97.21%.

Positional encoding-guided transformer-based multiple instance learning for histopathology whole slide images classification

Background and objectives:Whole slide image (WSI) classification is of great clinical significance in computer-aided pathological diagnosis. Due to the high cost of manual annotation, weakly supervised WSI classification methods have gained more attention. As the most representative, multiple instance learning (MIL) generally aggregates the predictions or features of the patches within a WSI to achieve the slide-level classification under the weak supervision of WSI labels. However, most existing MIL methods ignore spatial position relationships of the patches, which is likely to strengthen the discriminative ability of WSI-level features. Methods:In this paper, we propose a novel positional encoding-guided transformer-based multiple instance learning (PEGTB-MIL) method for histopathology WSI classification. It aims to encode the spatial positional property of the patch into its corresponding semantic features and explore the potential correlation among the patches for improving the WSI classification performance. Concretely, the deep features of the patches in WSI are first extracted and simultaneously a position encoder is used to encode the spatial 2D positional information of the patches into the spatial-aware features. After incorporating the semantic features and spatial embeddings, multi-head self-attention (MHSA) is applied to explore the contextual and spatial dependencies of the fused features. Particularly, we introduce an auxiliary reconstruction task to enhance the spatial-semantic consistency and generalization ability of features. Results:The proposed method is evaluated on two public benchmark TCGA datasets (TCGA-LUNG and TCGA-BRCA) and two in-house clinical datasets (USTC-EGFR and USTC-GIST). Experimental results validate it is effective in the tasks of cancer subtyping and gene mutation status prediction. In the test stage, the proposed PEGTB-MIL outperforms the other state-of-the-art methods and respectively achieves 97.13±0.34%, 86.74±2.64%, 83.25±1.65%, and 72.52±1.63% of the area under the receiver operating characteristic (ROC) curve (AUC). Conclusion:PEGTB-MIL utilizes positional encoding to effectively guide and reinforce MIL, leading to enhanced performance on downstream WSI classification tasks. Specifically, the introduced auxiliary reconstruction module adeptly preserves the spatial-semantic consistency of patch features. More significantly, this study investigates the relationship between position information and disease diagnosis and presents a promising avenue for further research.

Exploring the Efficacy of Various CNN Architectures in Diagnosing Oral Cancer from Squamous Cell Carcinoma

Oral cancer can result from mutations in cells located in the lips or mouth. Diagnosing oral cavity squamous cell carcinoma (OCSCC) is particularly challenging, often occurring at advanced stages. To address this, computer-aided diagnosis methods are increasingly being used. In this work, a deep learning-based approach utilizing models such as VGG16, ResNet50, LeNet-5, MobileNetV2, and Inception V3 is presented. NEOR and OCSCC datasets were used for feature extraction, with virtual slide images divided into tiles and classified as normal or squamous cell cancer. Performance metrics like accuracy, F1-score, AUC, precision, and recall were analyzed to determine the prerequisites for optimal CNN performance. The proposed CNN approaches were effective for classifying OCSCC and oral dysplasia, with the highest accuracy of 95.41% achieved using MobileNetV2. Key findingsDeep learning models, particularly MobileNetV2, achieved high classification accuracy (95.41%) for OCSCC.CNN-based methods show promise for early-stage OCSCC and oral dysplasia diagnosis. Performance parameters like precision, recall, and F1-score help optimize CNN model selection for this task.

LSSF-Net: Lightweight segmentation with self-awareness, spatial attention, and focal modulation

Accurate segmentation of skin lesions within dermoscopic images plays a crucial role in the timely identification of skin cancer for computer-aided diagnosis on mobile platforms. However, varying shapes of the lesions, lack of defined edges, and the presence of obstructions such as hair strands and marker colors make this challenge more complex. Additionally, skin lesions often exhibit subtle variations in texture and color that are difficult to differentiate from surrounding healthy skin, necessitating models that can capture both fine-grained details and broader contextual information. Currently, melanoma segmentation models are commonly based on fully connected networks and U-Nets. However, these models often struggle with capturing the complex and varied characteristics of skin lesions, such as the presence of indistinct boundaries and diverse lesion appearances, which can lead to suboptimal segmentation performance. To address these challenges, we propose a novel lightweight network specifically designed for skin lesion segmentation utilizing mobile devices, featuring a minimal number of learnable parameters (only 0.8 million). This network comprises an encoder–decoder architecture that incorporates conformer-based focal modulation attention, self-aware local and global spatial attention, and split channel-shuffle. The efficacy of our model has been evaluated on four well-established benchmark datasets for skin lesion segmentation: ISIC 2016, ISIC 2017, ISIC 2018, and PH2. Empirical findings substantiate its state-of-the-art performance, notably reflected in a high Jaccard index.