A ViT-AMC Network With Adaptive Model Fusion and Multiobjective Optimization for Interpretable Laryngeal Tumor Grading From Histopathological Images

Semantic Consistency Network with Edge Learner and Connectivity Enhancer for Cervical Tumor Segmentation from Histopathology Images

Accurate tumor grading and regional identification of cervical tumors are important for diagnosis and prognosis. Traditional manual microscopy methods suffer from time-consuming, labor-intensive, and subjective bias problems, so tumor segmentation methods based on deep learning are gradually becoming a hotspot in current research. Cervical tumors have diverse morphologies, which leads to low similarity between the mask edge and ground-truth edge of existing semantic segmentation models. Moreover, the texture and geometric arrangement features of normal tissues and tumors are highly similar, which causes poor pixel connectivity in the mask of the segmentation model. To this end, we propose an end-to-end semantic consistency network with the edge learner and the connectivity enhancer, i.e., ERNet. First, the edge learner consists of a stacked shallow convolutional neural network, so it can effectively enhance the ability of ERNet to learn and represent polymorphic tumor edges. Second, the connectivity enhancer learns detailed information and contextual information of tumor images, so it can enhance the pixel connectivity of the masks. Finally, edge features and pixel-level features are adaptively coupled, and the segmentation results are additionally optimized by the tumor classification task as a whole. The results show that, compared with those of other state-of-the-art segmentation models, the structural similarity and the mean intersection over union of ERNet are improved to 88.17% and 83.22%, respectively, which reflects the excellent edge similarity and pixel connectivity of the proposed model. Finally, we conduct a generalization experiment on laryngeal tumor images. Therefore, the ERNet network has good clinical popularization and practical value.

ModuCLIP: multi-scale CLIP framework for predicting foundation pit deformation in multi-modal robotic systems

Introduction

Foundation pit deformation prediction is a critical aspect of underground engineering safety assessment, influencing construction quality and personnel safety. However, due to complex geological conditions and numerous environmental interference factors, traditional prediction methods struggle to achieve precise modeling. Conventional approaches, including numerical simulations, empirical formulas, and machine learning models, suffer from limitations such as high computational costs, poor generalization, or excessive dependence on specific data distributions. Recently, deep learning models, particularly cross-modal architectures, have demonstrated great potential in engineering applications. However, effectively integrating multi-modal data for improved prediction accuracy remains a significant challenge.

Methods

This study proposes a Multi-Scale Contrastive Language-Image Pretraining (CLP) framework, ModuCLIP, designed for foundation pit deformation prediction in multi-modal robotic systems. The framework leverages a self-supervised contrastive learning mechanism to integrate multi-source information, including images, textual descriptions, and sensor data, while employing a multi-scale feature learning approach to enhance adaptability to complex conditions. Experiments conducted on multiple foundation pit engineering datasets demonstrate that ModuCLIP outperforms existing methods in terms of prediction accuracy, generalization, and robustness.

Results and discussion

The findings suggest that this framework provides an efficient and precise solution for foundation pit deformation prediction while offering new insights into multi-modal robotic perception and engineering monitoring applications.

Investigating the key principles in two-step heterogeneous transfer learning for early laryngeal cancer identification

Data scarcity in medical images makes transfer learning a common approach in computer-aided diagnosis. Some disease classification tasks can rely on large homogeneous public datasets to train the transferred model, while others cannot, i.e., endoscopic laryngeal cancer image identification. Distinguished from most current works, this work pioneers exploring a two-step heterogeneous transfer learning (THTL) framework for laryngeal cancer identification and summarizing the fundamental principles for the intermediate domain selection. For heterogeneity and clear vascular representation, diabetic retinopathy images were chosen as THTL's intermediate domain. The experiment results reveal two vital principles in intermediate domain selection for future studies: 1) the size of the intermediate domain is not a sufficient condition to improve the transfer learning performance; 2) even distinct vascular features in the intermediate domain do not guarantee improved performance in the target domain. We observe that radial vascular patterns benefit benign classification, whereas twisted and tangled patterns align more with malignant classification. Additionally, to compensate for the absence of twisted patterns in the intermediate domains, we propose the Step-Wise Fine-Tuning (SWFT) technique, guided by the Layer Class Activate Map (LayerCAM) visualization result, getting 20.4% accuracy increases compared to accuracy from THTL's, even higher than fine-tune all layers.

MCRANet: MTSL-based connectivity region attention network for PD-L1 status segmentation in H&E stained images

The quantitative analysis of Programmed death-ligand 1 (PD-L1) via Immunohistochemical (IHC) plays a crucial role in guiding immunotherapy. However, IHC faces challenges, including high costs, time consumption and result variability. Conversely, Hematoxylin-Eosin (H&E) staining offers cost-effectiveness, speed, and stable results. Nonetheless, H&E staining, which solely visualizes cellular morphological features, lacks clinical applicability in detecting biomarker expressions like PD-L1. Substituting H&E staining for IHC in determining PD-L1 status is a clinically significant and challenging task. Motivated by above observations, we propose a Multi-Task supervised learning (MTSL)-based connectivity region attention network (MCRANet) for PD-L1 status segmentation in H&E stained images. To reduce interference from non-tumor areas, the MTSL-based region attention is proposed to enhances the network's capability to distinguish between tumor and non-tumor regions. Consequently, this augmentation further improves the network's segmentation efficacy for PD-L1 positive and negative regions. Furthermore, the PD-L1 expression regions demonstrate interconnection throughout the tissue section. Leveraging this topological prior knowledge, we integrate a connectivity modeling module (CM module) within the MTSL-based region attention module (MRA module) to enhance the precision of MTSL-based region attention localization. This integration further improves the structural similarity between the segmentation results and the ground truth. Extensive visual and quantitative results demonstrate that our supervised-learning-guided MRA module produces more interpretable attention and the introduced CM module provides accurate positional attention to the MRA module. Compared to other state-of-the-art networks, MCRANet exhibits superior segmentation performance with a dice similarity coefficient (DSC) of 79.6 % on the lung squamous cell carcinoma (LUSC) PD-L1 status dataset.

ViT-Based Face Diagnosis Images Analysis for Schizophrenia Detection

OBJECTIVES

Computer-aided schizophrenia (SZ) detection methods mainly depend on electroencephalogram and brain magnetic resonance images, which both capture physical signals from patients' brains. These inspection techniques take too much time and affect patients' compliance and cooperation, while difficult for clinicians to comprehend the principle of detection decisions. This study proposes a novel method using face diagnosis images based on traditional Chinese medicine principles, providing a non-invasive, efficient, and interpretable alternative for SZ detection.

METHODS

An innovative face diagnosis image analysis method for SZ detection, which learns feature representations based on Vision Transformer (ViT) directly from face diagnosis images. It provides a face features distribution visualization and quantitative importance of each facial region and is proposed to supplement interpretation and to increase efficiency in SZ detection while keeping a high detection accuracy.

RESULTS

A benchmarking platform comprising 921 face diagnostic images, 6 benchmark methods, and 4 evaluation metrics was established. The experimental results demonstrate that our method significantly improves SZ detection performance with a 3-10% increase in accuracy scores. Additionally, it is found that facial regions rank in descending order according to importance in SZ detection as eyes, mouth, forehead, cheeks, and nose, which is exactly consistent with the clinical traditional Chinese medicine experience.

CONCLUSIONS

Our method fully leverages semantic feature representations of first-introduced face diagnosis images in SZ, offering strong interpretability and visualization capabilities. It not only opens a new path for SZ detection but also brings new tools and concepts to the research and application in the field of mental illness.

Prediction of PD-L1 tumor positive score in lung squamous cell carcinoma with H&E staining images and deep learning

Background

Detecting programmed death ligand 1 (PD-L1) expression based on immunohistochemical (IHC) staining is an important guide for the treatment of lung cancer with immune checkpoint inhibitors. However, this method has problems such as high staining costs, tumor heterogeneity, and subjective differences among pathologists. Therefore, the application of deep learning models to segment and quantitatively predict PD-L1 expression in digital sections of Hematoxylin and eosin (H&E) stained lung squamous cell carcinoma is of great significance.

Methods

We constructed a dataset comprising H&E-stained digital sections of lung squamous cell carcinoma and used a Transformer Unet (TransUnet) deep learning network with an encoder-decoder design to segment PD-L1 negative and positive regions and quantitatively predict the tumor cell positive score (TPS).

Results

The results showed that the dice similarity coefficient (DSC) and intersection overunion (IoU) of deep learning for PD-L1 expression segmentation of H&E-stained digital slides of lung squamous cell carcinoma were 80 and 72%, respectively, which were better than the other seven cutting-edge segmentation models. The root mean square error (RMSE) of quantitative prediction TPS was 26.8, and the intra-group correlation coefficients with the gold standard was 0.92 (95% CI: 0.90-0.93), which was better than the consistency between the results of five pathologists and the gold standard.

Conclusion

The deep learning model is capable of segmenting and quantitatively predicting PD-L1 expression in H&E-stained digital sections of lung squamous cell carcinoma, which has significant implications for the application and guidance of immune checkpoint inhibitor treatments. And the link to the code is https://github.com/Baron-Huang/PD-L1-prediction-via-HE-image.

Surgery-based radiation-free multimodality treatment for locally advanced cervical cancer

The current review described a 55-year woman using 28 months to finish her surgery-based radiation-free multimodality treatment journey to fight International Federation of Gynaecology & Obstetrics (FIGO) 2018 clinical stage IIA2 (cT2aN0M0) squamous cell carcinoma (SCC) of the cervix. She received six cycles of perioperative adjuvant therapy, including three cycles of neoadjuvant therapy (NAT) and three cycles of postoperative adjuvant therapy by using combination of dose-dense chemotherapy (CT, weekly paclitaxel 80 mg/m2+triweekly cisplatin 40 mg/m2), immunotherapy (IO, triweekly pembrolizumab 200 mg) and half-dose anti-angiogenic agent (triweekly bevacizumab 7.5 mg/kg) plus interval radical surgery (radical hysterectomy + bilateral salpingo-oophorectomy + bilateral pelvic lymph node dissection + para-aortic lymph node sampling) and following maintenance therapy with monthly 22 cycles of half-dose of IO (pembrolizumab 100 mg) and concomitant 4 cycles of single-agent CT (paclitaxel 175 mg/m2) and 18 cycles of half-dose anti-angiogenic agent (bevacizumab 7.5 mg/kg). During the cervical SCC fighting journey, two unwanted adverse events (AEs) occurred. One was pseudo-progressive disease during the NAT treatment and pathology-confirmed upgrading FIGO stage IIIC1p (ypT2a1N1M0) after radical surgery and the other was the occurrence of hypothyroidism during the post operative adjuvant therapy. Based on this case we presented, we review the recent trend in the management of women with locally advanced cervical cancer (LACC) using the radiation-free but surgery-based multimodality strategy and highlight the strengths and limitations about perioperative adjuvant therapy with dose-dense CT + IO + half-dose anti-angiogenic agent and maintenance treatment of half-dose IO combining with short-term single agent CT and following long-term half-dose anti-angiogenic agent. All underscore the possibility that women with LACC have an opportunity to receive surgery-based RT-free multi-modality strategy to manage their diseases with satisfactory results. Additionally, the evolving role of IO plus CT with/without anti-angiogenic agent functioning as either primary treatment or adjuvant therapy for the treatment of advanced CC has been in process continuously. Moreover, the patient's positive response to IO, pembrolizumab as an example, both during the primary and maintenance therapy, highlights the importance of integrating IO into CT regimens for CC, especially in cases where conventional therapies, RT as an example, are insufficient or who do not want to receive RT-based treatment. The sustained disease-free status of the patient over several years reinforces the potential of IO to significantly increase long-term survival outcomes in CC patients, particularly for those with LACC.

Towards laryngeal cancer diagnosis using Dandelion Optimizer Algorithm with ensemble learning on biomedical throat region images

Laryngeal cancer exhibits a notable global health burden, with later-stage detection contributing to a low mortality rate. Laryngeal cancer diagnosis on throat region images is a pivotal application of computer vision (CV) and medical image diagnoses in the medical sector. It includes detecting and analysing abnormal or cancerous tissue from the larynx, an integral part of the vocal and respiratory systems. The computer-aided system makes use of artificial intelligence (AI) through deep learning (DL) and machine learning (ML) models, including convolution neural networks (CNN), for automated disease diagnoses and detection. Various DL and ML approaches are executed to categorize the extraction feature as healthy and cancerous tissues. This article introduces an automated Laryngeal Cancer Diagnosis using the Dandelion Optimizer Algorithm with Ensemble Learning (LCD-DOAEL) method on Biomedical Throat Region Image. The LCD-DOAEL method aims to investigate the images of the throat region for the presence of laryngeal cancer. In the LCD-DOAEL method, the Gaussian filtering (GF) approach is applied to eliminate the noise in the biomedical images. Besides, the complex and intrinsic feature patterns can be extracted by the MobileNetv2 model. Meanwhile, the DOA model carries out the hyperparameter selection of MobileNetV2 architecture. Finally, the ensemble of three classifiers such as bidirectional long short-term memory (BiLSTM), regularized extreme learning machine (ELM), and backpropagation neural network (BPNN) models, are utilized for the classification process. A comprehensive set of simulations is conducted on the biomedical image dataset to highlight the efficient performance of the LCD-DOAEL technique. The comparison analysis of the LCD-DOAEL method exhibited a superior accuracy outcome of 97.54% over other existing techniques.

Auto-BCS: A Hybrid System for Real-Time Breast Cancer Screening from Pathological Images

Breast cancer is recognized as a prominent cause of cancer-related mortality among women globally, emphasizing the critical need for early diagnosis resulting improvement in survival rates. Current breast cancer diagnostic procedures depend on manual assessments of pathological images by medical professionals. However, in remote or underserved regions, the scarcity of expert healthcare resources often compromised the diagnostic accuracy. Machine learning holds great promise for early detection, yet existing breast cancer screening algorithms are frequently characterized by significant computational demands, rendering them unsuitable for deployment on low-processing-power mobile devices. In this paper, a real-time automated system "Auto-BCS" is introduced that significantly enhances the efficiency of early breast cancer screening. The system is structured into three distinct phases. In the initial phase, images undergo a pre-processing stage aimed at noise reduction. Subsequently, feature extraction is carried out using a lightweight and optimized deep learning model followed by extreme gradient boosting classifier, strategically employed to optimize the overall performance and prevent overfitting in the deep learning model. The system's performance is gauged through essential metrics, including accuracy, precision, recall, F1 score, and inference time. Comparative evaluations against state-of-the-art algorithms affirm that Auto-BCS outperforms existing models, excelling in both efficiency and processing speed. Computational efficiency is prioritized by Auto-BCS, making it particularly adaptable to low-processing-power mobile devices. Comparative assessments confirm the superior performance of Auto-BCS, signifying its potential to advance breast cancer screening technology.

Masked hypergraph learning for weakly supervised histopathology whole slide image classification

BACKGROUND AND OBJECTIVES

Graph neural network (GNN) has been extensively used in histopathology whole slide image (WSI) analysis due to the efficiency and flexibility in modelling relationships among entities. However, most existing GNN-based WSI analysis methods only consider the pairwise correlation of patches from one single perspective (e.g. spatial affinity or embedding similarity) yet ignore the intrinsic non-pairwise relationships present in gigapixel WSI, which are likely to contribute to feature learning and downstream tasks. The objective of this study is therefore to explore the non-pairwise relationships in histopathology WSI and exploit them to guide the learning of slide-level representations for better classification performance.

METHODS

In this paper, we propose a novel Masked HyperGraph Learning (MaskHGL) framework for weakly supervised histopathology WSI classification. Compared with most GNN-based WSI classification methods, MaskHGL exploits the non-pairwise correlations between patches with hypergraph and global message passing conducted by hypergraph convolution. Concretely, multi-perspective hypergraphs are first built for each WSI, then hypergraph attention is introduced into the jointed hypergraph to propagate the non-pairwise relationships and thus yield more discriminative node representation. More importantly, a masked hypergraph reconstruction module is devised to guide the hypergraph learning which can generate more powerful robustness and generalization than the method only using hypergraph modelling. Additionally, a self-attention-based node aggregator is also applied to explore the global correlation of patches in WSI and produce the slide-level representation for classification.

RESULTS

The proposed method is evaluated on two public TCGA benchmark datasets and one in-house dataset. On the public TCGA-LUNG (1494 WSIs) and TCGA-EGFR (696 WSIs) test set, the area under receiver operating characteristic (ROC) curve (AUC) were 0.9752±0.0024 and 0.7421±0.0380, respectively. On the USTC-EGFR (754 WSIs) dataset, MaskHGL achieved significantly better performance with an AUC of 0.8745±0.0100, which surpassed the second-best state-of-the-art method SlideGraph+ 2.64%.

CONCLUSIONS

MaskHGL shows a great improvement, brought by considering the intrinsic non-pairwise relationships within WSI, in multiple downstream WSI classification tasks. In particular, the designed masked hypergraph reconstruction module promisingly alleviates the data scarcity and greatly enhances the robustness and classification ability of our MaskHGL. Notably, it has shown great potential in cancer subtyping and fine-grained lung cancer gene mutation prediction from hematoxylin and eosin (H&E) stained WSIs.

A semi-supervised segmentation method for microscopic hyperspectral pathological images based on multi-consistency learning

Pathological images are considered the gold standard for clinical diagnosis and cancer grading. Automatic segmentation of pathological images is a fundamental and crucial step in constructing powerful computer-aided diagnostic systems. Medical microscopic hyperspectral pathological images can provide additional spectral information, further distinguishing different chemical components of biological tissues, offering new insights for accurate segmentation of pathological images. However, hyperspectral pathological images have higher resolution and larger area, and their annotation requires more time and clinical experience. The lack of precise annotations limits the progress of research in pathological image segmentation. In this paper, we propose a novel semi-supervised segmentation method for microscopic hyperspectral pathological images based on multi-consistency learning (MCL-Net), which combines consistency regularization methods with pseudo-labeling techniques. The MCL-Net architecture employs a shared encoder and multiple independent decoders. We introduce a Soft-Hard pseudo-label generation strategy in MCL-Net to generate pseudo-labels that are closer to real labels for pathological images. Furthermore, we propose a multi-consistency learning strategy, treating pseudo-labels generated by the Soft-Hard process as real labels, by promoting consistency between predictions of different decoders, enabling the model to learn more sample features. Extensive experiments in this paper demonstrate the effectiveness of the proposed method, providing new insights for the segmentation of microscopic hyperspectral tissue pathology images.

Efficacy and Safety of Atezolizumab as a PD-L1 Inhibitor in the Treatment of Cervical Cancer: A Systematic Review

BACKGROUND AND OBJECTIVES

The efficacy and safety of PD-L1 inhibitors in the treatment of cervical cancer is an ongoing research question. This review aims to establish a clear profile of atezolizumab, examining its impact on survival outcomes, response rates, and safety measured by serious adverse events (SAEs).

MATERIALS AND METHODS

A literature search was conducted using PubMed, Scopus, and Web of Science, focusing on articles published up to February 2024. The review followed the PRISMA guidelines and synthesized outcomes from four randomized trial studies involving atezolizumab administered at 1200 mg IV every three weeks, alone or in combination with chemoradiotherapy.

RESULTS

A total of 284 patients received atezolizumab, the majority being advanced stage cervical cancer (IVA-IVB). Median follow-up times ranged from 9 weeks to 32.9 months. It was found that combining atezolizumab with standard therapies extended median progression-free survival (PFS) from 10.4 to 13.7 months and overall survival (OS) from 22.8 to 32.1 months, according to the phase III trial. Monotherapy and initial treatment settings with atezolizumab also showed promising efficacy, with disease-free survival rates at 24 months reaching 79% compared to 52% with standard therapy alone. However, the treatment was associated with high rates of SAEs, reaching up to 79% in more intensive treatment combinations.

CONCLUSIONS

Atezolizumab demonstrates significant potential in improving PFS and OS in patients with cervical cancer, supporting its inclusion as a first-line treatment option. Despite the efficacy benefits, the high incidence of SAEs necessitates careful patient selection and management strategies to mitigate risks. This systematic review supports the continued evaluation of atezolizumab in broader clinical trials to refine its therapeutic profile and safety measures in the context of cervical cancer treatment.

Deep Learning-based Diagnosis of Pulmonary Tuberculosis on Chest X-ray in the Emergency Department: A Retrospective Study

Prompt and correct detection of pulmonary tuberculosis (PTB) is critical in preventing its spread. We aimed to develop a deep learning-based algorithm for detecting PTB on chest X-ray (CXRs) in the emergency department. This retrospective study included 3498 CXRs acquired from the National Taiwan University Hospital (NTUH). The images were chronologically split into a training dataset, NTUH-1519 (images acquired during the years 2015 to 2019; n = 2144), and a testing dataset, NTUH-20 (images acquired during the year 2020; n = 1354). Public databases, including the NIH ChestX-ray14 dataset (model training; 112,120 images), Montgomery County (model testing; 138 images), and Shenzhen (model testing; 662 images), were also used in model development. EfficientNetV2 was the basic architecture of the algorithm. Images from ChestX-ray14 were employed for pseudo-labelling to perform semi-supervised learning. The algorithm demonstrated excellent performance in detecting PTB (area under the receiver operating characteristic curve [AUC] 0.878, 95% confidence interval [CI] 0.854-0.900) in NTUH-20. The algorithm showed significantly better performance in posterior-anterior (PA) CXR (AUC 0.940, 95% CI 0.912-0.965, p-value < 0.001) compared with anterior-posterior (AUC 0.782, 95% CI 0.644-0.897) or portable anterior-posterior (AUC 0.869, 95% CI 0.814-0.918) CXR. The algorithm accurately detected cases of bacteriologically confirmed PTB (AUC 0.854, 95% CI 0.823-0.883). Finally, the algorithm tested favourably in Montgomery County (AUC 0.838, 95% CI 0.765-0.904) and Shenzhen (AUC 0.806, 95% CI 0.771-0.839). A deep learning-based algorithm could detect PTB on CXR with excellent performance, which may help shorten the interval between detection and airborne isolation for patients with PTB.

A non-aligned translation with a neoplastic classifier regularization to include vascular NBI patterns in standard colonoscopies

Polyp vascular patterns are key to categorizing colorectal cancer malignancy. These patterns are typically observed in situ from specialized narrow-band images (NBI). Nonetheless, such vascular characterization is lost from standard colonoscopies (the primary attention mechanism). Besides, even for NBI observations, the categorization remains biased for expert observations, reporting errors in classification from 59.5% to 84.2%. This work introduces an end-to-end computational strategy to enhance in situ standard colonoscopy observations, including vascular patterns typically observed from NBI mechanisms. These retrieved synthetic images are achieved by adjusting a deep representation under a non-aligned translation task from optical colonoscopy (OC) to NBI. The introduced scheme includes an architecture to discriminate enhanced neoplastic patterns achieving a remarkable separation into the embedding representation. The proposed approach was validated in a public dataset with a total of 76 sequences, including standard optical sequences and the respective NBI observations. The enhanced optical sequences were automatically classified among adenomas and hyperplastic samples achieving an F1-score of 0.86%. To measure the sensibility capability of the proposed approach, serrated samples were projected to the trained architecture. In this experiment, statistical differences from three classes with a ρ-value <0.05 were reported, following a Mann-Whitney U test. This work showed remarkable polyp discrimination results in enhancing OC sequences regarding typical NBI patterns. This method also learns polyp class distributions under the unpaired criteria (close to real practice), with the capability to separate serrated samples from adenomas and hyperplastic ones.

Automated Laryngeal Cancer Detection and Classification Using Dwarf Mongoose Optimization Algorithm with Deep Learning

Laryngeal cancer (LCA) is a serious disease with a concerning global rise in incidence. Accurate treatment for LCA is particularly challenging in later stages, due to its complex nature as a head and neck malignancy. To address this challenge, researchers have been actively developing various analysis methods and tools to assist medical professionals in efficient LCA identification. However, existing tools and methods often suffer from various limitations, including low accuracy in early-stage LCA detection, high computational complexity, and lengthy patient screening times. With this motivation, this study presents an Automated Laryngeal Cancer Detection and Classification using a Dwarf Mongoose Optimization Algorithm with Deep Learning (ALCAD-DMODL) technique. The main objective of the ALCAD-DMODL method is to recognize the existence of LCA using the DL model. In the presented ALCAD-DMODL technique, a median filtering (MF)-based noise removal process takes place to get rid of the noise. Additionally, the ALCAD-DMODL technique involves the EfficientNet-B0 model for deriving feature vectors from the pre-processed images. For optimal hyperparameter tuning of the EfficientNet-B0 model, the DMO algorithm can be applied to select the parameters. Finally, the multi-head bidirectional gated recurrent unit (MBGRU) model is applied for the recognition and classification of LCA. The simulation result analysis of the ALCAD-DMODL technique is carried out on the throat region image dataset. The comparison study stated the supremacy of the ALCAD-DMODL technique in terms of distinct measures.

Skeletal Fracture Detection with Deep Learning: A Comprehensive Review

Deep learning models have shown great promise in diagnosing skeletal fractures from X-ray images. However, challenges remain that hinder progress in this field. Firstly, a lack of clear definitions for recognition, classification, detection, and localization tasks hampers the consistent development and comparison of methodologies. The existing reviews often lack technical depth or have limited scope. Additionally, the absence of explainable facilities undermines the clinical application and expert confidence in results. To address these issues, this comprehensive review analyzes and evaluates 40 out of 337 recent papers identified in prestigious databases, including WOS, Scopus, and EI. The objectives of this review are threefold. Firstly, precise definitions are established for the bone fracture recognition, classification, detection, and localization tasks within deep learning. Secondly, each study is summarized based on key aspects such as the bones involved, research objectives, dataset sizes, methods employed, results obtained, and concluding remarks. This process distills the diverse approaches into a generalized processing framework or workflow. Moreover, this review identifies the crucial areas for future research in deep learning models for bone fracture diagnosis. These include enhancing the network interpretability, integrating multimodal clinical information, providing therapeutic schedule recommendations, and developing advanced visualization methods for clinical application. By addressing these challenges, deep learning models can be made more intelligent and specialized in this domain. In conclusion, this review fills the gap in precise task definitions within deep learning for bone fracture diagnosis and provides a comprehensive analysis of the recent research. The findings serve as a foundation for future advancements, enabling improved interpretability, multimodal integration, clinical decision support, and advanced visualization techniques.

UniVisNet: A Unified Visualization and Classification Network for accurate grading of gliomas from MRI

Accurate grading of brain tumors plays a crucial role in the diagnosis and treatment of glioma. While convolutional neural networks (CNNs) have shown promising performance in this task, their clinical applicability is still constrained by the interpretability and robustness of the models. In the conventional framework, the classification model is trained first, and then visual explanations are generated. However, this approach often leads to models that prioritize classification performance or complexity, making it difficult to achieve a precise visual explanation. Motivated by these challenges, we propose the Unified Visualization and Classification Network (UniVisNet), a novel framework that aims to improve both the classification performance and the generation of high-resolution visual explanations. UniVisNet addresses attention misalignment by introducing a subregion-based attention mechanism, which replaces traditional down-sampling operations. Additionally, multiscale feature maps are fused to achieve higher resolution, enabling the generation of detailed visual explanations. To streamline the process, we introduce the Unified Visualization and Classification head (UniVisHead), which directly generates visual explanations without the need for additional separation steps. Through extensive experiments, our proposed UniVisNet consistently outperforms strong baseline classification models and prevalent visualization methods. Notably, UniVisNet achieves remarkable results on the glioma grading task, including an AUC of 94.7%, an accuracy of 89.3%, a sensitivity of 90.4%, and a specificity of 85.3%. Moreover, UniVisNet provides visually interpretable explanations that surpass existing approaches. In conclusion, UniVisNet innovatively generates visual explanations in brain tumor grading by simultaneously improving the classification performance and generating high-resolution visual explanations. This work contributes to the clinical application of deep learning, empowering clinicians with comprehensive insights into the spatial heterogeneity of glioma.

A survey of Transformer applications for histopathological image analysis: New developments and future directions

Transformers have been widely used in many computer vision challenges and have shown the capability of producing better results than convolutional neural networks (CNNs). Taking advantage of capturing long-range contextual information and learning more complex relations in the image data, Transformers have been used and applied to histopathological image processing tasks. In this survey, we make an effort to present a thorough analysis of the uses of Transformers in histopathological image analysis, covering several topics, from the newly built Transformer models to unresolved challenges. To be more precise, we first begin by outlining the fundamental principles of the attention mechanism included in Transformer models and other key frameworks. Second, we analyze Transformer-based applications in the histopathological imaging domain and provide a thorough evaluation of more than 100 research publications across different downstream tasks to cover the most recent innovations, including survival analysis and prediction, segmentation, classification, detection, and representation. Within this survey work, we also compare the performance of CNN-based techniques to Transformers based on recently published papers, highlight major challenges, and provide interesting future research directions. Despite the outstanding performance of the Transformer-based architectures in a number of papers reviewed in this survey, we anticipate that further improvements and exploration of Transformers in the histopathological imaging domain are still required in the future. We hope that this survey paper will give readers in this field of study a thorough understanding of Transformer-based techniques in histopathological image analysis, and an up-to-date paper list summary will be provided at https://github.com/S-domain/Survey-Paper .

A CAD system for automatic dysplasia grading on H&E cervical whole-slide images

Cervical cancer is the fourth most common female cancer worldwide and the fourth leading cause of cancer-related death in women. Nonetheless, it is also among the most successfully preventable and treatable types of cancer, provided it is early identified and properly managed. As such, the detection of pre-cancerous lesions is crucial. These lesions are detected in the squamous epithelium of the uterine cervix and are graded as low- or high-grade intraepithelial squamous lesions, known as LSIL and HSIL, respectively. Due to their complex nature, this classification can become very subjective. Therefore, the development of machine learning models, particularly directly on whole-slide images (WSI), can assist pathologists in this task. In this work, we propose a weakly-supervised methodology for grading cervical dysplasia, using different levels of training supervision, in an effort to gather a bigger dataset without the need of having all samples fully annotated. The framework comprises an epithelium segmentation step followed by a dysplasia classifier (non-neoplastic, LSIL, HSIL), making the slide assessment completely automatic, without the need for manual identification of epithelial areas. The proposed classification approach achieved a balanced accuracy of 71.07% and sensitivity of 72.18%, at the slide-level testing on 600 independent samples, which are publicly available upon reasonable request.