Fibro-CoSANet: pulmonary fibrosis prognosis prediction using a convolutional self attention network

A systematic review of the role of quantitative CT in the prognostication and disease monitoring of interstitial lung disease

BACKGROUND

The unpredictable trajectory and heterogeneity of interstitial lung disease (ILDs) make prognostication challenging. Current prognostic indices and outcome measures have several limitations. Quantitative computed tomography (qCT) provides automated numerical assessment of CT imaging and has shown promise when applied to the prognostication and disease monitoring of ILD. This systematic review aims to highlight the current evidence underpinning the prognostic value of qCT in predicting outcomes in ILD.

METHODS

A comprehensive search of four databases (Medline, EMCare, Embase and CINAHL (Cumulative Index to Nursing and Allied Health Literature)) was conducted for studies published up to and including 22 November 2024. A modified CHARMS (CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies) checklist was used for data extraction. The risk of bias was assessed using a Quality in Prognostic Studies template.

RESULTS

The search identified 1134 unique studies, of which 185 studies met inclusion and exclusion criteria. Commonly studied ILD subtypes included idiopathic pulmonary fibrosis (41%, n=75), mixed subtypes (26%, n=48) and systemic sclerosis ILD (16%, n=30). Numerous studies showed significant prognostic signals, even when adjusted for common covariates and/or significant correlation between serial qCT biomarkers and conventional outcome measures. Heterogenous and nonstandardised reporting methods meant that direct comparison or meta-analysis of studies was not possible. Studies were limited by the use of retrospective methodology without prospective validation and significant study attrition.

DISCUSSION

qCT has shown efficacy in the prognostication and disease monitoring of a range of ILDs. Hurdles exist to widespread adoption including governance concerns, appropriate algorithm anchoring and standardisation of image acquisition. International collaboration is underway to address these hurdles, paving the way for regulatory approval and ultimately patient benefit.

Multi-level digital-twin models of pulmonary mechanics: correlation analysis of 3D CT lung volume and 2D Chest motion

Creating multi-level digital-twin models for mechanical ventilation requires a detailed estimation of regional lung volume. An accurate generic map between 2D chest surface motion and 3D regional lung volume could provide improved regionalisation and clinically acceptable estimates localising lung damage. This work investigates the relationship between CT lung volumes and the forced vital capacity (FVC) a surrogate of tidal volume proven linked to 2D chest motion. In particular, a convolutional neural network (CNN) with U-Net architecture is employed to build a lung segmentation model using a benchmark CT scan dataset. An automated thresholding method is proposed for image morphology analysis to improve model performance. Finally, the trained model is applied to an independent CT dataset with FVC measurements for correlation analysis of CT lung volume projection to lung recruitment capacity. Model training results show a clear improvement of lung segmentation performance with the proposed automated thresholding method compared to a typically suggested fixed value selection, achieving accuracy greater than 95% for both training and independent validation sets. The correlation analysis for 160 patients shows a good correlation ofRsquared value of 0.73 between the proposed 2D volume projection and the FVC value, which indicates a larger and denser projection of lung volume relative to a greater FVC value and lung recruitable capacity. The overall results thus validate the potential of using non-contact, non-invasive 2D measures to enable regionalising lung mechanics models to equivalent 3D models with a generic map based on the good correlation. The clinical impact of improved lung mechanics digital twins due to regionalising the lung mechanics and volume to specific lung regions could be very high in managing mechanical ventilation and diagnosing or locating lung injury or dysfunction based on regular monitoring instead of intermittent and invasive lung imaging modalities.

CytoNet: an efficient dual attention based automatic prediction of cancer sub types in cytology studies

Computer-assisted diagnosis (CAD) plays a key role in cancer diagnosis or screening. Whereas, current CAD performs poorly on whole slide image (WSI) analysis, and thus fails to generalize well. This research aims to develop an automatic classification system to distinguish between different types of carcinomas. Obtaining rich deep features in multi-class classification while achieving high accuracy is still a challenging problem. The detection and classification of cancerous cells in WSI are quite challenging due to the misclassification of normal lumps and cancerous cells. This is due to cluttering, occlusion, and irregular cell distribution. Researchers in the past mostly obtained the hand-crafted features while neglecting the above-mentioned challenges which led to a reduction of the classification accuracy. To mitigate this problem we proposed an efficient dual attention-based network (CytoNet). The proposed network is composed of two main modules (i) Efficient-Net and (ii) Dual Attention Module (DAM). Efficient-Net is capable of obtaining higher accuracy and enhancing efficiency as compared to existing Convolutional Neural Networks (CNNs). It is also useful to obtain the most generic features as it has been trained on ImageNet. Whereas DAM is very robust in obtaining attention and targeted features while negating the background. In this way, the combination of an efficient and attention module is useful to obtain the robust, and intrinsic features to obtain comparable performance. Further, we evaluated the proposed network on two well-known datasets (i) Our generated thyroid dataset (ii) Mendeley Cervical dataset (Hussain in Data Brief, 2019) with enhanced performance compared to their counterparts. CytoNet demonstrated a 99% accuracy rate on the thyroid dataset in comparison to its counterpart. The precision, recall, and F1-score values achieved on the Mendeley Cervical dataset are 0.992, 0.985, and 0.977, respectively. The code implementation is available on GitHub. https://github.com/naveedilyas/CytoNet-An-Efficient-Dual-Attention-based-Automatic-Prediction-of-Cancer-Sub-types-in-Cytol.

Is Attention all You Need in Medical Image Analysis? A Review

Medical imaging is a key component in clinical diagnosis, treatment planning and clinical trial design, accounting for almost 90% of all healthcare data. CNNs achieved performance gains in medical image analysis (MIA) over the last years. CNNs can efficiently model local pixel interactions and be trained on small-scale MI data. Despite their important advances, typical CNN have relatively limited capabilities in modelling "global" pixel interactions, which restricts their generalisation ability to understand out-of-distribution data with different "global" information. The recent progress of Artificial Intelligence gave rise to Transformers, which can learn global relationships from data. However, full Transformer models need to be trained on large-scale data and involve tremendous computational complexity. Attention and Transformer compartments ("Transf/Attention") which can well maintain properties for modelling global relationships, have been proposed as lighter alternatives of full Transformers. Recently, there is an increasing trend to co-pollinate complementary local-global properties from CNN and Transf/Attention architectures, which led to a new era of hybrid models. The past years have witnessed substantial growth in hybrid CNN-Transf/Attention models across diverse MIA problems. In this systematic review, we survey existing hybrid CNN-Transf/Attention models, review and unravel key architectural designs, analyse breakthroughs, and evaluate current and future opportunities as well as challenges. We also introduced an analysis framework on generalisation opportunities of scientific and clinical impact, based on which new data-driven domain generalisation and adaptation methods can be stimulated.

CVCL: Context-aware Voxel-wise Contrastive Learning for label-efficient multi-organ segmentation

Despite the significant performance improvement on multi-organ segmentation with supervised deep learning-based methods, the label-hungry nature hinders their applications in practical disease diagnosis and treatment planning. Due to the challenges in obtaining expert-level accurate, densely annotated multi-organ datasets, label-efficient segmentation, such as partially supervised segmentation trained on partially labeled datasets or semi-supervised medical image segmentation, has attracted increasing attention recently. However, most of these methods suffer from the limitation that they neglect or underestimate the challenging unlabeled regions during model training. To this end, we propose a novel Context-aware Voxel-wise Contrastive Learning method, referred as CVCL, to take full advantage of both labeled and unlabeled information in label-scarce datasets for a performance improvement on multi-organ segmentation. Experimental results demonstrate that our proposed method achieves superior performance than other state-of-the-art methods.

An Atrous Convolved Hybrid Seg-Net Model with residual and attention mechanism for gland detection and segmentation in histopathological images

PURPOSE

A clinically compatible computerized segmentation model is presented here that aspires to supply clinical gland informative details by seizing every small and intricate variation in medical images, integrate second opinions, and reduce human errors.

APPROACH

It comprises of enhanced learning capability that extracts denser multi-scale gland-specific features, recover semantic gap during concatenation, and effectively handle resolution-degradation and vanishing gradient problems. It is having three proposed modules namely Atrous Convolved Residual Learning Module in the encoder as well as decoder, Residual Attention Module in the skip connection paths, and Atrous Convolved Transitional Module as the transitional and output layer. Also, pre-processing techniques like patch-sampling, stain-normalization, augmentation, etc. are employed to develop its generalization capability. To verify its robustness and invigorate network invariance against digital variability, extensive experiments are carried out employing three different public datasets i.e., GlaS (Gland Segmentation Challenge), CRAG (Colorectal Adenocarcinoma Gland) and LC-25000 (Lung Colon-25000) dataset and a private HosC (Hospital Colon) dataset.

RESULTS

The presented model accomplished combative gland detection outcomes having F1-score (GlaS(Test A(0.957), Test B(0.926)), CRAG(0.935), LC 25000(0.922), HosC(0.963)); and gland segmentation results having Object-Dice Index (GlaS(Test A(0.961), Test B(0.933)), CRAG(0.961), LC-25000(0.940), HosC(0.929)), and Object-Hausdorff Distance (GlaS(Test A(21.77) and Test B(69.74)), CRAG(87.63), LC-25000(95.85), HosC(83.29)). In addition, validation score (GlaS (Test A(0.945), Test B(0.937)), CRAG(0.934), LC-25000(0.911), HosC(0.928)) supplied by the proficient pathologists is integrated for the end segmentation results to corroborate the applicability and appropriateness for assistance at the clinical level applications.

CONCLUSION

The proposed system will assist pathologists in devising precise diagnoses by offering a referential perspective during morphology assessment of colon histopathology images.

An intelligent neuromarketing system for predicting consumers' future choice from electroencephalography signals

Neuromarketing utilizes Brain-Computer Interface (BCI) technologies to provide insight into consumers responses on marketing stimuli. In order to achieve insight information, marketers spend about $400 billion annually on marketing, promotion, and advertisement using traditional marketing research tools. In addition, these tools like personal depth interviews, surveys, focus group discussions, etc. are expensive and frequently criticized for failing to extract actual consumer preferences. Neuromarketing, on the other hand, promises to overcome such constraints. In this work, an EEG-based neuromarketing framework is employed for predicting consumer future choice (affective attitude) while they view E-commerce products. After preprocessing, three types of features, namely, time, frequency, and time-frequency domain features are extracted. Then, wrapper-based Support Vector Machine-Recursive Feature Elimination (SVM-RFE) along with correlation bias reduction is used for feature selection. Lastly, we use SVM for categorizing positive affective attitude and negative affective attitude. Experiments show that the frontal cortex achieves the best accuracy of 98.67±2.98, 98±3.22, and 98.67±3.52 for 5-fold, 10-fold, and leave-one-subject-out (LOSO) respectively. In addition, among all the channels, F_z achieves best accuracy 90±7.81, 90.67±9.53, and 92.67±7.03 for 5-fold, 10-fold, and LOSO respectively. Subsequently, this work opens the door for implementing such a neuromarketing framework using consumer-grade devices in a real-life setting for marketers. As a result, it is evident that EEG-based neuromarketing technologies can assist brands and enterprises in forecasting future consumer preferences accurately. Hence, it will pave the way for the creation of an intelligent marketing assistive system for neuromarketing applications in future.

BCI-Based Consumers' Choice Prediction From EEG Signals: An Intelligent Neuromarketing Framework

Neuromarketing relies on Brain Computer Interface (BCI) technology to gain insight into how customers react to marketing stimuli. Marketers spend about $750 billion annually on traditional marketing camping. They use traditional marketing research procedures such as Personal Depth Interviews, Surveys, Focused Group Discussions, and so on, which are frequently criticized for failing to extract true consumer preferences. On the other hand, Neuromarketing promises to overcome such constraints. This work proposes a machine learning framework for predicting consumers' purchase intention (PI) and affective attitude (AA) from analyzing EEG signals. In this work, EEG signals are collected from 20 healthy participants while administering three advertising stimuli settings: product, endorsement, and promotion. After preprocessing, features are extracted in three domains (time, frequency, and time-frequency). Then, after selecting features using wrapper-based methods Recursive Feature Elimination, Support Vector Machine is used for categorizing positive and negative (AA and PI). The experimental results show that proposed framework achieves an accuracy of 84 and 87.00% for PI and AA ensuring the simulation of real-life results. In addition, AA and PI signals show N200 and N400 components when people tend to take decision after visualizing static advertisement. Moreover, negative AA signals shows more dispersion than positive AA signals. Furthermore, this work paves the way for implementing such a neuromarketing framework using consumer-grade EEG devices in a real-life setting. Therefore, it is evident that BCI-based neuromarketing technology can help brands and businesses effectively predict future consumer preferences. Hence, EEG-based neuromarketing technologies can assist brands and enterprizes in accurately forecasting future consumer preferences.