Healthcare has witnessed a technological advancement in improving the quality of care and speeding the process of diagnosing patients due to its intervention with the internet of medical things. IoT in healthcare (H-IoT) plays a significant role in facilitating the process of diagnosing and detecting diseases. Different IoT-based medical sensors are used to measure biometrics and send them to the cloud for more analysis. However, the sensed data are massive and vary in their criticality level in which some sensed data are more critical (health-related data) than others. Moreover, computing such critical data in the cloud encounters some delay which is not preferable in real-time monitoring applications. Thus, this work proposes an IoT-fog-based framework to classify the streamed data according to their criticality level and compute the critical data in the fog to detect abnormalities with low latency and high response time. Before designing the proposed work, an analysis was conducted to explore the real data collected by IoT-based medical apps. The exploration of the data involved downloading and manually analyzing up-to-date privacy policies of eight IoT-based medical apps that provide details about data collection practices. The study showed that the streamed data in H-IoT include medical sensors data, apps registration data (personal information), device information, and other information related to cookies. The proposed work introduced the design of fog-based data classification and the algorithm for such classification. The implementation and evaluation of the proposed framework is future work.

An early evaluation of colorectal cancer liver metastasis (CRCLM) is crucial in determining treatment options that ultimately affect patient survival rates and outcomes. Radiomics (quantitative imaging features) have recently gained popularity in diagnostic and therapeutic strategies. Despite this, radiomics faces many challenges and limitations. This study sheds light on these limitations by reviewing the studies that used radiomics to predict therapeutic response in CRCLM. Despite radiomics’ potential to enhance clinical decision-making, it lacks standardization. According to the results of this study, the instability of radiomics quantification is caused by changes in CT scan parameters used to obtain CT scans, lesion segmentation methods used for contouring liver metastases, feature extraction methods, and dataset size used for experimentation and validation. Accordingly, the study recommends combining radiomics with deep learning to improve prediction accuracy.

Histopathological image analysis remains the cornerstone of cancer diagnosis; however, manual assessment is challenged by stain variability, differences in imaging magnification, and complex morphological patterns. The proposed multi-pretrained deep learning fusion (MPDLF) approach combines two widely used CNN architectures: ResNet50, which captures deeper semantic representations, and VGG16, which extracts fine-grained details. This work differs from previous fusion studies by providing a controlled evaluation of early, intermediate, and late fusion for integrating two pretrained CNN backbones (ResNet50 and VGG16) under single-modality histopathology constraints. To isolate the fusion effect, identical training settings are used across three public H&E datasets. Early fusion achieved the best test performance for the two primary tasks reported here: breast cancer binary classification (accuracy = 0.9070, 95% CI: 0.8742–0.9404; AUC = 0.9707, 95% CI: 0.9541–0.9844) and renal clear cell carcinoma (RCCC) five-class grading (accuracy = 0.8792, 95% CI: 0.8529–0.9041; AUC (OvR, macro) = 0.9895, 95% CI: 0.9859–0.9927). Future work will extend these experiments to additional magnification levels (100×, 200×, and 400×) for breast cancer histopathology images and explore advanced hybrid fusion strategies across different histopathology datasets.