Healthcare (HC) supply chains are complicated configurations spanning numerous geographical and organizational boundaries, offering significant backbone to the services essential for daily life. Accordingly, current research hasemphasized the requirement for robust and end-to-end tracking as well as traceability systems for pharmaceutical supply chains (PSC). Thereby, the end-to-end product traceability system over PSC is vital to assure the safety of drugs and reject counterfeits. The usability of blockchain (BC) adds visibility and traceability of the supply chains like PSC and offers every data from end to end. Various current traceability systems are centralized directing to data privacy, authenticity and transparency problems in HC supply chains. In this research, Pyramidal ShuffleNet (Py-ShuffleNet) is introduced for distributed medical supply chain (MSC) drug traceability. Initially, the Blockchain Reputation-Based Consensus (BRBC) system model is simulated. The entities involved are pharmaceutical Company (PC) (manufacturer), wholesaler, Food and Drug Administration (FDA), distributor, Inter Planetary File System (IPFS), smart contract (SC), patients and retailer (pharmacy). The steps performed are registration, authentication, drug distribution, certificate generation, key generation, verification, drug traceability, access control, miner selection, implicit jury selection, miner monitoring and malicious miner expulsion. Here, miner monitoring is accomplished by utilizing Py-ShuffleNet for security purposes. However, Py-ShuffleNet is devised by integrating Deep Pyramidal Residual Network (PyramidNet) with ShuffleNet. Furthermore, Py-ShuffleNet achieved a maximal average reputation score of about 0.945, average transition score of about 0.930, malicious behavior detection of about 667.304 s, a ratio of expulsion of about 0.969, Computational cost of 4.161 s, Energy consumption of 0.590 J, False Negative Rate (FNR) of 0.081, latency of 0.512 s, and transaction cost of 0.406.

Since medical images are very sensitive and important for diagnosis and treatment, protecting their security and confidentiality is extremely important. There could be serious privacy and medical care issues if unlicensed personnel access or change such images. So, making sure medical images are transmitted and stored securely helps ensure private patient data is not compromised and healthcare systems maintain their reputation. It addresses these issues by suggesting a new entropy-based encryption system as a feature of the Mimic Octopus Adaptive Framework (MOAF). This method is made to securely save confidential data in the images of patients without changing their diagnostic usefulness or quality. Depending on the Shannon entropy present in the image data, MOAF opts for the most suitable compression algorithms (Vector Quantization or Huffman Coding) and suitable encryption algorithms (3DES or AES). Because of adaptive selection, each image gets its own third-tier security measure which boosts both safety and efficiency. Besides, a distinct cryptographic key is generated for each secret image using the SHA-256 hash function and the information from the extracted features and image entropy. Security and the process of decoding are improved by having the header appender directly embed vital data like the entropy, chosen algorithms and key into the header of the image. Evaluating the method experimentally reveals a peak signal-to-noise ratio (PSNR) of 81.31 and a structural similarity index measure (SSIM) of 1.0 at a payload capacity of 79,747 bytes. This proves that the quality of the image is extremely well preserved. It is shown through comparisons that MOAF works better than other techniques at being less detectable and stronger against various forms of attacks.

Polycystic ovary syndrome (PCOS) is an endocrine disorder affecting women of reproductive age characterized by the presence of multiple follicles in the ovaries that are detectable via ultrasound imaging. Early diagnosis of PCOS morphology can be challenging due to low resolution and increased speckle noise, making it difficult to identify smaller follicle boundaries. This article introduces a novel methodology, multiscale gradient-weighted oriented Otsu thresholding with sum of product fusion (MOT-SF), to address these challenges. The MOT-SF technique precisely recognizes smaller region boundaries even at lower resolutions by employing a pyramidal structure for image computation at multiple scales. Otsu's thresholding is used to segment the image, optimizing the threshold by minimizing the interclass variance at each stage. Incorporating gradient weights (λ) within classes enhances smaller boundary regions and reduces noise. Additionally, the MOT-SF method integrates a sum of product fusion strategies, combining segmented images from various scales to produce a final image that preserves both small and large PCOS structures while mitigating noise. The experimental results show that MOT-SF outperforms traditional methods such as Otsu’s thresholding and Chan-Vese models, as well as deep learning approaches such as R-CNN, in terms of computational efficiency and robustness to variations in ultrasound image quality. The MOT-SF methodology achieves an accuracy of nearly 85% and a precision of 94%, highlighting its potential to improve the detection and characterization of follicles in ultrasound images and advancing diagnostic tools in reproductive health.

Underground crop leave disease classification is the most significant area in the agriculture sector as they are the significant source of carbohydrates for human food. However, a disease-ridden plant could threaten the availability of food for millions of people. Researchers tried to use computer vision (CV) to develop an image classification algorithm that might warn farmers by clicking the images of plant’s leaves to find if the crop is diseased or not. This work develops anew DHCLDC model for underground crop leave disease classification that considers the plants like cassava, potato and groundnut. Here, preprocessing is done by employing median filter, followed by segmentation using Improved U-net (U-Net with nested convolutional block). Further, the features extracted comprise of color features, shape features and improved multi text on (MT) features. Finally, Hybrid classifier (HC) model is developed for DHCLDC, which comprised CNN and LSTM models. The outputs from HC(CNN + LSTM) are then given for improved score level fusion (SLF) from which final detected e are attained. Finally, simulations are done with 3 datasets to show the betterment of HC (CNN + LSTM) based DHCLDC model. The specificity of HC (CNN + LSTM) is high, at 95.41, compared to DBN, NN, RF, KNN, CNN, LSTM, DCNN, and SVM.