An Enhanced Agile V-Model: Conformance to regulatory bodies and experiences from model's adoption to medical device development.

Context: Medical devices fall under the broad topic encompass everything from basic hardware to integrated software systems. The integration of software into hardware devices is not simple due to requirements of regional regulatory bodies. Therefore, medical businesses need to oversee not only the creation of devices but also the observance of guidelines and standards established by regulatory bodies. While plan-driven methodologies prevented software from evolving or changing, agile methodologies have inherent characteristics of insufficient planning and documentation. Objectives: The objective of our research is to propose a suitable process model for medical device development, keeping in mind the regulatory requirements. Methods: First, based on the detailed analysis of literature and McHughs proposed model, we suggested the Enhanced Agile V-Model (EAV), which combines plan-driven and agile approaches. Second, we mapped the proposed model to the MDEVSPICE framework to confirm that it adhered to the rules outlined in the standard IEC62304. Finally, the proposed model is evaluated through implication to case study of wave therapeutic medical device. Results: The support of both agile and waterfall approach in EAV model helps in accommodating new requirements in the medical devices and the proposed systems engineering approach helps in hardware and software integration. The mapping of the EAV model to the MDEVSPICE shows complete compliance. Moreover, the implication of the proposed model has been clearly shown statistically and successfully implemented in our case study. Further, device usability and efficiency metrics showed confidence of P < 0.05 and for device safety and efficiency, we conducted an experiment which shows significant improvement in selected parameters. Conclusion: The proposed model shows conformance to regulatory standards, and successfully implemented in development of wave therapeutic device. However, its applicability to more compact and straightforward medical products is unknown and can be determined by using this model to analyze the performance of other medical products.

Attention based automated radiology report generation using CNN and LSTM.

The automated generation of radiology reports provides X-rays and has tremendous potential to enhance the clinical diagnosis of diseases in patients. A new research direction is gaining increasing attention that involves the use of hybrid approaches based on natural language processing and computer vision techniques to create auto medical report generation systems. The auto report generator, producing radiology reports, will significantly reduce the burden on doctors and assist them in writing manual reports. Because the sensitivity of chest X-ray (CXR) findings provided by existing techniques not adequately accurate, producing comprehensive explanations for medical photographs remains a difficult task. A novel approach to address this issue was proposed, based on the continuous integration of convolutional neural networks and long short-term memory for detecting diseases, followed by the attention mechanism for sequence generation based on these diseases. Experimental results obtained by using the Indiana University CXR and MIMIC-CXR datasets showed that the proposed model attained the current state-of-the-art efficiency as opposed to other solutions of the baseline. BLEU-1, BLEU-2, BLEU-3, and BLEU-4 were used as the evaluation metrics.

An incremental learning approach to automatically recognize pulmonary diseases from the multi-vendor chest radiographs.

The human respiratory network is a vital system that provides oxygen supply and nourishment to the whole body. Pulmonary diseases can cause severe respiratory problems, leading to sudden death if not treated timely. Many researchers have utilized deep learning systems (in both transfer learning and fine-tuning modes) to diagnose pulmonary disorders using chest X-rays (CXRs). However, such systems require exhaustive training efforts on large-scale (and well-annotated) data to effectively diagnose chest abnormalities (at the inference stage). Furthermore, procuring such large-scale data (in a clinical setting) is often infeasible and impractical, especially for rare diseases. With the recent advances in incremental learning, researchers have periodically tuned deep neural networks to learn different classification tasks with few training examples. Although, such systems can resist catastrophic forgetting, they treat the knowledge representations (which the network learns periodically) independently of each other, and this limits their classification performance. Also, to the best of our knowledge, there is no incremental learning-driven image diagnostic framework (to date) that is specifically designed to screen pulmonary disorders from the CXRs. To address this, we present a novel framework that can learn to screen different chest abnormalities incrementally (via few-shot training). In addition to this, the proposed framework is penalized through an incremental learning loss function that infers Bayesian theory to recognize structural and semantic inter-dependencies between incrementally learned knowledge representations to diagnose the pulmonary diseases effectively (at the inference stage), regardless of the scanner specifications. We tested the proposed framework on five public CXR datasets containing different chest abnormalities, where it achieved an accuracy of 0.8405 and the F1 score of 0.8303, outperforming various state-of-the-art incremental learning schemes. It also achieved a highly competitive performance compared to the conventional fine-tuning (transfer learning) approaches while significantly reducing the training and computational requirements.