From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks.

Deep neural networks (DNNs) have been widely used in many artificial intelligence (AI) tasks. However, deploying them brings significant challenges due to the huge cost of memory, energy, and computation. To address these challenges, researchers have developed various model compression techniques such as model quantization and model pruning. Recently, there has been a surge in research on compression methods to achieve model efficiency while retaining performance. Furthermore, more and more works focus on customizing the DNN hardware accelerators to better leverage the model compression techniques. In addition to efficiency, preserving security and privacy is critical for deploying DNNs. However, the vast and diverse body of related works can be overwhelming. This inspires us to conduct a comprehensive survey on recent research toward the goal of high-performance, cost-efficient, and safe deployment of DNNs. Our survey first covers the mainstream model compression techniques, such as model quantization, model pruning, knowledge distillation, and optimizations of nonlinear operations. We then introduce recent advances in designing hardware accelerators that can adapt to efficient model compression approaches. In addition, we discuss how homomorphic encryption can be integrated to secure DNN deployment. Finally, we discuss several issues, such as hardware evaluation, generalization, and integration of various compression approaches. Overall, we aim to provide a big picture of efficient DNNs from algorithm to hardware accelerators and security perspectives.

Automated Segmentation of Lymph Nodes on Neck CT Scans Using Deep Learning.

Early and accurate detection of cervical lymph nodes is essential for the optimal management and staging of patients with head and neck malignancies. Pilot studies have demonstrated the potential for radiomic and artificial intelligence (AI) approaches in increasing diagnostic accuracy for the detection and classification of lymph nodes, but implementation of many of these approaches in real-world clinical settings would necessitate an automated lymph node segmentation pipeline as a first step. In this study, we aim to develop a non-invasive deep learning (DL) algorithm for detecting and automatically segmenting cervical lymph nodes in 25,119 CT slices from 221 normal neck contrast-enhanced CT scans from patients without head and neck cancer. We focused on the most challenging task of segmentation of small lymph nodes, evaluated multiple architectures, and employed U-Net and our adapted spatial context network to detect and segment small lymph nodes measuring 5-10 mm. The developed algorithm achieved a Dice score of 0.8084, indicating its effectiveness in detecting and segmenting cervical lymph nodes despite their small size. A segmentation framework successful in this task could represent an essential initial block for future algorithms aiming to evaluate small objects such as lymph nodes in different body parts, including small lymph nodes looking normal to the naked human eye but harboring early nodal metastases.

Medical imaging and multimodal artificial intelligence models for streamlining and enhancing cancer care: opportunities and challenges.

INTRODUCTION: Artificial intelligence (AI) has the potential to transform oncologic care. There have been significant developments in AI applications in medical imaging and increasing interest in multimodal models. These are likely to enable improved oncologic care through more precise diagnosis, increasingly in a more personalized and less invasive manner. In this review, we provide an overview of the current state and challenges that clinicians, administrative personnel and policy makers need to be aware of and mitigate for the technology to reach its full potential. AREAS COVERED: The article provides a brief targeted overview of AI, a high-level review of the current state and future potential AI applications in diagnostic radiology and to a lesser extent digital pathology, focusing on oncologic applications. This is followed by a discussion of emerging approaches, including multimodal models. The article concludes with a discussion of technical, regulatory challenges and infrastructure needs for AI to realize its full potential. EXPERT OPINION: There is a large volume of promising research, and steadily increasing commercially available tools using AI. For the most advanced and promising precision diagnostic applications of AI to be used clinically, robust and comprehensive quality monitoring systems and informatics platforms will likely be required.

Improving transparency and representational generalizability through parallel continual learning.

This paper takes a parallel learning approach in continual learning scenarios. We define parallel continual learning as learning a sequence of tasks where the data for the previous tasks, whose distribution may have shifted over time, are also available while learning new tasks. We propose a parallel continual learning method by assigning subnetworks to each task, and simultaneously training only the assigned subnetworks on their corresponding tasks. In doing so, some parts of the network will be shared across multiple tasks. This is unlike the existing literature in continual learning which aims at learning incoming tasks sequentially, with the assumption that the data for the previous tasks have a fixed distribution. Our proposed method offers promises in: (1) Transparency in the network and in the relationship across tasks by enabling examination of the learned representations by independent and shared subnetworks, (2) Representation generalizability through sharing and training subnetworks on multiple tasks simultaneously. Our analysis shows that compared to many competing approaches such as continual learning, neural architecture search, and multi-task learning, parallel continual learning is capable of learning more generalizable representations. Also, (3)Parallel continual learning overcomes the common issue of catastrophic forgetting in continual learning algorithms. This is the first effort to train a neural network on multiple tasks and input domains simultaneously in a continual learning scenario. Our code is available at https://github.com/yours-anonym/PaRT.

Multidimensional management of a vascular injury following total knee arthroplasty: A rare case report.

Acute vascular injury during total knee arthroplasty (TKA) is an extremely rare complication, but one which can have devastating consequences threatening the limb and/or life of the patient if not diagnosed and managed at the earliest. The clinical presentation can vary from acute haemorrhage or ischemia in the peri operative period; to a delayed presentation of recurrent swelling and pain secondary to a geniculate or popliteal artery pseudoaneurysm. This is the first reported case of an acute inferolateral genicular artery haemorrhage following TKA and the associated medical complications. It was successfully managed with emergency percutaneous endovascular coiling and appropriate medical management. This case highlights that clinical suspicion, prompt diagnosis and urgent intervention with a multidisciplinary approach can help successfully manage a vascular insult.

Application of in vivo stain of methylene blue as a diagnostic aid in the early detection and screening of oral cancerous and precancerous lesions.

BACKGROUND: Periodic clinical examination of the oral cavity is the mainstay for the early detection of oral cancers which can be further aided by screening individuals with high-risk factors that will identify candidates who should receive treatment to prevent cancer progression and reduce patient mortality. Among the diagnostic tools, in vivo staining is advocated as a simple, inexpensive and fairly sensitive method. MATERIALS AND METHODS: The present study involved the examination of fifty patients suspected of oral malignant or precancerous lesions by methylene blue staining. The results of methylene blue uptake were compared with a simultaneous biopsy of these lesions, while benign epithelial lesions were included as the negative subjects of screening. RESULTS: The results revealed a sensitivity of 89%, a specificity of 91%, a positive predictive value of 97% and a negative predictive value of 73%. CONCLUSION: We recommend that methylene blue staining is a useful diagnostic adjunct in a large, community-based oral cancer screening program for high-risk individuals.

Push-out bond strength of different endodontic obturation material at three different sites - In-vitro study.

BACKGROUND: The key to success of any root canal therapy is adequate obturation of the prepared root canal space. Root canal sealers are not dimensionally stable and might dissolve partially over a period of time. The objective of this in vitro study is to evaluate the push-out bond strength to intraradicular dentin of two endodontic obturation materials. MATERIAL AND METHODS: Forty extracted single rooted permanent teeth were used. Canals orifice was explored, teeth were instrumented. The samples were divided into two groups each containing twenty specimens obturated with different obturation material (Group1 Epiphany/Resilon and Group 2 Gutta Percha/AH Plus).The obturation systems used in this study was Element Obturation unit (Sybron Endo). Each tooth root was horizontally sectioned in approximately 2-mm thick slices from the coronal 1/3rd, middle 1/3rd and apical 1/3rd. The push-out bond strength of each specimen was calculated using Universal Testing Machine. The statistical analysis was done using two way analysis of variance (ANOVA) and tukey's test. RESULTS: There was significant difference between push out bond strength of Resilon/Epiphany and AH Plus/Gutta Percha. Gutta percha group was superior with push out bond strength of 2.22 (± 0.16) Mpa in comparison to Resilon/Epiphany group with 1.61 (±0.14) Mpa (p<0.001). CONCLUSIONS: The interfacial bond strength achieved with Resilon/Epiphany self-etch (SE) to intraradicular dentine was not superior to that of AH Plus/Gutta Percha. Key words:AH Plus, Apical leakage, Epiphany, Gutta percha, Push-out test Resilon.

Fibrofascitis - An Enigma for the Dentist: A Case Report.

Fibromyalgia is a chronic syndrome that causes widespread musculoskeletal pain and stiffness throughout the connective tissues that support and move the bones and joints. Pain and localized tender points occur in the muscles, particularly those that support the neck, spine, shoulders, and hips. Moreover the disorder includes fatigue, depression, sleep disturbances and constipation. A combination of treatments including medications, patient education, physical therapy and counseling are usually recommended. Here, we present a case report of fibromyalgia and the treatment given to the patient, a combination of dental and orthopedic treatment.

Analgesic efficacy of acetaminophen for controlling postextraction dental pain.

BACKGROUND: Considering the clinical safety of acetaminophen over other nonsteroidal anti-inflammatory drugs, this clinical trial was formulated to assess the analgesic efficacy of acetaminophen for controlling postextraction dental pain when compared to commonly prescribed ibuprofen. AIM: The aim was to assess the analgesic efficacy of paracetamol/acetaminophen in postextraction dental pain. SETTINGS AND DESIGN: Double-blind, randomized prospective clinical trial. MATERIALS AND METHODS: A total of 30 patients requiring bilateral maxillary and mandibular premolar extraction for their orthodontic treatment were included in the study to evaluate the efficacy of acetaminophen in controlling postextraction dental pain. STATISTICAL ANALYSIS USED: Unpaired t-test. RESULTS AND CONCLUSIONS: Clinically, both the postoperative analgesics exerted similar pain control with minor variations of recorded visual analog scale scores by the patients in both the groups. It may be concluded from the findings of this study that paracetamol at a dosage of 500 mg thrice a day (1.5 g) is sufficient to achieve reliable pain control following exodontia provided the surgical trauma caused to the investing tissues is minimal.