Reza Haghighi Osgouei

Rectal examination through proctoscopy or rigid sigmoidoscopy is a common investigation in clinical practice. It is an important diagnostic tool for the workup and management of anorectal pathologies. Performing the examination can be daunting not only for patients but also for junior doctors. There are associated risks with the procedure, such as pain, diagnostic failure, and perforation of the bowel. Simulation-based training is recognised as an important adjunct in clinical education. It allows students and doctors to practice skills and techniques at their own pace in a risk-free environment. These skills can then be transferred to and developed further in clinical practice. There is extensive research published regarding the role of simulation-based training in endoscopy, however, we identified no published study regarding simulation-based training in rigid sigmoidoscopy or proctoscopy. This study aims to establish the initial face, content, and construct validity of a tool-based visual anorectal examination advanced simulator model for proctoscopy and rigid sigmoidoscopy. This innovative, highly realistic simulated environment aims to enhance the training of healthcare professionals and improve the efficiency of detecting and diagnosing distal colorectal disease.

Background: Performing physiotherapy exercises in front of a physiotherapist yields qualitative assessment notes and immediate feedback. However, practicing the exercises at home lacks feedback on how well patients are performing the prescribed tasks. The absence of proper feedback might result in patients performing the exercises incorrectly, which could worsen their condition. We present an approach to generate performance scores to enable tracking the progress by both the patient at home and the physiotherapist in the clinic. Objective: This study aims to propose the use of 2 machine learning algorithms, dynamic time warping (DTW) and hidden Markov model (HMM), to quantitatively assess the patient’s performance with respect to a reference. Methods: Movement data were recorded using a motion sensor (Kinect V2), capable of detecting 25 joints in the human skeleton model, and were compared with those of a reference. A total of 16 participants were recruited to perform 4 different exercises: shoulder abduction, hip abduction, lunge, and sit-to-stand exercises. Their performance was compared with that of a physiotherapist as a reference. Results: Both algorithms showed a similar trend in assessing participant performance. However, their sensitivity levels were different. Although DTW was more sensitive to small changes, HMM captured a general view of the performance, being less sensitive to the details. Conclusions: The chosen algorithms demonstrated their capacity to objectively assess the performance of physical therapy. HMM may be more suitable in the early stages of a physiotherapy program to capture and report general performance, whereas DTW could be used later to focus on the details. The scores enable the patient to monitor their daily performance. They can also be reported back to the physiotherapist to track and assess patient progress, provide feedback, and adjust the exercise program if needed.

Background: Digital rectal examination is a difficult examination to learn and teach because of limited opportunities for practice; however, the main challenge is that students and tutors cannot see the finger when it is palpating the anal canal and prostate gland inside the patients. Objective: This paper presents an augmented reality system to be used with benchtop models commonly available in medical schools with the aim of addressing the problem of lack of visualization. The system enables visualization of the examining finger, as well as of the internal organs when performing digital rectal examinations. Magnetic tracking sensors are used to track the movement of the finger, and a pressure sensor is used to monitor the applied pressure. By overlaying a virtual finger on the real finger and a virtual model on the benchtop model, students can see through the examination and finger maneuvers. Methods: The system was implemented in the Unity game engine (Unity Technologies) and uses a first-generation HoloLens (Microsoft Inc) as an augmented reality device. To evaluate the system, 19 participants (9 clinicians who routinely performed digital rectal examinations and 10 medical students) were asked to use the system and answer 12 questions regarding the usefulness of the system. Results: The system showed the movement of an examining finger in real time with a frame rate of 60 fps on the HoloLens and accurately aligned the virtual and real models with a mean error of 3.9 mm. Users found the movement of the finger was realistic (mean 3.9, SD 1.2); moreover, they found the visualization of the finger and internal organs were useful for teaching, learning, and assessment of digital rectal examinations (finger: mean 4.1, SD 1.1; organs: mean 4.6, SD 0.8), mainly targeting a novice group. Conclusions: The proposed augmented reality system was designed to improve teaching and learning of digital rectal examination skills by providing visualization of the finger and internal organs. The initial user study proved its applicability and usefulness.

Touchscreens are versatile devices that can display visual content and receive touch input, but they lack the ability to provide programmable tactile feedback. This limitation has been addressed by a few approaches generally called surface haptics technology. This technology modulates the friction between a user’s fingertip and a touchscreen surface to create different tactile sensations when the finger explores the touchscreen. This functionality enables the user to see and feel digital content simultaneously, leading to improved usability and user experiences. One major approach in surface haptics relies on the electrostatic force induced between the finger and an insulating surface on the touchscreen by supplying high AC voltage. The use of AC also induces a vibrational sensation called electrovibration to the user. Electrostatic friction displays require only electrical components and provide uniform friction over the screen. This tactile feedback technology not only allows easy and lightweight integration into touchscreen devices but also provides dynamic, rich, and satisfactory user interfaces. In this chapter, we review the fundamental operation of the electrovibration technology as well as applications have been built upon.

BACKGROUND Digital rectal examination is a difficult examination to learn and teach because of limited opportunities for practice; however, the main challenge is that students and tutors cannot see the finger when it is palpating the anal canal and prostate gland inside the patients. OBJECTIVE This paper presents an augmented reality system to be used with benchtop models commonly available in medical schools with the aim of addressing the problem of lack of visualization. The system enables visualization of the examining finger, as well as of the internal organs when performing digital rectal examinations. Magnetic tracking sensors are used to track the movement of the finger, and a pressure sensor is used to monitor the applied pressure. By overlaying a virtual finger on the real finger and a virtual model on the benchtop model, students can see through the examination and finger maneuvers. METHODS The system was implemented in the Unity game engine (Unity Technologies) and uses a first-generation HoloLens (Microsoft Inc) as an augmented reality device. To evaluate the system, 19 participants (9 clinicians who routinely performed digital rectal examinations and 10 medical students) were asked to use the system and answer 12 questions regarding the usefulness of the system. RESULTS The system showed the movement of an examining finger in real time with a frame rate of 60 fps on the HoloLens and accurately aligned the virtual and real models with a mean error of 3.9 mm. Users found the movement of the finger was realistic (mean 3.9, SD 1.2); moreover, they found the visualization of the finger and internal organs were useful for teaching, learning, and assessment of digital rectal examinations (finger: mean 4.1, SD 1.1; organs: mean 4.6, SD 0.8), mainly targeting a novice group. CONCLUSIONS The proposed augmented reality system was designed to improve teaching and learning of digital rectal examination skills by providing visualization of the finger and internal organs. The initial user study proved its applicability and usefulness.

Sphincter tone examination, as part of digital rectal examination (DRE), can provide essential information to support the early detection of colorectal cancer. Mastering DRE skills for junior doctors is always challenging due to the lack of real training cases. In this article, we developed a soft pneumatic active actuator,made of a compound of silicone rubber materials, to mimic human sphincter muscles and simulate various anal sphincter tones for the purpose of training. Different pumping actuation (syringe and bellows) and driving mechanisms (linear, stepper, and servo motor) were implemented and compared for their effect on the rendered tones. A further comparison was made with a previous prototype based on a cable-driven mechanism. Both quantitative and qualitative assessments were conducted to evaluate the performance of each mechanism. A differential pressure sensor was used to measure applied pressure on a catheter balloon placed inside the sphincter, comparing the readings with anorectal manometry data obtained from real patients. Qualitative feedback was gathered through a user study with ten colorectal expert practitioners. Four questions were asked targeting reaction/response time, pressure level, pressure quality, and similarity to a real case. The results show the capacity and limitation of each mechanism, with the one based on a servo motor and a bellows being the most favourably rated.

BACKGROUND Performing physiotherapy exercises in front of a physiotherapist yields qualitative assessment notes and immediate feedback. However, practicing the exercises at home lacks feedback on how well patients are performing the prescribed tasks. The absence of proper feedback might result in patients performing the exercises incorrectly, which could worsen their condition. We present an approach to generate performance scores to enable tracking the progress by both the patient at home and the physiotherapist in the clinic. OBJECTIVE This study aims to propose the use of 2 machine learning algorithms, dynamic time warping (DTW) and hidden Markov model (HMM), to quantitatively assess the patient’s performance with respect to a reference. METHODS Movement data were recorded using a motion sensor (Kinect V2), capable of detecting 25 joints in the human skeleton model, and were compared with those of a reference. A total of 16 participants were recruited to perform 4 different exercises: shoulder abduction, hip abduction, lunge, and sit-to-stand exercises. Their performance was compared with that of a physiotherapist as a reference. RESULTS Both algorithms showed a similar trend in assessing participant performance. However, their sensitivity levels were different. Although DTW was more sensitive to small changes, HMM captured a general view of the performance, being less sensitive to the details. CONCLUSIONS The chosen algorithms demonstrated their capacity to objectively assess the performance of physical therapy. HMM may be more suitable in the early stages of a physiotherapy program to capture and report general performance, whereas DTW could be used later to focus on the details. The scores enable the patient to monitor their daily performance. They can also be reported back to the physiotherapist to track and assess patient progress, provide feedback, and adjust the exercise program if needed.

With the introduction of variable friction displays, new possibilities have emerged in haptic texture rendering on flat surfaces. In this work, we propose a data-driven method for realistic texture rendering on an electrovibration display. We first describe a motorized linear tribometer designed to collect lateral frictional forces from textured surfaces under various scanning velocities and normal forces. We then propose an inverse dynamics model of the display to describe its output-input relationship using nonlinear autoregressive neural networks with external input. Forces resulting from applying a pseudo-random binary signal to the display are used to train each network under the given experimental condition. In addition, we propose a two-step interpolation scheme to estimate actuation signals for arbitrary conditions under which no prior data have been collected. A comparison between real and virtual forces in the frequency domain shows promising results for recreating virtual textures similar to the real ones, also revealing the capabilities and limitations of the proposed method. We also conducted a human user study to compare the performance of our neural-network-based method with that of a record-and-playback method. The results showed that the similarity between the real and virtual textures generated by our approach was significantly higher.

The aim of this work is to objectively evaluate the performance of patients using a virtual rehabilitation system called MIRA. MIRA is a software platform which converts conventional therapeutic exercises into games, enabling the user to practice the given exercise by playing a game. The system includes a motion sensor to track and capture user's movements. Our assessment of the performance quality is based on the recorded trajectories of the human skeleton joints. We employ two different machine learning approaches, dynamic time warping (DTW) and hidden Markov modeling (HMM), both widely used for gesture recognition, to compare the user's performance with that of a reference as ground truth.

With the introduction of variable friction displays, new possibilities have emerged in haptic texture rendering on flat surfaces. In this work, we propose a data-driven method for realistic texture rendering on an electrovibration display. We first describe a motorized linear tribometer we developed to collect lateral frictional forces from the textured surfaces under various scanning velocities and normal forces. We then propose an inverse dynamics model of the display to describe its output-input relationship using nonlinear autoregressive with external input (NARX) neural networks. Forces resulting from applying a pseudo-random binary signal (PRBS) to the display are used to train each network under the given experimental condition. A comparison between the real and virtual forces in frequency domain shows promising results for recreating virtual textures similar to the real ones and also reveals the capabilities and limitations of the proposed method.