Collagen fiber centerline tracking in fibrotic tissue via deep neural networks with variational autoencoder-based synthetic training data generation.

The role of fibrillar collagen in the tissue microenvironment is critical in disease contexts ranging from cancers to chronic inflammations, as evidenced by many studies. Quantifying fibrillar collagen organization has become a powerful approach for characterizing the topology of collagen fibers and studying the role of collagen fibers in disease progression. We present a deep learning-based pipeline to quantify collagen fibers' topological properties in microscopy-based collagen images from pathological tissue samples. Our method leverages deep neural networks to extract collagen fiber centerlines and deep generative models to create synthetic training data, addressing the current shortage of large-scale annotations. As a part of this effort, we have created and annotated a collagen fiber centerline dataset, with the hope of facilitating further research in this field. Quantitative measurements such as fiber orientation, alignment, density, and length can be derived based on the centerline extraction results. Our pipeline comprises three stages. Initially, a variational autoencoder is trained to generate synthetic centerlines possessing controllable topological properties. Subsequently, a conditional generative adversarial network synthesizes realistic collagen fiber images from the synthetic centerlines, yielding a synthetic training set of image-centerline pairs. Finally, we train a collagen fiber centerline extraction network using both the original and synthetic data. Evaluation using collagen fiber images from pancreas, liver, and breast cancer samples collected via second-harmonic generation microscopy demonstrates our pipeline's superiority over several popular fiber centerline extraction tools. Incorporating synthetic data into training further enhances the network's generalizability. Our code is available at https://github.com/uw-loci/collagen-fiber-metrics.

A computer based facial flaps simulator using projective dynamics.

BACKGROUND AND OBJECTIVES: Interactive surgical simulation using the finite element method to model human skin mechanics has been an elusive goal. Mass-spring networks, while fast, do not provide the required accuracy. METHODS: This paper presents an interactive, cognitive, facial flaps simulator based on a projective dynamics computational framework. Projective dynamics is able to generate rapid, stable results following changes to the facial soft tissues created by the surgeon, even in the face of sudden increases in skin resistance as its stretch limit is reached or collision between tissues occurs. Our prior work with the finite element method had been hampered by these considerations. Surgical tools are provided for; skin incision, undermining, deep tissue cutting, and excision. A spring-like "skin hook" is used for retraction. Spring-based sutures can be placed individually or automatically placed as a row between cardinal sutures. RESULTS: Examples of an Abbe/Estlander lip reconstruction, a paramedian forehead flap to the nose, a retroauricular flap reconstruction of the external ear, and a cervico-facial flap reconstruction of a cheek defect are presented. CONCLUSIONS: Projective dynamics has significant advantages over mass-spring and finite element methods as the physics backbone for interactive soft tissue surgical simulation.

Long-Term Results of the Murawski Unilateral Cleft Lip Repair.

BACKGROUND: In 1968, Ralph Millard published his "Millard II" method for repair of wide, complete unilateral cleft lip and nose deformity. In 1979, Murawski published a major modification of the Millard II procedure in Polish. This motif was taken up 8 years later by Mohler and 22 years later by Cutting. The Murawski variation on the Millard II procedure has become a dominant motif in unilateral cleft lip repair worldwide. This brief report intends to introduce the method to the English language literature and present long-term results. METHODS: The Murawski method alters the Millard II procedure by changing the upper medial curve into a point in the columellar base. This creates a broad C flap used to fill the entire defect produced by downward rotation of the medial lip. Millard's lateral advancement flap becomes unnecessary. A lateral approach to primary nasal reconstruction allows the lateral C flap to be used to construct the nasal floor and sill. The method is described using a physics-based surgical simulator. RESULTS: Long-term results of the method are demonstrated with four patients with 15 to 25-year follow-up. None of these patients had any revisions to the lip or nose. CONCLUSIONS: The Murawski repair was the first to modify the Millard II repair by sharpening the medial columellar incision, eliminating the need for a lateral advancement flap. This motif was put forth in the years to follow by Mohler and Cutting. Long-term results of the method are presented.

Low-latency time-of-flight non-line-of-sight imaging at 5 frames per second.

Non-Line-Of-Sight (NLOS) imaging aims at recovering the 3D geometry of objects that are hidden from the direct line of sight. One major challenge with this technique is the weak available multibounce signal limiting scene size, capture speed, and reconstruction quality. To overcome this obstacle, we introduce a multipixel time-of-flight non-line-of-sight imaging method combining specifically designed Single Photon Avalanche Diode (SPAD) array detectors with a fast reconstruction algorithm that captures and reconstructs live low-latency videos of non-line-of-sight scenes with natural non-retroreflective objects. We develop a model of the signal-to-noise-ratio of non-line-of-sight imaging and use it to devise a method that reconstructs the scene such that signal-to-noise-ratio, motion blur, angular resolution, and depth resolution are all independent of scene depth suggesting that reconstruction of very large scenes may be possible.

Fibrillar Collagen Quantification With Curvelet Transform Based Computational Methods.

Quantification of fibrillar collagen organization has given new insight into the possible role of collagen topology in many diseases and has also identified candidate image-based bio-markers in breast cancer and pancreatic cancer. We have been developing collagen quantification tools based on the curvelet transform (CT) algorithm and have demonstrated this to be a powerful multiscale image representation method due to its unique features in collagen image denoising and fiber edge enhancement. In this paper, we present our CT-based collagen quantification software platform with a focus on new features and also giving a detailed description of curvelet-based fiber representation. These new features include C++-based code optimization for fast individual fiber tracking, Java-based synthetic fiber generator module for method validation, automatic tumor boundary generation for fiber relative quantification, parallel computing for large-scale batch mode processing, region-of-interest analysis for user-specified quantification, and pre- and post-processing modules for individual fiber visualization. We present a validation of the tracking of individual fibers and fiber orientations by using synthesized fibers generated by the synthetic fiber generator. In addition, we provide a comparison of the fiber orientation calculation on pancreatic tissue images between our tool and three other quantitative approaches. Lastly, we demonstrate the use of our software tool for the automatic tumor boundary creation and the relative alignment quantification of collagen fibers in human breast cancer pathology images, as well as the alignment quantification of in vivo mouse xenograft breast cancer images.

Local flaps: a real-time finite element based solution to the plastic surgery defect puzzle.

One of the most fundamental challenges in plastic surgery is the alteration of the geometry and topology of the skin. The specific decisions made by the surgeon concerning the size and shape of the tissue to be removed and the subsequent closure of the resulting wound may have a dramatic affect on the quality of life for the patient after the procedure is completed. The plastic surgeon must look at the defect created as an organic puzzle, designing the optimal pattern to close the hole aesthetically and efficiently. In the past, such skills were the distillation of years of hands-on practice on live patients, while relevant reference material was limited to two-dimensional illustrations. Practicing this procedure on a personal computer [1] has been largely impractical to date, but recent technological advances may come to challenge this limitation. We present a comprehensive real-time virtual surgical environment, based on finite element modeling and simulation of tissue cutting and manipulation. Our system demonstrates the fundamental building blocks of plastic surgery procedures on a localized tissue flap, and provides a proof of concept for larger simulation systems usable in the authoring of complex procedures on elaborate subject geometry.

A Real-Time Local Flaps Surgical Simulator Based on Advances in Computational Algorithms for Finite Element Models.

BACKGROUND: This article presents a real-time surgical simulator for teaching three- dimensional local flap concepts. Mass-spring based simulators are interactive, but they compromise accuracy and realism. Accurate finite element approaches have traditionally been too slow to permit development of a real-time simulator. METHODS: A new computational formulation of the finite element method has been applied to a simulated surgical environment. The surgical operators of retraction, incision, excision, and suturing are provided for three-dimensional operation on skin sheets and scalp flaps. A history mechanism records a user's surgical sequence. Numerical simulation was accomplished by a single small-form-factor computer attached to eight inexpensive Web-based terminals at a total cost of $2100. A local flaps workshop was held for the plastic surgery residents at the University of Wisconsin hospitals. RESULTS: Various flap designs of Z-plasty, rotation, rhomboid flaps, S-plasty, and related techniques were demonstrated in three dimensions. Angle and incision segment length alteration advantages were demonstrated (e.g., opening the angle of a Z-plasty in a three-dimensional web contracture). These principles were then combined in a scalp flap model demonstrating rotation flaps, dual S-plasty, and the Dufourmentel Mouly quad rhomboid flap procedure to demonstrate optimal distribution of secondary defect closure stresses. CONCLUSIONS: A preliminary skin flap simulator has been demonstrated to be an effective teaching platform for the real-time elucidation of local flap principles. Future work will involve adaptation of the system to facial flaps, breast surgery, cleft lip, and other problems in plastic surgery as well as surgery in general.

Creating and simulating skeletal muscle from the visible human data set.

Simulation of the musculoskeletal system has important applications in biomechanics, biomedical engineering, surgery simulation, and computer graphics. The accuracy of the muscle, bone, and tendon geometry as well as the accuracy of muscle and tendon dynamic deformation are of paramount importance in all these applications. We present a framework for extracting and simulating high resolution musculoskeletal geometry from the segmented visible human data set. We simulate 30 contact/collision coupled muscles in the upper limb and describe a computationally tractable implementation using an embedded mesh framework. Muscle geometry is embedded in a nonmanifold, connectivity preserving simulation mesh molded out of a lower resolution BCC lattice containing identical, well-shaped elements, leading to a relaxed time step restriction for stability and, thus, reduced computational cost. The muscles are endowed with a transversely isotropic, quasi-incompressible constitutive model that incorporates muscle fiber fields as well as passive and active components. The simulation takes advantage of a new robust finite element technique that handles both degenerate and inverted tetrahedra.