An Interpretable and Accurate Deep-Learning Diagnosis Framework Modeled With Fully and Semi-Supervised Reciprocal Learning.

The deployment of automated deep-learning classifiers in clinical practice has the potential to streamline the diagnosis process and improve the diagnosis accuracy, but the acceptance of those classifiers relies on both their accuracy and interpretability. In general, accurate deep-learning classifiers provide little model interpretability, while interpretable models do not have competitive classification accuracy. In this paper, we introduce a new deep-learning diagnosis framework, called InterNRL, that is designed to be highly accurate and interpretable. InterNRL consists of a student-teacher framework, where the student model is an interpretable prototype-based classifier (ProtoPNet) and the teacher is an accurate global image classifier (GlobalNet). The two classifiers are mutually optimised with a novel reciprocal learning paradigm in which the student ProtoPNet learns from optimal pseudo labels produced by the teacher GlobalNet, while GlobalNet learns from ProtoPNet's classification performance and pseudo labels. This reciprocal learning paradigm enables InterNRL to be flexibly optimised under both fully- and semi-supervised learning scenarios, reaching state-of-the-art classification performance in both scenarios for the tasks of breast cancer and retinal disease diagnosis. Moreover, relying on weakly-labelled training images, InterNRL also achieves superior breast cancer localisation and brain tumour segmentation results than other competing methods.

ADMANI: Annotated Digital Mammograms and Associated Non-Image Datasets.

Supplemental material is available for this article. Keywords: Mammography, Screening, Convolutional Neural Network (CNN) Published under a CC BY 4.0 license. See also the commentary by Cadrin-Chênevert in this issue.

Findings from machine learning in clinical medical imaging applications - Lessons for translation to the forensic setting.

Machine learning (ML) techniques are increasingly being used in clinical medical imaging to automate distinct processing tasks. In post-mortem forensic radiology, the use of these algorithms presents significant challenges due to variability in organ position, structural changes from decomposition, inconsistent body placement in the scanner, and the presence of foreign bodies. Existing ML approaches in clinical imaging can likely be transferred to the forensic setting with careful consideration to account for the increased variability and temporal factors that affect the data used to train these algorithms. Additional steps are required to deal with these issues, by incorporating the possible variability into the training data through data augmentation, or by using atlases as a pre-processing step to account for death-related factors. A key application of ML would be then to highlight anatomical and gross pathological features of interest, or present information to help optimally determine the cause of death. In this review, we highlight results and limitations of applications in clinical medical imaging that use ML to determine key implications for their application in the forensic setting.

Development of a simple numerical model for trabecular bone structures.

PURPOSE: Advances in additive manufacturing processes are enabling the fabrication of surrogate bone structures for applications including use in high-resolution anthropomorphic phantoms. In this research, a simple numerical model is proposed that enables the generation of microarchitecture with similar statistical distribution to trabecular bone. METHODS: A human humerus, radius, ulna, and several vertebrae were scanned on the Imaging and Medical beamline at the Australian Synchrotron and the proposed numerical model was developed through the definition of two complex functions that encode the trabecular thickness and position-dependant spacing to generate volumetric surrogate trabecular structures. The structures reproduced those observed at 19 separate axial locations through the experimental bone volumes. The applicability of the model when incorporating a two-material approximation to absorption- and phase-contrast CT was also investigated through simulation. RESULTS: The synthetic structures, when compared with the real trabecular microarchitecture, yielded an average mean thickness error of 2 µm, and a mean difference in standard deviation of 33 µm for the humerus, 24 µm for the ulna and radius, and 15 µm for the vertebrae. Simulated absorption- and propagation-based phase contrast CT projection data were generated and reconstructed using the derived mathematical simplifications from the two-material approximation, and the phase-contrast effects were successfully demonstrated. CONCLUSIONS: The presented model reproduced trabecular distributions that could be used to generate phantoms for quality assurance and validation processes. The implication of utilizing a two-material approximation results in simplification of the additive manufacturing process and the generation of synthetic data that could be used for training of machine learning applications.

Effect of external fixation rod coupling in computed tomography.

External fixation is a common tool in the treatment of complex fractures, correction of limb deformity, and salvage arthrodesis. These devices typically incorporate radio-opaque metal rods/struts connected at varying distances and orientations between rings. Whilst the predominant imaging modality is plain film radiology, computed tomography (CT) may be performed in order for the surgeon to make a more confident clinical decision (e.g. timing of frame removal, assessment of degree of arthrodesis). We used a fractured sheep leg to systematically assess CT imaging performance with a Discovery CT750 HD CT scanner (GE Healthcare) to show how rod coupling in both traditional Ilizarov and hexapod frames distorts images. We also investigated the role of dual-energy CT (DECT) and metal artefact reduction software (MARS) on the visualisation of the fractured leg. Whilst mechanical reasons predominantly dictate the rod/strut configurations when building a circular frame, rod coupling in CT can be minimised. Firstly, ideally, all or all but one rod can be removed during imaging resulting in no rod coupling. If this is not possible, strategies for configuring the rods to minimise the effect of the rod coupling on the region of interest are demonstrated, e.g., in the case of a four-rod construct, switching the two anterior rods to a more central single one will achieve this goal without particularly jeopardising mechanical strength for a short period. It is also shown that the addition of DECT and MARS results in a reduction of artefacts, but also affects tissue and bone differentiation.

Identificación de las barreras del entorno que afectan la inclusión social de las personas con discapacidad motriz de miembros inferiores / Identifying environmental barriers that affect social inclusion of people with physical disability in lower limbs

Objetivo: Identificar las barreras del entorno que afectan la inclusión social de una población con discapacidad motriz. Materiales y métodos: Se realizó un estudio descriptivo en el que participaron 45 adultos con discapacidad motriz de miembros inferiores. La encuesta incluyó las categorías: a) sociodemográfica, de salud y características del entorno, b) del acompañante o cuidador, c) sobre los productos de apoyo, d) actividades y participación, y e) factores ambientales. Resultados: Un 98% pertenecía a los estratos socioeconómicos 1, 2 y 3, y en su mayoría (53%) activos laboralmente, con salarios que no sobrepasan el mínimo legal vigente en Colombia. La causa principal de la discapacidad (42%) fue la violencia. El 67% tenía alguna dificultad para acceder al entorno físico, la información y la comunicación. Las mayores barreras fueron el acceso a los edificios públicos (54%) y a la educación técnica (83%). Conclusiones: Las múltiples barreras que afectan la inclusión social sugieren que se debe abordar esta problemática desde la estructura y organización social del entorno en que se desempeña la persona y no solamente desde su deficiencia. Como en otros estudios en Colombia, se corrobora la simultaneidad de pobreza, violencia y discapacidad.

Objective: Identify environmental barriers that affect social inclusion of people with motor impairment. Materials and methods: We conducted a descriptive study involving 45 adults with lower limb motor impairment. The survey included the following categories: a) socio-demographic, health and environmental characteristics, b) companion or caretaker, c) as-sistive products, d) activities and participation, and e) environmental factors. Results: 98% of the people belonged to socioeconomic strata 1, 2 and 3, and most of them (53%) are working with salaries that do not exceed the national monthly legal wage in Colombia. The main cause of disability (42%) was violence. 67% had some difficulty to access to the built environment, information and communication. The biggest barriers were access to public buildings (54%) and to technical education (83%). Conclusions: The multiple barriers that affect social inclusion suggest that this problem must be addressed from the structure and social organization of the environment in which the person is engaged and not just from his/her deficiency. As in other studies in Colombia, it is confirmed the simultaneity of poverty, violence and disability.